Applying Deep Learning to Stereotypical Motor Movement Detection in Autism Spectrum Disorders

Abstract

Autism Spectrum Disorders (ASD) are often associated with specific atypical postural or motor behaviors, of which Stereotypical Motor Movements (SMMs) interfere with learning and social interaction. Wireless inertial sensing technology offers a valid infrastructure for real-time SMM detection, whose automation would provide support for tuned intervention and possibly early alert on the onset of meltdown events. The identification and the quantification of SMM patterns remains complex due to strong inter-subject and intra-subject variability, in particular when handcrafted features are considered. This study aims at developing automatic SMM detection systems in a real world setting, based on a deep learning architecture. Here, after a review of the current state of the art of automatic SMM detection, we propose to employ the deep learning paradigm in order to learn the discriminating features from multi-sensor accelerometer signals. Our results with convolutional neural networks provided the preliminary evidence that feature learning and transfer learning embedded in deep architectures can provide accurate SMM detectors in longitudinal scenarios.