Publications

For a full list of publications please also see my Google Scholar profile.

2024

• 
  1.

  Stegink, J., Klein, A., Kersten, J., Bockhahn, R., Basler, M., Becker, M., Abel, D., and Zierath, J. (2024) Rotor Thrust Estimation Using RNN in TensorFlow-a Preliminary for Wind Turbine Control (abstract). In Proceedings of the Seventh International Conference on Multibody System Dynamics.

  BibTeXEndNoteBibSonomy

  @inproceedings{stegink2024rotor,
  author = {Stegink, Jeffrey and Klein, Andreas and Kersten, Julia and Bockhahn, Reik and Basler, Maximilian and Becker, Martin and Abel, Dirk and Zierath, Janos},
  booktitle = {Proceedings of the Seventh International Conference on Multibody System Dynamics},
  keywords = {rotor},
  month = {06},
  title = {Rotor Thrust Estimation Using RNN in TensorFlow-a Preliminary for Wind Turbine Control (abstract)},
  year = 2024
  }
  

  %0 Conference Paper
  %1 stegink2024rotor
  %A Stegink, Jeffrey
  %A Klein, Andreas
  %A Kersten, Julia
  %A Bockhahn, Reik
  %A Basler, Maximilian
  %A Becker, Martin
  %A Abel, Dirk
  %A Zierath, Janos
  %B Proceedings of the Seventh International Conference on Multibody System Dynamics
  %D 2024
  %T Rotor Thrust Estimation Using RNN in TensorFlow-a Preliminary for Wind Turbine Control (abstract)
  

• 
  1.

  Mirzaei, A., Hiller, B. C., Stelzer, I. A., Thiele, K., Tan, Y., and Becker, M. (2024) Computational Approaches for Connecting Maternal Stress to Preterm Birth, Clinics in Perinatology.

  URLBibTeXEndNoteDOIBibSonomyDownload

  @article{mirzaei2024computational,
  author = {Mirzaei, Amin and Hiller, Bjarne C. and Stelzer, Ina A. and Thiele, Kristin and Tan, Yuqi and Becker, Martin},
  journal = {Clinics in Perinatology},
  keywords = {computational},
  title = {Computational Approaches for Connecting Maternal Stress to Preterm Birth},
  year = 2024
  }
  

  %0 Journal Article
  %1 mirzaei2024computational
  %A Mirzaei, Amin
  %A Hiller, Bjarne C.
  %A Stelzer, Ina A.
  %A Thiele, Kristin
  %A Tan, Yuqi
  %A Becker, Martin
  %D 2024
  %J Clinics in Perinatology
  %R https://doi.org/10.1016/j.clp.2024.02.003
  %T Computational Approaches for Connecting Maternal Stress to Preterm Birth
  %U https://www.sciencedirect.com/science/article/pii/S0095510824000137
  

• 
  1.

  Koopmann, T., Becker, M., Lemmerich, F., and Hotho, A. (2024) CompTrails: comparing hypotheses across behavioral networks, Data Mining and Knowledge Discovery.

  AbstractURLBibTeXEndNoteDOIBibSonomyDownload

  The term Behavioral Networks describes networks that contain relational information on human behavior. This ranges from social networks that contain friendships or cooperations between individuals, to navigational networks that contain geographical or web navigation, and many more. Understanding the forces driving behavior within these networks can be beneficial to improving the underlying network, for example, by generating new hyperlinks on websites, or by proposing new connections and friends on social networks. Previous approaches considered different hypotheses on a single network and evaluated which hypothesis fits best. These hypotheses can represent human intuition and expert opinions or be based on previous insights. In this work, we extend these approaches to enable the comparison of a single hypothesis between multiple networks. We unveil several issues of naive approaches that potentially impact comparisons and lead to undesired results. Based on these findings, we propose a framework with five flexible components that allow addressing specific analysis goals tailored to the application scenario. We show the benefits and limits of our approach by applying it to synthetic data and several real-world datasets, including web navigation, bibliometric navigation, and geographic navigation. Our work supports practitioners and researchers with the aim of understanding similarities and differences in human behavior between environments.

  @article{koopmann2024comptrails,
  abstract = {The term Behavioral Networks describes networks that contain relational information on human behavior. This ranges from social networks that contain friendships or cooperations between individuals, to navigational networks that contain geographical or web navigation, and many more. Understanding the forces driving behavior within these networks can be beneficial to improving the underlying network, for example, by generating new hyperlinks on websites, or by proposing new connections and friends on social networks. Previous approaches considered different hypotheses on a single network and evaluated which hypothesis fits best. These hypotheses can represent human intuition and expert opinions or be based on previous insights. In this work, we extend these approaches to enable the comparison of a single hypothesis between multiple networks. We unveil several issues of naive approaches that potentially impact comparisons and lead to undesired results. Based on these findings, we propose a framework with five flexible components that allow addressing specific analysis goals tailored to the application scenario. We show the benefits and limits of our approach by applying it to synthetic data and several real-world datasets, including web navigation, bibliometric navigation, and geographic navigation. Our work supports practitioners and researchers with the aim of understanding similarities and differences in human behavior between environments.},
  author = {Koopmann, Tobias and Becker, Martin and Lemmerich, Florian and Hotho, Andreas},
  journal = {Data Mining and Knowledge Discovery},
  keywords = {hypotheses},
  title = {CompTrails: comparing hypotheses across behavioral networks},
  year = 2024
  }
  

  %0 Journal Article
  %1 koopmann2024comptrails
  %A Koopmann, Tobias
  %A Becker, Martin
  %A Lemmerich, Florian
  %A Hotho, Andreas
  %D 2024
  %J Data Mining and Knowledge Discovery
  %R 10.1007/s10618-023-00996-8
  %T CompTrails: comparing hypotheses across behavioral networks
  %U https://doi.org/10.1007/s10618-023-00996-8
  %X The term Behavioral Networks describes networks that contain relational information on human behavior. This ranges from social networks that contain friendships or cooperations between individuals, to navigational networks that contain geographical or web navigation, and many more. Understanding the forces driving behavior within these networks can be beneficial to improving the underlying network, for example, by generating new hyperlinks on websites, or by proposing new connections and friends on social networks. Previous approaches considered different hypotheses on a single network and evaluated which hypothesis fits best. These hypotheses can represent human intuition and expert opinions or be based on previous insights. In this work, we extend these approaches to enable the comparison of a single hypothesis between multiple networks. We unveil several issues of naive approaches that potentially impact comparisons and lead to undesired results. Based on these findings, we propose a framework with five flexible components that allow addressing specific analysis goals tailored to the application scenario. We show the benefits and limits of our approach by applying it to synthetic data and several real-world datasets, including web navigation, bibliometric navigation, and geographic navigation. Our work supports practitioners and researchers with the aim of understanding similarities and differences in human behavior between environments.
  

• 
  1.

  Panelli, D. M., Wang, X., Mayo, J., Wong, R. J., Hong, X., Becker, M., Aghaeepour, N., Druzin, M. L., Zuckerman, B. S., Stevenson, D. K., and others. (2024) Association of pregnancy complications and postpartum maternal leukocyte telomeres in two diverse cohorts: a nested case-control study, BMC Pregnancy and Childbirth, BMC 24.

  BibTeXEndNoteBibSonomy

  @article{panelli2024association,
  author = {Panelli, Danielle M and Wang, Xiaobin and Mayo, Jonathan and Wong, Ronald J and Hong, Xiumei and Becker, Martin and Aghaeepour, Nima and Druzin, Maurice L and Zuckerman, Barry S and Stevenson, David K and others},
  journal = {BMC Pregnancy and Childbirth},
  keywords = {myown},
  publisher = {BMC},
  title = {Association of pregnancy complications and postpartum maternal leukocyte telomeres in two diverse cohorts: a nested case-control study},
  volume = 24,
  year = 2024
  }
  

  %0 Journal Article
  %1 panelli2024association
  %A Panelli, Danielle M
  %A Wang, Xiaobin
  %A Mayo, Jonathan
  %A Wong, Ronald J
  %A Hong, Xiumei
  %A Becker, Martin
  %A Aghaeepour, Nima
  %A Druzin, Maurice L
  %A Zuckerman, Barry S
  %A Stevenson, David K
  %A others,
  %D 2024
  %I BMC
  %J BMC Pregnancy and Childbirth
  %T Association of pregnancy complications and postpartum maternal leukocyte telomeres in two diverse cohorts: a nested case-control study
  %V 24
  

• 
  1.

  Panelli, D. M., Mayo, J. A., Wong, R. J., Becker, M., Feyaerts, D., Mari{{\’c}}, I., Wu, E., Gotlib, I. H., Gaudilli{è}re, B., Aghaeepour, N., and others. (2024) Mode of delivery predicts postpartum maternal leukocyte telomere length, European Journal of Obstetrics \& Gynecology and Reproductive Biology, Elsevier 300, 224–229.

  BibTeXEndNoteBibSonomy

  @article{panelli2024mode,
  author = {Panelli, Danielle M and Mayo, Jonathan A and Wong, Ronald J and Becker, Martin and Feyaerts, Dorien and Mari{{\'c}}, Ivana and Wu, Erica and Gotlib, Ian H and Gaudilli{è}re, Brice and Aghaeepour, Nima and others},
  journal = {European Journal of Obstetrics \& Gynecology and Reproductive Biology},
  keywords = {myown},
  pages = {224--229},
  publisher = {Elsevier},
  title = {Mode of delivery predicts postpartum maternal leukocyte telomere length},
  volume = 300,
  year = 2024
  }
  

  %0 Journal Article
  %1 panelli2024mode
  %A Panelli, Danielle M
  %A Mayo, Jonathan A
  %A Wong, Ronald J
  %A Becker, Martin
  %A Feyaerts, Dorien
  %A Mari{{\'c}}, Ivana
  %A Wu, Erica
  %A Gotlib, Ian H
  %A Gaudilli{è}re, Brice
  %A Aghaeepour, Nima
  %A others,
  %D 2024
  %I Elsevier
  %J European Journal of Obstetrics \& Gynecology and Reproductive Biology
  %P 224--229
  %T Mode of delivery predicts postpartum maternal leukocyte telomere length
  %V 300
  

• 
  1.

  Tan, Y., Kempchen, T. N., Becker, M., Haist, M., Feyaerts, D., Xiao, Y., Su, G., Rech, A. J., Fan, R., Hickey, J. W., and others. (2024) SPACEc: A Streamlined, Interactive Python Workflow for Multiplexed Image Processing and Analysis, bioRxiv (under review), Cold Spring Harbor Laboratory 2024–06.

  BibTeXEndNoteBibSonomy

  @article{tan2024spacec,
  author = {Tan, Yuqi and Kempchen, Tim N and Becker, Martin and Haist, Maximilian and Feyaerts, Dorien and Xiao, Yang and Su, Graham and Rech, Andrew J and Fan, Rong and Hickey, John W and others},
  journal = {bioRxiv (under review)},
  keywords = {cell},
  pages = {2024--06},
  publisher = {Cold Spring Harbor Laboratory},
  title = {SPACEc: A Streamlined, Interactive Python Workflow for Multiplexed Image Processing and Analysis},
  year = 2024
  }
  

  %0 Journal Article
  %1 tan2024spacec
  %A Tan, Yuqi
  %A Kempchen, Tim N
  %A Becker, Martin
  %A Haist, Maximilian
  %A Feyaerts, Dorien
  %A Xiao, Yang
  %A Su, Graham
  %A Rech, Andrew J
  %A Fan, Rong
  %A Hickey, John W
  %A others,
  %D 2024
  %I Cold Spring Harbor Laboratory
  %J bioRxiv (under review)
  %P 2024--06
  %T SPACEc: A Streamlined, Interactive Python Workflow for Multiplexed Image Processing and Analysis
  

• 
  1.

  Becker, M., Fehr, K., Goguen, S., Miliku, K., Field, C., Robertson, B., Yonemitsu, C., Bode, L., Simons, E., Marshall, J., Dawod, B., Mandhane, P., Turvey, S. E., Moraes, T. J., Subbarao, P., Rodriguez, N., Aghaeepour, N., and Azad, M. B. (2024) Multimodal machine learning for modeling infant head circumference, mothers’ milk composition, and their shared environment, Scientific Reports 14, 2977.

  AbstractURLBibTeXEndNoteDOIBibSonomyDownload

  Links between human milk (HM) and infant development are poorly understood and often focus on individual HM components. Here we apply multi-modal predictive machine learning to study HM and head circumference (a proxy for brain development) among 1022 mother-infant dyads of the CHILD Cohort. We integrated HM data (19 oligosaccharides, 28 fatty acids, 3 hormones, 28 chemokines) with maternal and infant demographic, health, dietary and home environment data. Head circumference was significantly predictable at 3 and 12 months. Two of the most associated features were HM n3-polyunsaturated fatty acid C22:6n3 (docosahexaenoic acid, DHA; p{\thinspace}={\thinspace}9.6e−05) and maternal intake of fish (p{\thinspace}={\thinspace}4.1e−03), a key dietary source of DHA with established relationships to brain function. Thus, using a systems biology approach, we identified meaningful relationships between HM and brain development, which validates our statistical approach, gives credence to the novel associations we observed, and sets the foundation for further research with additional cohorts and HM analytes.

  @article{becker2024multimodal,
  abstract = {Links between human milk (HM) and infant development are poorly understood and often focus on individual HM components. Here we apply multi-modal predictive machine learning to study HM and head circumference (a proxy for brain development) among 1022 mother-infant dyads of the CHILD Cohort. We integrated HM data (19 oligosaccharides, 28 fatty acids, 3 hormones, 28 chemokines) with maternal and infant demographic, health, dietary and home environment data. Head circumference was significantly predictable at 3 and 12 months. Two of the most associated features were HM n3-polyunsaturated fatty acid C22:6n3 (docosahexaenoic acid, DHA; p{\thinspace}={\thinspace}9.6e−05) and maternal intake of fish (p{\thinspace}={\thinspace}4.1e−03), a key dietary source of DHA with established relationships to brain function. Thus, using a systems biology approach, we identified meaningful relationships between HM and brain development, which validates our statistical approach, gives credence to the novel associations we observed, and sets the foundation for further research with additional cohorts and HM analytes.},
  author = {Becker, Martin and Fehr, Kelsey and Goguen, Stephanie and Miliku, Kozeta and Field, Catherine and Robertson, Bianca and Yonemitsu, Chloe and Bode, Lars and Simons, Elinor and Marshall, Jean and Dawod, Bassel and Mandhane, Piushkumar and Turvey, Stuart E. and Moraes, Theo J. and Subbarao, Padmaja and Rodriguez, Natalie and Aghaeepour, Nima and Azad, Meghan B.},
  journal = {Scientific Reports},
  keywords = {head},
  month = {02},
  number = 1,
  pages = 2977,
  title = {Multimodal machine learning for modeling infant head circumference, mothers' milk composition, and their shared environment},
  volume = 14,
  year = 2024
  }
  

  %0 Journal Article
  %1 becker2024multimodal
  %A Becker, Martin
  %A Fehr, Kelsey
  %A Goguen, Stephanie
  %A Miliku, Kozeta
  %A Field, Catherine
  %A Robertson, Bianca
  %A Yonemitsu, Chloe
  %A Bode, Lars
  %A Simons, Elinor
  %A Marshall, Jean
  %A Dawod, Bassel
  %A Mandhane, Piushkumar
  %A Turvey, Stuart E.
  %A Moraes, Theo J.
  %A Subbarao, Padmaja
  %A Rodriguez, Natalie
  %A Aghaeepour, Nima
  %A Azad, Meghan B.
  %D 2024
  %J Scientific Reports
  %N 1
  %P 2977
  %R 10.1038/s41598-024-52323-w
  %T Multimodal machine learning for modeling infant head circumference, mothers' milk composition, and their shared environment
  %U https://doi.org/10.1038/s41598-024-52323-w
  %V 14
  %X Links between human milk (HM) and infant development are poorly understood and often focus on individual HM components. Here we apply multi-modal predictive machine learning to study HM and head circumference (a proxy for brain development) among 1022 mother-infant dyads of the CHILD Cohort. We integrated HM data (19 oligosaccharides, 28 fatty acids, 3 hormones, 28 chemokines) with maternal and infant demographic, health, dietary and home environment data. Head circumference was significantly predictable at 3 and 12 months. Two of the most associated features were HM n3-polyunsaturated fatty acid C22:6n3 (docosahexaenoic acid, DHA; p{\thinspace}={\thinspace}9.6e−05) and maternal intake of fish (p{\thinspace}={\thinspace}4.1e−03), a key dietary source of DHA with established relationships to brain function. Thus, using a systems biology approach, we identified meaningful relationships between HM and brain development, which validates our statistical approach, gives credence to the novel associations we observed, and sets the foundation for further research with additional cohorts and HM analytes.
  

2023

• 
  1.

  Ravindra, N. G., Espinosa, C., Berson, E., Phongpreecha, T., Zhao, P., Becker, M., Chang, A. L., Shome, S., Mari{{\’c}}, I., De Francesco, D., and others. (2023) Deep representation learning identifies associations between physical activity and sleep patterns during pregnancy and prematurity, npj Digital Medicine, Nature Publishing Group UK London 6, 171.

  BibTeXEndNoteBibSonomy

  @article{ravindra2023deep,
  author = {Ravindra, Neal G and Espinosa, Camilo and Berson, Eloise and Phongpreecha, Thanaphong and Zhao, Peinan and Becker, Martin and Chang, Alan L and Shome, Sayane and Mari{{\'c}}, Ivana and De Francesco, Davide and others},
  journal = {npj Digital Medicine},
  keywords = {representation},
  number = 1,
  pages = 171,
  publisher = {Nature Publishing Group UK London},
  title = {Deep representation learning identifies associations between physical activity and sleep patterns during pregnancy and prematurity},
  volume = 6,
  year = 2023
  }
  

  %0 Journal Article
  %1 ravindra2023deep
  %A Ravindra, Neal G
  %A Espinosa, Camilo
  %A Berson, Eloise
  %A Phongpreecha, Thanaphong
  %A Zhao, Peinan
  %A Becker, Martin
  %A Chang, Alan L
  %A Shome, Sayane
  %A Mari{{\'c}}, Ivana
  %A De Francesco, Davide
  %A others,
  %D 2023
  %I Nature Publishing Group UK London
  %J npj Digital Medicine
  %N 1
  %P 171
  %T Deep representation learning identifies associations between physical activity and sleep patterns during pregnancy and prematurity
  %V 6
  

• 
  1.

  Berson, E., Gajera, C. R., Phongpreecha, T., Perna, A., Bukhari, S. A., Becker, M., Chang, A. L., De Francesco, D., Espinosa, C., Ravindra, N. G., and others. (2023) Cross-species comparative analysis of single presynapses, Scientific Reports, Nature Publishing Group UK London 13, 13849.

  BibTeXEndNoteBibSonomy

  @article{berson2023cross,
  author = {Berson, Eloise and Gajera, Chandresh R and Phongpreecha, Thanaphong and Perna, Amalia and Bukhari, Syed A and Becker, Martin and Chang, Alan L and De Francesco, Davide and Espinosa, Camilo and Ravindra, Neal G and others},
  journal = {Scientific Reports},
  keywords = {cytof},
  number = 1,
  pages = 13849,
  publisher = {Nature Publishing Group UK London},
  title = {Cross-species comparative analysis of single presynapses},
  volume = 13,
  year = 2023
  }
  

  %0 Journal Article
  %1 berson2023cross
  %A Berson, Eloise
  %A Gajera, Chandresh R
  %A Phongpreecha, Thanaphong
  %A Perna, Amalia
  %A Bukhari, Syed A
  %A Becker, Martin
  %A Chang, Alan L
  %A De Francesco, Davide
  %A Espinosa, Camilo
  %A Ravindra, Neal G
  %A others,
  %D 2023
  %I Nature Publishing Group UK London
  %J Scientific Reports
  %N 1
  %P 13849
  %T Cross-species comparative analysis of single presynapses
  %V 13
  

• 
  1.

  Panelli, D. M., Mayo, J. A., Wong, R. J., Becker, M., Maric, I., Wu, E., Gotlib, I. H., Aghaeepour, N., Druzin, M. L., Stevenson, D. K., and others. (2023) Shorter maternal leukocyte telomere length following cesarean birth: Implications for future research, American Journal of Obstetrics \& Gynecology, Elsevier 228, S456-S457.

  BibTeXEndNoteBibSonomy

  @article{panelli2023shorter,
  author = {Panelli, Danielle M and Mayo, Jonathan A and Wong, Ronald J and Becker, Martin and Maric, Ivana and Wu, Erica and Gotlib, Ian H and Aghaeepour, Nima and Druzin, Maurice L and Stevenson, David K and others},
  journal = {American Journal of Obstetrics \& Gynecology},
  keywords = {cesarean},
  number = 1,
  pages = {S456--S457},
  publisher = {Elsevier},
  title = {Shorter maternal leukocyte telomere length following cesarean birth: Implications for future research},
  volume = 228,
  year = 2023
  }
  

  %0 Journal Article
  %1 panelli2023shorter
  %A Panelli, Danielle M
  %A Mayo, Jonathan A
  %A Wong, Ronald J
  %A Becker, Martin
  %A Maric, Ivana
  %A Wu, Erica
  %A Gotlib, Ian H
  %A Aghaeepour, Nima
  %A Druzin, Maurice L
  %A Stevenson, David K
  %A others,
  %D 2023
  %I Elsevier
  %J American Journal of Obstetrics \& Gynecology
  %N 1
  %P S456--S457
  %T Shorter maternal leukocyte telomere length following cesarean birth: Implications for future research
  %V 228
  

• 
  1.

  Espinosa, C. A., Khan, W., Khanam, R., Das, S., Khalid, J., Pervin, J., Kasaro, M. P., Contrepois, K., Chang, A. L., Phongpreecha, T., Michael, B., Ellenberger, M., Mehmood, U., Hotwani, A., Nizar, A., Kabir, F., Wong, R. J., Becker, M., Berson, E., Culos, A., Francesco, D. D., Mataraso, S., Ravindra, N., Thuraiappah, M., Xenochristou, M., Stelzer, I. A., Marić, I., Dutta, A., Raqib, R., Ahmed, S., Rahman, S., Hasan, A. S. M. T., Ali, S. M., Juma, M. H., Rahman, M., Aktar, S., Deb, S., Price, J. T., Wise, P. H., Winn, V. D., Druzin, M. L., Gibbs, R. S., Darmstadt, G. L., Murray, J. C., Stringer, J. S. A., Gaudilliere, B., Snyder, M. P., Angst, M. S., Rahman, A., Baqui, A. H., Jehan, F., Nisar, M. I., Vwalika, B., Sazawal, S., Shaw, G. M., Stevenson, D. K., and Aghaeepour, N. (2023) Multiomic signals associated with maternal epidemiological factors contributing to preterm birth in low- and middle-income countries, Science Advances 9, eade7692.

  AbstractURLBibTeXEndNoteDOIBibSonomy

  Preterm birth (PTB) is the leading cause of death in children under five, yet comprehensive studies are hindered by its multiple complex etiologies. Epidemiological associations between PTB and maternal characteristics have been previously described. This work used multiomic profiling and multivariate modeling to investigate the biological signatures of these characteristics. Maternal covariates were collected during pregnancy from 13,841 pregnant women across five sites. Plasma samples from 231 participants were analyzed to generate proteomic, metabolomic, and lipidomic datasets. Machine learning models showed robust performance for the prediction of PTB (AUROC = 0.70), time-to-delivery (r = 0.65), maternal age (r = 0.59), gravidity (r = 0.56), and BMI (r = 0.81). Time-to-delivery biological correlates included fetal-associated proteins (e.g., ALPP, AFP, and PGF) and immune proteins (e.g., PD-L1, CCL28, and LIFR). Maternal age negatively correlated with collagen COL9A1, gravidity with endothelial NOS and inflammatory chemokine CXCL13, and BMI with leptin and structural protein FABP4. These results provide an integrated view of epidemiological factors associated with PTB and identify biological signatures of clinical covariates affecting this disease. Deep biological profiling and machine learning reveal insights into the epidemiology of preterm birth.

