Early Detection of Autism using SVM Classifier

Abstract

The Autism Spectrum Disorder (ASD) is a Neuro development disorder caused duetodamageintheactivityofthebrain.Inthisprojectthebrainwaveswerecollectedfrom the normal and autism subjects using Neuromax 32. The raw signals were extracted by placing the electrodes on the scalp of the subjects. The signals were normalized and allowed to pass through the band pass filter. The filtere dout put is allowed to subjected to DWT. The features were extracted from EEG signals. Features such as variance, kurtosis, and Shannon entropy are extracted. By using mathematical expressions, the features were extracted. The variations in the features of the normal and autism signals are noticed. The output of the features is given as input to the classifier algorithm named Support Vector Machine (SVM) to classify the signals as normal or abnormal. The EEG datasets are used totrain the algorithm and then testing is done to identify the accuracy of classifier.