Analysis of Autism Spectrum Disorder ASD by Feature Extraction of EEG Signals Using Deep Learning Algorithms

Abstract

Autism Spectrum Disorder (ASD) is a neurodevelopmental condition characterised by abnormal brain development, which is influenced by genetic, biological, and environmental factors. Early diagnosis of ASD is crucial for timely intervention and improved long-term outcomes. However, current diagnostic methods primarily rely on behavioural observations and are subject to limitations and biases. Therefore, there is a need for alternative diagnostic approaches that are less reliant on subjective assessments. This dissertation proposes the use of Artificial Intelligence (AI)-based Computer-Aided Diagnostic Systems (CADS) for ASD diagnosis using Electroencephalography (EEG) signals and Deep Learning (DL) algorithms. The thesis investigated the effectiveness of DL classifiers in categorising individuals with ASD based on raw EEG signals without manual feature extraction newline