Hierarchical Span-Based Conditional Random Fields for Labeling and Segmenting Events in Wearable Sensor Data Streams

Roy Adams, Nazir Saleheen, Edison Thomaz, Abhinav Parate, Santosh Kumar, Benjamin Marlin
; Proceedings of The 33rd International Conference on Machine Learning, PMLR 48:334-343, 2016.

Abstract

The field of mobile health (mHealth) has the potential to yield new insights into health and behavior through the analysis of continuously recorded data from wearable health and activity sensors. In this paper, we present a hierarchical span-based conditional random field model for the key problem of jointly detecting discrete events in such sensor data streams and segmenting these events into high-level activity sessions. Our model includes higher-order cardinality factors and inter-event duration factors to capture domain-specific structure in the label space. We show that our model supports exact MAP inference in quadratic time via dynamic programming, which we leverage to perform learning in the structured support vector machine framework. We apply the model to the problems of smoking and eating detection using four real data sets. Our results show statistically significant improvements in segmentation performance relative to a hierarchical pairwise CRF.

Cite this Paper


BibTeX
@InProceedings{pmlr-v48-adams16, title = {Hierarchical Span-Based Conditional Random Fields for Labeling and Segmenting Events in Wearable Sensor Data Streams}, author = {Roy Adams and Nazir Saleheen and Edison Thomaz and Abhinav Parate and Santosh Kumar and Benjamin Marlin}, booktitle = {Proceedings of The 33rd International Conference on Machine Learning}, pages = {334--343}, year = {2016}, editor = {Maria Florina Balcan and Kilian Q. Weinberger}, volume = {48}, series = {Proceedings of Machine Learning Research}, address = {New York, New York, USA}, month = {20--22 Jun}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v48/adams16.pdf}, url = {http://proceedings.mlr.press/v48/adams16.html}, abstract = {The field of mobile health (mHealth) has the potential to yield new insights into health and behavior through the analysis of continuously recorded data from wearable health and activity sensors. In this paper, we present a hierarchical span-based conditional random field model for the key problem of jointly detecting discrete events in such sensor data streams and segmenting these events into high-level activity sessions. Our model includes higher-order cardinality factors and inter-event duration factors to capture domain-specific structure in the label space. We show that our model supports exact MAP inference in quadratic time via dynamic programming, which we leverage to perform learning in the structured support vector machine framework. We apply the model to the problems of smoking and eating detection using four real data sets. Our results show statistically significant improvements in segmentation performance relative to a hierarchical pairwise CRF.} }
Endnote
%0 Conference Paper %T Hierarchical Span-Based Conditional Random Fields for Labeling and Segmenting Events in Wearable Sensor Data Streams %A Roy Adams %A Nazir Saleheen %A Edison Thomaz %A Abhinav Parate %A Santosh Kumar %A Benjamin Marlin %B Proceedings of The 33rd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2016 %E Maria Florina Balcan %E Kilian Q. Weinberger %F pmlr-v48-adams16 %I PMLR %J Proceedings of Machine Learning Research %P 334--343 %U http://proceedings.mlr.press %V 48 %W PMLR %X The field of mobile health (mHealth) has the potential to yield new insights into health and behavior through the analysis of continuously recorded data from wearable health and activity sensors. In this paper, we present a hierarchical span-based conditional random field model for the key problem of jointly detecting discrete events in such sensor data streams and segmenting these events into high-level activity sessions. Our model includes higher-order cardinality factors and inter-event duration factors to capture domain-specific structure in the label space. We show that our model supports exact MAP inference in quadratic time via dynamic programming, which we leverage to perform learning in the structured support vector machine framework. We apply the model to the problems of smoking and eating detection using four real data sets. Our results show statistically significant improvements in segmentation performance relative to a hierarchical pairwise CRF.
RIS
TY - CPAPER TI - Hierarchical Span-Based Conditional Random Fields for Labeling and Segmenting Events in Wearable Sensor Data Streams AU - Roy Adams AU - Nazir Saleheen AU - Edison Thomaz AU - Abhinav Parate AU - Santosh Kumar AU - Benjamin Marlin BT - Proceedings of The 33rd International Conference on Machine Learning PY - 2016/06/11 DA - 2016/06/11 ED - Maria Florina Balcan ED - Kilian Q. Weinberger ID - pmlr-v48-adams16 PB - PMLR SP - 334 DP - PMLR EP - 343 L1 - http://proceedings.mlr.press/v48/adams16.pdf UR - http://proceedings.mlr.press/v48/adams16.html AB - The field of mobile health (mHealth) has the potential to yield new insights into health and behavior through the analysis of continuously recorded data from wearable health and activity sensors. In this paper, we present a hierarchical span-based conditional random field model for the key problem of jointly detecting discrete events in such sensor data streams and segmenting these events into high-level activity sessions. Our model includes higher-order cardinality factors and inter-event duration factors to capture domain-specific structure in the label space. We show that our model supports exact MAP inference in quadratic time via dynamic programming, which we leverage to perform learning in the structured support vector machine framework. We apply the model to the problems of smoking and eating detection using four real data sets. Our results show statistically significant improvements in segmentation performance relative to a hierarchical pairwise CRF. ER -
APA
Adams, R., Saleheen, N., Thomaz, E., Parate, A., Kumar, S. & Marlin, B.. (2016). Hierarchical Span-Based Conditional Random Fields for Labeling and Segmenting Events in Wearable Sensor Data Streams. Proceedings of The 33rd International Conference on Machine Learning, in PMLR 48:334-343

Related Material