Paperdoi:10.3389/fninf.2017.00009
Automated detection of stereotypical motor movements in autism spectrum disorder using recurrence quantification analysis
Frontiers in Neuroinformatics 2017
TL;DR
Recurrence-quantification features on the public six-person Goodwin accelerometer set improved stereotypical-movement detection by about nine accuracy points over a then-standard baseline (random forest about 0.83 versus 0.76). A single wrist was weaker on average than the torso or the full three-sensor kit, and the better experiments used leave-one-session or leave-one-participant checks.
- Form factor: wearable
Abstract
A number of recent studies using accelerometer features as input to machine learning classifiers show promising results for automatically detecting stereotypical motor movements (SMM) in individuals with Autism Spectrum Disorder (ASD). However, replicating these results across different types of accelerometers and their position on the body still remains a challenge. We introduce a new set of features in this domain based on recurrence plot and quantification analyses that are orientation invariant and able to capture non-linear dynamics of SMM. Applying these features to an existing published data set containing acceleration data, we achieve up to 9% average increase in accuracy compared to current state-of-the-art published results. Furthermore, we provide evidence that a single torso sensor can automatically detect multiple types of SMM in ASD, and that our approach allows recognition of SMM with high accuracy in individuals when using a person-independent classifier.
Verbatim from Europe PMC (opens in a new tab) · Licence: cc by
Results on ChatPPG leaderboards
All leaderboardsNo results from this paper on ChatPPG leaderboards yet. Browse the leaderboards.
Tasks & signals
Signals
Keywords
How it works
Cite this paper
Großekathöfer, U., Manyakov, N. V., Mihajlović, V., Pandina, G., Skalkin, A., Ness, S., Bangerter, A., & Goodwin, M. S. (2017). Automated detection of stereotypical motor movements in autism spectrum disorder using recurrence quantification analysis. Frontiers in Neuroinformatics 2017. https://doi.org/10.3389/fninf.2017.00009
Großekathöfer, Ulf, Nikolay V. Manyakov, Vojkan Mihajlović, Gahan Pandina, Andrew Skalkin, Seth Ness, Abigail Bangerter, and Matthew S. Goodwin. 2017. "Automated detection of stereotypical motor movements in autism spectrum disorder using recurrence quantification analysis." Frontiers in Neuroinformatics 2017. https://doi.org/10.3389/fninf.2017.00009.
Großekathöfer, U., Manyakov, N. V., Mihajlović, V., Pandina, G., Skalkin, A., Ness, S., Bangerter, A. and Goodwin, M. S. (2017) 'Automated detection of stereotypical motor movements in autism spectrum disorder using recurrence quantification analysis', Frontiers in Neuroinformatics 2017. doi: 10.3389/fninf.2017.00009.
Großekathöfer, Ulf, et al. "Automated detection of stereotypical motor movements in autism spectrum disorder using recurrence quantification analysis." Frontiers in Neuroinformatics 2017, 2017. https://doi.org/10.3389/fninf.2017.00009.
U. Großekathöfer et al., "Automated detection of stereotypical motor movements in autism spectrum disorder using recurrence quantification analysis," Frontiers in Neuroinformatics 2017, 2017, doi: 10.3389/fninf.2017.00009.
@article{groekathofer2017automated,
title = {{Automated detection of stereotypical motor movements in autism spectrum disorder using recurrence quantification analysis}},
author = {Großekathöfer, Ulf and Manyakov, Nikolay V. and Mihajlović, Vojkan and Pandina, Gahan and Skalkin, Andrew and Ness, Seth and Bangerter, Abigail and Goodwin, Matthew S.},
year = {2017},
journal = {Frontiers in Neuroinformatics 2017},
doi = {10.3389/fninf.2017.00009}
}Added to the ChatPPG research hub