TriadSense: ear-worn (OpenEarable 2.0) + wrist IMU (Xsens DOT) sensing of group activity in 9 triads. Recorded signals include imu, accel, gyro.
TriadSense contains synchronised sensor recordings of nine groups of three people who assembled a puzzle together, with annotations of what every participant, every pair and the whole group did. Each participant wore an ear-worn device (OpenEarable 2.0) and a wrist-worn device (Xsens DOT); an optical motion-capture system (OptiTrack) recorded their positions. The record holds the raw recordings of the nine sessions, the annotations of three annotators (the final annotations, the original annotator's annotations before the review, and the reliability sample of 76 clips), the synchronised streams with the final labels on every sample, and the 5-second window table of the benchmark. Video and audio are not released.
README.md describes every file and column. Access to the files requires accepting the terms of use (TERMS_OF_USE.md), which prohibit any attempt to re-identify the participants. The code that reproduces the processing and the benchmark: https://anonymous.4open.science/r/triadsense-pipeline-78DB/
Verbatim fromZenodo· Licence: cc-by-4.0
No model in the hub reports results on this dataset yet.
Full photo credits and licences are on each device page. An icon means we have no openly licensed or manufacturer-cleared photo of that exact device yet.
TriadSense: ear-worn (OpenEarable 2.0) + wrist IMU (Xsens DOT) sensing of group activity in 9 triads [Data set]. (n.d.). https://doi.org/10.5281/zenodo.23806200
@misc{triadsensetriadsense,
title = {{TriadSense: ear-worn (OpenEarable 2.0) + wrist IMU (Xsens DOT) sensing of group activity in 9 triads}},
doi = {10.5281/zenodo.23806200}
}Cite the dated snapshot 2026-10 for a fixed, reproducible version. Please also cite the original publications listed above.
ChatPPG. (2026). TriadSense: ear-worn (OpenEarable 2.0) + wrist IMU (Xsens DOT) sensing of group activity in 9 triads: dataset record (Version 2026-10) [Data set]. ChatPPG Research Hub. https://chatppg.com/research/datasets/triadsense
@misc{chatppg_dataset_triadsense,
author = {{ChatPPG}},
title = {{TriadSense: ear-worn (OpenEarable 2.0) + wrist IMU (Xsens DOT) sensing of group activity in 9 triads: dataset record}},
year = {2026},
month = nov,
version = {2026-10},
howpublished = {\url{https://chatppg.com/research/datasets/triadsense}},
note = {ChatPPG Research Hub, Snapshot 2026-10, https://chatppg.com/research/snapshots/2026-10}
}cff-version: 1.2.0 message: "If you use this resource, please cite it as below." type: dataset title: "TriadSense: ear-worn (OpenEarable 2.0) + wrist IMU (Xsens DOT) sensing of group activity in 9 triads: dataset record" authors: - name: "ChatPPG" url: "https://chatppg.com/research/datasets/triadsense" repository-artifact: "https://chatppg.com/research/snapshots/2026-10" version: "2026-10" date-released: "2026-11-04"
Record updated
ActiNet: an open-source tool for activity intensity classification of wrist-worn accelerometry using self-supervised deep learningSame task: Activity recognitionScientific Reports · 2026
An open-source deep learning model for classifying real-world activity intensities in persons with chronic pain using a wrist-worn accelerometerSame task: Activity recognitionFrontiers in Digital Health 8:1783507 · 2026
