An optimised machine learning algorithm for classification of epileptic seizures using EMD-based dynamic features of EEG. (27th June 2022)

• Record Type: Journal Article
• Authors: Chirasani, Sateesh Kumar Reddy; Manikandan, Suchetha
• Is Part Of: International journal of ad hoc and ubiquitous computing. Volume 40:Number 1/3(2022)
• Page Start: 127
• Page End: 138
• Publication Date: 2022-06-27
• Subjects: empirical mode decomposition -- seizure detection -- electroencephalogram -- EEG -- support vector machine -- SVM -- epilepsy; Ubiquitous computing -- Periodicals; Embedded computer systems -- Periodicals; Electronic data processing -- Distributed processing -- Periodicals; Wireless communication systems -- Periodicals; Computer architecture -- Periodicals; 004.2
• Languages: English
• ISSNs: 1743-8225

Abstract

The seizure is an unexpected change in neurons, which leads to the second most common disease of the brain called epilepsy. An automatic seizure detection technique is essential for primary diagnosis and treatment because the traditional methods of seizure detection are time-consuming and inaccurate. In this regard, this proposal shows a novel seizure detection technique with two unique features of time-frequency. The two features are computed from the intrinsic mode functions (IMF) levels of empirical mode decomposition (EMD). Further, the support vector machine (SVM) is optimised with a marginal sampling approach to classify healthy and seizure subjects. The efficiency of the proposed method has compared with different classification methods such as K-nearest neighbours (KNN), decision tree (DT), and naive Bayes (NB) respectively. We can notice that the proposed method attained the best average performance with an accuracy of 99.23% and less computational time.