A Framework for Intelligent Learning Assistant Platform Based on Cognitive Computing for Children with Autism Spectrum Disorder

Children with Autism Spectrum Disorder(ASD) suffer from social and communication issues. In addition to that they also exhibit a complex collection of behaviors which makes it difficult for the trainers to identify the methodology to be adapted for training them. At present a mishmash of techniques are used to evaluate them in general, without identifying their uniqueness or specific characteristics. In this paper, we propose a cognitive computing based intelligent learning assistant that could provide suitable courseware by identifying a child specifically based on the behavioural patterns that aids the autistic student's learning. A hybrid approach which blends cognitive, developmental and behavioural psychology is used to generate an autism assessment model, by using which a specific courseware is provided to the child. An interactive chatbot along with a visual aid is used as an interface to interact with the child so as to capture his real-time responses. This system features Reinforcement learning, Regional Convolution Neural Network (R-CNN), Deep Convolution Neural Network (deep-CNN) to provide a personalized learning assistant platform for children with Autism Spectrum Disorder(ASD).