Title: Automatic ischaemic beats classification using Genetic-based Least Square Support Vector Machine

Authors: S. Murugan; S. Radhakrishnan

Addresses: Department of ICE, Arulmigu Kalasalingam College of Engineering, Krishnankoil 626190, Srivilliputhur, Tamil Nadu, India. ' Department of ICE, Arulmigu Kalasalingam College of Engineering, Krishnankoil 626190, Srivilliputhur, Tamil Nadu, India

Abstract: Myocardial ischaemia is the detection of ischaemic episodes in the Electrocardiogram (ECG) recordings can be very supportive to the physicians, relies heavily on the relevant and efficient feature extraction and classification of the ST segment. In this paper, the Genetic Algorithm (GA) and fuzzy logic is combined with PCA and ICA to improve their performance; the algorithms are Fuzzy-Genetic PCA (FGPCA) and Fuzzy-Genetic ICA (FGICA). In the proposed method, the features are classified using a Genetic-based Least Square Support Vector Machine (GLSSVM). The results demonstrated that the GLSSVM with FGICA achieved greater accuracy higher than the other automated diagnostic systems.

Keywords: myocardial ischaemia; GAs; genetic algorithms; classification; ischaemic beats; least squares SVM; support vector machines; electrocardiograms; ECG; fuzzy logic; automated diagnosis; heartbeats; cardic problems; cardiovascular disease; heart rate; feature extraction; PCA; principal component analysis; ICA; independent component analysis.

DOI: 10.1504/IJBET.2012.045356

International Journal of Biomedical Engineering and Technology, 2012 Vol.8 No.1, pp.36 - 48

Published online: 12 Dec 2014 *

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