Affiliations: [a] Department of Computer Engineering, Science and Research Branch, Islamic Azad University, Tehran, Iran. E-mail: askary.elham@gmail.com | [b] Control and Intelligent Processing Center of Excellence, School of Electrical and Computer Engineering, College of Engineering, University of Tehran, Tehran, Iran. E-mail: ksetareh@ut.ac.ir | [c] Department of Biomedical Engineering, Science and Research Branch, Islamic Azad University, Tehran, Iran. E-mail: sheikhani_al_81@srbiau.ac.ir | [d] Psychiatry and Psychology Research Center, Roozbeh Hospital, Tehran University of Medical Sciences, Tehran, Iran. E-mail: mohammadimr@tums.ac.ir | [e] Department of Control Engineering, K.N. Toosi University of Technology, Tehran, Iran. E-mail: teshnehlab@eetd.kntu.ac.ir
Abstract: In neuropsychological disorders, the significant abnormalities in the brain connections in some regions are observed. This paper presents a novel model to demonstrate the connections between different regions in children with autism. The proposed model first conducts the wavelet decomposition of electroencephalography signals by wavelet transform then the features are extracted, such as relative energy and entropy. These features are fed to the 3D-cellular neural network model as inputs to indicate the brain connections. The results showed that there are significant differences and abnormalities in the left hemisphere, (p<0.05) at the electrodes AF3, F3, P7, T7 and O1 in alpha band, AF3, F7, T7 and O1 in beta band, T7 and P7 in gamma band for children with autism compared with the control children. Also, the evaluation of the obtained connections values between brain regions indicated that there are more abnormalities in the connectivity of frontal and parietal lobes and the relations of the neighboring regions in all three bands especially in gamma band for autistic children. Evaluation of the analysis demonstrated that alpha frequency band had the best distinction level of 96.6% based on the obtained values of the cellular neural network using support vector machine method.
