Convolutional Neural Network for Stereotypical Motor Movement Detection in Autism

Autism Spectrum Disorders (ASDs) are associated with specific atypical postural or motor behaviors, of which Stereotypical Motor Movements (SMMs) may severely interfere with learning and social interactions. Wireless inertial sensing technology offers a valid infrastructure for automatic and real-time SMM detection, which would provide support for tuned intervention and possibly early alert on the onset of meltdown events. However, the identification and the quantification of SMM patterns remains complex due to strong inter-subject and intra-subject variability, hard to deal with by handcrafted features. Here we propose to employ the deep learning paradigm in order to learn discriminative features directly from multi-sensor accelerometer signals. Our results with convolutional neural networks provide preliminary evidence that feature learning and transfer learning embedded in deep architectures may lead to accurate and robust SMM detectors in longitudinal scenarios.