Loading

Epileptic Seizure Detection Using HWPT based ANFIS Classifier
K.R. Anupriya1, T. Sasilatha2

1K.R. Anupriya, Research Scholar, AMET Deemed to be University, Chennai (Tamil Nadu), India.
2Dr. T. Sasilatha, Professor and Dean, AMET Deemed to be University, Chennai (Tamil Nadu), India.
Manuscript received on 05 February 2019 | Revised Manuscript received on 18 February 2019 | Manuscript Published on 04 March 2019 | PP: 20-23 | Volume-7 Issue-5S2 January 2019 | Retrieval Number: ES2000017519/19©BEIESP
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 patients experience challenges in everyday life due to precautions they have to take in order to cope with this situation .When a seizure occurs it might cause injuries or endanger the lives of the patients or others when they are using heavy machinery or driving etc. Prediction of epileptic activities before they occur will enable the patients and caregivers to take appropriate precautions. This paper proposes a novel patientspecific epileptic seizure detection using electroencephalogram (EEG). The proposed method combined both harmonic wavelet packet trans-form (HWPT) and fractal dimension (FD) to extract feature vectors from EEG signals effectively. Finally, the Adaptive Neuro-Fuzzy Inference System (ANFIS) is used to classify the feature vectors obtained from the epileptic electroencephalogram (EEG) signals. The ANFIS classification method combines both neural networks and the fuzzy logic principles together. Finally, the use of less computationally intensive feature extraction techniques facilitates speedy epileptic seizure detection when compared with existing techniques, signifying potential usage in real-time applications.
Keywords: Seizure, Classifier, EEG, ANFIS, HWPT, Fractal Dimension.
Scope of the Article: Agent-Based Software Engineering