Paperdoi:10.1016/j.sigpro.2017.10.011
Deep learning for automatic stereotypical motor movement detection using wearable sensors in autism spectrum disorders
Signal Processing (Elsevier) 2018
TL;DR
CNN feature learning plus LSTM temporal models for stereotypical motor movement detection on the public six-person accelerometer set, evaluated across subjects. Learned features improved F1 by about 0.10 and 0.20 versus handcrafted features on a simulated set and on Study 1, but were 0.05 F1 worse on Study 2. An ensemble of LSTMs was more stable than a single LSTM.
- Form factor: wearable
Abstract
Autism Spectrum Disorders are associated with atypical movements, of which stereotypical motor movements (SMMs) interfere with learning and social interaction. The automatic SMM detection using inertial measurement units (IMU) remains complex due to the strong intra and inter-subject variability, especially when handcrafted features are extracted from the signal. We propose a new application of the deep learning to facilitate automatic SMM detection using multi-axis IMUs. We use a convolutional neural network (CNN) to learn a discriminative feature space from raw data. We show how the CNN can be used for parameter transfer learning to enhance the detection rate on longitudinal data. We also combine the long short-term memory (LSTM) with CNN to model the temporal patterns in a sequence of multi-axis signals. Further, we employ ensemble learning to combine multiple LSTM learners into a more robust SMM detector. Our results show that: 1) feature learning outperforms handcrafted features; 2) parameter transfer learning is beneficial in longitudinal settings; 3) using LSTM to learn the temporal dynamic of signals enhances the detection rate especially for skewed training data; 4) an ensemble of LSTMs provides more accurate and stable detectors. These findings provide a significant step toward accurate SMM detection in real-time scenarios.
Verbatim from Semantic Scholar (opens in a new tab) · Abstract via Semantic Scholar; © the authors/publisher
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
Rad, N. M., Kia, S. M., Zarbo, C., van Laarhoven, T., Jurman, G., Venuti, P., Furlanello, C., & paper, C.-A. A. O. T. A. (2018). Deep learning for automatic stereotypical motor movement detection using wearable sensors in autism spectrum disorders. Signal Processing 2018. https://doi.org/10.1016/j.sigpro.2017.10.011
Rad, Nastaran Mohammadian, Seyed Mostafa Kia, Calogero Zarbo, Twan van Laarhoven, Giuseppe Jurman, Paola Venuti, Cesare Furlanello, and co-authors as on the archival paper. 2018. "Deep learning for automatic stereotypical motor movement detection using wearable sensors in autism spectrum disorders." Signal Processing 2018. https://doi.org/10.1016/j.sigpro.2017.10.011.
Rad, N. M., Kia, S. M., Zarbo, C., van Laarhoven, T., Jurman, G., Venuti, P., Furlanello, C. and paper, C.-A. A. O. T. A. (2018) 'Deep learning for automatic stereotypical motor movement detection using wearable sensors in autism spectrum disorders', Signal Processing 2018. doi: 10.1016/j.sigpro.2017.10.011.
Rad, Nastaran Mohammadian, et al. "Deep learning for automatic stereotypical motor movement detection using wearable sensors in autism spectrum disorders." Signal Processing 2018, 2018. https://doi.org/10.1016/j.sigpro.2017.10.011.
N. M. Rad et al., "Deep learning for automatic stereotypical motor movement detection using wearable sensors in autism spectrum disorders," Signal Processing 2018, 2018, doi: 10.1016/j.sigpro.2017.10.011.
@article{rad2018deep,
title = {{Deep learning for automatic stereotypical motor movement detection using wearable sensors in autism spectrum disorders}},
author = {Rad, Nastaran Mohammadian and Kia, Seyed Mostafa and Zarbo, Calogero and van Laarhoven, Twan and Jurman, Giuseppe and Venuti, Paola and Furlanello, Cesare and paper, co-authors as on the archival},
year = {2018},
journal = {Signal Processing 2018},
publisher = {Elsevier},
doi = {10.1016/j.sigpro.2017.10.011}
}Added to the ChatPPG research hub