Authors: Sulekha Saxena; Vijay Kumar Gupta; P.N. Hrisheekesha; R.S. Singh
Addresses: Dr. Abdul Kalam Technical University, Lucknow, Uttar Pradesh, India ' Inderprastha Engineering College, Ghaziabad, Uttar Pradesh, India ' Chandigarh Group of Colleges, Landran, Mohali, Punjab, India ' Electronics & Communication Eng (SIG) Department, School of Electrical Engineering & Computing, ASTU, Adama, Ethiopia
Abstract: This paper presents an automated Machine Learning (ML) algorithm to detect the Coronary Disease like Congestive Heart Failure (CHF) and Coronary Artery Disease (CAD). The proposed method has been employed as a combination of non-linear feature extraction methods: Online Sequential machine (OS-ELM) and Linear Discriminate Analysis (LDA) as well as Generalised Discriminate Analysis (GDA) as feature reduction algorithms. For training and validation of ML, 12 non-linear features were extracted from Heart Rate Variablility (HRV) signal. The numerical experiments were carried out on the sets as CAD-CHF, YOUNG-ELDERLY-CAD and YOUNG-ELDERLY-CHF subjects. The numerical simulation results clearly have shown that GDA combined with OS-ELM gives better detection performance compared to OSELM. To test the robustness of proposed method the classification performance like accuracy, positive prediction value, sensitivity and specificity were calculated on 100 trials and it achieved average performance accuracy of 99.77% for YOUNG-ELDERLY-CAD and 100% for CAD-CHF and YOUNG-ELDERLY CHF subjects.
Keywords: lempel-ziv; Poincare plot; OSELM; sample entropy; dimension reduction method; detrended fluctuation analysis.
International Journal of Computer Applications in Technology, 2021 Vol.66 No.2, pp.172 - 191
Received: 03 Sep 2020
Accepted: 22 Nov 2020
Published online: 14 Dec 2021 *