Data Quality as a Bottleneck in Developing a Social-Serious-Game-Based Multi-modal System for Early Screening for 'High Functioning' Cases of Autism Spectrum Condition

摘要

Our aim is to explore raw data quality in the first evaluation of the first fully playable prototype of a social-serious-game-based, multi-modal, interactive software system for screening for high functioning cases of autism spectrum condition at kindergarten age. Data were collected from 10 high functioning children with autism spectrum condition and 10 typically developing children. Mouse and eye-tracking data, and data from automated emotional facial expression recognition were analyzed quantitatively. Results show a sub-optimal level of raw data quality and suggest that it is a bottleneck in developing screening/diagnostic/assessment tools based on multi-mode behavioral data.