Chapter 12 - EEG-based computer-aided diagnosis of autism spectrum disorder

Abstract

Autism is a group of developmental disorders, referred to as autism spectrum disorder (ASD). Most autistic persons show symptoms of withdrawal from social interaction and a lack of emotional empathy toward others. This behavior is usually attributed to their inability in understanding or expressing emotions. The underlying causes of ASD are still not well understood, but an alarming number of persons are diagnosed with this disorder. People with heightened sensitivity to sounds, fluorescent lights, and fragrances in everyday products, eye contact, and other environmental stimuli can easily become overloaded and can “shut down.” Many people with autism suffer from such overload, which can also lead to behaviors that are injurious to the self or others. Autism comprises a wide range of neurodevelopmental disorders, and its intensity differs greatly in individuals. Therefore, setting a clear boundary between healthy and autistic people is difficult, and the mechanisms of autism have not yet been clarified. In this chapter, discussions about the Internet of Things -connected sensors which will help collect EEG data from the disorder patients and then preprocess the data to remove data duplications and then investigate different feature extractions, like features extracted from the EEG signals, and applying EEG classification techniques for assisting epilepsy and ASD diagnosis. We also compare different classification methods, including artificial neural networks, k-nearest neighbor, support vector machine, and linear discriminant analysis.