  @article{doi:10.1126/sciadv.ade7692,
  abstract = {Preterm birth (PTB) is the leading cause of death in children under five, yet comprehensive studies are hindered by its multiple complex etiologies. Epidemiological associations between PTB and maternal characteristics have been previously described. This work used multiomic profiling and multivariate modeling to investigate the biological signatures of these characteristics. Maternal covariates were collected during pregnancy from 13,841 pregnant women across five sites. Plasma samples from 231 participants were analyzed to generate proteomic, metabolomic, and lipidomic datasets. Machine learning models showed robust performance for the prediction of PTB (AUROC = 0.70), time-to-delivery (r = 0.65), maternal age (r = 0.59), gravidity (r = 0.56), and BMI (r = 0.81). Time-to-delivery biological correlates included fetal-associated proteins (e.g., ALPP, AFP, and PGF) and immune proteins (e.g., PD-L1, CCL28, and LIFR). Maternal age negatively correlated with collagen COL9A1, gravidity with endothelial NOS and inflammatory chemokine CXCL13, and BMI with leptin and structural protein FABP4. These results provide an integrated view of epidemiological factors associated with PTB and identify biological signatures of clinical covariates affecting this disease. Deep biological profiling and machine learning reveal insights into the epidemiology of preterm birth.},
  author = {Espinosa, Camilo A. and Khan, Waqasuddin and Khanam, Rasheda and Das, Sayan and Khalid, Javairia and Pervin, Jesmin and Kasaro, Margaret P. and Contrepois, Kévin and Chang, Alan L. and Phongpreecha, Thanaphong and Michael, Basil and Ellenberger, Mathew and Mehmood, Usma and Hotwani, Aneeta and Nizar, Ambreen and Kabir, Furqan and Wong, Ronald J. and Becker, Martin and Berson, Eloise and Culos, Anthony and Francesco, Davide De and Mataraso, Samson and Ravindra, Neal and Thuraiappah, Melan and Xenochristou, Maria and Stelzer, Ina A. and Marić, Ivana and Dutta, Arup and Raqib, Rubhana and Ahmed, Salahuddin and Rahman, Sayedur and Hasan, A. S. M. Tarik and Ali, Said M. and Juma, Mohamed H. and Rahman, Monjur and Aktar, Shaki and Deb, Saikat and Price, Joan T. and Wise, Paul H. and Winn, Virginia D. and Druzin, Maurice L. and Gibbs, Ronald S. and Darmstadt, Gary L. and Murray, Jeffrey C. and Stringer, Jeffrey S. A. and Gaudilliere, Brice and Snyder, Michael P. and Angst, Martin S. and Rahman, Anisur and Baqui, Abdullah H. and Jehan, Fyezah and Nisar, Muhammad Imran and Vwalika, Bellington and Sazawal, Sunil and Shaw, Gary M. and Stevenson, David K. and Aghaeepour, Nima},
  journal = {Science Advances},
  keywords = {ehr},
  number = 21,
  pages = {eade7692},
  title = {Multiomic signals associated with maternal epidemiological factors contributing to preterm birth in low- and middle-income countries},
  volume = 9,
  year = 2023
  }
  

  %0 Journal Article
  %1 doi:10.1126/sciadv.ade7692
  %A Espinosa, Camilo A.
  %A Khan, Waqasuddin
  %A Khanam, Rasheda
  %A Das, Sayan
  %A Khalid, Javairia
  %A Pervin, Jesmin
  %A Kasaro, Margaret P.
  %A Contrepois, Kévin
  %A Chang, Alan L.
  %A Phongpreecha, Thanaphong
  %A Michael, Basil
  %A Ellenberger, Mathew
  %A Mehmood, Usma
  %A Hotwani, Aneeta
  %A Nizar, Ambreen
  %A Kabir, Furqan
  %A Wong, Ronald J.
  %A Becker, Martin
  %A Berson, Eloise
  %A Culos, Anthony
  %A Francesco, Davide De
  %A Mataraso, Samson
  %A Ravindra, Neal
  %A Thuraiappah, Melan
  %A Xenochristou, Maria
  %A Stelzer, Ina A.
  %A Marić, Ivana
  %A Dutta, Arup
  %A Raqib, Rubhana
  %A Ahmed, Salahuddin
  %A Rahman, Sayedur
  %A Hasan, A. S. M. Tarik
  %A Ali, Said M.
  %A Juma, Mohamed H.
  %A Rahman, Monjur
  %A Aktar, Shaki
  %A Deb, Saikat
  %A Price, Joan T.
  %A Wise, Paul H.
  %A Winn, Virginia D.
  %A Druzin, Maurice L.
  %A Gibbs, Ronald S.
  %A Darmstadt, Gary L.
  %A Murray, Jeffrey C.
  %A Stringer, Jeffrey S. A.
  %A Gaudilliere, Brice
  %A Snyder, Michael P.
  %A Angst, Martin S.
  %A Rahman, Anisur
  %A Baqui, Abdullah H.
  %A Jehan, Fyezah
  %A Nisar, Muhammad Imran
  %A Vwalika, Bellington
  %A Sazawal, Sunil
  %A Shaw, Gary M.
  %A Stevenson, David K.
  %A Aghaeepour, Nima
  %D 2023
  %J Science Advances
  %N 21
  %P eade7692
  %R 10.1126/sciadv.ade7692
  %T Multiomic signals associated with maternal epidemiological factors contributing to preterm birth in low- and middle-income countries
  %U https://www.science.org/doi/abs/10.1126/sciadv.ade7692
  %V 9
  %X Preterm birth (PTB) is the leading cause of death in children under five, yet comprehensive studies are hindered by its multiple complex etiologies. Epidemiological associations between PTB and maternal characteristics have been previously described. This work used multiomic profiling and multivariate modeling to investigate the biological signatures of these characteristics. Maternal covariates were collected during pregnancy from 13,841 pregnant women across five sites. Plasma samples from 231 participants were analyzed to generate proteomic, metabolomic, and lipidomic datasets. Machine learning models showed robust performance for the prediction of PTB (AUROC = 0.70), time-to-delivery (r = 0.65), maternal age (r = 0.59), gravidity (r = 0.56), and BMI (r = 0.81). Time-to-delivery biological correlates included fetal-associated proteins (e.g., ALPP, AFP, and PGF) and immune proteins (e.g., PD-L1, CCL28, and LIFR). Maternal age negatively correlated with collagen COL9A1, gravidity with endothelial NOS and inflammatory chemokine CXCL13, and BMI with leptin and structural protein FABP4. These results provide an integrated view of epidemiological factors associated with PTB and identify biological signatures of clinical covariates affecting this disease. Deep biological profiling and machine learning reveal insights into the epidemiology of preterm birth.
  

• 
  1.

  Donovan, S. M., Aghaeepour, N., Andres, A., Azad, M. B., Becker, M., Carlson, S. E., J{ä}rvinen, K. M., Lin, W., L{ö}nnerdal, B., Slupsky, C. M., and others. (2023) Evidence for human milk as a biological system and recommendations for study design—a report from “Breastmilk Ecology: Genesis of Infant Nutrition (BEGIN)” Working Group 4, The American Journal of Clinical Nutrition, Elsevier 117, S61-S86.

  BibTeXEndNoteBibSonomy

  @article{donovan2023evidence,
  author = {Donovan, Sharon M and Aghaeepour, Nima and Andres, Aline and Azad, Meghan B and Becker, Martin and Carlson, Susan E and J{ä}rvinen, Kirsi M and Lin, Weili and L{ö}nnerdal, Bo and Slupsky, Carolyn M and others},
  journal = {The American Journal of Clinical Nutrition},
  keywords = {infant},
  pages = {S61--S86},
  publisher = {Elsevier},
  title = {Evidence for human milk as a biological system and recommendations for study design—a report from “Breastmilk Ecology: Genesis of Infant Nutrition (BEGIN)” Working Group 4},
  volume = 117,
  year = 2023
  }
  

  %0 Journal Article
  %1 donovan2023evidence
  %A Donovan, Sharon M
  %A Aghaeepour, Nima
  %A Andres, Aline
  %A Azad, Meghan B
  %A Becker, Martin
  %A Carlson, Susan E
  %A J{ä}rvinen, Kirsi M
  %A Lin, Weili
  %A L{ö}nnerdal, Bo
  %A Slupsky, Carolyn M
  %A others,
  %D 2023
  %I Elsevier
  %J The American Journal of Clinical Nutrition
  %P S61--S86
  %T Evidence for human milk as a biological system and recommendations for study design—a report from “Breastmilk Ecology: Genesis of Infant Nutrition (BEGIN)” Working Group 4
  %V 117
  

• 
  1.

  Phongpreecha, T., De Francesco, D., Chang, A., Thuraiappah, M., Becker, M., Ravindra, N., Berson, E., Espinosa, C., Mataraso, S., Godrich, D., and others. (2023) Prediction of multiple neuropathologic changes from features available during life, Alzheimer’s \& Dementia, Wiley Online Library 19, e067030.

  BibTeXEndNoteBibSonomy

  @article{phongpreecha2023prediction,
  author = {Phongpreecha, Thanaphong and De Francesco, Davide and Chang, Alan and Thuraiappah, Melan and Becker, Martin and Ravindra, Neal and Berson, Eloise and Espinosa, Camilo and Mataraso, Samson and Godrich, Dana and others},
  journal = {Alzheimer's \& Dementia},
  keywords = {myown},
  pages = {e067030},
  publisher = {Wiley Online Library},
  title = {Prediction of multiple neuropathologic changes from features available during life},
  volume = 19,
  year = 2023
  }
  

  %0 Journal Article
  %1 phongpreecha2023prediction
  %A Phongpreecha, Thanaphong
  %A De Francesco, Davide
  %A Chang, Alan
  %A Thuraiappah, Melan
  %A Becker, Martin
  %A Ravindra, Neal
  %A Berson, Eloise
  %A Espinosa, Camilo
  %A Mataraso, Samson
  %A Godrich, Dana
  %A others,
  %D 2023
  %I Wiley Online Library
  %J Alzheimer's \& Dementia
  %P e067030
  %T Prediction of multiple neuropathologic changes from features available during life
  %V 19
  

• 
  1.

  Thiele, K., Urbschat, C., Schepanski, S., Becker, M., Qi, M., Alawi, M., and Arck, P. (2023) Pregnancy-induced memory CD4+ regulatory T cells: identification of specific immune memory markers using Infinity Flow, Journal of Reproductive Immunology, Elsevier 159, 104052.

  BibTeXEndNoteBibSonomy

  @article{thiele2023pregnancy,
  author = {Thiele, K and Urbschat, C and Schepanski, S and Becker, M and Qi, M and Alawi, M and Arck, PC},
  journal = {Journal of Reproductive Immunology},
  keywords = {myown},
  pages = 104052,
  publisher = {Elsevier},
  title = {Pregnancy-induced memory CD4+ regulatory T cells: identification of specific immune memory markers using Infinity Flow},
  volume = 159,
  year = 2023
  }
  

  %0 Journal Article
  %1 thiele2023pregnancy
  %A Thiele, K
  %A Urbschat, C
  %A Schepanski, S
  %A Becker, M
  %A Qi, M
  %A Alawi, M
  %A Arck, PC
  %D 2023
  %I Elsevier
  %J Journal of Reproductive Immunology
  %P 104052
  %T Pregnancy-induced memory CD4+ regulatory T cells: identification of specific immune memory markers using Infinity Flow
  %V 159
  

• 
  1.

  Francesco, D. D., Reiss, J. D., Roger, J., Tang, A. S., Chang, A. L., Becker, M., Phongpreecha, T., Espinosa, C., Morin, S., Berson, E., Thuraiappah, M., Le, B. L., Ravindra, N. G., Payrovnaziri, S. N., Mataraso, S., Kim, Y., Xue, L., Rosenstein, M. G., Oskotsky, T., Marić, I., Gaudilliere, B., Carvalho, B., Bateman, B. T., Angst, M. S., Prince, L. S., Blumenfeld, Y. J., Benitz, W. E., Fuerch, J. H., Shaw, G. M., Sylvester, K. G., Stevenson, D. K., Sirota, M., and Aghaeepour, N. (2023) Data-driven longitudinal characterization of neonatal health and morbidity, Science Translational Medicine 15, eadc9854.

  AbstractURLBibTeXEndNoteDOIBibSonomy

  Although prematurity is the single largest cause of death in children under 5 years of age, the current definition of prematurity, based on gestational age, lacks the precision needed for guiding care decisions. Here, we propose a longitudinal risk assessment for adverse neonatal outcomes in newborns based on a deep learning model that uses electronic health records (EHRs) to predict a wide range of outcomes over a period starting shortly before conception and ending months after birth. By linking the EHRs of the Lucile Packard Children’s Hospital and the Stanford Healthcare Adult Hospital, we developed a cohort of 22,104 mother-newborn dyads delivered between 2014 and 2018. Maternal and newborn EHRs were extracted and used to train a multi-input multitask deep learning model, featuring a long short-term memory neural network, to predict 24 different neonatal outcomes. An additional cohort of 10,250 mother-newborn dyads delivered at the same Stanford Hospitals from 2019 to September 2020 was used to validate the model. Areas under the receiver operating characteristic curve at delivery exceeded 0.9 for 10 of the 24 neonatal outcomes considered and were between 0.8 and 0.9 for 7 additional outcomes. Moreover, comprehensive association analysis identified multiple known associations between various maternal and neonatal features and specific neonatal outcomes. This study used linked EHRs from more than 30,000 mother-newborn dyads and would serve as a resource for the investigation and prediction of neonatal outcomes. An interactive website is available for independent investigators to leverage this unique dataset: https://maternal-child-health-associations.shinyapps.io/shiny\_app/. Machine learning models that use maternal and neonatal EHR data can assist in the assessment of risk of multiple adverse neonatal outcomes. Reduction of neonatal mortality and morbidity requires timely risk assessment so that care can be appropriately managed. Using multiple cohorts of mother and newborn dyads, De Francesco et\ al. trained and externally validated a deep learning model to predict different adverse neonatal outcomes by mining the paired electronic health records (EHRs). Their method largely outperformed currently used EHR-based clinical risk scores and can be applied to EHR data at time points ranging from early gestation to at or after birth, positioning their risk assessment model to be of potential clinical utility. —CAC

  @article{francesco2023datadriven,
  abstract = {Although prematurity is the single largest cause of death in children under 5 years of age, the current definition of prematurity, based on gestational age, lacks the precision needed for guiding care decisions. Here, we propose a longitudinal risk assessment for adverse neonatal outcomes in newborns based on a deep learning model that uses electronic health records (EHRs) to predict a wide range of outcomes over a period starting shortly before conception and ending months after birth. By linking the EHRs of the Lucile Packard Children’s Hospital and the Stanford Healthcare Adult Hospital, we developed a cohort of 22,104 mother-newborn dyads delivered between 2014 and 2018. Maternal and newborn EHRs were extracted and used to train a multi-input multitask deep learning model, featuring a long short-term memory neural network, to predict 24 different neonatal outcomes. An additional cohort of 10,250 mother-newborn dyads delivered at the same Stanford Hospitals from 2019 to September 2020 was used to validate the model. Areas under the receiver operating characteristic curve at delivery exceeded 0.9 for 10 of the 24 neonatal outcomes considered and were between 0.8 and 0.9 for 7 additional outcomes. Moreover, comprehensive association analysis identified multiple known associations between various maternal and neonatal features and specific neonatal outcomes. This study used linked EHRs from more than 30,000 mother-newborn dyads and would serve as a resource for the investigation and prediction of neonatal outcomes. An interactive website is available for independent investigators to leverage this unique dataset: https://maternal-child-health-associations.shinyapps.io/shiny\_app/. Machine learning models that use maternal and neonatal EHR data can assist in the assessment of risk of multiple adverse neonatal outcomes. Reduction of neonatal mortality and morbidity requires timely risk assessment so that care can be appropriately managed. Using multiple cohorts of mother and newborn dyads, De Francesco et\ al. trained and externally validated a deep learning model to predict different adverse neonatal outcomes by mining the paired electronic health records (EHRs). Their method largely outperformed currently used EHR-based clinical risk scores and can be applied to EHR data at time points ranging from early gestation to at or after birth, positioning their risk assessment model to be of potential clinical utility. —CAC},
  author = {Francesco, Davide De and Reiss, Jonathan D. and Roger, Jacquelyn and Tang, Alice S. and Chang, Alan L. and Becker, Martin and Phongpreecha, Thanaphong and Espinosa, Camilo and Morin, Susanna and Berson, Eloïse and Thuraiappah, Melan and Le, Brian L. and Ravindra, Neal G. and Payrovnaziri, Seyedeh Neelufar and Mataraso, Samson and Kim, Yeasul and Xue, Lei and Rosenstein, Melissa G. and Oskotsky, Tomiko and Marić, Ivana and Gaudilliere, Brice and Carvalho, Brendan and Bateman, Brian T. and Angst, Martin S. and Prince, Lawrence S. and Blumenfeld, Yair J. and Benitz, William E. and Fuerch, Janene H. and Shaw, Gary M. and Sylvester, Karl G. and Stevenson, David K. and Sirota, Marina and Aghaeepour, Nima},
  journal = {Science Translational Medicine},
  keywords = {longitudinal},
  number = 683,
  pages = {eadc9854},
  title = {Data-driven longitudinal characterization of neonatal health and morbidity},
  volume = 15,
  year = 2023
  }
  

  %0 Journal Article
  %1 francesco2023datadriven
  %A Francesco, Davide De
  %A Reiss, Jonathan D.
  %A Roger, Jacquelyn
  %A Tang, Alice S.
  %A Chang, Alan L.
  %A Becker, Martin
  %A Phongpreecha, Thanaphong
  %A Espinosa, Camilo
  %A Morin, Susanna
  %A Berson, Eloïse
  %A Thuraiappah, Melan
  %A Le, Brian L.
  %A Ravindra, Neal G.
  %A Payrovnaziri, Seyedeh Neelufar
  %A Mataraso, Samson
  %A Kim, Yeasul
  %A Xue, Lei
  %A Rosenstein, Melissa G.
  %A Oskotsky, Tomiko
  %A Marić, Ivana
  %A Gaudilliere, Brice
  %A Carvalho, Brendan
  %A Bateman, Brian T.
  %A Angst, Martin S.
  %A Prince, Lawrence S.
  %A Blumenfeld, Yair J.
  %A Benitz, William E.
  %A Fuerch, Janene H.
  %A Shaw, Gary M.
  %A Sylvester, Karl G.
  %A Stevenson, David K.
  %A Sirota, Marina
  %A Aghaeepour, Nima
  %D 2023
  %J Science Translational Medicine
  %N 683
  %P eadc9854
  %R 10.1126/scitranslmed.adc9854
  %T Data-driven longitudinal characterization of neonatal health and morbidity
  %U https://www.science.org/doi/abs/10.1126/scitranslmed.adc9854
  %V 15
  %X Although prematurity is the single largest cause of death in children under 5 years of age, the current definition of prematurity, based on gestational age, lacks the precision needed for guiding care decisions. Here, we propose a longitudinal risk assessment for adverse neonatal outcomes in newborns based on a deep learning model that uses electronic health records (EHRs) to predict a wide range of outcomes over a period starting shortly before conception and ending months after birth. By linking the EHRs of the Lucile Packard Children’s Hospital and the Stanford Healthcare Adult Hospital, we developed a cohort of 22,104 mother-newborn dyads delivered between 2014 and 2018. Maternal and newborn EHRs were extracted and used to train a multi-input multitask deep learning model, featuring a long short-term memory neural network, to predict 24 different neonatal outcomes. An additional cohort of 10,250 mother-newborn dyads delivered at the same Stanford Hospitals from 2019 to September 2020 was used to validate the model. Areas under the receiver operating characteristic curve at delivery exceeded 0.9 for 10 of the 24 neonatal outcomes considered and were between 0.8 and 0.9 for 7 additional outcomes. Moreover, comprehensive association analysis identified multiple known associations between various maternal and neonatal features and specific neonatal outcomes. This study used linked EHRs from more than 30,000 mother-newborn dyads and would serve as a resource for the investigation and prediction of neonatal outcomes. An interactive website is available for independent investigators to leverage this unique dataset: https://maternal-child-health-associations.shinyapps.io/shiny\_app/. Machine learning models that use maternal and neonatal EHR data can assist in the assessment of risk of multiple adverse neonatal outcomes. Reduction of neonatal mortality and morbidity requires timely risk assessment so that care can be appropriately managed. Using multiple cohorts of mother and newborn dyads, De Francesco et\ al. trained and externally validated a deep learning model to predict different adverse neonatal outcomes by mining the paired electronic health records (EHRs). Their method largely outperformed currently used EHR-based clinical risk scores and can be applied to EHR data at time points ranging from early gestation to at or after birth, positioning their risk assessment model to be of potential clinical utility. —CAC
  

• 
  1.

  Berson, E., Sreenivas, A., Phongpreecha, T., Perna, A., Grandi, F. C., Xue, L., Ravindra, N. G., Payrovnaziri, N., Mataraso, S., Kim, Y., Espinosa, C., Chang, A. L., Becker, M., Montine, K. S., Fox, E. J., Chang, H. Y., Corces, M. R., Aghaeepour, N., and Montine, T. J. (2023) Whole genome deconvolution unveils Alzheimer’s resilient epigenetic signature, Nature Communications, Nature Publishing Group UK London 14, 4947.

  BibTeXEndNoteBibSonomy

  @article{berson2023whole,
  author = {Berson, Eloise and Sreenivas, Anjali and Phongpreecha, Thanaphong and Perna, Amalia and Grandi, Fiorella C. and Xue, Lei and Ravindra, Neal G. and Payrovnaziri, Neelufar and Mataraso, Samson and Kim, Yeasul and Espinosa, Camilo and Chang, Alan L. and Becker, Martin and Montine, Kathleen S. and Fox, Edward J. and Chang, Howard Y. and Corces, M. Ryan and Aghaeepour, Nima and Montine, Thomas J.},
  journal = {Nature Communications},
  keywords = {learning},
  number = 1,
  pages = 4947,
  publisher = {Nature Publishing Group UK London},
  title = {Whole genome deconvolution unveils Alzheimer’s resilient epigenetic signature},
  volume = 14,
  year = 2023
  }
  

  %0 Journal Article
  %1 berson2023whole
  %A Berson, Eloise
  %A Sreenivas, Anjali
  %A Phongpreecha, Thanaphong
  %A Perna, Amalia
  %A Grandi, Fiorella C.
  %A Xue, Lei
  %A Ravindra, Neal G.
  %A Payrovnaziri, Neelufar
  %A Mataraso, Samson
  %A Kim, Yeasul
  %A Espinosa, Camilo
  %A Chang, Alan L.
  %A Becker, Martin
  %A Montine, Kathleen S.
  %A Fox, Edward J.
  %A Chang, Howard Y.
  %A Corces, M. Ryan
  %A Aghaeepour, Nima
  %A Montine, Thomas J.
  %D 2023
  %I Nature Publishing Group UK London
  %J Nature Communications
  %N 1
  %P 4947
  %T Whole genome deconvolution unveils Alzheimer’s resilient epigenetic signature
  %V 14
  

• 
  1.

  Urbschat, C., Thiele, K., Stelzer, I., Zhang, T., Zhao, Y., Kehribar, T., Pagenkemper, M., Hansen, G., Gaudilli{è}re, B., Diemert, A., and others. (2023) Differential cellular immune response in pregnant and non-pregnant women upon vaccination against SARS-CoV-2 infection, Journal of Reproductive Immunology, Elsevier 159, 104041.

  BibTeXEndNoteBibSonomy

  @article{urbschat2023differential,
  author = {Urbschat, Christopher and Thiele, Kristin and Stelzer, Ina and Zhang, Tianran and Zhao, Yu and Kehribar, Tayyip and Pagenkemper, Mirja and Hansen, Gudula and Gaudilli{è}re, Brice and Diemert, Anke and others},
  journal = {Journal of Reproductive Immunology},
  keywords = {cell},
  pages = 104041,
  publisher = {Elsevier},
  title = {Differential cellular immune response in pregnant and non-pregnant women upon vaccination against SARS-CoV-2 infection},
  volume = 159,
  year = 2023
  }
  

  %0 Journal Article
  %1 urbschat2023differential
  %A Urbschat, Christopher
  %A Thiele, Kristin
  %A Stelzer, Ina
  %A Zhang, Tianran
  %A Zhao, Yu
  %A Kehribar, Tayyip
  %A Pagenkemper, Mirja
  %A Hansen, Gudula
  %A Gaudilli{è}re, Brice
  %A Diemert, Anke
  %A others,
  %D 2023
  %I Elsevier
  %J Journal of Reproductive Immunology
  %P 104041
  %T Differential cellular immune response in pregnant and non-pregnant women upon vaccination against SARS-CoV-2 infection
  %V 159
  

• 
  1.

  Becker, M., Nassar, H., Espinosa, C., Stelzer, I. A., Feyaerts, D., Berson, E., Bidoki, N. H., Chang, A. L., Saarunya, G., Culos, A., Francesco, D. D., Fallahzadeh, R., Liu, Q., Kim, Y., Maric, I., Mataraso, S., Payrovnaziri, S. N., Phongpreecha, T., Ravindra, N. G., Stanley, N., Shome, S., Tan, Y., Thuraiappah, M., Xenochristou, M., Xue, L., Shaw, G., Stevenson, D., Angst, M. S., Gaudilliere, B., and Aghaeepour, N. (2023) Large-scale correlation network construction for unraveling the coordination of complex biological systems, Nature Computational Science.

  BibTeXEndNoteBibSonomy

  @article{becker2023large,
  author = {Becker, Martin and Nassar, Huda and Espinosa, Camilo and Stelzer, Ina A. and Feyaerts, Dorien and Berson, Eloise and Bidoki, Neda H. and Chang, Alan L. and Saarunya, Geetha and Culos, Anthony and Francesco, Davide De and Fallahzadeh, Ramin and Liu, Qun and Kim, Yeasul and Maric, Ivana and Mataraso, Samson and Payrovnaziri, Seyedeh Neelufar and Phongpreecha, Thanaphong and Ravindra, Neal G. and Stanley, Natalie and Shome, Sayane and Tan, Yuqi and Thuraiappah, Melan and Xenochristou, Maria and Xue, Lei and Shaw, Gary and Stevenson, David and Angst, Martin S. and Gaudilliere, Brice and Aghaeepour, Nima},
  journal = {Nature Computational Science},
  keywords = {skipstats},
  month = {04},
  title = {Large-scale correlation network construction for unraveling the coordination of complex biological systems},
  year = 2023
  }
  

  %0 Journal Article
  %1 becker2023large
  %A Becker, Martin
  %A Nassar, Huda
  %A Espinosa, Camilo
  %A Stelzer, Ina A.
  %A Feyaerts, Dorien
  %A Berson, Eloise
  %A Bidoki, Neda H.
  %A Chang, Alan L.
  %A Saarunya, Geetha
  %A Culos, Anthony
  %A Francesco, Davide De
  %A Fallahzadeh, Ramin
  %A Liu, Qun
  %A Kim, Yeasul
  %A Maric, Ivana
  %A Mataraso, Samson
  %A Payrovnaziri, Seyedeh Neelufar
  %A Phongpreecha, Thanaphong
  %A Ravindra, Neal G.
  %A Stanley, Natalie
  %A Shome, Sayane
  %A Tan, Yuqi
  %A Thuraiappah, Melan
  %A Xenochristou, Maria
  %A Xue, Lei
  %A Shaw, Gary
  %A Stevenson, David
  %A Angst, Martin S.
  %A Gaudilliere, Brice
  %A Aghaeepour, Nima
  %D 2023
  %J Nature Computational Science
  %T Large-scale correlation network construction for unraveling the coordination of complex biological systems
  

2022

• 
  1.

