Capturing play activities of young children to detect autism red flags

Abstract

The use of IoT devices to monitor activities of users is an established methodology in e-health and ambient assisted living, even if its adoption is still limited to a few, albeit popular, applications. We propose its adoption also in a niche application, namely the observation of young children during their games, which is a common test performed by specialists to diagnose autistic spectrum disorders in an early stage. Specifically, we describe an IoT system that employs miniaturized sensors and data fusion algorithms based on machine learning to identify automatically the movements applied to the toys by the children, and we propose a protocol for its use in the forthcoming pilot experiments.