Physiological Signal Analysis for Emotion Estimation of Children with Autism Spectrum Disorder

The diagnosis of Autism Spectrum Disorder (ASD) in children is based on human observations by a clinician. The medical evaluation assesses deficits in social communication, social interaction, and restricted, repetitive behaviors. Robotic technology can assist in quantitatively measuring the observations to be used as a future tool for autism diagnosis and intervention. The project explores this technology to produce robotic partners that can adapt to the needs of the ASD population. This way, such robots could serve as instructors or learning peers. A friendly, partner robot, specifically designed for children with ASD could be used to investigate the effect of therapy and the connection between the motor, sensory, and emotional cortex in the brains of children with ASD. Affective computing is the study and development of systems and devices that can recognize, interpret, process, and simulate human emotions. The robots are envisioned to interpret physiological signals and appropriately adapt to the emotional responses of a user. Research has found that physiological pattern recognition can potentially aid in assessing and quantifying emotions. Thus, one of the purposes in this research is to analyze physiological data collected from human subjects to show its relationship to changes in emotional reactions during different activities. This poster illustrates observations made of the Heart Rate signal collected during different activities performed in a human-subject study by six patients with a diagnosis of ASD. The Heart Rate signal analysis shows a statistical difference that can support broader research in this area of interest