  {De Francesco}, D., Blumenfeld, Y. J., Marić, I., Mayo, J. A., Chang, A. L., Fallahzadeh, R., Phongpreecha, T., Butwick, A. J., Xenochristou, M., Phibbs, C. S., Bidoki, N. H., Becker, M., Culos, A., Espinosa, C., Liu, Q., Sylvester, K. G., Gaudilliere, B., Angst, M. S., Stevenson, D. K., Shaw, G. M., and Aghaeepour, N. (2022) A data-driven health index for neonatal morbidities, iScience, Elsevier 104143.

  BibTeXEndNoteBibSonomyDownload

  @article{defrancesco2022datadriven,
  author = {{De Francesco}, Davide and Blumenfeld, Yair J. and Marić, Ivana and Mayo, Jonathan A. and Chang, Alan L. and Fallahzadeh, Ramin and Phongpreecha, Thanaphong and Butwick, Alex J. and Xenochristou, Maria and Phibbs, Ciaran S. and Bidoki, Neda H. and Becker, Martin and Culos, Anthony and Espinosa, Camilo and Liu, Qun and Sylvester, Karl G. and Gaudilliere, Brice and Angst, Martin S. and Stevenson, David K. and Shaw, Gary M. and Aghaeepour, Nima},
  journal = {iScience},
  keywords = {nn},
  pages = 104143,
  publisher = {Elsevier},
  title = {A data-driven health index for neonatal morbidities},
  year = 2022
  }
  

  %0 Journal Article
  %1 defrancesco2022datadriven
  %A {De Francesco}, Davide
  %A Blumenfeld, Yair J.
  %A Marić, Ivana
  %A Mayo, Jonathan A.
  %A Chang, Alan L.
  %A Fallahzadeh, Ramin
  %A Phongpreecha, Thanaphong
  %A Butwick, Alex J.
  %A Xenochristou, Maria
  %A Phibbs, Ciaran S.
  %A Bidoki, Neda H.
  %A Becker, Martin
  %A Culos, Anthony
  %A Espinosa, Camilo
  %A Liu, Qun
  %A Sylvester, Karl G.
  %A Gaudilliere, Brice
  %A Angst, Martin S.
  %A Stevenson, David K.
  %A Shaw, Gary M.
  %A Aghaeepour, Nima
  %D 2022
  %I Elsevier
  %J iScience
  %P 104143
  %T A data-driven health index for neonatal morbidities
  

• 
  1.

  Panelli, D. M., Leonard, S. A., Wong, R. J., Becker, M., Mayo, J. A., Wu, E., Girsen, A. I., Gotlib, I. H., Aghaeepour, N., Druzin, M. L., and others. (2022) Leukocyte telomere dynamics across gestation in uncomplicated pregnancies and associations with stress, BMC Pregnancy and Childbirth, BioMed Central 22, 1–12.

  BibTeXEndNoteBibSonomyDownload

  @article{panelli2022leukocyte,
  author = {Panelli, Danielle M and Leonard, Stephanie A and Wong, Ronald J and Becker, Martin and Mayo, Jonathan A and Wu, Erica and Girsen, Anna I and Gotlib, Ian H and Aghaeepour, Nima and Druzin, Maurice L and others},
  journal = {BMC Pregnancy and Childbirth},
  keywords = {learning},
  number = 1,
  pages = {1--12},
  publisher = {BioMed Central},
  title = {Leukocyte telomere dynamics across gestation in uncomplicated pregnancies and associations with stress},
  volume = 22,
  year = 2022
  }
  

  %0 Journal Article
  %1 panelli2022leukocyte
  %A Panelli, Danielle M
  %A Leonard, Stephanie A
  %A Wong, Ronald J
  %A Becker, Martin
  %A Mayo, Jonathan A
  %A Wu, Erica
  %A Girsen, Anna I
  %A Gotlib, Ian H
  %A Aghaeepour, Nima
  %A Druzin, Maurice L
  %A others,
  %D 2022
  %I BioMed Central
  %J BMC Pregnancy and Childbirth
  %N 1
  %P 1--12
  %T Leukocyte telomere dynamics across gestation in uncomplicated pregnancies and associations with stress
  %V 22
  

• 
  1.

  Becker, M., Feyaerts, D., Stelzer, I. A., Berson, E., Chang, A. L., Espinosa, C., Francesco, D. D., Fallahzadeh, R., Maric, I., Mataraso, S. J., Nassar, H., Phongpreecha, T., Ravindra, N. G., Stanley, N., Thuraiappah, M., Shaw, G., Stevenson, D., Angst, M. S., Gaudilliere, B., and Aghaeepour, N. (2022) Profiling functional disruption in biological systems, Under review.

  BibTeXEndNoteBibSonomy

  @article{becker2022profiling,
  author = {Becker, Martin and Feyaerts, Dorien and Stelzer, Ina A. and Berson, Eloise and Chang, Alan L. and Espinosa, Camilo and Francesco, Davide De and Fallahzadeh, Ramin and Maric, Ivana and Mataraso, Samson J. and Nassar, Huda and Phongpreecha, Thanaphong and Ravindra, Neal G. and Stanley, Natalie and Thuraiappah, Melan and Shaw, Gary and Stevenson, David and Angst, Martin S. and Gaudilliere, Brice and Aghaeepour, Nima},
  journal = {Under review},
  keywords = {skipstats},
  title = {Profiling functional disruption in biological systems},
  year = 2022
  }
  

  %0 Journal Article
  %1 becker2022profiling
  %A Becker, Martin
  %A Feyaerts, Dorien
  %A Stelzer, Ina A.
  %A Berson, Eloise
  %A Chang, Alan L.
  %A Espinosa, Camilo
  %A Francesco, Davide De
  %A Fallahzadeh, Ramin
  %A Maric, Ivana
  %A Mataraso, Samson J.
  %A Nassar, Huda
  %A Phongpreecha, Thanaphong
  %A Ravindra, Neal G.
  %A Stanley, Natalie
  %A Thuraiappah, Melan
  %A Shaw, Gary
  %A Stevenson, David
  %A Angst, Martin S.
  %A Gaudilliere, Brice
  %A Aghaeepour, Nima
  %D 2022
  %J Under review
  %T Profiling functional disruption in biological systems
  

• 
  1.

  Mari{{\’c}}, I., Contrepois, K., Moufarrej, M. N., Stelzer, I. A., Feyaerts, D., Han, X., Tang, A., Stanley, N., Wong, R. J., Traber, G. M., and others. (2022) Early prediction and longitudinal modeling of preeclampsia from multiomics, Patterns, Elsevier 3, 100655.

  BibTeXEndNoteBibSonomy

  @article{maric2022early,
  author = {Mari{{\'c}}, Ivana and Contrepois, K{é}vin and Moufarrej, Mira N and Stelzer, Ina A and Feyaerts, Dorien and Han, Xiaoyuan and Tang, Andy and Stanley, Natalie and Wong, Ronald J and Traber, Gavin M and others},
  journal = {Patterns},
  keywords = {longitudinal},
  number = 12,
  pages = 100655,
  publisher = {Elsevier},
  title = {Early prediction and longitudinal modeling of preeclampsia from multiomics},
  volume = 3,
  year = 2022
  }
  

  %0 Journal Article
  %1 maric2022early
  %A Mari{{\'c}}, Ivana
  %A Contrepois, K{é}vin
  %A Moufarrej, Mira N
  %A Stelzer, Ina A
  %A Feyaerts, Dorien
  %A Han, Xiaoyuan
  %A Tang, Andy
  %A Stanley, Natalie
  %A Wong, Ronald J
  %A Traber, Gavin M
  %A others,
  %D 2022
  %I Elsevier
  %J Patterns
  %N 12
  %P 100655
  %T Early prediction and longitudinal modeling of preeclampsia from multiomics
  %V 3
  

• 
  1.

  Becker, M., Dai, J., Chang, A. L., Feyaerts, D., Stelzer, I. A., Zhang, M., Berson, E., Saarunya, G., De Francesco, D., Espinosa, C., and others. (2022) Revealing the impact of lifestyle stressors on the risk of adverse pregnancy outcomes with multitask machine learning, Frontiers in Pediatrics, Frontiers Media SA 10.

  BibTeXEndNoteBibSonomy

  @article{becker2022revealing,
  author = {Becker, Martin and Dai, Jennifer and Chang, Alan L and Feyaerts, Dorien and Stelzer, Ina A and Zhang, Miao and Berson, Eloise and Saarunya, Geetha and De Francesco, Davide and Espinosa, Camilo and others},
  journal = {Frontiers in Pediatrics},
  keywords = {single},
  publisher = {Frontiers Media SA},
  title = {Revealing the impact of lifestyle stressors on the risk of adverse pregnancy outcomes with multitask machine learning},
  volume = 10,
  year = 2022
  }
  

  %0 Journal Article
  %1 becker2022revealing
  %A Becker, Martin
  %A Dai, Jennifer
  %A Chang, Alan L
  %A Feyaerts, Dorien
  %A Stelzer, Ina A
  %A Zhang, Miao
  %A Berson, Eloise
  %A Saarunya, Geetha
  %A De Francesco, Davide
  %A Espinosa, Camilo
  %A others,
  %D 2022
  %I Frontiers Media SA
  %J Frontiers in Pediatrics
  %T Revealing the impact of lifestyle stressors on the risk of adverse pregnancy outcomes with multitask machine learning
  %V 10
  

• 
  1.

  Choi, J., Aghaeepour, N., and Becker, M. (2022) Machine Learning Techniques. In Statistics and Research Methods for Acute Care and General Surgeons (Ceresoli, M., Abu-Zidan, F. M., Staudenmayer, K. L., Catena, F., and Coccolini, F., Eds.), pp. 147–164, Springer International Publishing, Cham.

  AbstractURLBibTeXEndNoteDOIBibSonomy

  Machine learning comprises algorithms that can perform tasks they were not explicitly programmed to perform. Explicitly programmed algorithms perform tasks according to a predefined sequence of instructions. Conversely, machine learning algorithms are programmed to learn to perform tasks using input data. In the era of abundant data, affordable data storage, and computational capabilities, understanding machine learning algorithms is critical to better explore and answer questions that can advance surgical science.

  @inbook{Choi2022,
  abstract = {Machine learning comprises algorithms that can perform tasks they were not explicitly programmed to perform. Explicitly programmed algorithms perform tasks according to a predefined sequence of instructions. Conversely, machine learning algorithms are programmed to learn to perform tasks using input data. In the era of abundant data, affordable data storage, and computational capabilities, understanding machine learning algorithms is critical to better explore and answer questions that can advance surgical science.},
  address = {Cham},
  author = {Choi, Jeff and Aghaeepour, Nima and Becker, Martin},
  booktitle = {Statistics and Research Methods for Acute Care and General Surgeons},
  editor = {Ceresoli, Marco and Abu-Zidan, Fikri M. and Staudenmayer, Kristan L. and Catena, Fausto and Coccolini, Federico},
  keywords = {surgery},
  pages = {147--164},
  publisher = {Springer International Publishing},
  title = {Machine Learning Techniques},
  year = 2022
  }
  

  %0 Book Section
  %1 Choi2022
  %A Choi, Jeff
  %A Aghaeepour, Nima
  %A Becker, Martin
  %B Statistics and Research Methods for Acute Care and General Surgeons
  %C Cham
  %D 2022
  %E Ceresoli, Marco
  %E Abu-Zidan, Fikri M.
  %E Staudenmayer, Kristan L.
  %E Catena, Fausto
  %E Coccolini, Federico
  %I Springer International Publishing
  %P 147--164
  %R 10.1007/978-3-031-13818-8_12
  %T Machine Learning Techniques
  %U https://doi.org/10.1007/978-3-031-13818-8_12
  %X Machine learning comprises algorithms that can perform tasks they were not explicitly programmed to perform. Explicitly programmed algorithms perform tasks according to a predefined sequence of instructions. Conversely, machine learning algorithms are programmed to learn to perform tasks using input data. In the era of abundant data, affordable data storage, and computational capabilities, understanding machine learning algorithms is critical to better explore and answer questions that can advance surgical science.
  %@ 978-3-031-13818-8
  

• 
  1.

  Fallahzadeh, R., Bidoki, N. H., Stelzer, I. A., Becker, M., Mari{{\’c}}, I., Chang, A. L., Culos, A., Phongpreecha, T., Xenochristou, M., De Francesco, D., and others. (2022) In-Silico Generation of High-Dimensional Immune Response Data in Patients using a Deep Neural Network, Cytometry Part A, Wiley Online Library.

  BibTeXEndNoteBibSonomy

  @article{fallahzadeh2022silico,
  author = {Fallahzadeh, Ramin and Bidoki, Neda H and Stelzer, Ina A and Becker, Martin and Mari{{\'c}}, Ivana and Chang, Alan L and Culos, Anthony and Phongpreecha, Thanaphong and Xenochristou, Maria and De Francesco, Davide and others},
  journal = {Cytometry Part A},
  keywords = {cell},
  publisher = {Wiley Online Library},
  title = {In-Silico Generation of High-Dimensional Immune Response Data in Patients using a Deep Neural Network},
  year = 2022
  }
  

  %0 Journal Article
  %1 fallahzadeh2022silico
  %A Fallahzadeh, Ramin
  %A Bidoki, Neda H
  %A Stelzer, Ina A
  %A Becker, Martin
  %A Mari{{\'c}}, Ivana
  %A Chang, Alan L
  %A Culos, Anthony
  %A Phongpreecha, Thanaphong
  %A Xenochristou, Maria
  %A De Francesco, Davide
  %A others,
  %D 2022
  %I Wiley Online Library
  %J Cytometry Part A
  %T In-Silico Generation of High-Dimensional Immune Response Data in Patients using a Deep Neural Network
  

2021

• 
  1.

  Phongpreecha, T., Gajera, C. R., Liu, C. C., Vijayaragavan, K., Chang, A. L., Becker, M., Fallahzadeh, R., Fernandez, R., Postupna, N., Sherfield, E., and others. (2021) Single-synapse analyses of Alzheimer’s disease implicate pathologic tau, DJ1, CD47, and ApoE, Science advances, American Association for the Advancement of Science 7, eabk0473.

  BibTeXEndNoteBibSonomyDownload

  @article{phongpreecha2021single,
  author = {Phongpreecha, Thanaphong and Gajera, Chandresh R and Liu, Candace C and Vijayaragavan, Kausalia and Chang, Alan L and Becker, Martin and Fallahzadeh, Ramin and Fernandez, Rosemary and Postupna, Nadia and Sherfield, Emily and others},
  journal = {Science advances},
  keywords = {single},
  number = 51,
  pages = {eabk0473},
  publisher = {American Association for the Advancement of Science},
  title = {Single-synapse analyses of Alzheimer’s disease implicate pathologic tau, DJ1, CD47, and ApoE},
  volume = 7,
  year = 2021
  }
  

  %0 Journal Article
  %1 phongpreecha2021single
  %A Phongpreecha, Thanaphong
  %A Gajera, Chandresh R
  %A Liu, Candace C
  %A Vijayaragavan, Kausalia
  %A Chang, Alan L
  %A Becker, Martin
  %A Fallahzadeh, Ramin
  %A Fernandez, Rosemary
  %A Postupna, Nadia
  %A Sherfield, Emily
  %A others,
  %D 2021
  %I American Association for the Advancement of Science
  %J Science advances
  %N 51
  %P eabk0473
  %T Single-synapse analyses of Alzheimer’s disease implicate pathologic tau, DJ1, CD47, and ApoE
  %V 7
  

• 
  1.

  Ramirez-Celis, A., Becker, M., Nu{ñ}o, M., Schauer, J., Aghaeepour, N., and Van de Water, J. (2021) Risk assessment analysis for maternal autoantibody-related autism (MAR-ASD): a subtype of autism, Molecular Psychiatry, Nature Publishing Group 1–10.

  BibTeXEndNoteBibSonomyDownload

  @article{ramirez2021risk,
  author = {Ramirez-Celis, Alexandra and Becker, Martin and Nu{ñ}o, Miriam and Schauer, Joseph and Aghaeepour, Nima and Van de Water, Judy},
  journal = {Molecular Psychiatry},
  keywords = {p21},
  pages = {1--10},
  publisher = {Nature Publishing Group},
  title = {Risk assessment analysis for maternal autoantibody-related autism (MAR-ASD): a subtype of autism},
  year = 2021
  }
  

  %0 Journal Article
  %1 ramirez2021risk
  %A Ramirez-Celis, Alexandra
  %A Becker, Martin
  %A Nu{ñ}o, Miriam
  %A Schauer, Joseph
  %A Aghaeepour, Nima
  %A Van de Water, Judy
  %D 2021
  %I Nature Publishing Group
  %J Molecular Psychiatry
  %P 1--10
  %T Risk assessment analysis for maternal autoantibody-related autism (MAR-ASD): a subtype of autism
  

• 
  1.

  Stelzer, I. A., Ghaemi, M. S., Han, X., Ando, K., Hedou, J. J., Feyaerts, D., Peterson, L. S., Rumer, K. K., Tsai, E. S., Ganio, E. A., Gaudilliere, D. K., Tsai, A. S., Choisy, B., Gaigne, L. P., Verdonk, F., Jacobsen, D., Gavasso, S., Traber, G. M., Ellenberger, M., Stanley, N., Becker, M., Culos, A., Fallahzadeh, R., Wong, R. J., Darmstadt, G. L., Druzin, M. L., Winn, V. D., Gibbs, R. S., Ling, X. B., Sylvester, K., Carvalho, B., Snyder, M. P., Shaw, G. M., Stevenson, D. K., Contrepois, K., Angst, M. S., Aghaeepour, N., and Gaudilliere, B. (2021) Integrated trajectories of the maternal metabolome, proteome, and immunome predict labor onset, Science Translational Medicine, American Association for the Advancement of Science 13.

  AbstractURLBibTeXEndNoteDOIBibSonomyDownload

  Current methods to predict spontaneous labor are fairly inaccurate. To provide better estimates and biomarkers of labor onset, the biological processes that lead up to labor need to be better understood. Stelzer et al. performed metabolome, proteome, and immunome studies on blood samples from 63 women in the 100 days before delivery. They identified a surge in IL-1R4 and steroid hormones in the weeks before delivery, which was coordinated with a switch from immune activation to regulation of inflammatory responses. A model was then constructed to predict time to labor independent of gestational age. These results may be helpful for development of more accurate methods to predict labor.Estimating the time of delivery is of high clinical importance because pre- and postterm deviations are associated with complications for the mother and her offspring. However, current estimations are inaccurate. As pregnancy progresses toward labor, major transitions occur in fetomaternal immune, metabolic, and endocrine systems that culminate in birth. The comprehensive characterization of maternal biology that precedes labor is key to understanding these physiological transitions and identifying predictive biomarkers of delivery. Here, a longitudinal study was conducted in 63 women who went into labor spontaneously. More than 7000 plasma analytes and peripheral immune cell responses were analyzed using untargeted mass spectrometry, aptamer-based proteomic technology, and single-cell mass cytometry in serial blood samples collected during the last 100 days of pregnancy. The high-dimensional dataset was integrated into a multiomic model that predicted the time to spontaneous labor [R = 0.85, 95\% confidence interval (CI) [0.79 to 0.89], P = 1.2 {\texttimes} 10-40, N = 53, training set; R = 0.81, 95\% CI [0.61 to 0.91], P = 3.9 {\texttimes} 10-7, N = 10, independent test set]. Coordinated alterations in maternal metabolome, proteome, and immunome marked a molecular shift from pregnancy maintenance to prelabor biology 2 to 4 weeks before delivery. A surge in steroid hormone metabolites and interleukin-1 receptor type 4 that preceded labor coincided with a switch from immune activation to regulation of inflammatory responses. Our study lays the groundwork for developing blood-based methods for predicting the day of labor, anchored in mechanisms shared in preterm and term pregnancies.

  @article{stelzer2021integrated,
  abstract = {Current methods to predict spontaneous labor are fairly inaccurate. To provide better estimates and biomarkers of labor onset, the biological processes that lead up to labor need to be better understood. Stelzer et al. performed metabolome, proteome, and immunome studies on blood samples from 63 women in the 100 days before delivery. They identified a surge in IL-1R4 and steroid hormones in the weeks before delivery, which was coordinated with a switch from immune activation to regulation of inflammatory responses. A model was then constructed to predict time to labor independent of gestational age. These results may be helpful for development of more accurate methods to predict labor.Estimating the time of delivery is of high clinical importance because pre- and postterm deviations are associated with complications for the mother and her offspring. However, current estimations are inaccurate. As pregnancy progresses toward labor, major transitions occur in fetomaternal immune, metabolic, and endocrine systems that culminate in birth. The comprehensive characterization of maternal biology that precedes labor is key to understanding these physiological transitions and identifying predictive biomarkers of delivery. Here, a longitudinal study was conducted in 63 women who went into labor spontaneously. More than 7000 plasma analytes and peripheral immune cell responses were analyzed using untargeted mass spectrometry, aptamer-based proteomic technology, and single-cell mass cytometry in serial blood samples collected during the last 100 days of pregnancy. The high-dimensional dataset was integrated into a multiomic model that predicted the time to spontaneous labor [R = 0.85, 95\% confidence interval (CI) [0.79 to 0.89], P = 1.2 {\texttimes} 10-40, N = 53, training set; R = 0.81, 95\% CI [0.61 to 0.91], P = 3.9 {\texttimes} 10-7, N = 10, independent test set]. Coordinated alterations in maternal metabolome, proteome, and immunome marked a molecular shift from pregnancy maintenance to prelabor biology 2 to 4 weeks before delivery. A surge in steroid hormone metabolites and interleukin-1 receptor type 4 that preceded labor coincided with a switch from immune activation to regulation of inflammatory responses. Our study lays the groundwork for developing blood-based methods for predicting the day of labor, anchored in mechanisms shared in preterm and term pregnancies.},
  author = {Stelzer, Ina A. and Ghaemi, Mohammad S. and Han, Xiaoyuan and Ando, Kazuo and Hedou, Julien J. and Feyaerts, Dorien and Peterson, Laura S. and Rumer, Kristen K. and Tsai, Eileen S. and Ganio, Edward A. and Gaudilliere, Dyani K. and Tsai, Amy S. and Choisy, Benjamin and Gaigne, Lea P. and Verdonk, Franck and Jacobsen, Danielle and Gavasso, Sonia and Traber, Gavin M. and Ellenberger, Mathew and Stanley, Natalie and Becker, Martin and Culos, Anthony and Fallahzadeh, Ramin and Wong, Ronald J. and Darmstadt, Gary L. and Druzin, Maurice L. and Winn, Virginia D. and Gibbs, Ronald S. and Ling, Xuefeng B. and Sylvester, Karl and Carvalho, Brendan and Snyder, Michael P. and Shaw, Gary M. and Stevenson, David K. and Contrepois, Kevin and Angst, Martin S. and Aghaeepour, Nima and Gaudilliere, Brice},
  journal = {Science Translational Medicine},
  keywords = {onset},
  number = 592,
  publisher = {American Association for the Advancement of Science},
  title = {Integrated trajectories of the maternal metabolome, proteome, and immunome predict labor onset},
  volume = 13,
  year = 2021
  }
  

  %0 Journal Article
  %1 stelzer2021integrated
  %A Stelzer, Ina A.
  %A Ghaemi, Mohammad S.
  %A Han, Xiaoyuan
  %A Ando, Kazuo
  %A Hedou, Julien J.
  %A Feyaerts, Dorien
  %A Peterson, Laura S.
  %A Rumer, Kristen K.
  %A Tsai, Eileen S.
  %A Ganio, Edward A.
  %A Gaudilliere, Dyani K.
  %A Tsai, Amy S.
  %A Choisy, Benjamin
  %A Gaigne, Lea P.
  %A Verdonk, Franck
  %A Jacobsen, Danielle
  %A Gavasso, Sonia
  %A Traber, Gavin M.
  %A Ellenberger, Mathew
  %A Stanley, Natalie
  %A Becker, Martin
  %A Culos, Anthony
  %A Fallahzadeh, Ramin
  %A Wong, Ronald J.
  %A Darmstadt, Gary L.
  %A Druzin, Maurice L.
  %A Winn, Virginia D.
  %A Gibbs, Ronald S.
  %A Ling, Xuefeng B.
  %A Sylvester, Karl
  %A Carvalho, Brendan
  %A Snyder, Michael P.
  %A Shaw, Gary M.
  %A Stevenson, David K.
  %A Contrepois, Kevin
  %A Angst, Martin S.
  %A Aghaeepour, Nima
  %A Gaudilliere, Brice
  %D 2021
  %I American Association for the Advancement of Science
  %J Science Translational Medicine
  %N 592
  %R 10.1126/scitranslmed.abd9898
  %T Integrated trajectories of the maternal metabolome, proteome, and immunome predict labor onset
  %U https://stm.sciencemag.org/content/13/592/eabd9898
  %V 13
  %X Current methods to predict spontaneous labor are fairly inaccurate. To provide better estimates and biomarkers of labor onset, the biological processes that lead up to labor need to be better understood. Stelzer et al. performed metabolome, proteome, and immunome studies on blood samples from 63 women in the 100 days before delivery. They identified a surge in IL-1R4 and steroid hormones in the weeks before delivery, which was coordinated with a switch from immune activation to regulation of inflammatory responses. A model was then constructed to predict time to labor independent of gestational age. These results may be helpful for development of more accurate methods to predict labor.Estimating the time of delivery is of high clinical importance because pre- and postterm deviations are associated with complications for the mother and her offspring. However, current estimations are inaccurate. As pregnancy progresses toward labor, major transitions occur in fetomaternal immune, metabolic, and endocrine systems that culminate in birth. The comprehensive characterization of maternal biology that precedes labor is key to understanding these physiological transitions and identifying predictive biomarkers of delivery. Here, a longitudinal study was conducted in 63 women who went into labor spontaneously. More than 7000 plasma analytes and peripheral immune cell responses were analyzed using untargeted mass spectrometry, aptamer-based proteomic technology, and single-cell mass cytometry in serial blood samples collected during the last 100 days of pregnancy. The high-dimensional dataset was integrated into a multiomic model that predicted the time to spontaneous labor [R = 0.85, 95\% confidence interval (CI) [0.79 to 0.89], P = 1.2 {\texttimes} 10-40, N = 53, training set; R = 0.81, 95\% CI [0.61 to 0.91], P = 3.9 {\texttimes} 10-7, N = 10, independent test set]. Coordinated alterations in maternal metabolome, proteome, and immunome marked a molecular shift from pregnancy maintenance to prelabor biology 2 to 4 weeks before delivery. A surge in steroid hormone metabolites and interleukin-1 receptor type 4 that preceded labor coincided with a switch from immune activation to regulation of inflammatory responses. Our study lays the groundwork for developing blood-based methods for predicting the day of labor, anchored in mechanisms shared in preterm and term pregnancies.
  

