Data-driven generation of synthetic behavioral feature vectors modeling children with autism spectrum disorders

Behavioral data on children with Autism Spectrum Disorders (ASD) are available thanks to standardized diagnostic tools, such as the Autism Diagnostic Observation Schedule (ADOS). This data can be of great use to enhance the learning and reasoning of agents interacting with children with ASD. However, the amount of such available data is limited and may not prove useful by itself to inform the algorithms of complex agents. To address this data scarcity problem, we present a method for generating synthetic behavioral data in the form of feature vectors characterizing a wide range of children with ASD. Our method relies on a thorough analysis and partition of the feature space based on a real dataset containing the ADOS scores of 279 children. We first analyze the real dataset using dimensionality reduction techniques, then introduce data-driven descriptors that partition the feature space into regions naturally arising from the data. We end by presenting a descriptor-based sampling method to generate synthetic feature vectors that successfully preserves the correlation structure of the real dataset.