EEG signal classification using Modified Fuzzy Clustering algorithm

Abstract — Epilepsy is a brain disorder in which clusters of nerve cells, or neurons, in the brain sometimes signal abnormally. The Empirical Mode Decomposition (EMD) is used to extract the features of EEG signals which help us to detect the epilepsy. In this paper, An Enhanced Classifier with Modified Fuzzy Clustering Algorithm to detect epilepsy is proposed. This proposed approach is evolving for multiclass classification problem. Bayesian theory is utilized to formulate the problem of clustering and classification. In clustering algorithm the selection of learning parameter i.e., clusters membership Degree is initially chosen at random, but here in the proposed methodology, the value of clusters membership degree is calculated on the basis of randomly initialized cluster centers. It is demonstrated by experiments that, this method improve the performance of the algorithm. The same is being verified with EEG signal datasets