Deep learning for automatic stereotypical motor movement detection using wearable sensors in autism spectrum disorders

Citation data:

Signal Processing, ISSN: 0165-1684, Vol: 144, Page: 180-191

Publication Year:
Usage 39
Abstract Views 36
Link-outs 3
Captures 16
Readers 16
Mentions 1
Blog Mentions 1
Social Media 4
Tweets 4
Citations 3
Citation Indexes 3
Nastaran Mohammadian Rad; Seyed Mostafa Kia; Calogero Zarbo; Twan van Laarhoven; Giuseppe Jurman; Paola Venuti; Elena Marchiori; Cesare Furlanello
Elsevier BV
Engineering; Computer Science
Most Recent Tweet View All Tweets
Most Recent Blog Mention
article description
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.