• 
  1.

  Espinosa, C., Becker, M., Maric, I., Wong, R. J., Shaw, G. M., Gaudilliere, B., Aghaeepour, N., Stevenson, D. K., Stelzer, I. A., Peterson, L. S., Chang, A. L., Xenochristou, M., Phongpreecha, T., {De Francesco}, D., Katz, M., Blumenfeld, Y. J., and Angst, M. S. (2021) Data-Driven Modeling of Pregnancy-Related Complications, Trends in Molecular Medicine.

  AbstractURLBibTeXEndNoteDOIBibSonomyDownload

  A healthy pregnancy depends on complex interrelated biological adaptations involving placentation, maternal immune responses, and hormonal homeostasis. Recent advances in high-throughput technologies have provided access to multiomics biological data that, combined with clinical and social data, can provide a deeper understanding of normal and abnormal pregnancies. Integration of these heterogeneous datasets using state-of-the-art machine-learning methods can enable the prediction of short- and long-term health trajectories for a mother and offspring and the development of treatments to prevent or minimize complications. We review advanced machine-learning methods that could: provide deeper biological insights into a pregnancy not yet unveiled by current methodologies; clarify the etiologies and heterogeneity of pathologies that affect a pregnancy; and suggest the best approaches to address disparities in outcomes affecting vulnerable populations.

  @article{espinosa2021datadriven,
  abstract = {A healthy pregnancy depends on complex interrelated biological adaptations involving placentation, maternal immune responses, and hormonal homeostasis. Recent advances in high-throughput technologies have provided access to multiomics biological data that, combined with clinical and social data, can provide a deeper understanding of normal and abnormal pregnancies. Integration of these heterogeneous datasets using state-of-the-art machine-learning methods can enable the prediction of short- and long-term health trajectories for a mother and offspring and the development of treatments to prevent or minimize complications. We review advanced machine-learning methods that could: provide deeper biological insights into a pregnancy not yet unveiled by current methodologies; clarify the etiologies and heterogeneity of pathologies that affect a pregnancy; and suggest the best approaches to address disparities in outcomes affecting vulnerable populations.},
  author = {Espinosa, Camilo and Becker, Martin and Maric, Ivana and Wong, Ronald J. and Shaw, Gary M. and Gaudilliere, Brice and Aghaeepour, Nima and Stevenson, David K. and Stelzer, Ina A. and Peterson, Laura S. and Chang, Alan L. and Xenochristou, Maria and Phongpreecha, Thanaphong and {De Francesco}, Davide and Katz, Michael and Blumenfeld, Yair J. and Angst, Martin S.},
  journal = {Trends in Molecular Medicine},
  keywords = {driven},
  title = {Data-Driven Modeling of Pregnancy-Related Complications},
  year = 2021
  }
  

  %0 Journal Article
  %1 espinosa2021datadriven
  %A Espinosa, Camilo
  %A Becker, Martin
  %A Maric, Ivana
  %A Wong, Ronald J.
  %A Shaw, Gary M.
  %A Gaudilliere, Brice
  %A Aghaeepour, Nima
  %A Stevenson, David K.
  %A Stelzer, Ina A.
  %A Peterson, Laura S.
  %A Chang, Alan L.
  %A Xenochristou, Maria
  %A Phongpreecha, Thanaphong
  %A {De Francesco}, Davide
  %A Katz, Michael
  %A Blumenfeld, Yair J.
  %A Angst, Martin S.
  %D 2021
  %J Trends in Molecular Medicine
  %R https://doi.org/10.1016/j.molmed.2021.01.007
  %T Data-Driven Modeling of Pregnancy-Related Complications
  %U https://www.sciencedirect.com/science/article/pii/S1471491421000393
  %X A healthy pregnancy depends on complex interrelated biological adaptations involving placentation, maternal immune responses, and hormonal homeostasis. Recent advances in high-throughput technologies have provided access to multiomics biological data that, combined with clinical and social data, can provide a deeper understanding of normal and abnormal pregnancies. Integration of these heterogeneous datasets using state-of-the-art machine-learning methods can enable the prediction of short- and long-term health trajectories for a mother and offspring and the development of treatments to prevent or minimize complications. We review advanced machine-learning methods that could: provide deeper biological insights into a pregnancy not yet unveiled by current methodologies; clarify the etiologies and heterogeneity of pathologies that affect a pregnancy; and suggest the best approaches to address disparities in outcomes affecting vulnerable populations.
  

• 
  1.

  Stamm, F. I., Becker, M., Strohmaier, M., and Lemmerich, F. (2021) Redescription Model Mining. In Proceedings of the 27nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, ACM.

  BibTeXEndNoteDOIBibSonomyDownload

  @inproceedings{stamm2021redescription,
  author = {Stamm, Felix I. and Becker, Martin and Strohmaier, Markus and Lemmerich, Florian},
  booktitle = {Proceedings of the 27nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining},
  keywords = {redescription},
  publisher = {ACM},
  series = {KDD '21},
  title = {Redescription Model Mining},
  year = 2021
  }
  

  %0 Conference Paper
  %1 stamm2021redescription
  %A Stamm, Felix I.
  %A Becker, Martin
  %A Strohmaier, Markus
  %A Lemmerich, Florian
  %B Proceedings of the 27nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
  %D 2021
  %I ACM
  %R 10.1145/3447548.3467366
  %T Redescription Model Mining
  

• 
  1.

  Becker, M., Mayo, J. A., Phogat, N. K., Quaintance, C. C., Laborde, A., King, L., Gotlib, I. H., Gaudilliere, B., Angst, M. S., Shaw, G. M., Stevenson, D. K., Aghaeepour, N., and Dhabhar, F. S. (2021) Deleterious and Protective Psychosocial and Stress-Related Factors Predict Risk of Spontaneous Preterm Birth, American journal of perinatology.

  URLBibTeXEndNoteDOIBibSonomyDownload

  @article{becker2021deleterious,
  author = {Becker, Martin and Mayo, Jonathan A and Phogat, Nisha K and Quaintance, Cecele C and Laborde, Ana and King, Lucy and Gotlib, Ian H and Gaudilliere, Brice and Angst, Martin S and Shaw, Gary M and Stevenson, David K and Aghaeepour, Nima and Dhabhar, Firdaus S},
  journal = {American journal of perinatology},
  keywords = {learning},
  month = {05},
  title = {Deleterious and Protective Psychosocial and Stress-Related Factors Predict Risk of Spontaneous Preterm Birth},
  year = 2021
  }
  

  %0 Journal Article
  %1 becker2021deleterious
  %A Becker, Martin
  %A Mayo, Jonathan A
  %A Phogat, Nisha K
  %A Quaintance, Cecele C
  %A Laborde, Ana
  %A King, Lucy
  %A Gotlib, Ian H
  %A Gaudilliere, Brice
  %A Angst, Martin S
  %A Shaw, Gary M
  %A Stevenson, David K
  %A Aghaeepour, Nima
  %A Dhabhar, Firdaus S
  %D 2021
  %J American journal of perinatology
  %R 10.1055/s-0041-1729162
  %T Deleterious and Protective Psychosocial and Stress-Related Factors Predict Risk of Spontaneous Preterm Birth
  %U https://doi.org/10.1055/s-0041-1729162
  

• 
  1.

  Fallahzadeh, R., Verdonk, F., Ganio, E., Culos, A., Stanley, N., Maric, I., Chang, A. L., Becker, M., Phongpreecha, T., Xenochristou, M., and others. (2021) Objective Activity Parameters Track Patient-Specific Physical Recovery Trajectories After Surgery and Link With Individual Preoperative Immune States, Annals of Surgery, LWW.

  BibTeXEndNoteDOIBibSonomyDownload

  @article{fallahzadeh2021objective,
  author = {Fallahzadeh, Ramin and Verdonk, Franck and Ganio, Ed and Culos, Anthony and Stanley, Natalie and Maric, Ivana and Chang, Alan L and Becker, Martin and Phongpreecha, Thanaphong and Xenochristou, Maria and others},
  journal = {Annals of Surgery},
  keywords = {surgery},
  month = 10,
  publisher = {LWW},
  title = {Objective Activity Parameters Track Patient-Specific Physical Recovery Trajectories After Surgery and Link With Individual Preoperative Immune States},
  year = 2021
  }
  

  %0 Journal Article
  %1 fallahzadeh2021objective
  %A Fallahzadeh, Ramin
  %A Verdonk, Franck
  %A Ganio, Ed
  %A Culos, Anthony
  %A Stanley, Natalie
  %A Maric, Ivana
  %A Chang, Alan L
  %A Becker, Martin
  %A Phongpreecha, Thanaphong
  %A Xenochristou, Maria
  %A others,
  %D 2021
  %I LWW
  %J Annals of Surgery
  %R 10.1097/sla.0000000000005250
  %T Objective Activity Parameters Track Patient-Specific Physical Recovery Trajectories After Surgery and Link With Individual Preoperative Immune States
  

2020

• 
  1.

  Culos, A., Tsai, A. S., Stanley, N., Becker, M., Ghaemi, M. S., McIlwain, D. R., Fallahzadeh, R., Tanada, A., Nassar, H., Espinosa, C., and others. (2020) Integration of mechanistic immunological knowledge into a machine learning pipeline improves predictions, Nature Machine Intelligence, Nature Publishing Group 2, 619–628.

  BibTeXEndNoteBibSonomyDownload

  @article{culos2020integration,
  author = {Culos, Anthony and Tsai, Amy S and Stanley, Natalie and Becker, Martin and Ghaemi, Mohammad S and McIlwain, David R and Fallahzadeh, Ramin and Tanada, Athena and Nassar, Huda and Espinosa, Camilo and others},
  journal = {Nature Machine Intelligence},
  keywords = {p21},
  number = 10,
  pages = {619--628},
  publisher = {Nature Publishing Group},
  title = {Integration of mechanistic immunological knowledge into a machine learning pipeline improves predictions},
  volume = 2,
  year = 2020
  }
  

  %0 Journal Article
  %1 culos2020integration
  %A Culos, Anthony
  %A Tsai, Amy S
  %A Stanley, Natalie
  %A Becker, Martin
  %A Ghaemi, Mohammad S
  %A McIlwain, David R
  %A Fallahzadeh, Ramin
  %A Tanada, Athena
  %A Nassar, Huda
  %A Espinosa, Camilo
  %A others,
  %D 2020
  %I Nature Publishing Group
  %J Nature Machine Intelligence
  %N 10
  %P 619--628
  %T Integration of mechanistic immunological knowledge into a machine learning pipeline improves predictions
  %V 2
  

• 
  1.

  Steininger, M., Kobs, K., Zehe, A., Lautenschlager, F., Becker, M., and Hotho, A. (2020) MapLUR: Exploring a New Paradigm for Estimating Air Pollution Using Deep Learning on Map Images, ACM Transactions on Spatial Algorithms and Systems (TSAS), ACM New York, NY, USA 6, 1–24.

  BibTeXEndNoteBibSonomyDownload

  @article{steininger2020maplur,
  author = {Steininger, Michael and Kobs, Konstantin and Zehe, Albin and Lautenschlager, Florian and Becker, Martin and Hotho, Andreas},
  journal = {ACM Transactions on Spatial Algorithms and Systems (TSAS)},
  keywords = {open},
  number = 3,
  pages = {1--24},
  publisher = {ACM New York, NY, USA},
  title = {MapLUR: Exploring a New Paradigm for Estimating Air Pollution Using Deep Learning on Map Images},
  volume = 6,
  year = 2020
  }
  

  %0 Journal Article
  %1 steininger2020maplur
  %A Steininger, Michael
  %A Kobs, Konstantin
  %A Zehe, Albin
  %A Lautenschlager, Florian
  %A Becker, Martin
  %A Hotho, Andreas
  %D 2020
  %I ACM New York, NY, USA
  %J ACM Transactions on Spatial Algorithms and Systems (TSAS)
  %N 3
  %P 1--24
  %T MapLUR: Exploring a New Paradigm for Estimating Air Pollution Using Deep Learning on Map Images
  %V 6
  

• 
  1.

  Lautenschlager, F., Becker, M., Kobs, K., Steininger, M., Davidson, P., Krause, A., and Hotho, A. (2020) OpenLUR: Off-the-shelf air pollution modeling with open features and machine learning, Atmospheric Environment 233, 117535.

  AbstractURLBibTeXEndNoteDOIBibSonomyDownload

  To assess the exposure of citizens to pollutants like NOx or particulate matter in urban areas, land use regression (LUR) models are a well established method. LUR models leverage information about environmental and anthropogenic factors such as cars, heating, or industry to predict air pollution in areas where no measurements have been made. However, existing approaches are often not globally applicable and require tedious hyper-parameter tuning to enable high quality predictions. In this work, we tackle these issues by introducing OpenLUR, an off-the-shelf approach for modeling air pollution that (i) works on a set of novel features solely extracted from the globally and openly available data source OpenStreetMap and (ii) is based on state-of-the-art machine learning featuring automated hyper-parameter tuning in order to minimize manual effort. We show that our proposed features are able to outperform their counterparts from local and closed sources, and illustrate how automated hyper parameter tuning can yield competitve results while alleviating the need for expert knowledge in machine learning and manual effort. Importantly, we further demonstrate the potential of the global availability of our features by applying cross-learning across different cities in order to reduce the need for a large amount of training samples. Overall, OpenLUR represents an off-the-shelf approach that facilitates easily reproducible experiments and the development of globally applicable models.

  @article{lautenschlager2020openlur,
  abstract = {To assess the exposure of citizens to pollutants like NOx or particulate matter in urban areas, land use regression (LUR) models are a well established method. LUR models leverage information about environmental and anthropogenic factors such as cars, heating, or industry to predict air pollution in areas where no measurements have been made. However, existing approaches are often not globally applicable and require tedious hyper-parameter tuning to enable high quality predictions. In this work, we tackle these issues by introducing OpenLUR, an off-the-shelf approach for modeling air pollution that (i) works on a set of novel features solely extracted from the globally and openly available data source OpenStreetMap and (ii) is based on state-of-the-art machine learning featuring automated hyper-parameter tuning in order to minimize manual effort. We show that our proposed features are able to outperform their counterparts from local and closed sources, and illustrate how automated hyper parameter tuning can yield competitve results while alleviating the need for expert knowledge in machine learning and manual effort. Importantly, we further demonstrate the potential of the global availability of our features by applying cross-learning across different cities in order to reduce the need for a large amount of training samples. Overall, OpenLUR represents an off-the-shelf approach that facilitates easily reproducible experiments and the development of globally applicable models.},
  author = {Lautenschlager, Florian and Becker, Martin and Kobs, Konstantin and Steininger, Michael and Davidson, Padraig and Krause, Anna and Hotho, Andreas},
  journal = {Atmospheric Environment},
  keywords = {open},
  pages = 117535,
  title = {OpenLUR: Off-the-shelf air pollution modeling with open features and machine learning},
  volume = 233,
  year = 2020
  }
  

  %0 Journal Article
  %1 lautenschlager2020openlur
  %A Lautenschlager, Florian
  %A Becker, Martin
  %A Kobs, Konstantin
  %A Steininger, Michael
  %A Davidson, Padraig
  %A Krause, Anna
  %A Hotho, Andreas
  %D 2020
  %J Atmospheric Environment
  %P 117535
  %R https://doi.org/10.1016/j.atmosenv.2020.117535
  %T OpenLUR: Off-the-shelf air pollution modeling with open features and machine learning
  %U http://www.sciencedirect.com/science/article/pii/S1352231020302703
  %V 233
  %X To assess the exposure of citizens to pollutants like NOx or particulate matter in urban areas, land use regression (LUR) models are a well established method. LUR models leverage information about environmental and anthropogenic factors such as cars, heating, or industry to predict air pollution in areas where no measurements have been made. However, existing approaches are often not globally applicable and require tedious hyper-parameter tuning to enable high quality predictions. In this work, we tackle these issues by introducing OpenLUR, an off-the-shelf approach for modeling air pollution that (i) works on a set of novel features solely extracted from the globally and openly available data source OpenStreetMap and (ii) is based on state-of-the-art machine learning featuring automated hyper-parameter tuning in order to minimize manual effort. We show that our proposed features are able to outperform their counterparts from local and closed sources, and illustrate how automated hyper parameter tuning can yield competitve results while alleviating the need for expert knowledge in machine learning and manual effort. Importantly, we further demonstrate the potential of the global availability of our features by applying cross-learning across different cities in order to reduce the need for a large amount of training samples. Overall, OpenLUR represents an off-the-shelf approach that facilitates easily reproducible experiments and the development of globally applicable models.
  

• 
  1.

  Stanley, N., Stelzer, I. A., Tsai, A. S., Fallahzadeh, R., Ganio, E., Becker, M., Phongpreecha, T., Nassar, H., Ghaemi, S., Maric, I., Culos, A., Chang, A. L., Xenochristou, M., Han, X., Espinosa, C., Rumer, K., Peterson, L., Verdonk, F., Gaudilliere, D., Tsai, E., Feyaerts, D., Einhaus, J., Ando, K., Wong, R. J., Obermoser, G., Shaw, G. M., Stevenson, D. K., Angst, M. S., Gaudilliere, B., and Aghaeepour, N. (2020) VoPo leverages cellular heterogeneity for predictive modeling of single-cell data, Nature Communications 11, 3738-.

  AbstractURLBibTeXEndNoteDOIBibSonomyDownload

  High-throughput single-cell analysis technologies produce an abundance of data that is critical for profiling the heterogeneity of cellular systems. We introduce VoPo (https://github.com/stanleyn/VoPo), a machine learning algorithm for predictive modeling and comprehensive visualization of the heterogeneity captured in large single-cell datasets. In three mass cytometry datasets, with the largest measuring hundreds of millions of cells over hundreds of samples, VoPo defines phenotypically and functionally homogeneous cell populations. VoPo further outperforms state-of-the-art machine learning algorithms in classification tasks, and identified immune-correlates of clinically-relevant parameters.

  @article{stanley2020vopo,
  abstract = {High-throughput single-cell analysis technologies produce an abundance of data that is critical for profiling the heterogeneity of cellular systems. We introduce VoPo (https://github.com/stanleyn/VoPo), a machine learning algorithm for predictive modeling and comprehensive visualization of the heterogeneity captured in large single-cell datasets. In three mass cytometry datasets, with the largest measuring hundreds of millions of cells over hundreds of samples, VoPo defines phenotypically and functionally homogeneous cell populations. VoPo further outperforms state-of-the-art machine learning algorithms in classification tasks, and identified immune-correlates of clinically-relevant parameters.},
  author = {Stanley, Natalie and Stelzer, Ina A. and Tsai, Amy S. and Fallahzadeh, Ramin and Ganio, Edward and Becker, Martin and Phongpreecha, Thanaphong and Nassar, Huda and Ghaemi, Sajjad and Maric, Ivana and Culos, Anthony and Chang, Alan L. and Xenochristou, Maria and Han, Xiaoyuan and Espinosa, Camilo and Rumer, Kristen and Peterson, Laura and Verdonk, Franck and Gaudilliere, Dyani and Tsai, Eileen and Feyaerts, Dorien and Einhaus, Jakob and Ando, Kazuo and Wong, Ronald J. and Obermoser, Gerlinde and Shaw, Gary M. and Stevenson, David K. and Angst, Martin S. and Gaudilliere, Brice and Aghaeepour, Nima},
  journal = {Nature Communications},
  keywords = {cytof},
  number = 1,
  pages = {3738--},
  title = {VoPo leverages cellular heterogeneity for predictive modeling of single-cell data},
  volume = 11,
  year = 2020
  }
  

  %0 Journal Article
  %1 stanley2020vopo
  %A Stanley, Natalie
  %A Stelzer, Ina A.
  %A Tsai, Amy S.
  %A Fallahzadeh, Ramin
  %A Ganio, Edward
  %A Becker, Martin
  %A Phongpreecha, Thanaphong
  %A Nassar, Huda
  %A Ghaemi, Sajjad
  %A Maric, Ivana
  %A Culos, Anthony
  %A Chang, Alan L.
  %A Xenochristou, Maria
  %A Han, Xiaoyuan
  %A Espinosa, Camilo
  %A Rumer, Kristen
  %A Peterson, Laura
  %A Verdonk, Franck
  %A Gaudilliere, Dyani
  %A Tsai, Eileen
  %A Feyaerts, Dorien
  %A Einhaus, Jakob
  %A Ando, Kazuo
  %A Wong, Ronald J.
  %A Obermoser, Gerlinde
  %A Shaw, Gary M.
  %A Stevenson, David K.
  %A Angst, Martin S.
  %A Gaudilliere, Brice
  %A Aghaeepour, Nima
  %D 2020
  %J Nature Communications
  %N 1
  %P 3738--
  %R 10.1038/s41467-020-17569-8
  %T VoPo leverages cellular heterogeneity for predictive modeling of single-cell data
  %U https://doi.org/10.1038/s41467-020-17569-8
  %V 11
  %X High-throughput single-cell analysis technologies produce an abundance of data that is critical for profiling the heterogeneity of cellular systems. We introduce VoPo (https://github.com/stanleyn/VoPo), a machine learning algorithm for predictive modeling and comprehensive visualization of the heterogeneity captured in large single-cell datasets. In three mass cytometry datasets, with the largest measuring hundreds of millions of cells over hundreds of samples, VoPo defines phenotypically and functionally homogeneous cell populations. VoPo further outperforms state-of-the-art machine learning algorithms in classification tasks, and identified immune-correlates of clinically-relevant parameters.
  

• 
  1.

  Jehan, F., Sazawal, S., Baqui, A. H., Nisar, M. I., Dhingra, U., Khanam, R., Ilyas, M., Dutta, A., Mitra, D. K., Mehmood, U., Deb, S., Mahmud, A., Hotwani, A., Ali, S. M., Rahman, S., Nizar, A., Ame, S. M., Moin, M. I., Muhammad, S., Chauhan, A., Begum, N., Khan, W., Das, S., Ahmed, S., Hasan, T., Khalid, J., Rizvi, S. J. R., Juma, M. H., Chowdhury, N. H., Kabir, F., Aftab, F., Quaiyum, A., Manu, A., Yoshida, S., Bahl, R., Rahman, A., Pervin, J., Winston, J., Musonda, P., Stringer, J. S. A., Litch, J. A., Ghaemi, M. S., Moufarrej, M. N., Contrepois, K., Chen, S., Stelzer, I. A., Stanley, N., Chang, A. L., Hammad, G. B., Wong, R. J., Liu, C., Quaintance, C. C., Culos, A., Espinosa, C., Xenochristou, M., Becker, M., Fallahzadeh, R., Ganio, E., Tsai, A. S., Gaudilliere, D., Tsai, E. S., Han, X., Ando, K., Tingle, M., Maric, I., Wise, P. H., Winn, V. D., Druzin, M. L., Gibbs, R. S., Darmstadt, G. L., Murray, J. C., Shaw, G. M., Stevenson, D. K., Snyder, M. P., Quake, S. R., Angst, M. S., Gaudilliere, B., and Aghaeepour, N. (2020) Multiomics Characterization of Preterm Birth in Low- and Middle-Income Countries, JAMA Network Open 3, e2029655-e2029655.

