Self-Stimulatory Behavior Detection Using Wearable Sensors for Children With Autistic Spectrum Disorder

An affordable, user-friendly and reliable infrastructure that supportsevidence based tools for health assessment of children withAutistic Spectrum Disorder (ASD) has been developed. This systemcan detect the behaviors of children at various stages of autismand enables the therapist and parents to monitor, assist diagnosisand therapies of autistic children. The system incorporates 2different sensor platforms which are wearable and static. Thewearable system consists of a 3-axis accelerometer, small microprocessor and a Bluetooth module to transmit data to the basestation. This wearable device integrates these 3 modules to a customizedPrinted Circuit Board (PCB) which can be worn as a cuff or could be sewed intothe sleeves of a child's shirt. The static sensor is composed of an audio sensorand a webcam which detects the sound/speech and captures video data of thesubject within the room. Using this sensor system, we are able to achieve thenecessary information for assessment and therapy in autism research.Based on the data collected and our preliminary analysis, we wereable to detect and recognize several self-stimulatory behaviors of achild with autism. The device allows for a continuous monitoringof the activities and self-stimulatory behaviors. It benefits both therapistsand parents by helping them to better understand the behaviors of an autisticchild and it will also enable early diagnosis of ASD.