ABSTRACT
Autism spectrum disorder is a complex disorder in which the individuals show a variety of disabilities. Autism spectrum disorder is characterized by symptoms such as repetitive behavior and inability to socially interact. The complexity of this disorder develops a need for developing a system for the detection of autism spectrum disorder at an early stage. The purpose of this book chapter is to develop a diagnostic system for the accurate diagnosis of autism using adaptive neuro fuzzy inference system (ANFIS). The traits were extracted from ERP, and the Takagi-Sugeno fuzzy inference system was used which combines artificial network and fuzzy logic into a single frame. In this chapter, hierarchical fuzzy system has been used to diagnose ASD at an early stage. The system accuracy is 99.3% in the classification (i.e., ASD vs. normal) and 88.78% in the severity level (normal/low, medium and high) of ASD. The proposed diagnostic module examines both the behavioral aspects as well as the brain’s activity response under different psychiatric conditions (ERP). The primary modules make the decision and check the severity level of ASD.
