Stress detection
Personalized stress models from heart rate, HRV and electrodermal activity in everyday settings, including active learning that needs fewer participant labels.
Stress, mood and mental health, measured in daily life.
We combine physiological signals, smartphone sensing and EMAs to monitor stress, forecast affect and detect symptoms, with models personalized to each participant.
What we deliver
Stress and mental health analytics, end to end.
Affect forecasting
Prediction of tomorrow’s mood from multimodal physiological and behavioral data and self-reported diaries.
Loneliness and depressive symptoms
Detection from passive smartphone and wearable data, as in our studies of college students and pregnant women.
Pain assessment
Pain recognition from ECG, electrodermal activity and multimodal features in postoperative patients.
Electrodermal activity
Tonic and phasic decomposition and features with our open-source pyEDA toolkit.
Privacy-preserving models
Federated and differentially private learning when data cannot leave a site.
How we analyze it
- Personalized and adaptive machine learning
- Multimodal feature engineering from wearables, phones and EMAs
- Active and reinforcement learning to reduce labeling burden
- Federated transfer learning with differential privacy
What you receive
- Validated stress, affect or symptom measures
- Model performance reports with explainability
- Figures and a methods section for publication
- Documented, reproducible code
Evidence
Selected peer-reviewed work by our team.
- Han et al. Objective stress monitoring based on wearable sensors in everyday settings. Journal of Medical Engineering and Technology, 2020. doi:10.1080/03091902.2020.1759707
- Tazarv et al. Personalized stress monitoring using wearable sensors in everyday settings. IEEE EMBC, 2021. doi:10.1109/EMBC46164.2021.9630224
- Tazarv et al. Active reinforcement learning for personalized stress monitoring in everyday settings. ACM/IEEE CHASE, 2023. doi:10.1145/3580252.3586979
- Jafarlou et al. Objective prediction of next-day’s affect using multimodal physiological and behavioral data: algorithm development and validation study. JMIR Formative Research, 2023. doi:10.2196/39425
- Yang et al. Integrating wearable sensor data and self-reported diaries for personalized affect forecasting. Smart Health, 2024. doi:10.1016/j.smhl.2024.100464
- Jafarlou et al. Objective monitoring of loneliness levels using smart devices: a multi-device approach for mental health applications. PLOS ONE, 2024. doi:10.1371/journal.pone.0298949
- Borelli et al. Detection of depressive symptoms in college students using multimodal passive sensing data and light gradient boosting machine: longitudinal pilot study. JMIR Formative Research, 2025. doi:10.2196/67964
- Sarhaddi et al. Maternal social loneliness detection using passive sensing through continuous monitoring in everyday settings: longitudinal study. JMIR Formative Research, 2023. doi:10.2196/47950
- Wang et al. Differential private federated transfer learning for mental health monitoring in everyday settings: a case study on stress detection. IEEE EMBC, 2024. doi:10.1109/EMBC53108.2024.10782516
- Aqajari et al. pyEDA: an open-source Python toolkit for pre-processing and feature extraction of electrodermal activity. Procedia Computer Science, 2021. doi:10.1016/j.procs.2021.03.021
- Kasaeyan Naeini et al. Pain recognition with electrocardiographic features in postoperative patients: method validation study. Journal of Medical Internet Research, 2021. doi:10.2196/25079
- Subramanian et al. Multimodal pain recognition in postoperative patients: machine learning approach. JMIR Formative Research, 2025. doi:10.2196/67969