An approach for agitation detection and intervention in sufferers of autism spectrum disorder

Autism spectrum disorder (ASD) is a condition that is being diagnosed in a growing portion of the population. ASD represents a range of complex dis-orders with a number of symptoms including social difficulties and behavioral issues. Some individuals suffering from ASD are prone to incidents of agitation that can lead to escalation and meltdowns. Such incidents represent a risk to the individuals with ASD and others who share their environment. This paper intro-duces a novel approach to monitor triggers for these incidents with an aim to detect and predict an incident happening. Non-invasive sensors monitor factors within an environment that may indicate such an incident. Combined with an NFC and smart phone based mechanism to report incidents in a relatively friction free manner. These reports will be combined with sensor records to train a pre-diction system based on supervised machine learning. Future work will identify the best performing machine-learning technique and will evaluate the approach.