期刊名称：International Journal of Innovative Research in Computer and Communication Engineering
印刷版ISSN：2320-9798
电子版ISSN：2320-9801
出版年度：2017
卷号：5
期号：4
页码：8744
DOI：10.15680/IJIRCCE.2017.05040305
出版社：S&S Publications
摘要：Electroencephalogram (EEG) is recording of electrical activity of the brain which can be used to detectEpileptic Seizures. Group of Neurons when misfiring produce abnormal electrical discharge which produces seizure.Epilepsy is tendency to have recurrent and unprovoked seizure. It is common brain disorder that affects about 1% of theworld population. A wavelet based fuzzy approximate entropy (fApEn) method is presented for the classification ofelectroencephalogram (EEG) signals into healthy/interictal versus ictal EEGs. Discrete wavelet transform is used todecompose the EEG signals into different sub bands. The fuzzy approximate entropy of different sub-bands is used asfeature vector for the classifier. In this work it is observed that the quantitative value of fuzzy approximate entropydrops during the ictal period which proves that the epileptic EEG signal is more ordered than the EEG signal of anormal subject. The fApEn values of different sub-bands of all the data sets are used to form feature vectors and thesevectors are used as inputs to Convolutional Neural Network (CNN) classifier. The fApEn feature of different sub-bands(D1–D5, A5) and classifiers is desired to correctly discriminate between three types of EEGs. It is revealed that thehighest classification than earlier results published. Classification accuracy of 98% is obtained while classifying normaland epileptic subjects while 97% is obtained while classifying normal and interictal subjects. The results are discussedquite in detail towards the last section of the present paper.