  URLBibTeXEndNoteBibSonomyDownload

  @article{jehan2020multiomics,
  author = {Jehan, Fyezah and Sazawal, Sunil and Baqui, Abdullah H. and Nisar, Muhammad Imran and Dhingra, Usha and Khanam, Rasheda and Ilyas, Muhammad and Dutta, Arup and Mitra, Dipak K. and Mehmood, Usma and Deb, Saikat and Mahmud, Arif and Hotwani, Aneeta and Ali, Said Mohammed and Rahman, Sayedur and Nizar, Ambreen and Ame, Shaali Makame and Moin, Mamun Ibne and Muhammad, Sajid and Chauhan, Aishwarya and Begum, Nazma and Khan, Waqasuddin and Das, Sayan and Ahmed, Salahuddin and Hasan, Tarik and Khalid, Javairia and Rizvi, Syed Jafar Raza and Juma, Mohammed Hamad and Chowdhury, Nabidul Haque and Kabir, Furqan and Aftab, Fahad and Quaiyum, Abdul and Manu, Alexander and Yoshida, Sachiyo and Bahl, Rajiv and Rahman, Anisur and Pervin, Jesmin and Winston, Jennifer and Musonda, Patrick and Stringer, Jeffrey S. A. and Litch, James A. and Ghaemi, Mohammad Sajjad and Moufarrej, Mira N. and Contrepois, Kevin and Chen, Songjie and Stelzer, Ina A. and Stanley, Natalie and Chang, Alan L. and Hammad, Ghaith Bany and Wong, Ronald J. and Liu, Candace and Quaintance, Cecele C. and Culos, Anthony and Espinosa, Camilo and Xenochristou, Maria and Becker, Martin and Fallahzadeh, Ramin and Ganio, Edward and Tsai, Amy S. and Gaudilliere, Dyani and Tsai, Eileen S. and Han, Xiaoyuan and Ando, Kazuo and Tingle, Martha and Maric, Ivana and Wise, Paul H. and Winn, Virginia D. and Druzin, Maurice L. and Gibbs, Ronald S. and Darmstadt, Gary L. and Murray, Jeffrey C. and Shaw, Gary M. and Stevenson, David K. and Snyder, Michael P. and Quake, Stephen R. and Angst, Martin S. and Gaudilliere, Brice and Aghaeepour, Nima},
  booktitle = {JAMA Network Open},
  journal = {JAMA Network Open},
  keywords = {p21},
  pages = {e2029655-e2029655},
  series = 12,
  title = {Multiomics Characterization of Preterm Birth in Low- and Middle-Income Countries},
  volume = 3,
  year = 2020
  }
  

  %0 Journal Article
  %1 jehan2020multiomics
  %A Jehan, Fyezah
  %A Sazawal, Sunil
  %A Baqui, Abdullah H.
  %A Nisar, Muhammad Imran
  %A Dhingra, Usha
  %A Khanam, Rasheda
  %A Ilyas, Muhammad
  %A Dutta, Arup
  %A Mitra, Dipak K.
  %A Mehmood, Usma
  %A Deb, Saikat
  %A Mahmud, Arif
  %A Hotwani, Aneeta
  %A Ali, Said Mohammed
  %A Rahman, Sayedur
  %A Nizar, Ambreen
  %A Ame, Shaali Makame
  %A Moin, Mamun Ibne
  %A Muhammad, Sajid
  %A Chauhan, Aishwarya
  %A Begum, Nazma
  %A Khan, Waqasuddin
  %A Das, Sayan
  %A Ahmed, Salahuddin
  %A Hasan, Tarik
  %A Khalid, Javairia
  %A Rizvi, Syed Jafar Raza
  %A Juma, Mohammed Hamad
  %A Chowdhury, Nabidul Haque
  %A Kabir, Furqan
  %A Aftab, Fahad
  %A Quaiyum, Abdul
  %A Manu, Alexander
  %A Yoshida, Sachiyo
  %A Bahl, Rajiv
  %A Rahman, Anisur
  %A Pervin, Jesmin
  %A Winston, Jennifer
  %A Musonda, Patrick
  %A Stringer, Jeffrey S. A.
  %A Litch, James A.
  %A Ghaemi, Mohammad Sajjad
  %A Moufarrej, Mira N.
  %A Contrepois, Kevin
  %A Chen, Songjie
  %A Stelzer, Ina A.
  %A Stanley, Natalie
  %A Chang, Alan L.
  %A Hammad, Ghaith Bany
  %A Wong, Ronald J.
  %A Liu, Candace
  %A Quaintance, Cecele C.
  %A Culos, Anthony
  %A Espinosa, Camilo
  %A Xenochristou, Maria
  %A Becker, Martin
  %A Fallahzadeh, Ramin
  %A Ganio, Edward
  %A Tsai, Amy S.
  %A Gaudilliere, Dyani
  %A Tsai, Eileen S.
  %A Han, Xiaoyuan
  %A Ando, Kazuo
  %A Tingle, Martha
  %A Maric, Ivana
  %A Wise, Paul H.
  %A Winn, Virginia D.
  %A Druzin, Maurice L.
  %A Gibbs, Ronald S.
  %A Darmstadt, Gary L.
  %A Murray, Jeffrey C.
  %A Shaw, Gary M.
  %A Stevenson, David K.
  %A Snyder, Michael P.
  %A Quake, Stephen R.
  %A Angst, Martin S.
  %A Gaudilliere, Brice
  %A Aghaeepour, Nima
  %B JAMA Network Open
  %D 2020
  %J JAMA Network Open
  %P e2029655-e2029655
  %T Multiomics Characterization of Preterm Birth in Low- and Middle-Income Countries
  %U https://doi.org/10.1001/jamanetworkopen.2020.29655
  %V 3
  

2018

• 
  1.

  Zehe, A., Schlör, D., Henny-Krahmer, U., Becker, M., and Hotho, A. (2018) A White-Box Model for Detecting Author Nationality by Linguistic Differences in Spanish Novels. In Digital Humanities (Palau, J. G., and Russell, I. G., Eds.), pp. 519–521, ADHO.

  BibTeXEndNoteBibSonomyDownload

  @inproceedings{zehe2018whitebox,
  author = {Zehe, Albin and Schlör, Daniel and Henny-Krahmer, Ulrike and Becker, Martin and Hotho, Andreas},
  booktitle = {Digital Humanities},
  editor = {Palau, Jonathan Girón and Russell, Isabel Galina},
  keywords = {digital},
  organization = {ADHO},
  pages = {519--521},
  title = {A White-Box Model for Detecting Author Nationality by Linguistic Differences in Spanish Novels},
  year = 2018
  }
  

  %0 Conference Paper
  %1 zehe2018whitebox
  %A Zehe, Albin
  %A Schlör, Daniel
  %A Henny-Krahmer, Ulrike
  %A Becker, Martin
  %A Hotho, Andreas
  %B Digital Humanities
  %D 2018
  %E Palau, Jonathan Girón
  %E Russell, Isabel Galina
  %P 519--521
  %T A White-Box Model for Detecting Author Nationality by Linguistic Differences in Spanish Novels
  

• 
  1.

  Kibanov, M., Becker, M., Mueller, J., Atzmueller, M., Hotho, A., and Stumme, G. (2018) Adaptive kNN Using Expected Accuracy for Classification of Geo-spatial Data. In Proceedings of the 33rd Annual ACM Symposium on Applied Computing, pp. 857–865, ACM, Pau, France.

  AbstractURLBibTeXEndNoteDOIBibSonomyDownload

  The k-Nearest Neighbor (kNN) classification approach is conceptually simple - yet widely applied since it often performs well in practical applications. However, using a global constant k does not always provide an optimal solution, e. g., for datasets with an irregular density distribution of data points. This paper proposes an adaptive kNN classifier where k is chosen dynamically for each instance (point) to be classified, such that the expected accuracy of classification is maximized. We define the expected accuracy as the accuracy of a set of structurally similar observations. An arbitrary similarity function can be used to find these observations. We introduce and evaluate different similarity functions. For the evaluation, we use five different classification tasks based on geo-spatial data. Each classification task consists of (tens of) thousands of items. We demonstrate, that the presented expected accuracy measures can be a good estimator for kNN performance, and the proposed adaptive kNN classifier outperforms common kNN and previously introduced adaptive kNN algorithms. Also, we show that the range of considered k can be significantly reduced to speed up the algorithm without negative influence on classification accuracy.

  @inproceedings{kibanov2018adaptive,
  abstract = {The k-Nearest Neighbor (kNN) classification approach is conceptually simple - yet widely applied since it often performs well in practical applications. However, using a global constant k does not always provide an optimal solution, e. g., for datasets with an irregular density distribution of data points. This paper proposes an adaptive kNN classifier where k is chosen dynamically for each instance (point) to be classified, such that the expected accuracy of classification is maximized. We define the expected accuracy as the accuracy of a set of structurally similar observations. An arbitrary similarity function can be used to find these observations. We introduce and evaluate different similarity functions. For the evaluation, we use five different classification tasks based on geo-spatial data. Each classification task consists of (tens of) thousands of items. We demonstrate, that the presented expected accuracy measures can be a good estimator for kNN performance, and the proposed adaptive kNN classifier outperforms common kNN and previously introduced adaptive kNN algorithms. Also, we show that the range of considered k can be significantly reduced to speed up the algorithm without negative influence on classification accuracy.},
  address = {New York, NY, USA},
  author = {Kibanov, Mark and Becker, Martin and Mueller, Juergen and Atzmueller, Martin and Hotho, Andreas and Stumme, Gerd},
  booktitle = {Proceedings of the 33rd Annual ACM Symposium on Applied Computing},
  keywords = {kassel},
  pages = {857--865},
  publisher = {ACM},
  series = {SAC '18},
  title = {Adaptive kNN Using Expected Accuracy for Classification of Geo-spatial Data},
  year = 2018
  }
  

  %0 Conference Paper
  %1 kibanov2018adaptive
  %A Kibanov, Mark
  %A Becker, Martin
  %A Mueller, Juergen
  %A Atzmueller, Martin
  %A Hotho, Andreas
  %A Stumme, Gerd
  %B Proceedings of the 33rd Annual ACM Symposium on Applied Computing
  %C New York, NY, USA
  %D 2018
  %I ACM
  %P 857--865
  %R 10.1145/3167132.3167226
  %T Adaptive kNN Using Expected Accuracy for Classification of Geo-spatial Data
  %U http://doi.acm.org/10.1145/3167132.3167226
  %X The k-Nearest Neighbor (kNN) classification approach is conceptually simple - yet widely applied since it often performs well in practical applications. However, using a global constant k does not always provide an optimal solution, e. g., for datasets with an irregular density distribution of data points. This paper proposes an adaptive kNN classifier where k is chosen dynamically for each instance (point) to be classified, such that the expected accuracy of classification is maximized. We define the expected accuracy as the accuracy of a set of structurally similar observations. An arbitrary similarity function can be used to find these observations. We introduce and evaluate different similarity functions. For the evaluation, we use five different classification tasks based on geo-spatial data. Each classification task consists of (tens of) thousands of items. We demonstrate, that the presented expected accuracy measures can be a good estimator for kNN performance, and the proposed adaptive kNN classifier outperforms common kNN and previously introduced adaptive kNN algorithms. Also, we show that the range of considered k can be significantly reduced to speed up the algorithm without negative influence on classification accuracy.
  %@ 978-1-4503-5191-1
  

• 
  1.

  Schöch, C., Schlör, D., Zehe, A., Gebhard, H., Becker, M., and Hotho, A. (2018) Burrows’ Zeta: Exploring and Evaluating Variants and Parameters. In Digital Humanities (Palau, J. G., and Russell, I. G., Eds.), pp. 274–277.

  URLBibTeXEndNoteBibSonomyDownload

  @inproceedings{schoech2018zeta,
  author = {Schöch, Christof and Schlör, Daniel and Zehe, Albin and Gebhard, Henning and Becker, Martin and Hotho, Andreas},
  booktitle = {Digital Humanities},
  editor = {Palau, Jonathan Girón and Russell, Isabel Galina},
  keywords = {digital},
  pages = {274--277},
  title = {Burrows’ Zeta: Exploring and Evaluating Variants and Parameters},
  year = 2018
  }
  

  %0 Conference Paper
  %1 schoech2018zeta
  %A Schöch, Christof
  %A Schlör, Daniel
  %A Zehe, Albin
  %A Gebhard, Henning
  %A Becker, Martin
  %A Hotho, Andreas
  %B Digital Humanities
  %D 2018
  %E Palau, Jonathan Girón
  %E Russell, Isabel Galina
  %P 274--277
  %T Burrows’ Zeta: Exploring and Evaluating Variants and Parameters
  %U http://dblp.uni-trier.de/db/conf/dihu/dh2018.html#SchochSZG0H18
  

• 
  1.

  Lautenschlager, F., Becker, M., Steininger, M., and Hotho, A. (2018) EveryAware Gears: A Tool to visualize and analyze all types of Citizen Science Data. In Proceedings of VGI Geovisual Analytics Workshop, colocated with BDVA 2018 (Burghardt, D., Chen, S., Andrienko, G., Andrienko, N., Purves, R., and Diehl, A., Eds.), KOPS.

  BibTeXEndNoteBibSonomyDownload

  @inproceedings{lautenschlager2018everyaware,
  author = {Lautenschlager, Florian and Becker, Martin and Steininger, Michael and Hotho, Andreas},
  booktitle = {Proceedings of VGI Geovisual Analytics Workshop, colocated with BDVA 2018},
  editor = {Burghardt, Dirk and Chen, Siming and Andrienko, Gennady and Andrienko, Nathalia and Purves, Ross and Diehl, Alexandra},
  keywords = {myown},
  month = 10,
  publisher = {KOPS},
  title = {EveryAware Gears: A Tool to visualize and analyze all types of Citizen Science Data},
  year = 2018
  }
  

  %0 Conference Paper
  %1 lautenschlager2018everyaware
  %A Lautenschlager, Florian
  %A Becker, Martin
  %A Steininger, Michael
  %A Hotho, Andreas
  %B Proceedings of VGI Geovisual Analytics Workshop, colocated with BDVA 2018
  %D 2018
  %E Burghardt, Dirk
  %E Chen, Siming
  %E Andrienko, Gennady
  %E Andrienko, Nathalia
  %E Purves, Ross
  %E Diehl, Alexandra
  %I KOPS
  %T EveryAware Gears: A Tool to visualize and analyze all types of Citizen Science Data
  

• 
  1.

  Becker, M. (2018) Understanding Human Navigation using Bayesian Hypothesis Comparison, PhD dissertation, University of W{ü}rzburg.

  BibTeXEndNoteBibSonomyDownload

  @phdthesis{becker2018understanding,
  author = {Becker, Martin},
  keywords = {behavior},
  school = {University of W{ü}rzburg},
  title = {Understanding Human Navigation using Bayesian Hypothesis Comparison},
  type = {Doctoral Thesis},
  year = 2018
  }
  

  %0 Thesis
  %1 becker2018understanding
  %A Becker, Martin
  %D 2018
  %T Understanding Human Navigation using Bayesian Hypothesis Comparison
  

• 
  1.

  Becker, M., Lautenschlager, F., and Hotho, A. (2018) Air Trails--Urban Air Quality Campaign Exploration Patterns. In Proceedings of VGI-ALIVE 2018 Workshop, colocated with AGILE 2018.

  URLBibTeXEndNoteBibSonomyDownload

  @inproceedings{becker2018airtrails,
  author = {Becker, Martin and Lautenschlager, Florian and Hotho, Andreas},
  booktitle = {Proceedings of VGI-ALIVE 2018 Workshop, colocated with AGILE 2018},
  keywords = {eva},
  title = {Air Trails--Urban Air Quality Campaign Exploration Patterns},
  year = 2018
  }
  

  %0 Conference Paper
  %1 becker2018airtrails
  %A Becker, Martin
  %A Lautenschlager, Florian
  %A Hotho, Andreas
  %B Proceedings of VGI-ALIVE 2018 Workshop, colocated with AGILE 2018
  %D 2018
  %T Air Trails--Urban Air Quality Campaign Exploration Patterns
  %U http://www.cs.nuim.ie/~pmooney/vgi-alive2018/index.html
  

• 
  1.

  Werdin, F., Tenenhaus, M., Becker, M., and Rennekampff, H.-O. (2018) Healing Time Correlates With the Quality of Scaring: Results From a Prospective Randomized Control Donor Site Trial, Dermatologic Surgery, LWW 44, 521–527.

  BibTeXEndNoteBibSonomyDownload

  @article{werdin2018healing,
  author = {Werdin, Frank and Tenenhaus, Mayer and Becker, Martin and Rennekampff, Hans-Oliver},
  journal = {Dermatologic Surgery},
  keywords = {tissue},
  number = 4,
  pages = {521--527},
  publisher = {LWW},
  title = {Healing Time Correlates With the Quality of Scaring: Results From a Prospective Randomized Control Donor Site Trial},
  volume = 44,
  year = 2018
  }
  

  %0 Journal Article
  %1 werdin2018healing
  %A Werdin, Frank
  %A Tenenhaus, Mayer
  %A Becker, Martin
  %A Rennekampff, Hans-Oliver
  %D 2018
  %I LWW
  %J Dermatologic Surgery
  %N 4
  %P 521--527
  %T Healing Time Correlates With the Quality of Scaring: Results From a Prospective Randomized Control Donor Site Trial
  %V 44
  

• 
  1.

  Lemmerich, F., and Becker, M. (2018) pysubgroup: Easy-to-Use Subgroup Discovery in Python.. In ECML/PKDD (3) (Brefeld, U., Curry, E., Daly, E., MacNamee, B., Marascu, A., Pinelli, F., Berlingerio, M., and Hurley, N., Eds.), pp. 658–662, Springer.

  URLBibTeXEndNoteBibSonomyDownload

  @inproceedings{lemmerich2018pysubgroup,
  author = {Lemmerich, Florian and Becker, Martin},
  booktitle = {ECML/PKDD (3)},
  crossref = {conf/pkdd/2018-3},
  editor = {Brefeld, Ulf and Curry, Edward and Daly, Elizabeth and MacNamee, Brian and Marascu, Alice and Pinelli, Fabio and Berlingerio, Michele and Hurley, Neil},
  keywords = {python},
  pages = {658-662},
  publisher = {Springer},
  series = {Lecture Notes in Computer Science},
  title = {pysubgroup: Easy-to-Use Subgroup Discovery in Python.},
  volume = 11053,
  year = 2018
  }
  

  %0 Conference Paper
  %1 lemmerich2018pysubgroup
  %A Lemmerich, Florian
  %A Becker, Martin
  %B ECML/PKDD (3)
  %D 2018
  %E Brefeld, Ulf
  %E Curry, Edward
  %E Daly, Elizabeth
  %E MacNamee, Brian
  %E Marascu, Alice
  %E Pinelli, Fabio
  %E Berlingerio, Michele
  %E Hurley, Neil
  %I Springer
  %P 658-662
  %T pysubgroup: Easy-to-Use Subgroup Discovery in Python.
  %U http://dblp.uni-trier.de/db/conf/pkdd/pkdd2018-3.html#Lemmerich018
  %V 11053
  %@ 978-3-030-10997-4
  

2017

• 
  1.

  Becker, M., Lemmerich, F., Singer, P., Strohmaier, M., and Hotho, A. (2017) MixedTrails: Bayesian hypothesis comparison on heterogeneous sequential data, Data Mining and Knowledge Discovery 31, 1359–1390.

  AbstractURLBibTeXEndNoteDOIBibSonomyDownload

  Sequential traces of user data are frequently observed online and offline, e.g., as sequences of visited websites or as sequences of locations captured by GPS. However, understanding factors explaining the production of sequence data is a challenging task, especially since the data generation is often not homogeneous. For example, navigation behavior might change in different phases of browsing a website or movement behavior may vary between groups of users. In this work, we tackle this task and propose MixedTrails , a Bayesian approach for comparing the plausibility of hypotheses regarding the generative processes of heterogeneous sequence data. Each hypothesis is derived from existing literature, theory, or intuition and represents a belief about transition probabilities between a set of states that can vary between groups of observed transitions. For example, when trying to understand human movement in a city and given some data, a hypothesis assuming tourists to be more likely to move towards points of interests than locals can be shown to be more plausible than a hypothesis assuming the opposite. Our approach incorporates such hypotheses as Bayesian priors in a generative mixed transition Markov chain model, and compares their plausibility utilizing Bayes factors. We discuss analytical and approximate inference methods for calculating the marginal likelihoods for Bayes factors, give guidance on interpreting the results, and illustrate our approach with several experiments on synthetic and empirical data from Wikipedia and Flickr. Thus, this work enables a novel kind of analysis for studying sequential data in many application areas.

  @article{becker2017mixedtrails,
  abstract = {Sequential traces of user data are frequently observed online and offline, e.g., as sequences of visited websites or as sequences of locations captured by GPS. However, understanding factors explaining the production of sequence data is a challenging task, especially since the data generation is often not homogeneous. For example, navigation behavior might change in different phases of browsing a website or movement behavior may vary between groups of users. In this work, we tackle this task and propose MixedTrails , a Bayesian approach for comparing the plausibility of hypotheses regarding the generative processes of heterogeneous sequence data. Each hypothesis is derived from existing literature, theory, or intuition and represents a belief about transition probabilities between a set of states that can vary between groups of observed transitions. For example, when trying to understand human movement in a city and given some data, a hypothesis assuming tourists to be more likely to move towards points of interests than locals can be shown to be more plausible than a hypothesis assuming the opposite. Our approach incorporates such hypotheses as Bayesian priors in a generative mixed transition Markov chain model, and compares their plausibility utilizing Bayes factors. We discuss analytical and approximate inference methods for calculating the marginal likelihoods for Bayes factors, give guidance on interpreting the results, and illustrate our approach with several experiments on synthetic and empirical data from Wikipedia and Flickr. Thus, this work enables a novel kind of analysis for studying sequential data in many application areas.},
  author = {Becker, Martin and Lemmerich, Florian and Singer, Philipp and Strohmaier, Markus and Hotho, Andreas},
  journal = {Data Mining and Knowledge Discovery},
  keywords = {selected},
  month = {09},
  number = 5,
  pages = {1359--1390},
  title = {MixedTrails: Bayesian hypothesis comparison on heterogeneous sequential data},
  volume = 31,
  year = 2017
  }
  

  %0 Journal Article
  %1 becker2017mixedtrails
  %A Becker, Martin
  %A Lemmerich, Florian
  %A Singer, Philipp
  %A Strohmaier, Markus
  %A Hotho, Andreas
  %D 2017
  %J Data Mining and Knowledge Discovery
  %N 5
  %P 1359--1390
  %R 10.1007/s10618-017-0518-x
  %T MixedTrails: Bayesian hypothesis comparison on heterogeneous sequential data
  %U http://dx.doi.org/10.1007/s10618-017-0518-x
  %V 31
  %X Sequential traces of user data are frequently observed online and offline, e.g., as sequences of visited websites or as sequences of locations captured by GPS. However, understanding factors explaining the production of sequence data is a challenging task, especially since the data generation is often not homogeneous. For example, navigation behavior might change in different phases of browsing a website or movement behavior may vary between groups of users. In this work, we tackle this task and propose MixedTrails , a Bayesian approach for comparing the plausibility of hypotheses regarding the generative processes of heterogeneous sequence data. Each hypothesis is derived from existing literature, theory, or intuition and represents a belief about transition probabilities between a set of states that can vary between groups of observed transitions. For example, when trying to understand human movement in a city and given some data, a hypothesis assuming tourists to be more likely to move towards points of interests than locals can be shown to be more plausible than a hypothesis assuming the opposite. Our approach incorporates such hypotheses as Bayesian priors in a generative mixed transition Markov chain model, and compares their plausibility utilizing Bayes factors. We discuss analytical and approximate inference methods for calculating the marginal likelihoods for Bayes factors, give guidance on interpreting the results, and illustrate our approach with several experiments on synthetic and empirical data from Wikipedia and Flickr. Thus, this work enables a novel kind of analysis for studying sequential data in many application areas.
  

• 
  1.

  Gravino, P., Sirbu, A., Becker, M., Servedio, V. D., and Loreto, V. (2017) Experimental Assessment of the Emergence of Awareness and Its Influence on Behavioral Changes: The Everyaware Lesson. In Participatory Sensing, Opinions and Collective Awareness, pp. 337–362, Springer International Publishing, Cham.

  URLBibTeXEndNoteDOIBibSonomyDownload

  @inbook{gravino2017experimental,
  address = {Cham},
  author = {Gravino, Pietro and Sirbu, Alina and Becker, Martin and Servedio, Vito DP and Loreto, Vittorio},
  booktitle = {Participatory Sensing, Opinions and Collective Awareness},
  keywords = {everyaware},
  pages = {337--362},
  publisher = {Springer International Publishing},
  title = {Experimental Assessment of the Emergence of Awareness and Its Influence on Behavioral Changes: The Everyaware Lesson},
  year = 2017
  }
  

  %0 Book Section
  %1 gravino2017experimental
  %A Gravino, Pietro
  %A Sirbu, Alina
  %A Becker, Martin
  %A Servedio, Vito DP
  %A Loreto, Vittorio
  %B Participatory Sensing, Opinions and Collective Awareness
  %C Cham
  %D 2017
  %I Springer International Publishing
  %P 337--362
  %R 10.1007/978-3-319-25658-0_16
  %T Experimental Assessment of the Emergence of Awareness and Its Influence on Behavioral Changes: The Everyaware Lesson
  %U https://doi.org/10.1007/978-3-319-25658-0_16
  %@ 978-3-319-25658-0
  

• 
  1.

  Lemmerich, F., Singer, P., Becker, M., Espin-Noboa, L., Dimitrov, D., Helic, D., Hotho, A., and Strohmaier, M. (2017) Comparing Hypotheses About Sequential Data: A Bayesian Approach and Its Applications. In Joint European Conference on Machine Learning and Knowledge Discovery in Databases, pp. 354–357, Springer.

  BibTeXEndNoteBibSonomyDownload

  @inproceedings{lemmerich2017comparing,
  author = {Lemmerich, Florian and Singer, Philipp and Becker, Martin and Espin-Noboa, Lisette and Dimitrov, Dimitar and Helic, Denis and Hotho, Andreas and Strohmaier, Markus},
  booktitle = {Joint European Conference on Machine Learning and Knowledge Discovery in Databases},
  keywords = {nectar},
  organization = {Springer},
  pages = {354--357},
  title = {Comparing Hypotheses About Sequential Data: A Bayesian Approach and Its Applications},
  year = 2017
  }
  

  %0 Conference Paper
  %1 lemmerich2017comparing
  %A Lemmerich, Florian
  %A Singer, Philipp
  %A Becker, Martin
  %A Espin-Noboa, Lisette
  %A Dimitrov, Dimitar
  %A Helic, Denis
  %A Hotho, Andreas
  %A Strohmaier, Markus
  %B Joint European Conference on Machine Learning and Knowledge Discovery in Databases
  %D 2017
  %P 354--357
  %T Comparing Hypotheses About Sequential Data: A Bayesian Approach and Its Applications
  

• 
  1.

  Treff, G., Winkert, K., Sareban, M., Steinacker, J. M., Becker, M., and Sperlich, B. (2017) Eleven-Week Preparation Involving Polarized Intensity Distribution Is Not Superior to Pyramidal Distribution in National Elite Rowers, Frontiers in Physiology 8, 515.

