A case study on Discrete Wavelet Transform based Hurst exponent for epilepsy detection. (2nd January 2018)

• Record Type: Journal Article
• Authors: Madan, Saiby; Srivastava, Kajri; Sharmila, A.; Mahalakshmi, P.
• Is Part Of: Journal of medical engineering & technology. Volume 42:Number 1(2018)
• Page Start: 9
• Page End: 17
• Publication Date: 2018-01-02
• Subjects: Epilepsy -- Hurst exponent -- support vector machine -- discrete wavelet transform -- K-nearest neighbour; Biomedical engineering -- Periodicals; Medical technology -- Periodicals; 610.28
• DOI: 10.1080/03091902.2017.1394390
• Languages: English
• ISSNs: 0309-1902

Abstract

Abstract: Epileptic seizures are manifestations of epilepsy. Careful analysis of EEG records can provide valuable insight and improved understanding of the mechanism causing epileptic disorders. The detection of epileptic form discharges in EEG is an important component in the diagnosis of epilepsy. As EEG signals are non-stationary, the conventional frequency and time domain analysis does not provide better accuracy. So, in this work an attempt has been made to provide an overview of the determination of epilepsy by implementation of Hurst exponent (HE)-based discrete wavelet transform techniques for feature extraction from EEG data sets obtained during ictal and pre ictal stages of affected person and finally classifying EEG signals using SVM and KNN Classifiers. The The highest accuracy of 99% is obtained using SVM.