Paperdoi:10.5281/zenodo.24157652
Revealing Misclassification of Exercise Sessions in Wearable Stress Detection for Automated Insulin Delivery (code, segment index and pre-registered rules)
Sensors (under revision, 2026) — paper not yet public; code on Zenodo/GitHub
TL;DR
MIT-licensed, pre-registered (OSF) re-evaluation of stress vs exercise recognition from Empatica E4 wrist signals on the PhysioNet induced-stress/structured-exercise set, measuring how often a stress detector fires during exercise and testing an exercise-robust detector on a sealed hold-out and on WESAD. Paper under revision at Sensors.
- Form factor: wrist (Empatica E4)
Abstract
Analysis code, segment index, hashed pre-specified rules and trial log for a pre-registered re-evaluation of stress and exercise recognition from Empatica E4 wrist signals (PhysioNet dataset doi:10.13026/he0v-tf17), with an external test on WESAD. Version 1.1.0 adds the post hoc analyses, figures and number summary of the revised manuscript. Version 1.1.1 documents the integrity checks of the data files, pre-specification documents and sealed-participant list, and adds the Figure 1 script of the second revision. Raw data are not redistributed. Pre-registration: https://osf.io/swge8. This research was financially supported by the Deanship of Scientific Research and Graduate Studies at King Khalid University under research grant number (R.G.P.2/191/47).
Verbatim from DataCite (opens in a new tab) · Licence: https://opensource.org/licenses/MIT
Results on ChatPPG leaderboards
All leaderboardsNo results from this paper on ChatPPG leaderboards yet. Browse the leaderboards.
Tasks & signals
Tasks
Signals
Devices
Keywords
Datasets used
How it works
Cite this paper
Owida, H. A., Alsarhan, A., Banat, M., Al-Fraihat, D., & Algarni, A. (2026). Revealing Misclassification of Exercise Sessions in Wearable Stress Detection for Automated Insulin Delivery (code, segment index and pre-registered rules). Sensors — paper not yet public. https://doi.org/10.5281/zenodo.24157652
Owida, Hamza Abu, Ayoub Alsarhan, Mohannad Banat, Dimah Al-Fraihat, and Abdulmohsen Algarni. 2026. "Revealing Misclassification of Exercise Sessions in Wearable Stress Detection for Automated Insulin Delivery (code, segment index and pre-registered rules)." Sensors — paper not yet public. https://doi.org/10.5281/zenodo.24157652.
Owida, H. A., Alsarhan, A., Banat, M., Al-Fraihat, D. and Algarni, A. (2026) 'Revealing Misclassification of Exercise Sessions in Wearable Stress Detection for Automated Insulin Delivery (code, segment index and pre-registered rules)', Sensors — paper not yet public. doi: 10.5281/zenodo.24157652.
Owida, Hamza Abu, et al. "Revealing Misclassification of Exercise Sessions in Wearable Stress Detection for Automated Insulin Delivery (code, segment index and pre-registered rules)." Sensors — paper not yet public, 2026. https://doi.org/10.5281/zenodo.24157652.
H. A. Owida, A. Alsarhan, M. Banat, D. Al-Fraihat, and A. Algarni, "Revealing Misclassification of Exercise Sessions in Wearable Stress Detection for Automated Insulin Delivery (code, segment index and pre-registered rules)," Sensors — paper not yet public, 2026, doi: 10.5281/zenodo.24157652.
@article{owida2026revealing,
title = {{Revealing Misclassification of Exercise Sessions in Wearable Stress Detection for Automated Insulin Delivery (code, segment index and pre-registered rules)}},
author = {Owida, Hamza Abu and Alsarhan, Ayoub and Banat, Mohannad and Al-Fraihat, Dimah and Algarni, Abdulmohsen},
year = {2026},
journal = {Sensors — paper not yet public},
doi = {10.5281/zenodo.24157652}
}Added to the ChatPPG research hub
