Providing Adaptive and Personalized Visual Support based on Behavioral Tracking of Children with Autism for Assessing Reciprocity and Coordination Skills in a Joint Attention Training Application

Recent works have demonstrated the applicability of the activity and behavioral pattern analysis mechanisms to assist therapists, care-givers and individuals with development disorders including those with autism spectrum disorder (ASD); the computational cost and sophistication of such behavioral modeling systems might prevent them from deploying. As such, in this paper, we proposed an easily deployable automatic system to train joint attention (JA) skills, assess the frequency and degree of reciprocity and provide visual cues accordingly. Our proposed approach is different from most of earlier attempts in that we do not capitalize the sophisticated feature-space construction methodology; instead, the simple design, in-game automatic data collection for adaptive visual supports offers hassle-free benefits especially for low-functioning ASD individuals and those with severe verbal impairments.