Autism Spectrum Disorder (ASD) is a neurodevelopmental disorder that is often accompanied by stereotypical motor movements. Health professionals typically assess the severity of these behaviors during therapy, which limits observations to a structured clinical setting. Recent advancements in ubiquitous computing and wearable sensors enable an ability to monitor these motor movements objectively and in real-time while children with ASD are in different environments. In this paper, we present a smartwatch-based system designed to detect stereotypical motor movements. To validate the feasibility of our approach, we collected data from adults imitating example behaviors captured in YouTube videos of children with ASD, and we then evaluated several classification methods for accuracy. The best model can identify stereotypical motor activities of hand flapping, head banging, and repetitive dropping with 92.6% accuracy (precision 88.8% and recall 87.7%) in the presence of confounding play-type activities. We present the trade-offs between accuracy of the assessments and power consumption due to sensing from multiple modalities. Cross-participant validation shows that the results of using the model on an unknown subject are promising.
Learning Objective 1: Explore and evaluate the feasibility of using the smartwatch to recognize the stereotypical motor movements commonly observed in children with autism.
Learning Objective 2: Present the design considerations and challenges for designing a real-time system that can perform in a resource-constrained setting.
Hillol Sarker (Presenter)
Allison Tam, IBM Research
Morgan Foreman, IBM Research
Nicholas Fay, IBM Research
Murtaza Dhuliawala, IBM Research
Amar Das, IBM Research