Cognitive Load Measurement in a Virtual Reality-Based Driving System for Autism Intervention

摘要: Autism Spectrum Disorder (ASD) is a highly prevalent neurodevelopmental disorder with enormous individual and social cost. In this paper, novel virtual reality (VR)-based driving system was introduced to teach skills adolescents ASD. This capable of gathering eye gaze, electroencephalography, peripheral physiology data in addition performance data. The objective paper fuse multimodal information measure cognitive load during such that tasks can be individualized for optimal skill learning. Individualization ASD intervention an important criterion due the spectrum nature disorder. Twenty participated our study collected were used systematic feature extraction classification loads based on five well-known machine learning methods. Subsequently, three fusion schemes—feature level fusion, decision hybrid fusion—were explored. Results indicate high accuracy. Such mechanism essential since it will allow individualization training load, which facilitate acceptance clinical use eventual commercialization.