Paperdoi:10.1109/PerComWorkshops53856.2022.9767353

Shape-Based Conditional Neural Field for Wrist-Worn Change-Point Detection

Venue listed2022Added Nov 12, 2026

  • YS
  • VS
  • WO

Authors: Yuang Shi, Varsha Suresh, Wei Tsang Ooi

2022 IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops / WristSense)

TL;DR

Online change-point detection for wrist-worn activity streams: DTW shape features between adjacent intervals, then a conditional neural field (CRF-style) over those features. The authors describe the model as only a few hundred parameters, much smaller than an LSTM CPD baseline, and usable online or offline. Evaluated on ExtraSensory and HASC.

  • Form factor: wrist

Abstract

We consider the problem of online change-point detection in a time-series, with application to detecting switching of human activities through accelerometer readings on a wrist-worn device. Traditional approaches for change-point detection do not work well on human activities in the wild and are too computationally expensive for implementation on wrist-worn devices. To address these shortcomings, we propose ShapeCNF, a simple and fast online change-point detection method that uses shape-based features to model the activity patterns and a conditional neural field to model the temporal correlations among the time series segments. Extensive experiments conducted on a highly dynamic time-series dataset demonstrate the effectiveness and superiority of ShapeCNF over the state-of-the-art methods.

Verbatim from Semantic Scholar (opens in a new tab) · Abstract via Semantic Scholar; © the authors/publisher

Results on ChatPPG leaderboards

All leaderboards

No results from this paper on ChatPPG leaderboards yet. Browse the leaderboards.

Tasks & signals

Signals

Keywords

Change PointExercise OnsetWrist AccelerometerDtwCrfPercom Workshops 2022Apache 2.0

How it works

How Method works: Setup → Method → TargetSetup: Signals (accel); Form factor (wrist). Method: Method.SetupSignals: accelxyzSignalsaccelForm factor: wristForm factorwristMethodMethod

Cite this paper

Cite this paper with the fields recorded here. Check it against the publisher before submitting.

Shi, Y., Suresh, V., & Ooi, W. T. (2022). Shape-Based Conditional Neural Field for Wrist-Worn Change-Point Detection. 2022 IEEE International Conference on Pervasive Computing and Communications Workshops. https://doi.org/10.1109/PerComWorkshops53856.2022.9767353
Shi, Yuang, Varsha Suresh, and Wei Tsang Ooi. 2022. "Shape-Based Conditional Neural Field for Wrist-Worn Change-Point Detection." 2022 IEEE International Conference on Pervasive Computing and Communications Workshops. https://doi.org/10.1109/PerComWorkshops53856.2022.9767353.
Shi, Y., Suresh, V. and Ooi, W. T. (2022) 'Shape-Based Conditional Neural Field for Wrist-Worn Change-Point Detection', 2022 IEEE International Conference on Pervasive Computing and Communications Workshops. doi: 10.1109/PerComWorkshops53856.2022.9767353.
Shi, Yuang, et al. "Shape-Based Conditional Neural Field for Wrist-Worn Change-Point Detection." 2022 IEEE International Conference on Pervasive Computing and Communications Workshops, 2022. https://doi.org/10.1109/PerComWorkshops53856.2022.9767353.
Y. Shi, V. Suresh, and W. T. Ooi, "Shape-Based Conditional Neural Field for Wrist-Worn Change-Point Detection," 2022 IEEE International Conference on Pervasive Computing and Communications Workshops, 2022, doi: 10.1109/PerComWorkshops53856.2022.9767353.
@inproceedings{shi2022shapebased,
  title         = {{Shape-Based Conditional Neural Field for Wrist-Worn Change-Point Detection}},
  author        = {Shi, Yuang and Suresh, Varsha and Ooi, Wei Tsang},
  year          = {2022},
  booktitle     = {2022 IEEE International Conference on Pervasive Computing and Communications Workshops},
  doi           = {10.1109/PerComWorkshops53856.2022.9767353}
}

Added to the ChatPPG research hub