Temporally Multi-Scale Sparse Self-Attention for Physical Activity Data Imputation

Hui Wei, Maxwell A Xu, Colin Samplawski, James Matthew Rehg, Santosh Kumar, Benjamin Marlin
Proceedings of the fifth Conference on Health, Inference, and Learning, PMLR 248:137-154, 2024.

Abstract

Wearable sensors enable health researchers to continuously collect data pertaining to the physiological state of individuals in real-world settings. However, such data can be subject to extensive missingness due to a complex combination of factors. In this work, we study the problem of imputation of missing step count data, one of the most ubiquitous forms of wearable sensor data. We construct a novel and large scale data set consisting of a training set with over 3 million hourly step count observations and a test set with over 2.5 million hourly step count observations. We propose a domain knowledge-informed sparse self-attention model for this task that captures the temporal multi-scale nature of step-count data. We assess the performance of the model relative to baselines and conduct ablation studies to verify our specific model designs.

Cite this Paper

BibTeX
@InProceedings{pmlr-v248-wei24a, title = {Temporally Multi-Scale Sparse Self-Attention for Physical Activity Data Imputation}, author = {Wei, Hui and Xu, Maxwell A and Samplawski, Colin and Rehg, James Matthew and Kumar, Santosh and Marlin, Benjamin}, booktitle = {Proceedings of the fifth Conference on Health, Inference, and Learning}, pages = {137--154}, year = {2024}, editor = {Pollard, Tom and Choi, Edward and Singhal, Pankhuri and Hughes, Michael and Sizikova, Elena and Mortazavi, Bobak and Chen, Irene and Wang, Fei and Sarker, Tasmie and McDermott, Matthew and Ghassemi, Marzyeh}, volume = {248}, series = {Proceedings of Machine Learning Research}, month = {27--28 Jun}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v248/main/assets/wei24a/wei24a.pdf}, url = {https://proceedings.mlr.press/v248/wei24a.html}, abstract = {Wearable sensors enable health researchers to continuously collect data pertaining to the physiological state of individuals in real-world settings. However, such data can be subject to extensive missingness due to a complex combination of factors. In this work, we study the problem of imputation of missing step count data, one of the most ubiquitous forms of wearable sensor data. We construct a novel and large scale data set consisting of a training set with over 3 million hourly step count observations and a test set with over 2.5 million hourly step count observations. We propose a domain knowledge-informed sparse self-attention model for this task that captures the temporal multi-scale nature of step-count data. We assess the performance of the model relative to baselines and conduct ablation studies to verify our specific model designs.} }
Endnote
%0 Conference Paper %T Temporally Multi-Scale Sparse Self-Attention for Physical Activity Data Imputation %A Hui Wei %A Maxwell A Xu %A Colin Samplawski %A James Matthew Rehg %A Santosh Kumar %A Benjamin Marlin %B Proceedings of the fifth Conference on Health, Inference, and Learning %C Proceedings of Machine Learning Research %D 2024 %E Tom Pollard %E Edward Choi %E Pankhuri Singhal %E Michael Hughes %E Elena Sizikova %E Bobak Mortazavi %E Irene Chen %E Fei Wang %E Tasmie Sarker %E Matthew McDermott %E Marzyeh Ghassemi %F pmlr-v248-wei24a %I PMLR %P 137--154 %U https://proceedings.mlr.press/v248/wei24a.html %V 248 %X Wearable sensors enable health researchers to continuously collect data pertaining to the physiological state of individuals in real-world settings. However, such data can be subject to extensive missingness due to a complex combination of factors. In this work, we study the problem of imputation of missing step count data, one of the most ubiquitous forms of wearable sensor data. We construct a novel and large scale data set consisting of a training set with over 3 million hourly step count observations and a test set with over 2.5 million hourly step count observations. We propose a domain knowledge-informed sparse self-attention model for this task that captures the temporal multi-scale nature of step-count data. We assess the performance of the model relative to baselines and conduct ablation studies to verify our specific model designs.
APA
Wei, H., Xu, M.A., Samplawski, C., Rehg, J.M., Kumar, S. & Marlin, B.. (2024). Temporally Multi-Scale Sparse Self-Attention for Physical Activity Data Imputation. Proceedings of the fifth Conference on Health, Inference, and Learning, in Proceedings of Machine Learning Research 248:137-154 Available from https://proceedings.mlr.press/v248/wei24a.html.

Related Material