  AbstractURLBibTeXEndNoteDOIBibSonomyDownload

  Polarized (POL) training intensity distribution (TID) emphasizes high-volume low-intensity exercise in zone (Z)1 (< first lactate threshold) with a greater proportion of high-intensity Z3 (> second lactate threshold) compared to Z2 (between first and second lactate threshold). In highly trained rowers there is a lack of prospective controlled evidence whether POL is superior to pyramidal (PYR; i.e. greater volume in Z1 vs. Z2 vs. Z3) TID. The aim of the study was to compare the effect of POL vs. PYR TID in rowers during an 11-wk preparation period. Fourteen national elite male rowers participated (age: 20 ± 2 years, maximal oxygen uptake (⩒O2max): 66±5 mL/min/kg). The sample was split into PYR and POL by varying the percentage spent in Z2 and Z3 while Z1 was clamped to ~93\% and matched for total and rowing volume. Actual TIDs were based on time within heart rate zones (Z1 and Z2) and duration of Z3-intervals. The main outcome variables were average power in 2000 m ergometer-test (P2000m), power associated with 4 mmol/L [blood lactate] (P4[BLa]), and ⩒O2max. To quantify the level of polarization, we calculated a Polarization-Index as log (\%Z1 x \%Z3/\%Z2). PYR and POL did not significantly differ regarding rowing or total volume, but POL had a higher percentage of Z3 intensities (6±3\% vs. 2±1\%; p < .005) while Z2 was lower (1±1\% vs. 3±2\%; p < .05) and Z1 was similar (94±3\% vs. 93±2\%, p = .37). Consequently, Polarization-Index was significantly higher in POL (3.0±0.7 a.u. vs. 1.9±0.4 a.u.; p < .01) P2000m did not significantly change with PYR (1.5±1.7\%, p = .06) nor POL (1.5±2.6\%, p = .26). ⩒O2max did not change (1.7±5.6\%, p = .52 or 0.6±2.6, p = .67) and a small increase in P4[BLa] was observed in PYR only (1.9±4.8\%, p = .37 or -0.5±4.1\%, p = .77). Changes from pre to post were not significantly different between groups in any performance measure. POL did not prove to be superior to PYR, possibly due to the high and very similar percentage of Z1 in this study.

  @article{treff2017elevenweek,
  abstract = {Polarized (POL) training intensity distribution (TID) emphasizes high-volume low-intensity exercise in zone (Z)1 (< first lactate threshold) with a greater proportion of high-intensity Z3 (> second lactate threshold) compared to Z2 (between first and second lactate threshold). In highly trained rowers there is a lack of prospective controlled evidence whether POL is superior to pyramidal (PYR; i.e. greater volume in Z1 vs. Z2 vs. Z3) TID. The aim of the study was to compare the effect of POL vs. PYR TID in rowers during an 11-wk preparation period. Fourteen national elite male rowers participated (age: 20 ± 2 years, maximal oxygen uptake (⩒O2max): 66±5 mL/min/kg). The sample was split into PYR and POL by varying the percentage spent in Z2 and Z3 while Z1 was clamped to ~93\% and matched for total and rowing volume. Actual TIDs were based on time within heart rate zones (Z1 and Z2) and duration of Z3-intervals. The main outcome variables were average power in 2000 m ergometer-test (P2000m), power associated with 4 mmol/L [blood lactate] (P4[BLa]), and ⩒O2max. To quantify the level of polarization, we calculated a Polarization-Index as log (\%Z1 x \%Z3/\%Z2). PYR and POL did not significantly differ regarding rowing or total volume, but POL had a higher percentage of Z3 intensities (6±3\% vs. 2±1\%; p < .005) while Z2 was lower (1±1\% vs. 3±2\%; p < .05) and Z1 was similar (94±3\% vs. 93±2\%, p = .37). Consequently, Polarization-Index was significantly higher in POL (3.0±0.7 a.u. vs. 1.9±0.4 a.u.; p < .01) P2000m did not significantly change with PYR (1.5±1.7\%, p = .06) nor POL (1.5±2.6\%, p = .26). ⩒O2max did not change (1.7±5.6\%, p = .52 or 0.6±2.6, p = .67) and a small increase in P4[BLa] was observed in PYR only (1.9±4.8\%, p = .37 or -0.5±4.1\%, p = .77). Changes from pre to post were not significantly different between groups in any performance measure. POL did not prove to be superior to PYR, possibly due to the high and very similar percentage of Z1 in this study.},
  author = {Treff, Gunnar and Winkert, Kay and Sareban, Mahdi and Steinacker, Jürgen M. and Becker, Martin and Sperlich, Billy},
  journal = {Frontiers in Physiology},
  keywords = {rower},
  pages = 515,
  title = {Eleven-Week Preparation Involving Polarized Intensity Distribution Is Not Superior to Pyramidal Distribution in National Elite Rowers},
  volume = 8,
  year = 2017
  }
  

  %0 Journal Article
  %1 treff2017elevenweek
  %A Treff, Gunnar
  %A Winkert, Kay
  %A Sareban, Mahdi
  %A Steinacker, Jürgen M.
  %A Becker, Martin
  %A Sperlich, Billy
  %D 2017
  %J Frontiers in Physiology
  %P 515
  %R 10.3389/fphys.2017.00515
  %T Eleven-Week Preparation Involving Polarized Intensity Distribution Is Not Superior to Pyramidal Distribution in National Elite Rowers
  %U http://journal.frontiersin.org/article/10.3389/fphys.2017.00515
  %V 8
  %X Polarized (POL) training intensity distribution (TID) emphasizes high-volume low-intensity exercise in zone (Z)1 (< first lactate threshold) with a greater proportion of high-intensity Z3 (> second lactate threshold) compared to Z2 (between first and second lactate threshold). In highly trained rowers there is a lack of prospective controlled evidence whether POL is superior to pyramidal (PYR; i.e. greater volume in Z1 vs. Z2 vs. Z3) TID. The aim of the study was to compare the effect of POL vs. PYR TID in rowers during an 11-wk preparation period. Fourteen national elite male rowers participated (age: 20 ± 2 years, maximal oxygen uptake (⩒O2max): 66±5 mL/min/kg). The sample was split into PYR and POL by varying the percentage spent in Z2 and Z3 while Z1 was clamped to ~93\% and matched for total and rowing volume. Actual TIDs were based on time within heart rate zones (Z1 and Z2) and duration of Z3-intervals. The main outcome variables were average power in 2000 m ergometer-test (P2000m), power associated with 4 mmol/L [blood lactate] (P4[BLa]), and ⩒O2max. To quantify the level of polarization, we calculated a Polarization-Index as log (\%Z1 x \%Z3/\%Z2). PYR and POL did not significantly differ regarding rowing or total volume, but POL had a higher percentage of Z3 intensities (6±3\% vs. 2±1\%; p < .005) while Z2 was lower (1±1\% vs. 3±2\%; p < .05) and Z1 was similar (94±3\% vs. 93±2\%, p = .37). Consequently, Polarization-Index was significantly higher in POL (3.0±0.7 a.u. vs. 1.9±0.4 a.u.; p < .01) P2000m did not significantly change with PYR (1.5±1.7\%, p = .06) nor POL (1.5±2.6\%, p = .26). ⩒O2max did not change (1.7±5.6\%, p = .52 or 0.6±2.6, p = .67) and a small increase in P4[BLa] was observed in PYR only (1.9±4.8\%, p = .37 or -0.5±4.1\%, p = .77). Changes from pre to post were not significantly different between groups in any performance measure. POL did not prove to be superior to PYR, possibly due to the high and very similar percentage of Z1 in this study.
  

• 
  1.

  Sperlich, B., Becker, M., Hotho, A., Wallmann-Sperlich, B., Sareban, M., Winkert, K., Steinacker, J. M., and Treff, G. (2017) Sedentary Behavior among National Elite Rowers during Off-Training—A Pilot Study, Frontiers in Physiology 8, 655.

  AbstractURLBibTeXEndNoteDOIBibSonomyDownload

  The aim of this pilot study was to analyze the off-training physical activity (PA) profile in national elite German U23 rowers during 31 days of their preparation period. The hours spent in each PA category (i.e. sedentary: <1.5 MET; light physical activity: 1.5–3 MET; moderate physical activity: 3–6 MET and vigorous intense physical activity: >6 MET) were calculated for every valid day (i.e. > 480 min of wear time). The off-training PA during 21 weekdays and 10 weekend days of the final 11-wk preparation period was assessed by a wrist-worn multisensory device (Microsoft Band II (MSBII)). A total of 11 rowers provided valid data (i.e. > 480 min/day) for 11.6 week days and 4.8 weekend days during the 31 days observation period. The average sedentary time was 11.63±1.25 hours per day during the week and 12.49±1.10 hours per day on the weekend, with a tendency to be higher on the weekend compared to weekdays (p = 0.06; d = 0.73). The average time in light, moderate and vigorous PA during the weekdays was 1.27±1.15, 0.76±0.37, 0.51±0.44 hours per day and 0.67±0.43, 0.59±0.37, 0.53±0.32 hours per weekend day. Light physical activity was higher during weekdays compared to the weekend (p = 0.04; d = 0.69) Based on our pilot study of eleven national elite rowers we conclude that rowers display a considerable sedentary off-training behavior of more than 11.5 hours/day.

  @article{sperlich2017sedentary,
  abstract = {The aim of this pilot study was to analyze the off-training physical activity (PA) profile in national elite German U23 rowers during 31 days of their preparation period. The hours spent in each PA category (i.e. sedentary: <1.5 MET; light physical activity: 1.5–3 MET; moderate physical activity: 3–6 MET and vigorous intense physical activity: >6 MET) were calculated for every valid day (i.e. > 480 min of wear time). The off-training PA during 21 weekdays and 10 weekend days of the final 11-wk preparation period was assessed by a wrist-worn multisensory device (Microsoft Band II (MSBII)). A total of 11 rowers provided valid data (i.e. > 480 min/day) for 11.6 week days and 4.8 weekend days during the 31 days observation period. The average sedentary time was 11.63±1.25 hours per day during the week and 12.49±1.10 hours per day on the weekend, with a tendency to be higher on the weekend compared to weekdays (p = 0.06; d = 0.73). The average time in light, moderate and vigorous PA during the weekdays was 1.27±1.15, 0.76±0.37, 0.51±0.44 hours per day and 0.67±0.43, 0.59±0.37, 0.53±0.32 hours per weekend day. Light physical activity was higher during weekdays compared to the weekend (p = 0.04; d = 0.69) Based on our pilot study of eleven national elite rowers we conclude that rowers display a considerable sedentary off-training behavior of more than 11.5 hours/day.},
  author = {Sperlich, Billy and Becker, Martin and Hotho, Andreas and Wallmann-Sperlich, Birgit and Sareban, Mahdi and Winkert, Kay and Steinacker, Jürgen M. and Treff, Gunnar},
  journal = {Frontiers in Physiology},
  keywords = {behavior},
  pages = 655,
  title = {Sedentary Behavior among National Elite Rowers during Off-Training—A Pilot Study},
  volume = 8,
  year = 2017
  }
  

  %0 Journal Article
  %1 sperlich2017sedentary
  %A Sperlich, Billy
  %A Becker, Martin
  %A Hotho, Andreas
  %A Wallmann-Sperlich, Birgit
  %A Sareban, Mahdi
  %A Winkert, Kay
  %A Steinacker, Jürgen M.
  %A Treff, Gunnar
  %D 2017
  %J Frontiers in Physiology
  %P 655
  %R 10.3389/fphys.2017.00655
  %T Sedentary Behavior among National Elite Rowers during Off-Training—A Pilot Study
  %U http://journal.frontiersin.org/article/10.3389/fphys.2017.00655
  %V 8
  %X The aim of this pilot study was to analyze the off-training physical activity (PA) profile in national elite German U23 rowers during 31 days of their preparation period. The hours spent in each PA category (i.e. sedentary: <1.5 MET; light physical activity: 1.5–3 MET; moderate physical activity: 3–6 MET and vigorous intense physical activity: >6 MET) were calculated for every valid day (i.e. > 480 min of wear time). The off-training PA during 21 weekdays and 10 weekend days of the final 11-wk preparation period was assessed by a wrist-worn multisensory device (Microsoft Band II (MSBII)). A total of 11 rowers provided valid data (i.e. > 480 min/day) for 11.6 week days and 4.8 weekend days during the 31 days observation period. The average sedentary time was 11.63±1.25 hours per day during the week and 12.49±1.10 hours per day on the weekend, with a tendency to be higher on the weekend compared to weekdays (p = 0.06; d = 0.73). The average time in light, moderate and vigorous PA during the weekdays was 1.27±1.15, 0.76±0.37, 0.51±0.44 hours per day and 0.67±0.43, 0.59±0.37, 0.53±0.32 hours per weekend day. Light physical activity was higher during weekdays compared to the weekend (p = 0.04; d = 0.69) Based on our pilot study of eleven national elite rowers we conclude that rowers display a considerable sedentary off-training behavior of more than 11.5 hours/day.
  

• 
  1.

  Zehe, A., Becker, M., Jannidis, F., and Hotho, A. (2017) Towards Sentiment Analysis on German Literature. In Joint German/Austrian Conference on Artificial Intelligence (K{ü}nstliche Intelligenz), pp. 387–394, Springer.

  BibTeXEndNoteBibSonomyDownload

  @inproceedings{zehe2017towards,
  author = {Zehe, Albin and Becker, Martin and Jannidis, Fotis and Hotho, Andreas},
  booktitle = {Joint German/Austrian Conference on Artificial Intelligence (K{ü}nstliche Intelligenz)},
  keywords = {analysis},
  organization = {Springer},
  pages = {387--394},
  title = {Towards Sentiment Analysis on German Literature},
  year = 2017
  }
  

  %0 Conference Paper
  %1 zehe2017towards
  %A Zehe, Albin
  %A Becker, Martin
  %A Jannidis, Fotis
  %A Hotho, Andreas
  %B Joint German/Austrian Conference on Artificial Intelligence (K{ü}nstliche Intelligenz)
  %D 2017
  %P 387--394
  %T Towards Sentiment Analysis on German Literature
  

• 
  1.

  Atzmueller, M., Becker, M., and Mueller, J. (2017) Collective Sensing Platforms. In Participatory Sensing, Opinions and Collective Awareness (Loreto, V., Haklay, M., Hotho, A., Servedio, V. D., Stumme, G., Tria, F., and Theunis, J., Eds.), pp. 115–133, Springer International Publishing, Cham.

  URLBibTeXEndNoteDOIBibSonomyDownload

  @inbook{atzmueller2017collective,
  address = {Cham},
  author = {Atzmueller, Martin and Becker, Martin and Mueller, Juergen},
  booktitle = {Participatory Sensing, Opinions and Collective Awareness},
  editor = {Loreto, Vittorio and Haklay, Muki and Hotho, Andreas and Servedio, Vito D.P. and Stumme, Gerd and Tria, Francesca and Theunis, Jan},
  keywords = {eva},
  pages = {115--133},
  publisher = {Springer International Publishing},
  title = {Collective Sensing Platforms},
  year = 2017
  }
  

  %0 Book Section
  %1 atzmueller2017collective
  %A Atzmueller, Martin
  %A Becker, Martin
  %A Mueller, Juergen
  %B Participatory Sensing, Opinions and Collective Awareness
  %C Cham
  %D 2017
  %E Loreto, Vittorio
  %E Haklay, Muki
  %E Hotho, Andreas
  %E Servedio, Vito D.P.
  %E Stumme, Gerd
  %E Tria, Francesca
  %E Theunis, Jan
  %I Springer International Publishing
  %P 115--133
  %R 10.1007/978-3-319-25658-0_6
  %T Collective Sensing Platforms
  %U https://doi.org/10.1007/978-3-319-25658-0_6
  %@ 978-3-319-25658-0
  

• 
  1.

  Niebler, T., Becker, M., Pölitz, C., and Hotho, A. (2017) Learning Semantic Relatedness from Human Feedback Using Relative Relatedness Learning. In Proceedings of the ISWC 2017 Posters \& Demonstrations and Industry Tracks co-located with 16th International Semantic Web Conference (ISWC 2017) (Nikitina, N., Song, D., Fokoue, A., and Haase, P., Eds.).

  URLBibTeXEndNoteBibSonomyDownload

  @inproceedings{niebler2017metric,
  author = {Niebler, Thomas and Becker, Martin and Pölitz, Christian and Hotho, Andreas},
  booktitle = {Proceedings of the ISWC 2017 Posters \& Demonstrations and Industry Tracks co-located with 16th International Semantic Web Conference (ISWC 2017)},
  editor = {Nikitina, Nadeschda and Song, Dezhao and Fokoue, Achille and Haase, Peter},
  keywords = {metric},
  title = {Learning Semantic Relatedness from Human Feedback Using Relative Relatedness Learning},
  year = 2017
  }
  

  %0 Conference Paper
  %1 niebler2017metric
  %A Niebler, Thomas
  %A Becker, Martin
  %A Pölitz, Christian
  %A Hotho, Andreas
  %B Proceedings of the ISWC 2017 Posters \& Demonstrations and Industry Tracks co-located with 16th International Semantic Web Conference (ISWC 2017)
  %D 2017
  %E Nikitina, Nadeschda
  %E Song, Dezhao
  %E Fokoue, Achille
  %E Haase, Peter
  %T Learning Semantic Relatedness from Human Feedback Using Relative Relatedness Learning
  %U http://ceur-ws.org/Vol-1963/paper471.pdf
  

• 
  1.

  Atzmueller, M., Becker, M., Molino, A., Mueller, J., Peters, J., and Sirbu, A. (2017) Applications for Environmental Sensing in EveryAware. In Participatory Sensing, Opinions and Collective Awareness (Loreto, V., Haklay, M., Hotho, A., Servedio, V. D., Stumme, G., Tria, F., and Theunis, J., Eds.), pp. 135–155, Springer International Publishing, Cham.

  URLBibTeXEndNoteDOIBibSonomyDownload

  @inbook{atzmueller2017applications,
  address = {Cham},
  author = {Atzmueller, Martin and Becker, Martin and Molino, Andrea and Mueller, Juergen and Peters, Jan and Sirbu, Alina},
  booktitle = {Participatory Sensing, Opinions and Collective Awareness},
  editor = {Loreto, Vittorio and Haklay, Muki and Hotho, Andreas and Servedio, Vito D.P. and Stumme, Gerd and Tria, Francesca and Theunis, Jan},
  keywords = {participatory},
  pages = {135--155},
  publisher = {Springer International Publishing},
  title = {Applications for Environmental Sensing in EveryAware},
  year = 2017
  }
  

  %0 Book Section
  %1 atzmueller2017applications
  %A Atzmueller, Martin
  %A Becker, Martin
  %A Molino, Andrea
  %A Mueller, Juergen
  %A Peters, Jan
  %A Sirbu, Alina
  %B Participatory Sensing, Opinions and Collective Awareness
  %C Cham
  %D 2017
  %E Loreto, Vittorio
  %E Haklay, Muki
  %E Hotho, Andreas
  %E Servedio, Vito D.P.
  %E Stumme, Gerd
  %E Tria, Francesca
  %E Theunis, Jan
  %I Springer International Publishing
  %P 135--155
  %R 10.1007/978-3-319-25658-0_7
  %T Applications for Environmental Sensing in EveryAware
  %U https://doi.org/10.1007/978-3-319-25658-0_7
  %@ 978-3-319-25658-0
  

2016

• 
  1.

  Becker, M., Mewes, H., Hotho, A., Dimitrov, D., Lemmerich, F., and Strohmaier, M. (2016) SparkTrails: A MapReduce Implementation of HypTrails for Comparing Hypotheses About Human Trails. In International Conference Companion on World Wide Web, pp. 17–18, International World Wide Web Conferences Steering Committee, Republic and Canton of Geneva, Switzerland.

  URLBibTeXEndNoteDOIBibSonomyDownload

  @inproceedings{becker2016sparktrails,
  address = {Republic and Canton of Geneva, Switzerland},
  author = {Becker, Martin and Mewes, Hauke and Hotho, Andreas and Dimitrov, Dimitar and Lemmerich, Florian and Strohmaier, Markus},
  booktitle = {International Conference Companion on World Wide Web},
  keywords = {behavior},
  pages = {17--18},
  publisher = {International World Wide Web Conferences Steering Committee},
  series = {WWW '16 Companion},
  title = {SparkTrails: A MapReduce Implementation of HypTrails for Comparing Hypotheses About Human Trails},
  year = 2016
  }
  

  %0 Conference Paper
  %1 becker2016sparktrails
  %A Becker, Martin
  %A Mewes, Hauke
  %A Hotho, Andreas
  %A Dimitrov, Dimitar
  %A Lemmerich, Florian
  %A Strohmaier, Markus
  %B International Conference Companion on World Wide Web
  %C Republic and Canton of Geneva, Switzerland
  %D 2016
  %I International World Wide Web Conferences Steering Committee
  %P 17--18
  %R 10.1145/2872518.2889380
  %T SparkTrails: A MapReduce Implementation of HypTrails for Comparing Hypotheses About Human Trails
  %U https://doi.org/10.1145/2872518.2889380
  %@ 978-1-4503-4144-8
  

• 
  1.

  Niebler, T., Becker, M., Zoller, D., Doerfel, S., and Hotho, A. (2016) FolkTrails: Interpreting navigation behavior in a social tagging system. In International on Conference on Information and Knowledge Management, pp. 2311–2316, ACM, New York, NY, USA.

  AbstractURLBibTeXEndNoteDOIBibSonomyDownload

  Social tagging systems have established themselves as a quick and easy way to organize information by annotating resources with tags. In recent work, user behavior in social tagging systems was studied, that is, how users assign tags, and consume content. However, it is still unclear how users make use of the navigation options they are given. Understanding their behavior and differences in behavior of different user groups is an important step towards assessing the effectiveness of a navigational concept and of improving it to better suit the users' needs. In this work, we investigate navigation trails in the popular scholarly social tagging system BibSonomy from six years of log data. We discuss dynamic browsing behavior of the general user population and show that different navigational subgroups exhibit different navigational traits. Furthermore, we provide strong evidence that the semantic nature of the underlying folksonomy is an essential factor for explaining navigation.

  @inproceedings{niebler2016folktrails,
  abstract = {Social tagging systems have established themselves as a quick and easy way to organize information by annotating resources with tags. In recent work, user behavior in social tagging systems was studied, that is, how users assign tags, and consume content. However, it is still unclear how users make use of the navigation options they are given. Understanding their behavior and differences in behavior of different user groups is an important step towards assessing the effectiveness of a navigational concept and of improving it to better suit the users' needs. In this work, we investigate navigation trails in the popular scholarly social tagging system BibSonomy from six years of log data. We discuss dynamic browsing behavior of the general user population and show that different navigational subgroups exhibit different navigational traits. Furthermore, we provide strong evidence that the semantic nature of the underlying folksonomy is an essential factor for explaining navigation.},
  address = {New York, NY, USA},
  author = {Niebler, Thomas and Becker, Martin and Zoller, Daniel and Doerfel, Stephan and Hotho, Andreas},
  booktitle = {International on Conference on Information and Knowledge Management},
  keywords = {selected},
  pages = {2311--2316},
  publisher = {ACM},
  series = {CIKM '16},
  title = {FolkTrails: Interpreting navigation behavior in a social tagging system},
  year = 2016
  }
  

  %0 Conference Paper
  %1 niebler2016folktrails
  %A Niebler, Thomas
  %A Becker, Martin
  %A Zoller, Daniel
  %A Doerfel, Stephan
  %A Hotho, Andreas
  %B International on Conference on Information and Knowledge Management
  %C New York, NY, USA
  %D 2016
  %I ACM
  %P 2311--2316
  %R 10.1145/2983323.2983686
  %T FolkTrails: Interpreting navigation behavior in a social tagging system
  %U http://dx.doi.org/10.1145/2983323.2983686
  %X Social tagging systems have established themselves as a quick and easy way to organize information by annotating resources with tags. In recent work, user behavior in social tagging systems was studied, that is, how users assign tags, and consume content. However, it is still unclear how users make use of the navigation options they are given. Understanding their behavior and differences in behavior of different user groups is an important step towards assessing the effectiveness of a navigational concept and of improving it to better suit the users' needs. In this work, we investigate navigation trails in the popular scholarly social tagging system BibSonomy from six years of log data. We discuss dynamic browsing behavior of the general user population and show that different navigational subgroups exhibit different navigational traits. Furthermore, we provide strong evidence that the semantic nature of the underlying folksonomy is an essential factor for explaining navigation.
  

• 
  1.

  Lemmerich, F., Becker, M., Singer, P., Helic, D., Hotho, A., and Strohmaier, M. (2016) Mining Subgroups with Exceptional Transition Behavior. In Proceedings of the 22Nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 965–974, ACM, San Francisco, California, USA.

  AbstractURLBibTeXEndNoteDOIBibSonomyDownload

  We present a new method for detecting interpretable subgroups with exceptional transition behavior in sequential data. Identifying such patterns has many potential applications, e.g., for studying human mobility or analyzing the behavior of internet users. To tackle this task, we employ exceptional model mining, which is a general approach for identifying interpretable data subsets that exhibit unusual interactions between a set of target attributes with respect to a certain model class. Although exceptional model mining provides a well-suited framework for our problem, previously investigated model classes cannot capture transition behavior. To that end, we introduce first-order Markov chains as a novel model class for exceptional model mining and present a new interestingness measure that quantifies the exceptionality of transition subgroups. The measure compares the distance between the Markov transition matrix of a subgroup and the respective matrix of the entire data with the distance of random dataset samples. In addition, our method can be adapted to find subgroups that match or contradict given transition hypotheses. We demonstrate that our method is consistently able to recover subgroups with exceptional transition models from synthetic data and illustrate its potential in two application examples. Our work is relevant for researchers and practitioners interested in detecting exceptional transition behavior in sequential data.

