Paperdoi:10.1145/2632048.2632096

Moving towards a real-time system for automatically recognizing stereotypical motor movements in individuals on the autism spectrum using wireless accelerometry

Venue listed2014Added Nov 17, 2026

  • MG
  • MH
  • QT
  • MA
  • DE
  • SI

Authors: Matthew S. Goodwin, Marzieh Haghighi, Qu Tang, Murat Akçakaya, Deniz Erdogmus, Stephen S. Intille

UbiComp 2014 (ACM)

TL;DR

Follow-up on the same six people, recorded in classrooms about three years apart. The open abstract compares SVM and decision-tree classifiers on wireless three-axis accelerometer features and reports average accuracies from 81.2% (true-positive rate 0.91, false-positive rate 0.21) up to 99.1%. This is the paper whose public dataset and source still live on Bitbucket (no licence file).

  • Form factor: wearable

Abstract

This paper extends previous work automatically detecting stereotypical motor movements (SMM) in individuals on the autism spectrum. Using three-axis accelerometer data obtained through wearable wireless sensors, we compare recognition results for two different classifiers – Support Vector Machine and Decision Tree – in combination with different feature sets based on time-frequency characteristics of accelerometer data. We use data collected from six individuals on the autism spectrum who participated in two different studies conducted three years apart in classroom settings, and observe an average accuracy across all participants over time ranging from 81.2% (TPR: 0.91; FPR: 0.21) to 99.1% (TPR: 0.99; FPR: 0.01) for all combinations of classifiers and feature sets. We also provide analyses of kinematic parameters associated with observed movements in an attempt to explain classifier-feature specific performance. Based on our results, we conclude that real-time, person-dependent, adaptive algorithms are needed in order to accurately and consistently measure SMM automatically in individuals on the autism spectrum over time in real-word settings.

Verbatim from OpenAlex (opens in a new tab) · Abstract via OpenAlex (publisher-deposited); © 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

StimmingAutismStereotypyAccelerometer

How it works

How Method works: Setup → Method → TargetSetup: Signals (accelerometer); Form factor (wearable). Method: Method.SetupSignals: accelerometerxyzSignalsaccelerometerForm factor: wearableForm factorwearableMethodMethod

Cite this paper

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

Goodwin, M. S., Haghighi, M., Tang, Q., Akçakaya, M., Erdogmus, D., & Intille, S. S. (2014). Moving towards a real-time system for automatically recognizing stereotypical motor movements in individuals on the autism spectrum using wireless accelerometry. UbiComp 2014. https://doi.org/10.1145/2632048.2632096
Goodwin, Matthew S., Marzieh Haghighi, Qu Tang, Murat Akçakaya, Deniz Erdogmus, and Stephen S. Intille. 2014. "Moving towards a real-time system for automatically recognizing stereotypical motor movements in individuals on the autism spectrum using wireless accelerometry." UbiComp 2014. https://doi.org/10.1145/2632048.2632096.
Goodwin, M. S., Haghighi, M., Tang, Q., Akçakaya, M., Erdogmus, D. and Intille, S. S. (2014) 'Moving towards a real-time system for automatically recognizing stereotypical motor movements in individuals on the autism spectrum using wireless accelerometry', UbiComp 2014. doi: 10.1145/2632048.2632096.
Goodwin, Matthew S., et al. "Moving towards a real-time system for automatically recognizing stereotypical motor movements in individuals on the autism spectrum using wireless accelerometry." UbiComp 2014, 2014. https://doi.org/10.1145/2632048.2632096.
M. S. Goodwin, M. Haghighi, Q. Tang, M. Akçakaya, D. Erdogmus, and S. S. Intille, "Moving towards a real-time system for automatically recognizing stereotypical motor movements in individuals on the autism spectrum using wireless accelerometry," UbiComp 2014, 2014, doi: 10.1145/2632048.2632096.
@inproceedings{goodwin2014moving,
  title         = {{Moving towards a real-time system for automatically recognizing stereotypical motor movements in individuals on the autism spectrum using wireless accelerometry}},
  author        = {Goodwin, Matthew S. and Haghighi, Marzieh and Tang, Qu and Akçakaya, Murat and Erdogmus, Deniz and Intille, Stephen S.},
  year          = {2014},
  booktitle     = {UbiComp 2014},
  publisher     = {ACM},
  doi           = {10.1145/2632048.2632096}
}

Added to the ChatPPG research hub