EEG Signal Analysis for Identification of Epilepsy Using Machine Learning Classification Approaches
Sk. Ebraheem Khaleelulla1, Dr. P. Rajesh Kumar2

1SK. Ebraheem Khaleelulla, Department of Electronics and Communication Engineering, Andhra University College of Engineering, Visakhapatnam, India.

2Dr. P. Rajesh Kumar, Professor, Department of Electronics and Communication Engineering, Andhra University College of Engineering, Visakhapatnam, India.

Manuscript received on 10 April 2019 | Revised Manuscript received on 17 April 2019 | Manuscript Published on 26 July 2019 | PP: 683-688 | Volume-8 Issue-6S4 April 2019 | Retrieval Number: F11390486S419/19©BEIESP | DOI: 10.35940/ijitee.F1139.0486S419

Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open-access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: Epilepsy is censorious neurological disorder in which nerve cell activity in the brain is disturbed causing recurrent seizures which are sudden, uncontrolled electrical discharges in the brain cell. In clinical treatment of epileptic patients seizure reorganization has much prominence. Hence in detecting the phenomenon of epilepsy Electroencephalogram (EEG) signal is widely used as it includes important carnal data of the brain. Though it is critical to analyze the EEG signal and identify the seizures. So feature extraction of EEG signal plays a vital role for epilepsy detection. This paper describes an worthwhile feature extraction based on variational mode decomposition (VMD) to identify epilepsy. The extracted features fed to ANN, KNN and SVM in order to classify epilepsy. The performance of the SVM classifier shows the better classification compared to existing methods.

Keywords: Electroencephalogram, Variational Mode Decomposition, Artificial Neural Network, K-Nearest Neighbor, Support Vector Machine.
Scope of the Article: Classification