  @inproceedings{lemmerich2016mining,
  abstract = {We present a new method for detecting interpretable subgroups with exceptional transition behavior in sequential data. Identifying such patterns has many potential applications, e.g., for studying human mobility or analyzing the behavior of internet users. To tackle this task, we employ exceptional model mining, which is a general approach for identifying interpretable data subsets that exhibit unusual interactions between a set of target attributes with respect to a certain model class. Although exceptional model mining provides a well-suited framework for our problem, previously investigated model classes cannot capture transition behavior. To that end, we introduce first-order Markov chains as a novel model class for exceptional model mining and present a new interestingness measure that quantifies the exceptionality of transition subgroups. The measure compares the distance between the Markov transition matrix of a subgroup and the respective matrix of the entire data with the distance of random dataset samples. In addition, our method can be adapted to find subgroups that match or contradict given transition hypotheses. We demonstrate that our method is consistently able to recover subgroups with exceptional transition models from synthetic data and illustrate its potential in two application examples. Our work is relevant for researchers and practitioners interested in detecting exceptional transition behavior in sequential data.},
  address = {New York, NY, USA},
  author = {Lemmerich, Florian and Becker, Martin and Singer, Philipp and Helic, Denis and Hotho, Andreas and Strohmaier, Markus},
  booktitle = {Proceedings of the 22Nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining},
  keywords = {selected},
  pages = {965--974},
  publisher = {ACM},
  series = {KDD '16},
  title = {Mining Subgroups with Exceptional Transition Behavior},
  year = 2016
  }
  

  %0 Conference Paper
  %1 lemmerich2016mining
  %A Lemmerich, Florian
  %A Becker, Martin
  %A Singer, Philipp
  %A Helic, Denis
  %A Hotho, Andreas
  %A Strohmaier, Markus
  %B Proceedings of the 22Nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
  %C New York, NY, USA
  %D 2016
  %I ACM
  %P 965--974
  %R 10.1145/2939672.2939752
  %T Mining Subgroups with Exceptional Transition Behavior
  %U http://doi.acm.org/10.1145/2939672.2939752
  %X We present a new method for detecting interpretable subgroups with exceptional transition behavior in sequential data. Identifying such patterns has many potential applications, e.g., for studying human mobility or analyzing the behavior of internet users. To tackle this task, we employ exceptional model mining, which is a general approach for identifying interpretable data subsets that exhibit unusual interactions between a set of target attributes with respect to a certain model class. Although exceptional model mining provides a well-suited framework for our problem, previously investigated model classes cannot capture transition behavior. To that end, we introduce first-order Markov chains as a novel model class for exceptional model mining and present a new interestingness measure that quantifies the exceptionality of transition subgroups. The measure compares the distance between the Markov transition matrix of a subgroup and the respective matrix of the entire data with the distance of random dataset samples. In addition, our method can be adapted to find subgroups that match or contradict given transition hypotheses. We demonstrate that our method is consistently able to recover subgroups with exceptional transition models from synthetic data and illustrate its potential in two application examples. Our work is relevant for researchers and practitioners interested in detecting exceptional transition behavior in sequential data.
  %@ 978-1-4503-4232-2
  

• 
  1.

  Zehe, A., Becker, M., Hettinger, L., Hotho, A., Reger, I., and Jannidis, F. (2016) Prediction of Happy Endings in German Novels. In Proceedings of the Workshop on Interactions between Data Mining and Natural Language Processing 2016 (Cellier, P., Charnois, T., Hotho, A., Matwin, S., Moens, M.-F., and Toussaint, Y., Eds.), pp. 9–16.

  AbstractURLBibTeXEndNoteBibSonomyDownload

  Identifying plot structure in novels is a valuable step towards automatic processing of literary corpora. We present an approach to classify novels as either having a happy ending or not. To achieve this, we use features based on different sentiment lexica as input for an SVM- classifier, which yields an average F1-score of about 73\%.

  @inproceedings{zehe2016prediction,
  abstract = {Identifying plot structure in novels is a valuable step towards automatic processing of literary corpora. We present an approach to classify novels as either having a happy ending or not. To achieve this, we use features based on different sentiment lexica as input for an SVM- classifier, which yields an average F1-score of about 73\%.},
  author = {Zehe, Albin and Becker, Martin and Hettinger, Lena and Hotho, Andreas and Reger, Isabella and Jannidis, Fotis},
  booktitle = {Proceedings of the Workshop on Interactions between Data Mining and Natural Language Processing 2016},
  editor = {Cellier, Peggy and Charnois, Thierry and Hotho, Andreas and Matwin, Stan and Moens, Marie-Francine and Toussaint, Yannick},
  keywords = {classification},
  month = {07},
  pages = {9-16},
  title = {Prediction of Happy Endings in German Novels},
  year = 2016
  }
  

  %0 Conference Paper
  %1 zehe2016prediction
  %A Zehe, Albin
  %A Becker, Martin
  %A Hettinger, Lena
  %A Hotho, Andreas
  %A Reger, Isabella
  %A Jannidis, Fotis
  %B Proceedings of the Workshop on Interactions between Data Mining and Natural Language Processing 2016
  %D 2016
  %E Cellier, Peggy
  %E Charnois, Thierry
  %E Hotho, Andreas
  %E Matwin, Stan
  %E Moens, Marie-Francine
  %E Toussaint, Yannick
  %P 9-16
  %T Prediction of Happy Endings in German Novels
  %U http://ceur-ws.org/Vol-1646/
  %X Identifying plot structure in novels is a valuable step towards automatic processing of literary corpora. We present an approach to classify novels as either having a happy ending or not. To achieve this, we use features based on different sentiment lexica as input for an SVM- classifier, which yields an average F1-score of about 73\%.
  

• 
  1.

  Niebler, T., Schlör, D., Becker, M., and Hotho, A. (2016) Extracting Semantics from unconstrained navigation on wikipedia, KI - Künstliche Intelligenz, Springer Berlin Heidelberg 30, 163–168.

  URLBibTeXEndNoteDOIBibSonomyDownload

  @article{niebler2016extracting,
  author = {Niebler, Thomas and Schlör, Daniel and Becker, Martin and Hotho, Andreas},
  journal = {KI - Künstliche Intelligenz},
  keywords = {diss},
  month = {06},
  number = 2,
  pages = {163--168},
  publisher = {Springer Berlin Heidelberg},
  title = {Extracting Semantics from unconstrained navigation on wikipedia},
  volume = 30,
  year = 2016
  }
  

  %0 Journal Article
  %1 niebler2016extracting
  %A Niebler, Thomas
  %A Schlör, Daniel
  %A Becker, Martin
  %A Hotho, Andreas
  %D 2016
  %I Springer Berlin Heidelberg
  %J KI - Künstliche Intelligenz
  %N 2
  %P 163--168
  %R 10.1007/s13218-015-0417-5
  %T Extracting Semantics from unconstrained navigation on wikipedia
  %U http://dx.doi.org/10.1007/s13218-015-0417-5
  %V 30
  

2015

• 
  1.

  Atzmueller, M., Mueller, J., and Becker, M. (2015) Exploratory Subgroup Analytics on Ubiquitous Data. In Mining, Modeling, and Recommending ’Things’ in Social Media (Atzmueller, M., Chin, A., Scholz, C., and Trattner, C., Eds.), pp. 1–20, Springer International Publishing, Cham.

  AbstractBibTeXEndNoteBibSonomyDownload

  This paper presents exploratory subgroup analytics on ubiquitous data: We propose subgroup discovery and assessment approaches for obtaining interesting descriptive patterns and provide a novel graph-based analysis approach for assessing the relations between the obtained subgroup set. This exploratory visualization approaches allows for the comparison of subgroups according to their relations to other subgroups and to include further parameters, e.g., geo-spatial distribution indicators. We present and discuss analysis results utilizing real-world data given by geo-tagged noise measurements with associated subjective perceptions and a set of tags describing the semantic context.

  @inproceedings{atzmueller2015exploratory,
  abstract = {This paper presents exploratory subgroup analytics on ubiquitous data: We propose subgroup discovery and assessment approaches for obtaining interesting descriptive patterns and provide a novel graph-based analysis approach for assessing the relations between the obtained subgroup set. This exploratory visualization approaches allows for the comparison of subgroups according to their relations to other subgroups and to include further parameters, e.g., geo-spatial distribution indicators. We present and discuss analysis results utilizing real-world data given by geo-tagged noise measurements with associated subjective perceptions and a set of tags describing the semantic context.},
  address = {Cham},
  author = {Atzmueller, Martin and Mueller, Juergen and Becker, Martin},
  booktitle = {Mining, Modeling, and Recommending 'Things' in Social Media},
  editor = {Atzmueller, Martin and Chin, Alvin and Scholz, Christoph and Trattner, Christoph},
  keywords = {data},
  pages = {1--20},
  publisher = {Springer International Publishing},
  title = {Exploratory Subgroup Analytics on Ubiquitous Data},
  year = 2015
  }
  

  %0 Conference Paper
  %1 atzmueller2015exploratory
  %A Atzmueller, Martin
  %A Mueller, Juergen
  %A Becker, Martin
  %B Mining, Modeling, and Recommending 'Things' in Social Media
  %C Cham
  %D 2015
  %E Atzmueller, Martin
  %E Chin, Alvin
  %E Scholz, Christoph
  %E Trattner, Christoph
  %I Springer International Publishing
  %P 1--20
  %T Exploratory Subgroup Analytics on Ubiquitous Data
  %X This paper presents exploratory subgroup analytics on ubiquitous data: We propose subgroup discovery and assessment approaches for obtaining interesting descriptive patterns and provide a novel graph-based analysis approach for assessing the relations between the obtained subgroup set. This exploratory visualization approaches allows for the comparison of subgroups according to their relations to other subgroups and to include further parameters, e.g., geo-spatial distribution indicators. We present and discuss analysis results utilizing real-world data given by geo-tagged noise measurements with associated subjective perceptions and a set of tags describing the semantic context.
  %@ 978-3-319-14723-9
  

• 
  1.

  Becker, M., Singer, P., Lemmerich, F., Hotho, A., Helic, D., and Strohmaier, M. (2015) Photowalking the City: Comparing Hypotheses About Urban Photo Trails on Flickr. In International Conference on Social Informatics (Liu, T.-Y., Scollon, C. N., and Zhu, W., Eds.), pp. 227–244, Springer International Publishing, Cham.

  URLBibTeXEndNoteDOIBibSonomyDownload

  @inproceedings{becker2015photowalking,
  address = {Cham},
  author = {Becker, Martin and Singer, Philipp and Lemmerich, Florian and Hotho, Andreas and Helic, Denis and Strohmaier, Markus},
  booktitle = {International Conference on Social Informatics},
  editor = {Liu, Tie-Yan and Scollon, Christie Napa and Zhu, Wenwu},
  keywords = {markov},
  pages = {227--244},
  publisher = {Springer International Publishing},
  title = {Photowalking the City: Comparing Hypotheses About Urban Photo Trails on Flickr},
  year = 2015
  }
  

  %0 Conference Paper
  %1 becker2015photowalking
  %A Becker, Martin
  %A Singer, Philipp
  %A Lemmerich, Florian
  %A Hotho, Andreas
  %A Helic, Denis
  %A Strohmaier, Markus
  %B International Conference on Social Informatics
  %C Cham
  %D 2015
  %E Liu, Tie-Yan
  %E Scollon, Christie Napa
  %E Zhu, Wenwu
  %I Springer International Publishing
  %P 227--244
  %R 10.1007/978-3-319-27433-1_16
  %T Photowalking the City: Comparing Hypotheses About Urban Photo Trails on Flickr
  %U http://dx.doi.org/10.1007/978-3-319-27433-1_16
  %@ 978-3-319-27433-1
  

• 
  1.

  Ring, M., Otto, F., Becker, M., Niebler, T., Landes, D., and Hotho, A. (2015) ConDist: A Context-Driven Categorical Distance Measure. In Proceedings of the European Conference on Machine Learning and Knowledge Discovery in Databases (ECML PKDD) (Appice, A., Rodrigues, P. P., Costa, V. S., Soares, C., Gama, J., and Jorge, A., Eds.), pp. 251–266, Springer International Publishing, Cham.

  AbstractURLBibTeXEndNoteDOIBibSonomyDownload

  A distance measure between objects is a key requirement for many data mining tasks like clustering, classification or outlier detection. However, for objects characterized by categorical attributes, defining meaningful distance measures is a challenging task since the values within such attributes have no inherent order, especially without additional domain knowledge. In this paper, we propose an unsupervised distance measure for objects with categorical attributes based on the idea that categorical attribute values are similar if they appear with similar value distributions on correlated context attributes. Thus, the distance measure is automatically derived from the given data set. We compare our new distance measure to existing categorical distance measures and evaluate on different data sets from the UCI machine-learning repository. The experiments show that our distance measure is recommendable, since it achieves similar or better results in a more robust way than previous approaches.

  @inproceedings{ring2015condist,
  abstract = {A distance measure between objects is a key requirement for many data mining tasks like clustering, classification or outlier detection. However, for objects characterized by categorical attributes, defining meaningful distance measures is a challenging task since the values within such attributes have no inherent order, especially without additional domain knowledge. In this paper, we propose an unsupervised distance measure for objects with categorical attributes based on the idea that categorical attribute values are similar if they appear with similar value distributions on correlated context attributes. Thus, the distance measure is automatically derived from the given data set. We compare our new distance measure to existing categorical distance measures and evaluate on different data sets from the UCI machine-learning repository. The experiments show that our distance measure is recommendable, since it achieves similar or better results in a more robust way than previous approaches.},
  address = {Cham},
  author = {Ring, Markus and Otto, Florian and Becker, Martin and Niebler, Thomas and Landes, Dieter and Hotho, Andreas},
  booktitle = {Proceedings of the European Conference on Machine Learning and Knowledge Discovery in Databases (ECML PKDD)},
  editor = {Appice, Annalisa and Rodrigues, Pedro Pereira and Costa, Vitor Santos and Soares, Carlos and Gama, Joao and Jorge, Alipio},
  keywords = {categorical},
  pages = {251--266},
  publisher = {Springer International Publishing},
  title = {ConDist: A Context-Driven Categorical Distance Measure},
  year = 2015
  }
  

  %0 Conference Paper
  %1 ring2015condist
  %A Ring, Markus
  %A Otto, Florian
  %A Becker, Martin
  %A Niebler, Thomas
  %A Landes, Dieter
  %A Hotho, Andreas
  %B Proceedings of the European Conference on Machine Learning and Knowledge Discovery in Databases (ECML PKDD)
  %C Cham
  %D 2015
  %E Appice, Annalisa
  %E Rodrigues, Pedro Pereira
  %E Costa, Vitor Santos
  %E Soares, Carlos
  %E Gama, Joao
  %E Jorge, Alipio
  %I Springer International Publishing
  %P 251--266
  %R 10.1007/978-3-319-23528-8_16
  %T ConDist: A Context-Driven Categorical Distance Measure
  %U https://doi.org/10.1007/978-3-319-23528-8_16
  %X A distance measure between objects is a key requirement for many data mining tasks like clustering, classification or outlier detection. However, for objects characterized by categorical attributes, defining meaningful distance measures is a challenging task since the values within such attributes have no inherent order, especially without additional domain knowledge. In this paper, we propose an unsupervised distance measure for objects with categorical attributes based on the idea that categorical attribute values are similar if they appear with similar value distributions on correlated context attributes. Thus, the distance measure is automatically derived from the given data set. We compare our new distance measure to existing categorical distance measures and evaluate on different data sets from the UCI machine-learning repository. The experiments show that our distance measure is recommendable, since it achieves similar or better results in a more robust way than previous approaches.
  %@ 251--266
  

• 
  1.

  Becker, M., Singer, P., Lemmerich, F., Hotho, A., Helic, D., and Strohmaier, M. (2015) VizTrails: An Information Visualization Tool for Exploring Geographic Movement Trajectories. In Conference on Hypertext \& Social Media, pp. 319–320, ACM, Guzelyurt, Northern Cyprus.

  URLBibTeXEndNoteDOIBibSonomyDownload

  @inproceedings{becker2015viztrails,
  address = {New York, NY, USA},
  author = {Becker, Martin and Singer, Philipp and Lemmerich, Florian and Hotho, Andreas and Helic, Denis and Strohmaier, Markus},
  booktitle = {Conference on Hypertext \& Social Media},
  keywords = {movement},
  pages = {319--320},
  publisher = {ACM},
  series = {HT '15},
  title = {VizTrails: An Information Visualization Tool for Exploring Geographic Movement Trajectories},
  year = 2015
  }
  

  %0 Conference Paper
  %1 becker2015viztrails
  %A Becker, Martin
  %A Singer, Philipp
  %A Lemmerich, Florian
  %A Hotho, Andreas
  %A Helic, Denis
  %A Strohmaier, Markus
  %B Conference on Hypertext \& Social Media
  %C New York, NY, USA
  %D 2015
  %I ACM
  %P 319--320
  %R 10.1145/2700171.2791021
  %T VizTrails: An Information Visualization Tool for Exploring Geographic Movement Trajectories
  %U http://doi.acm.org/10.1145/2700171.2791021
  %@ 978-1-4503-3395-5
  

• 
  1.

  Sirbu, A., Becker, M., Caminiti, S., De Baets, B., Elen, B., Francis, L., Gravino, P., Hotho, A., Ingarra, S., Loreto, V., Molino, A., Mueller, J., Peters, J., Ricchiuti, F., Saracino, F., Servedio, V. D. P., Stumme, G., Theunis, J., Tria, F., and Van den Bossche, J. (2015) Participatory patterns in an international air quality monitoring initiative, PLoS ONE, Public Library of Science 10, e0136763.

  AbstractURLBibTeXEndNoteBibSonomyDownload

  The issue of sustainability is at the top of the political and societal agenda, being considered of extreme importance and urgency. Human individual action impacts the environment both locally (e.g., local air/water quality, noise disturbance) and globally (e.g., climate change, resource use). Urban environments represent a crucial example, with an increasing realization that the most effective way of producing a change is involving the citizens themselves in monitoring campaigns (a citizen science bottom-up approach). This is possible by developing novel technologies and IT infrastructures enabling large citizen participation. Here, in the wider framework of one of the first such projects, we show results from an international competition where citizens were involved in mobile air pollution monitoring using low cost sensing devices, combined with a web-based game to monitor perceived levels of pollution. Measures of shift in perceptions over the course of the campaign are provided, together with insights into participatory patterns emerging from this study. Interesting effects related to inertia and to direct involvement in measurement activities rather than indirect information exposure are also highlighted, indicating that direct involvement can enhance learning and environmental awareness. In the future, this could result in better adoption of policies towards decreasing pollution.

  @article{sirbu2015participatory,
  abstract = {The issue of sustainability is at the top of the political and societal agenda, being considered of extreme importance and urgency. Human individual action impacts the environment both locally (e.g., local air/water quality, noise disturbance) and globally (e.g., climate change, resource use). Urban environments represent a crucial example, with an increasing realization that the most effective way of producing a change is involving the citizens themselves in monitoring campaigns (a citizen science bottom-up approach). This is possible by developing novel technologies and IT infrastructures enabling large citizen participation. Here, in the wider framework of one of the first such projects, we show results from an international competition where citizens were involved in mobile air pollution monitoring using low cost sensing devices, combined with a web-based game to monitor perceived levels of pollution. Measures of shift in perceptions over the course of the campaign are provided, together with insights into participatory patterns emerging from this study. Interesting effects related to inertia and to direct involvement in measurement activities rather than indirect information exposure are also highlighted, indicating that direct involvement can enhance learning and environmental awareness. In the future, this could result in better adoption of policies towards decreasing pollution.},
  author = {Sirbu, Alina and Becker, Martin and Caminiti, Saverio and De Baets, Bernard and Elen, Bart and Francis, Louise and Gravino, Pietro and Hotho, Andreas and Ingarra, Stefano and Loreto, Vittorio and Molino, Andrea and Mueller, Juergen and Peters, Jan and Ricchiuti, Ferdinando and Saracino, Fabio and Servedio, Vito D. P. and Stumme, Gerd and Theunis, Jan and Tria, Francesca and Van den Bossche, Joris},
  journal = {PLoS ONE},
  keywords = {selected},
  month = {08},
  number = 8,
  pages = {e0136763},
  publisher = {Public Library of Science},
  title = {Participatory patterns in an international air quality monitoring initiative},
  volume = 10,
  year = 2015
  }
  

  %0 Journal Article
  %1 sirbu2015participatory
  %A Sirbu, Alina
  %A Becker, Martin
  %A Caminiti, Saverio
  %A De Baets, Bernard
  %A Elen, Bart
  %A Francis, Louise
  %A Gravino, Pietro
  %A Hotho, Andreas
  %A Ingarra, Stefano
  %A Loreto, Vittorio
  %A Molino, Andrea
  %A Mueller, Juergen
  %A Peters, Jan
  %A Ricchiuti, Ferdinando
  %A Saracino, Fabio
  %A Servedio, Vito D. P.
  %A Stumme, Gerd
  %A Theunis, Jan
  %A Tria, Francesca
  %A Van den Bossche, Joris
  %D 2015
  %I Public Library of Science
  %J PLoS ONE
  %N 8
  %P e0136763
  %T Participatory patterns in an international air quality monitoring initiative
  %U http://dx.doi.org/10.1371%2Fjournal.pone.0136763
  %V 10
  %X The issue of sustainability is at the top of the political and societal agenda, being considered of extreme importance and urgency. Human individual action impacts the environment both locally (e.g., local air/water quality, noise disturbance) and globally (e.g., climate change, resource use). Urban environments represent a crucial example, with an increasing realization that the most effective way of producing a change is involving the citizens themselves in monitoring campaigns (a citizen science bottom-up approach). This is possible by developing novel technologies and IT infrastructures enabling large citizen participation. Here, in the wider framework of one of the first such projects, we show results from an international competition where citizens were involved in mobile air pollution monitoring using low cost sensing devices, combined with a web-based game to monitor perceived levels of pollution. Measures of shift in perceptions over the course of the campaign are provided, together with insights into participatory patterns emerging from this study. Interesting effects related to inertia and to direct involvement in measurement activities rather than indirect information exposure are also highlighted, indicating that direct involvement can enhance learning and environmental awareness. In the future, this could result in better adoption of policies towards decreasing pollution.
  

• 
  1.

  Hettinger, L., Becker, M., Reger, I., Jannidis, F., and Hotho, A. (2015) Genre Classification on German Novels. In 26th International Workshop on Database and Expert Systems Applications (DEXA), pp. 249–253.

  BibTeXEndNoteDOIBibSonomyDownload

  @inproceedings{schwemmlein2015genre,
  author = {Hettinger, Lena and Becker, Martin and Reger, Isabella and Jannidis, Fotis and Hotho, Andreas},
  booktitle = {26th International Workshop on Database and Expert Systems Applications (DEXA)},
  keywords = {classification},
  month = {09},
  pages = {249--253},
  title = {Genre Classification on German Novels},
  year = 2015
  }
  

  %0 Conference Paper
  %1 schwemmlein2015genre
  %A Hettinger, Lena
  %A Becker, Martin
  %A Reger, Isabella
  %A Jannidis, Fotis
  %A Hotho, Andreas
  %B 26th International Workshop on Database and Expert Systems Applications (DEXA)
  %D 2015
  %P 249--253
  %R 10.1109/DEXA.2015.62
  %T Genre Classification on German Novels
  %@ 1529-4188
  

• 
  1.

  Becker, M., Borchert, K., Hirth, M., Mewes, H., Hotho, A., and Tran-Gia, P. (2015) MicroTrails: Comparing Hypotheses About Task Selection on a Crowdsourcing Platform. In International Conference on Knowledge Technologies and Data-driven Business, pp. 10:1–10:8, ACM, New York, NY, USA.

  URLBibTeXEndNoteBibSonomyDownload

  @inproceedings{becker2015microtrails,
  address = {New York, NY, USA},
  author = {Becker, Martin and Borchert, Kathrin and Hirth, Matthias and Mewes, Hauke and Hotho, Andreas and Tran-Gia, Phuoc},
  booktitle = {International Conference on Knowledge Technologies and Data-driven Business},
  keywords = {incentives},
  month = 10,
  pages = {10:1--10:8},
  publisher = {ACM},
  title = {MicroTrails: Comparing Hypotheses About Task Selection on a Crowdsourcing Platform},
  year = 2015
  }
  

  %0 Conference Paper
  %1 becker2015microtrails
  %A Becker, Martin
  %A Borchert, Kathrin
  %A Hirth, Matthias
  %A Mewes, Hauke
  %A Hotho, Andreas
  %A Tran-Gia, Phuoc
  %B International Conference on Knowledge Technologies and Data-driven Business
  %C New York, NY, USA
  %D 2015
  %I ACM
  %P 10:1--10:8
  %T MicroTrails: Comparing Hypotheses About Task Selection on a Crowdsourcing Platform
  %U http://doi.acm.org/10.1145/2809563.2809608
  %@ 978-1-4503-3721-2
  

2014

• 
  1.

  Atzmueller, M., Becker, M., Kibanov, M., Scholz, C., Doerfel, S., Hotho, A., Macek, B.-E., Mitzlaff, F., Mueller, J., and Stumme, G. (2014) Ubicon and its applications for ubiquitous social computing, New Review of Hypermedia and Multimedia 20, 53–77.

  AbstractURLBibTeXEndNoteDOIBibSonomyDownload

  The combination of ubiquitous and social computing is an emerging research area which integrates different but complementary methods, techniques and tools. In this paper, we focus on the Ubicon platform, its applications, and a large spectrum of analysis results. Ubicon provides an extensible framework for building and hosting applications targeting both ubiquitous and social environments. We summarize the architecture and exemplify its implementation using four real-world applications built on top of Ubicon. In addition, we discuss several scientific experiments in the context of these applications in order to give a better picture of the potential of the framework, and discuss analysis results using several real-world data sets collected utilizing Ubicon.

