Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

SigmaScheduling: Uncertainty-Informed Scheduling of Decision Points for Intelligent Mobile Health Interventions.

... International Conference on Wearable and Implantable Body Sensor Networks. International Conference on Wearable and Implantable Body Sensor Networks·2026

Same author

Heteroscedastic Temporal Variational Autoencoder for Irregular Time Series.

... International Conference on Learning Representations·2026

Same author

Multi-Time Attention Networks for Irregularly Sampled Time Series.

... International Conference on Learning Representations·2026

Same author

Dynamic Modeling and System Identification of User Engagement in mHealth Interventions using a Bayesian Approach for Missing Data Imputation.

Control engineering practice·2025

Same author

Understanding the Policy Space for AgeTech: Implications for AI and Digital Health.

The Public policy and aging report·2025

Same author

BayesLDM: A Domain-specific Modeling Language for Probabilistic Modeling of Longitudinal Data.

...IEEE...International Conference on Connected Health: Applications, Systems and Engineering Technologies. IEEE International Conference on Connected Health: Applications, Systems and Engineering Technologies·2023

Same journal

Towards the Efficient Inference by Incorporating Automated Computational Phenotypes under Covariate Shift.

Proceedings of machine learning research·2026

Same journal

Endo-SemiS: Towards Robust Semi-Supervised Image Segmentation for Endoscopic Video.

Proceedings of machine learning research·2026

Same journal

Perspective: Machine Learning for Health Should Consider Social Drivers of Health.

Proceedings of machine learning research·2026

Same journal

Classifying Phonotrauma Severity from Vocal Fold Images with Soft Ordinal Regression.

Proceedings of machine learning research·2026

Same journal

Does Domain-Specific Retrieval Augmented Generation Help LLMs Answer Consumer Health Questions?

Proceedings of machine learning research·2026

Same journal

Quantitative Convergence Analysis of Projected Stochastic Gradient Descent for Non-Convex Losses via the Goldstein Subdifferential.

Proceedings of machine learning research·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Jun 12, 2025

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

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

Hui Wei¹, Maxwell A Xu², Colin Samplawski¹

¹Manning College of Information & Computer Sciences, University of Massachusetts Amherst.

Proceedings of Machine Learning Research

|September 25, 2024

Summary

This summary is machine-generated.

This study addresses missing wearable sensor data by developing a novel model for imputing step count information. The research introduces a domain knowledge-informed sparse self-attention model for accurate data recovery.

More Related Videos

Visualization of Intensity Levels to Reduce the Gap Between Self-Reported and Directly Measured Physical Activity

Visualization of Intensity Levels to Reduce the Gap Between Self-Reported and Directly Measured Physical Activity

Published on: March 7, 2019

Author Spotlight: Enhancing Remote Rehabilitation with Virtual Reality and Electromyography

Author Spotlight: Enhancing Remote Rehabilitation with Virtual Reality and Electromyography

Published on: January 12, 2024

Related Experiment Videos

Last Updated: Jun 12, 2025

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

Visualization of Intensity Levels to Reduce the Gap Between Self-Reported and Directly Measured Physical Activity

Visualization of Intensity Levels to Reduce the Gap Between Self-Reported and Directly Measured Physical Activity

Published on: March 7, 2019

Author Spotlight: Enhancing Remote Rehabilitation with Virtual Reality and Electromyography

Author Spotlight: Enhancing Remote Rehabilitation with Virtual Reality and Electromyography

Published on: January 12, 2024

Area of Science:

Digital Health
Biomedical Data Science
Wearable Technology

Background:

Wearable sensors generate continuous physiological data in real-world settings.
Missing data in wearable sensor datasets is a significant challenge for health research.
Step count data is a common and crucial type of wearable sensor data.

Purpose of the Study:

To address the challenge of missing step count data from wearable sensors.
To develop and evaluate a novel imputation model for large-scale wearable sensor data.
To capture the temporal multi-scale characteristics inherent in step count data.

Main Methods:

Construction of a large-scale dataset with over 5.5 million hourly step count observations.
Proposal of a domain knowledge-informed sparse self-attention model.
Performance evaluation against baseline methods and ablation studies.

Main Results:

The proposed sparse self-attention model demonstrates effectiveness in imputing missing step count data.
Ablation studies confirm the specific design choices of the model.
The model successfully captures the temporal multi-scale nature of the data.

Conclusions:

The developed model offers a robust solution for handling missing step count data from wearable sensors.
This approach can improve the reliability of health research utilizing continuous wearable data.
The study highlights the potential of domain knowledge-informed deep learning for sensor data imputation.