UbiWell Lab Logo.

UbiWell Lab

The Ubiquitous Computing for Health and Well-being (UbiWell) Lab is an interdisciplinary research group at the Khoury College of Computer Sciences and the Bouvé College of Health Sciences at Northeastern University.
We work on developing data-driven solutions to enable effective sensing and interventions for mental- and behavioral-health outcomes with mobile and ubiquitous technologies.

Research Areas

Our interdisciplinary team works at the intersection of mobile/wearable sensing, data science, human-centered computing, and behavioral science.

We work on exploring and advancing the complete "lifecycle" of mental- and behavioral-health sensing and intervention, which includes (a) accurately sensing and detecting a mental or behavioral health condition, like stress and opioid use; (b) after detecting a particular condition, determining the right time to deliver the intervention or support, such that the user is most likely to be receptive to the interventions provided; and (c) choosing the best intervention delivery mechanism and modality to ensure just-in-time delivery and reachability.

Sensing to intervention lifecycle

A simplified representation of the sensing to intervention lifecycle.

Current Projects

Causal modeling for physiological stress

Stress predictions from physiological signals

We are working on various projects to leverage multimodal data and understand the contextual and behavioral factors that lead to physiological stress, and evaluate its association with the perception of stress.

Predicting relapse during OUD treatment

Stress predictions from physiological signals

We are working on a longitudinal study to detect at-risk indicators, e.g., stress, craving, and mood, among patients undergoing Opioid Use Disorder (OUD) treatment, using passively collected contextual and sensor data from smartphones and wearables.

States-of-receptivity for digital health interventions

Stress predictions from physiological signals

We have multiple projects currently underway to better evaluate the contexts where people are willing and able to engage with and use digital health interventions. These range from behavior-change interventions in free-living situations to interventions during specific scenarios, e.g., driving.

News

Show all

Recent Publications

Show all
Toward Music-Based Stress Management: Contemporary Biosensing Systems for Affective Regulation
Natasha Yamane, Varun Mishra, Matthew S. Goodwin
arXiv 2025
Show details
CardioAI: A Multimodal AI-based System to Support Symptom Monitoring and Risk Prediction of Cancer Treatment-Induced Cardiotoxicity
Siyi Wu, Weidan Cao, Shihan Fu, Bingsheng Yao, Ziqi Yang, Changchang Yin, Varun Mishra, Daniel Addison, Ping Zhang, Dakuo Wang
Proceedings of the Conference on Human Factors in Computing Systems (CHI) 2025
Show details
An Evaluation of Temporal and Categorical Uncertainty on Timelines: A Case Study in Human Activity Recall Visualizations
Veronika Potter, Ha Le, Uzma Haque Syeda, Stephen Intille, Michelle Borkin
In 2025 IEEE Visualization and Visual Analytics (VIS’25) 2025
Show details
A Multi-Agent LLM Network for Suggesting and Correcting Human Activity and Posture Annotations
Ha Le, Akshat Choube, Vedant Das Swain, Varun Mishra, Stephen Intille
Ubicomp 2025 (GenAI4HS Workshop) 2025
Show details
Feasibility and Utility of Multimodal Micro Ecological Momentary Assessment on a Smartwatch
Ha Le, Veronika Potter, Rithika Lakshminarayanan, Varun Mishra, Stephen Intille
Proceedings of the Conference on Human Factors in Computing Systems (CHI) 2025
Show details
Show all