  @article{atzmueller2014ubicon,
  abstract = {The combination of ubiquitous and social computing is an emerging research area which integrates different but complementary methods, techniques and tools. In this paper, we focus on the Ubicon platform, its applications, and a large spectrum of analysis results. Ubicon provides an extensible framework for building and hosting applications targeting both ubiquitous and social environments. We summarize the architecture and exemplify its implementation using four real-world applications built on top of Ubicon. In addition, we discuss several scientific experiments in the context of these applications in order to give a better picture of the potential of the framework, and discuss analysis results using several real-world data sets collected utilizing Ubicon.},
  author = {Atzmueller, Martin and Becker, Martin and Kibanov, Mark and Scholz, Christoph and Doerfel, Stephan and Hotho, Andreas and Macek, Bjoern-Elmar and Mitzlaff, Folke and Mueller, Juergen and Stumme, Gerd},
  journal = {New Review of Hypermedia and Multimedia},
  keywords = {diss},
  number = 1,
  pages = {53--77},
  title = {Ubicon and its applications for ubiquitous social computing},
  volume = 20,
  year = 2014
  }
  

  %0 Journal Article
  %1 atzmueller2014ubicon
  %A Atzmueller, Martin
  %A Becker, Martin
  %A Kibanov, Mark
  %A Scholz, Christoph
  %A Doerfel, Stephan
  %A Hotho, Andreas
  %A Macek, Bjoern-Elmar
  %A Mitzlaff, Folke
  %A Mueller, Juergen
  %A Stumme, Gerd
  %D 2014
  %J New Review of Hypermedia and Multimedia
  %N 1
  %P 53--77
  %R 10.1080/13614568.2013.873488
  %T Ubicon and its applications for ubiquitous social computing
  %U https://doi.org/10.1080/13614568.2013.873488
  %V 20
  %X The combination of ubiquitous and social computing is an emerging research area which integrates different but complementary methods, techniques and tools. In this paper, we focus on the Ubicon platform, its applications, and a large spectrum of analysis results. Ubicon provides an extensible framework for building and hosting applications targeting both ubiquitous and social environments. We summarize the architecture and exemplify its implementation using four real-world applications built on top of Ubicon. In addition, we discuss several scientific experiments in the context of these applications in order to give a better picture of the potential of the framework, and discuss analysis results using several real-world data sets collected utilizing Ubicon.
  

• 
  1.

  Becker, M., Hotho, A., Mueller, J., Kibanov, M., Atzmueller, M., and Stumme, G. (2014) Subjective vs. Objective Data: Bridging the Gap.

  AbstractURLBibTeXEndNoteBibSonomyDownload

  Sensor data is objective. But when measuring our environment, measured values are contrasted with our perception, which is always subjective. This makes interpreting sensor measurements difficult for a single person in her personal environment. In this context, the EveryAware projects directly connects the concepts of objective sensor data with subjective impressions and perceptions by providing a collective sensing platform with several client applications allowing to explicitly associate those two data types. The goal is to provide the user with personalized feedback, a characterization of the global as well as her personal environment, and enable her to position her perceptions in this global context. In this poster we summarize the collected data of two EveryAware applications, namely WideNoise for noise measurements and AirProbe for participatory air quality sensing. Basic insights are presented including user activity, learning processes and sensor data to perception correlations. These results provide an outlook on how this data can further be used to understand the connection between sensor data and perceptions.

  @misc{becker2014subjective,
  abstract = {Sensor data is objective. But when measuring our environment, measured values are contrasted with our perception, which is always subjective. This makes interpreting sensor measurements difficult for a single person in her personal environment. In this context, the EveryAware projects directly connects the concepts of objective sensor data with subjective impressions and perceptions by providing a collective sensing platform with several client applications allowing to explicitly associate those two data types. The goal is to provide the user with personalized feedback, a characterization of the global as well as her personal environment, and enable her to position her perceptions in this global context. In this poster we summarize the collected data of two EveryAware applications, namely WideNoise for noise measurements and AirProbe for participatory air quality sensing. Basic insights are presented including user activity, learning processes and sensor data to perception correlations. These results provide an outlook on how this data can further be used to understand the connection between sensor data and perceptions.},
  author = {Becker, Martin and Hotho, Andreas and Mueller, Juergen and Kibanov, Mark and Atzmueller, Martin and Stumme, Gerd},
  howpublished = {CSSWS 2014, Poster},
  keywords = {everyaware},
  title = {Subjective vs. Objective Data: Bridging the Gap},
  year = 2014
  }
  

  %0 Generic
  %1 becker2014subjective
  %A Becker, Martin
  %A Hotho, Andreas
  %A Mueller, Juergen
  %A Kibanov, Mark
  %A Atzmueller, Martin
  %A Stumme, Gerd
  %D 2014
  %T Subjective vs. Objective Data: Bridging the Gap
  %U http://www.gesis.org/en/events/css-wintersymposium/poster-presentation/
  %X Sensor data is objective. But when measuring our environment, measured values are contrasted with our perception, which is always subjective. This makes interpreting sensor measurements difficult for a single person in her personal environment. In this context, the EveryAware projects directly connects the concepts of objective sensor data with subjective impressions and perceptions by providing a collective sensing platform with several client applications allowing to explicitly associate those two data types. The goal is to provide the user with personalized feedback, a characterization of the global as well as her personal environment, and enable her to position her perceptions in this global context. In this poster we summarize the collected data of two EveryAware applications, namely WideNoise for noise measurements and AirProbe for participatory air quality sensing. Basic insights are presented including user activity, learning processes and sensor data to perception correlations. These results provide an outlook on how this data can further be used to understand the connection between sensor data and perceptions.
  

2013

• 
  1.

  Becker, M., Caminiti, S., Fiorella, D., Francis, L., Gravino, P., Haklay, M. (Muki), Hotho, A., Loreto, V., Mueller, J., Ricchiuti, F., Servedio, V. D. P., Sirbu, A., and Tria, F. (2013) Awareness and learning in participatory noise sensing, PLOS ONE 8, e81638.

  AbstractURLBibTeXEndNoteDOIBibSonomyDownload

  The development of ICT infrastructures has facilitated the emergence of new paradigms for looking at society and the environment over the last few years. Participatory environmental sensing, i.e. directly involving citizens in environmental monitoring, is one example, which is hoped to encourage learning and enhance awareness of environmental issues. In this paper, an analysis of the behaviour of individuals involved in noise sensing is presented. Citizens have been involved in noise measuring activities through the WideNoise smartphone application. This application has been designed to record both objective (noise samples) and subjective (opinions, feelings) data. The application has been open to be used freely by anyone and has been widely employed worldwide. In addition, several test cases have been organised in European countries. Based on the information submitted by users, an analysis of emerging awareness and learning is performed. The data show that changes in the way the environment is perceived after repeated usage of the application do appear. Specifically, users learn how to recognise different noise levels they are exposed to. Additionally, the subjective data collected indicate an increased user involvement in time and a categorisation effect between pleasant and less pleasant environments.

  @article{becker2013awareness,
  abstract = {The development of ICT infrastructures has facilitated the emergence of new paradigms for looking at society and the environment over the last few years. Participatory environmental sensing, i.e. directly involving citizens in environmental monitoring, is one example, which is hoped to encourage learning and enhance awareness of environmental issues. In this paper, an analysis of the behaviour of individuals involved in noise sensing is presented. Citizens have been involved in noise measuring activities through the WideNoise smartphone application. This application has been designed to record both objective (noise samples) and subjective (opinions, feelings) data. The application has been open to be used freely by anyone and has been widely employed worldwide. In addition, several test cases have been organised in European countries. Based on the information submitted by users, an analysis of emerging awareness and learning is performed. The data show that changes in the way the environment is perceived after repeated usage of the application do appear. Specifically, users learn how to recognise different noise levels they are exposed to. Additionally, the subjective data collected indicate an increased user involvement in time and a categorisation effect between pleasant and less pleasant environments.},
  author = {Becker, Martin and Caminiti, Saverio and Fiorella, Donato and Francis, Louise and Gravino, Pietro and Haklay, Mordechai (Muki) and Hotho, Andreas and Loreto, Vittorio and Mueller, Juergen and Ricchiuti, Ferdinando and Servedio, Vito D. P. and Sirbu, Alina and Tria, Francesca},
  journal = {PLOS ONE},
  keywords = {selected},
  month = 12,
  number = 12,
  pages = {e81638},
  title = {Awareness and learning in participatory noise sensing},
  volume = 8,
  year = 2013
  }
  

  %0 Journal Article
  %1 becker2013awareness
  %A Becker, Martin
  %A Caminiti, Saverio
  %A Fiorella, Donato
  %A Francis, Louise
  %A Gravino, Pietro
  %A Haklay, Mordechai (Muki)
  %A Hotho, Andreas
  %A Loreto, Vittorio
  %A Mueller, Juergen
  %A Ricchiuti, Ferdinando
  %A Servedio, Vito D. P.
  %A Sirbu, Alina
  %A Tria, Francesca
  %D 2013
  %J PLOS ONE
  %N 12
  %P e81638
  %R 10.1371/journal.pone.0081638
  %T Awareness and learning in participatory noise sensing
  %U http://dx.doi.org/10.1371%2Fjournal.pone.0081638
  %V 8
  %X The development of ICT infrastructures has facilitated the emergence of new paradigms for looking at society and the environment over the last few years. Participatory environmental sensing, i.e. directly involving citizens in environmental monitoring, is one example, which is hoped to encourage learning and enhance awareness of environmental issues. In this paper, an analysis of the behaviour of individuals involved in noise sensing is presented. Citizens have been involved in noise measuring activities through the WideNoise smartphone application. This application has been designed to record both objective (noise samples) and subjective (opinions, feelings) data. The application has been open to be used freely by anyone and has been widely employed worldwide. In addition, several test cases have been organised in European countries. Based on the information submitted by users, an analysis of emerging awareness and learning is performed. The data show that changes in the way the environment is perceived after repeated usage of the application do appear. Specifically, users learn how to recognise different noise levels they are exposed to. Additionally, the subjective data collected indicate an increased user involvement in time and a categorisation effect between pleasant and less pleasant environments.
  

• 
  1.

  Mueller, J., Doerfel, S., Becker, M., Hotho, A., and Stumme, G. (2013) Tag Recommendations for SensorFolkSonomies. In Proceedings of the Fifth ACM RecSys Workshop on Recommender Systems and the Social Web co-located with the 7th ACM Conference on Recommender Systems (RecSys 2013), CEUR-WS.

  AbstractURLBibTeXEndNoteBibSonomyDownload

  With the rising popularity of smart mobile devices, sensor data-based applications have become more and more popular. Their users record data during their daily routine or specifically for certain events. The application WideNoise Plus allows users to record sound samples and to annotate them with perceptions and tags. The app is being used to document and map the soundscape all over the world. The procedure of recording, including the assignment of tags, has to be as easy-to-use as possible. We therefore discuss the application of tag recommender algorithms in this particular scenario. We show, that this task is fundamentally different from the well-known tag recommendation problem in folksonomies as users do no longer tag fix resources but rather sensory data and impressions. The scenario requires efficient recommender algorithms that are able to run on the mobile device, since Internet connectivity cannot be assumed to be available. Therefore, we evaluate the performance of several tag recommendation algorithms and discuss their applicability in the mobile sensing use-case.

  @inproceedings{mueller2013tag,
  abstract = {With the rising popularity of smart mobile devices, sensor data-based applications have become more and more popular. Their users record data during their daily routine or specifically for certain events. The application WideNoise Plus allows users to record sound samples and to annotate them with perceptions and tags. The app is being used to document and map the soundscape all over the world. The procedure of recording, including the assignment of tags, has to be as easy-to-use as possible. We therefore discuss the application of tag recommender algorithms in this particular scenario. We show, that this task is fundamentally different from the well-known tag recommendation problem in folksonomies as users do no longer tag fix resources but rather sensory data and impressions. The scenario requires efficient recommender algorithms that are able to run on the mobile device, since Internet connectivity cannot be assumed to be available. Therefore, we evaluate the performance of several tag recommendation algorithms and discuss their applicability in the mobile sensing use-case.},
  author = {Mueller, Juergen and Doerfel, Stephan and Becker, Martin and Hotho, Andreas and Stumme, Gerd},
  booktitle = {Proceedings of the Fifth ACM RecSys Workshop on Recommender Systems and the Social Web co-located with the 7th ACM Conference on Recommender Systems (RecSys 2013)},
  crossref = {conf/recsys/2013rsweb},
  keywords = {sensor},
  publisher = {CEUR-WS},
  series = {CEUR Workshop Proceedings},
  title = {Tag Recommendations for SensorFolkSonomies},
  year = 2013
  }
  

  %0 Conference Paper
  %1 mueller2013tag
  %A Mueller, Juergen
  %A Doerfel, Stephan
  %A Becker, Martin
  %A Hotho, Andreas
  %A Stumme, Gerd
  %B Proceedings of the Fifth ACM RecSys Workshop on Recommender Systems and the Social Web co-located with the 7th ACM Conference on Recommender Systems (RecSys 2013)
  %D 2013
  %I CEUR-WS
  %T Tag Recommendations for SensorFolkSonomies
  %U http://ceur-ws.org/Vol-1066/Paper9.pdf
  %X With the rising popularity of smart mobile devices, sensor data-based applications have become more and more popular. Their users record data during their daily routine or specifically for certain events. The application WideNoise Plus allows users to record sound samples and to annotate them with perceptions and tags. The app is being used to document and map the soundscape all over the world. The procedure of recording, including the assignment of tags, has to be as easy-to-use as possible. We therefore discuss the application of tag recommender algorithms in this particular scenario. We show, that this task is fundamentally different from the well-known tag recommendation problem in folksonomies as users do no longer tag fix resources but rather sensory data and impressions. The scenario requires efficient recommender algorithms that are able to run on the mobile device, since Internet connectivity cannot be assumed to be available. Therefore, we evaluate the performance of several tag recommendation algorithms and discuss their applicability in the mobile sensing use-case.
  

• 
  1.

  Lemmerich, F., Becker, M., and Puppe, F. (2013) Difference-Based Estimates for Generalization-Aware Subgroup Discovery. In Proceedings of the European Conference on Machine Learning and Knowledge Discovery in Databases (ECML PKDD) (Blockeel, H., Kersting, K., Nijssen, S., and Zelezny, F., Eds.), pp. 288–303, Springer, Berlin, Heidelberg.

  URLBibTeXEndNoteDOIBibSonomyDownload

  @inproceedings{lemmerich2013differencebased,
  address = {Berlin, Heidelberg},
  author = {Lemmerich, Florian and Becker, Martin and Puppe, Frank},
  booktitle = {Proceedings of the European Conference on Machine Learning and Knowledge Discovery in Databases (ECML PKDD)},
  editor = {Blockeel, Hendrik and Kersting, Kristian and Nijssen, Siegfried and Zelezny, Filip},
  keywords = {estimates},
  pages = {288--303},
  publisher = {Springer},
  series = {Lecture Notes in Computer Science},
  title = {Difference-Based Estimates for Generalization-Aware Subgroup Discovery},
  year = 2013
  }
  

  %0 Conference Paper
  %1 lemmerich2013differencebased
  %A Lemmerich, Florian
  %A Becker, Martin
  %A Puppe, Frank
  %B Proceedings of the European Conference on Machine Learning and Knowledge Discovery in Databases (ECML PKDD)
  %C Berlin, Heidelberg
  %D 2013
  %E Blockeel, Hendrik
  %E Kersting, Kristian
  %E Nijssen, Siegfried
  %E Zelezny, Filip
  %I Springer
  %P 288--303
  %R 10.1007/978-3-642-40994-3_19
  %T Difference-Based Estimates for Generalization-Aware Subgroup Discovery
  %U https://doi.org/10.1007/978-3-642-40994-3_19
  %@ 978-3-642-40993-6
  

• 
  1.

  Becker, M., Mueller, J., Hotho, A., and Stumme, G. (2013) A Generic Platform for Ubiquitous and Subjective Data. In Conference on Pervasive and Ubiquitous Computing Adjunct Publication, pp. 1175–1182, New York, NY, USA.

  AbstractURLBibTeXEndNoteBibSonomyDownload

  An increasing number of platforms like Xively or ThingSpeak are available to manage ubiquitous sensor data enabling the Internet of Things. Strict data formats allow interoperability and informative visualizations, supporting the development of custom user applications. Yet, these strict data formats as well as the common feed-centric approach limit the flexibility of these platforms. We aim at providing a concept that supports data ranging from text-based formats like JSON to images and video footage. Furthermore, we introduce the concept of extensions, which allows to enrich existing data points with additional information, thus, taking a data point centric approach. This enables us to gain semantic and user specific context by attaching subjective data to objective values. This paper provides an overview of our architecture including concept, implementation details and present applications. We distinguish our approach from several other systems and describe two sensing applications namely AirProbe and WideNoise that were implemented for our platform.

  @inproceedings{becker2013generic,
  abstract = {An increasing number of platforms like Xively or ThingSpeak are available to manage ubiquitous sensor data enabling the Internet of Things. Strict data formats allow interoperability and informative visualizations, supporting the development of custom user applications. Yet, these strict data formats as well as the common feed-centric approach limit the flexibility of these platforms. We aim at providing a concept that supports data ranging from text-based formats like JSON to images and video footage. Furthermore, we introduce the concept of extensions, which allows to enrich existing data points with additional information, thus, taking a data point centric approach. This enables us to gain semantic and user specific context by attaching subjective data to objective values. This paper provides an overview of our architecture including concept, implementation details and present applications. We distinguish our approach from several other systems and describe two sensing applications namely AirProbe and WideNoise that were implemented for our platform.},
  address = {New York, NY, USA},
  author = {Becker, Martin and Mueller, Juergen and Hotho, Andreas and Stumme, Gerd},
  booktitle = {Conference on Pervasive and Ubiquitous Computing Adjunct Publication},
  keywords = {platform},
  pages = {1175--1182},
  series = {UbiComp '13 Adjunct},
  title = {A Generic Platform for Ubiquitous and Subjective Data},
  year = 2013
  }
  

  %0 Conference Paper
  %1 becker2013generic
  %A Becker, Martin
  %A Mueller, Juergen
  %A Hotho, Andreas
  %A Stumme, Gerd
  %B Conference on Pervasive and Ubiquitous Computing Adjunct Publication
  %C New York, NY, USA
  %D 2013
  %P 1175--1182
  %T A Generic Platform for Ubiquitous and Subjective Data
  %U http://dx.doi.org/10.1145/2494091.2499776
  %X An increasing number of platforms like Xively or ThingSpeak are available to manage ubiquitous sensor data enabling the Internet of Things. Strict data formats allow interoperability and informative visualizations, supporting the development of custom user applications. Yet, these strict data formats as well as the common feed-centric approach limit the flexibility of these platforms. We aim at providing a concept that supports data ranging from text-based formats like JSON to images and video footage. Furthermore, we introduce the concept of extensions, which allows to enrich existing data points with additional information, thus, taking a data point centric approach. This enables us to gain semantic and user specific context by attaching subjective data to objective values. This paper provides an overview of our architecture including concept, implementation details and present applications. We distinguish our approach from several other systems and describe two sensing applications namely AirProbe and WideNoise that were implemented for our platform.
  %@ 978-1-4503-2215-7
  

2012

• 
  1.

  Atzmueller, M., Becker, M., Doerfel, S., Kibanov, M., Hotho, A., Macek, B.-E., Mitzlaff, F., Mueller, J., Scholz, C., and Stumme, G. (2012) Ubicon: Observing Social and Physical Activities. In International Conference on Green Computing and Communications, pp. 317–324, IEEE, Washington, DC, USA.

  AbstractBibTeXEndNoteDOIBibSonomyDownload

  The connection of ubiquitous and social computing is an emerging research area which is combining two prominent areas of computer science. In this paper, we tackle this topic from different angles: We describe data mining methods for ubiquitous and social data, specifically focusing on physical and social activities, and provide exemplary analysis results. Furthermore, we give an overview on the Ubicon platform which provides a framework for the creation and hosting of ubiquitous and social applications for diverse tasks and projects. Ubicon features the collection and analysis of both physical and social activities of users for enabling inter-connected applications in ubiquitous and social contexts. We summarize three real-world systems built on top of Ubicon, and exemplarily discuss the according mining and analysis aspects.

  @inproceedings{atzmueller2012ubicon,
  abstract = {The connection of ubiquitous and social computing is an emerging research area which is combining two prominent areas of computer science. In this paper, we tackle this topic from different angles: We describe data mining methods for ubiquitous and social data, specifically focusing on physical and social activities, and provide exemplary analysis results. Furthermore, we give an overview on the Ubicon platform which provides a framework for the creation and hosting of ubiquitous and social applications for diverse tasks and projects. Ubicon features the collection and analysis of both physical and social activities of users for enabling inter-connected applications in ubiquitous and social contexts. We summarize three real-world systems built on top of Ubicon, and exemplarily discuss the according mining and analysis aspects.},
  address = {Washington, DC, USA},
  author = {Atzmueller, Martin and Becker, Martin and Doerfel, Stephan and Kibanov, Mark and Hotho, Andreas and Macek, Björn-Elmar and Mitzlaff, Folke and Mueller, Juergen and Scholz, Christoph and Stumme, Gerd},
  booktitle = {International Conference on Green Computing and Communications},
  keywords = {physical},
  month = 11,
  pages = {317--324},
  publisher = {IEEE},
  title = {Ubicon: Observing Social and Physical Activities},
  year = 2012
  }
  

  %0 Conference Paper
  %1 atzmueller2012ubicon
  %A Atzmueller, Martin
  %A Becker, Martin
  %A Doerfel, Stephan
  %A Kibanov, Mark
  %A Hotho, Andreas
  %A Macek, Björn-Elmar
  %A Mitzlaff, Folke
  %A Mueller, Juergen
  %A Scholz, Christoph
  %A Stumme, Gerd
  %B International Conference on Green Computing and Communications
  %C Washington, DC, USA
  %D 2012
  %I IEEE
  %P 317--324
  %R 10.1109/GreenCom.2012.75
  %T Ubicon: Observing Social and Physical Activities
  %X The connection of ubiquitous and social computing is an emerging research area which is combining two prominent areas of computer science. In this paper, we tackle this topic from different angles: We describe data mining methods for ubiquitous and social data, specifically focusing on physical and social activities, and provide exemplary analysis results. Furthermore, we give an overview on the Ubicon platform which provides a framework for the creation and hosting of ubiquitous and social applications for diverse tasks and projects. Ubicon features the collection and analysis of both physical and social activities of users for enabling inter-connected applications in ubiquitous and social contexts. We summarize three real-world systems built on top of Ubicon, and exemplarily discuss the according mining and analysis aspects.
  

• 
  1.

  Lemmerich, F., Becker, M., and Atzmueller, M. (2012) Generic Pattern Trees for Exhaustive Exceptional Model Mining. In European Conference on Machine Learning and Knowledge Discovery in Databases (Flach, P. A., De Bie, T., and Cristianini, N., Eds.), pp. 277–292, Springer Berlin Heidelberg, Berlin, Heidelberg.

  AbstractURLBibTeXEndNoteDOIBibSonomyDownload

  Exceptional model mining has been proposed as a variant of subgroup discovery especially focusing on complex target concepts. Currently, efficient mining algorithms are limited to heuristic (non exhaustive) methods. In this paper, we propose a novel approach for fast exhaustive exceptional model mining: We introduce the concept of valuation bases as an intermediate condensed data representation, and present the general GP-growth algorithm based on FP-growth. Furthermore, we discuss the scope of the proposed approach by drawing an analogy to data stream mining and provide examples for several different model classes. Runtime experiments show improvements of more than an order of magnitude in comparison to a naive exhaustive depth-first search.

  @inproceedings{lemmerich2012generic,
  abstract = {Exceptional model mining has been proposed as a variant of subgroup discovery especially focusing on complex target concepts. Currently, efficient mining algorithms are limited to heuristic (non exhaustive) methods. In this paper, we propose a novel approach for fast exhaustive exceptional model mining: We introduce the concept of valuation bases as an intermediate condensed data representation, and present the general GP-growth algorithm based on FP-growth. Furthermore, we discuss the scope of the proposed approach by drawing an analogy to data stream mining and provide examples for several different model classes. Runtime experiments show improvements of more than an order of magnitude in comparison to a naive exhaustive depth-first search.},
  address = {Berlin, Heidelberg},
  author = {Lemmerich, Florian and Becker, Martin and Atzmueller, Martin},
  booktitle = {European Conference on Machine Learning and Knowledge Discovery in Databases},
  editor = {Flach, Peter A. and De Bie, Tijl and Cristianini, Nello},
  keywords = {selected},
  pages = {277--292},
  publisher = {Springer Berlin Heidelberg},
  title = {Generic Pattern Trees for Exhaustive Exceptional Model Mining},
  year = 2012
  }
  

  %0 Conference Paper
  %1 lemmerich2012generic
  %A Lemmerich, Florian
  %A Becker, Martin
  %A Atzmueller, Martin
  %B European Conference on Machine Learning and Knowledge Discovery in Databases
  %C Berlin, Heidelberg
  %D 2012
  %E Flach, Peter A.
  %E De Bie, Tijl
  %E Cristianini, Nello
  %I Springer Berlin Heidelberg
  %P 277--292
  %R 10.1007/978-3-642-33486-3_18
  %T Generic Pattern Trees for Exhaustive Exceptional Model Mining
  %U https://doi.org/10.1007/978-3-642-33486-3_18
  %X Exceptional model mining has been proposed as a variant of subgroup discovery especially focusing on complex target concepts. Currently, efficient mining algorithms are limited to heuristic (non exhaustive) methods. In this paper, we propose a novel approach for fast exhaustive exceptional model mining: We introduce the concept of valuation bases as an intermediate condensed data representation, and present the general GP-growth algorithm based on FP-growth. Furthermore, we discuss the scope of the proposed approach by drawing an analogy to data stream mining and provide examples for several different model classes. Runtime experiments show improvements of more than an order of magnitude in comparison to a naive exhaustive depth-first search.
  %@ 978-3-642-33486-3
  

2011

• 
  1.

  Becker, M. (2011) Constraint Based Descriptive Pattern Mining (Hotho, A., Atzmueller, M., and Lemmrich, F., Eds.), Master thesis, University of Wuerzburg.

  URLBibTeXEndNoteBibSonomyDownload

  @mastersthesis{becker2011constraint,
  author = {Becker, Martin},
  editor = {Hotho, Andreas and Atzmueller, Martin and Lemmrich, Florian},
  keywords = {constraints},
  school = {University of Wuerzburg},
  title = {Constraint Based Descriptive Pattern Mining},
  year = 2011
  }
  

  %0 Thesis
  %1 becker2011constraint
  %A Becker, Martin
  %D 2011
  %E Hotho, Andreas
  %E Atzmueller, Martin
  %E Lemmrich, Florian
  %T Constraint Based Descriptive Pattern Mining
  %U http://www.is.informatik.uni-wuerzburg.de/fileadmin/10030600/staff/becker/20110713_becker_constraint-based-descriptive-pattern-mining_diplomathesis.pdf