Detection of Brain Abnormalities Using EEG Signals and Hilbert-Huang Transform

Abstract

The Analysis in this paper presents classification of normal and abnormal activities of EEG Signal using the featured relied on Hilbert-Huang transform. In this work the discrimination will be achieved by analysing EEG Signal from freely accessible database. Through this Hilbert-Huang Transform the information related to the intrinsic functions contained in the EEG signal can be extracted which helps to the frequency and local amplitude of the signal. Weighted frequencies are calculated based on this local information and a comparison between abnormal and seizure-free determinant intrinsic functions is then performed The method of comparison is t-test and Euclidean Clustering, using t-test results in a P-value < 0.02 and the clustering leads to accurate (94%) and the specific (96%) results.