Stereotypical Motor Movement Detection in Dynamic Feature Space

Abstract

Stereotypical Motor Movements (SMMs) are abnormal postural or motor behaviors that interfere with learning and social interaction in Autism Spectrum Disorder patients. An automatic SMM detection system, employing inertial sensing technology, provides a useful tool for real-time alert on the onset of these atypical behaviors, therefore facilitating personalized intervention therapies. To tackle critical issues with inter-subject variability, in this study, we propose to combine long short-term memory (LSTM) with convolutional neural network (CNN) to model the temporal patterns in the sequence of multi-axes IMU signals. Our results, on one simulated and two experimental datasets, show that transferring the raw feature space to a dynamic feature space via the proposed architecture enhances the performance of automatic SMM detection system especially for skewed training data. These findings facilitate the application of SMM detection system in real-time scenarios.