Fractality and a Wavelet-Chaos-Neural Network Methodology for EEG-Based Diagnosis of Autistic Spectrum Disorder

Abstract

A method is presented for investigation of EEG of children with autistic spectrum disorder using complexity and chaos theory with the goal of discovering a nonlinear feature space. Fractal Dimension is proposed for investigation of complexity and dynamical changes in autistic spectrum disorder in brain. Two methods are investigated for computation of fractal dimension: Higuchi's Fractal Dimension and Katz's Fractal Dimension. A wavelet-chaos-neural network methodology is presented for automated EEG-based diagnosis of autistic spectrum disorder. The model is tested on a database of eyes-closed EEG data obtained from two groups: nine autistic spectrum disorder children, 6 to 13 years old, and eight non-autistic spectrum disorder children, 7 to 13 years old. Using a radial basis function classifier, an accuracy of 90% was achieved based on the most significant features discovered via analysis of variation statistical test, which are three Katz's Fractal Dimensions in delta (of loci Fp2 and C3) and gamma (of locus T6) EEG sub-bands with P < 0.001.

A Source-Discrimination Approach for Detection of ASD Using EEG Data

“…TABLE II: PARAMETERS Table III shows the average accuracy for each class using different training sizes repeated 5 times for each try. The results are in the acceptable range comparing to the recent methods that is reported using quantitative EEG for detect ASD [4], [5]. However, in our model we combined all tasks together.…”

Application of Entropy Measures on Intrinsic Mode Functions for the Automated Identification of Focal Electroencephalogram Signals

“…In the literature, many studies are presented to analyze Alzheimer's disease [1], attention-deficit/hyperactivity disorder (ADHD) [2], autism [3], autistic spectrum disorder [4], alcoholism [5], epilepsy [6,7], depth of anesthesia [8,9], etc., using EEG signals. Epilepsy is a common neurological disorder that affects the quality of life of the patient, causing social impairment and a higher risk of death [10].…”

Nonlinear Dynamics Measures for Automated EEG-Based Sleep Stage Detection

“…The goal is to help physicians indicate different sleep stages and the occurrence of respiratory, cardiac and muscular events in the sleep scoring process [27]. Combinations of wavelet signal processing technique, chaos theory/nonlinear science and neural network pattern recognition techniques have been reported in recent years for the EEG-based diagnosis of varying disorders such as epilepsy [28,29,30,31,32,33], Alzheimer's disease [34,35], attention deficit hyperactivity disorder [36,37], autism spectrum disorder [38,39,40], major depressive disorder [29] and alcoholism [41]. …”