Title: A phase entropy based novel machine learning structure conditioned for classifying ictal and non-ictal signal aimed at proper clinical diagnosis

Authors: Santosh Kumar Sahoo; Sumant Kumar Mohapatra

Addresses: CVR College of Engineering, Hyderabad, Telangana, India ' Trident Academy of Technology, Bhubaneswar, Odisha, India

Abstract: Proposed scheme is based on the detection and classification of ictal and pre-ictal electro-encephalogram (EEG) signal of a partially affected epileptic patients. This work helps for the detection of ictal EEG signal as compared to pre-ictal EEG signal. In this work a conceptual method is used for the perfect detection of seizures. Here phase entropies (PEnS1 and PEnS2) are followed for feature extraction ictal and pre-ictal EEG signals. Again, extracted features are classified through multi-layer perception neural network (MLPNN) classifier tool. To train and test the classifier, map reduce quantum PSO (MRQPSO) is used. By considering various statistical parameters like Accuracy, Sensitivity, Specificity, positive predictive value, negative predictive value and Matthew's correlation coefficient, the performance of the proposed scheme has evaluated.

Keywords: EEG; multi-layer perception neural network; MLPNN; ictal; map reduce quantum PSO; MRQPSO.

DOI: 10.1504/IJCSYSE.2019.103667

International Journal of Computational Systems Engineering, 2019 Vol.5 No.5/6, pp.342 - 348

Received: 30 Jun 2018
Accepted: 19 Apr 2019

Published online: 18 Nov 2019 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article