You can view the full text of this article for free using the link below.

Title: A real-time automated epileptic seizure detection model for phenylketonuria patients using ANFIS, DWT, ST, CT and EGA

Authors: Sumant Kumar Mohapatra; Srikanta Patnaik

Addresses: Department of Computer Science and Engineering, S'O'A (Deemed to be University), Odisha, India ' Department of Computer Science and Engineering, S'O'A (Deemed to be University), Odisha, India

Abstract: One of the most ARSG diseases is a phenylketonuria (PKU). The patient suffered from the deficiency of blood circulation across brain which shows small epileptic seizure in EEG signal. In this work, three feature extraction methods (discrete wavelet transform, shearlet transform and contourlet transform) have been used to classify epileptic seizure EEG (PKU-EEG) and raw EEG signals (non-epileptic seizure EEG). The classification between PKU-EEG and raw EEG signals are performed using nine-rule adaptive neuro-fuzzy inference system (ANFIS) trained with a new enhanced genetic algorithm (EGA). The CT-ANFIS-EGA method outperforms than above methods for the classification of normal EEG and PKU-EEG signals. The proposed method has the accuracy, sensitivity and specificity of 99.82%, 99.88% and 99.93% respectively using real datasets. This study suggests that the proposed work could be effective for clinical classification of epileptic seizure by PKU in the children from their early childhood ages.

Keywords: PKU-EEG signal; epilepsy; single gene; EEG signal; adaptive neuro-fuzzy inference system; ANFIS; discrete wavelet transform; DWT; shearlet transform; ST; contourlet transform; CT; enhanced genetic algorithm; EGA.

DOI: 10.1504/IJTMCP.2022.123137

International Journal of Telemedicine and Clinical Practices, 2022 Vol.3 No.4, pp.302 - 326

Received: 09 Sep 2019
Accepted: 01 Apr 2020

Published online: 31 May 2022 *

Full-text access for editors Full-text access for subscribers Free access Comment on this article