A Novel Machine Learning Approach for Detection of Coronary Artery Disease Using Reduced Non-linear and Chaos Features
In this research paper, authors present an automated system in this paper that integrates a ranking technique with Principal Component Analysis (PCA), Generalized Discriminant Analysis (GDA) and a 1-Norm Bidirectional Extreme Learning Machine (1-NBELM) to reliably classify normal and coronary artery...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Bulgarian Academy of Sciences
2022-09-01
|
Series: | International Journal Bioautomation |
Subjects: | |
Online Access: | http://www.biomed.bas.bg/bioautomation/2022/vol_26.3/files/26.3_05.pdf |
_version_ | 1811206671262810112 |
---|---|
author | Ram Sewak Singh Demissie Jobir Gelmecha Satyasis Mishra Gemechu Dengia Devendra Kumar Sinha |
author_facet | Ram Sewak Singh Demissie Jobir Gelmecha Satyasis Mishra Gemechu Dengia Devendra Kumar Sinha |
author_sort | Ram Sewak Singh |
collection | DOAJ |
description | In this research paper, authors present an automated system in this paper that integrates a ranking technique with Principal Component Analysis (PCA), Generalized Discriminant Analysis (GDA) and a 1-Norm Bidirectional Extreme Learning Machine (1-NBELM) to reliably classify normal and coronary artery disease groups. Twenty chaotic and non-linear attributes were hauling out from the Heart Rate Variability (HRV) signal to detect coronary artery disease groups. The HRV data for this study derived from a typical database of Normal Old (ELY), Young (YNG), and Coronary Artery Disease (CAD) people. Fisher, Wilcoxon and Bhattacharya were used to compute the rankings of attributes. GDA then turned the ranking features into a new feature. The Radial Basis Function (RBF) kernel was used to transfer original features to a high-dimensional feature space in GDA and PCA, and then it was deployed to 1-NBELM, which utilized the sigmoidal or multiquadric non-linear activation. Numerical experiments were performed on the combination of database sets as Young-ELY, Healthy-CAD, and Healthy ELY-CAD subjects. The numerical results show that ROC with GDA and 1-NBELM approach achieved an accuracy of 98.12±0.14, 96.21±0.12 and 99.87±0.28 for Young-CAD, Young-ELY and Healthy ELY-CAD groups with the use of sigmoidal and multiquadric activation function. The Fisher with GDA and 1-NBELM and Bhattacharya with GDA and 1-Norm Extreme Learning Machine (1-NELM) approach achieved an accuracy of 99.98±0.21 for all databases. |
first_indexed | 2024-04-12T03:51:07Z |
format | Article |
id | doaj.art-cea20c85a002461f86f73e272d3634cf |
institution | Directory Open Access Journal |
issn | 1314-1902 1314-2321 |
language | English |
last_indexed | 2024-04-12T03:51:07Z |
publishDate | 2022-09-01 |
publisher | Bulgarian Academy of Sciences |
record_format | Article |
series | International Journal Bioautomation |
spelling | doaj.art-cea20c85a002461f86f73e272d3634cf2022-12-22T03:48:58ZengBulgarian Academy of SciencesInternational Journal Bioautomation1314-19021314-23212022-09-0126327329610.7546/ijba.2022.26.3.000786A Novel Machine Learning Approach for Detection of Coronary Artery Disease Using Reduced Non-linear and Chaos FeaturesRam Sewak Singh0Demissie Jobir GelmechaSatyasis MishraGemechu DengiaDevendra Kumar SinhaElectronics and Communication Engineering (SIG) Department, School of Electrical and Computing Engineering, Adama Science and Technology University, Adama, EthiopiaIn this research paper, authors present an automated system in this paper that integrates a ranking technique with Principal Component Analysis (PCA), Generalized Discriminant Analysis (GDA) and a 1-Norm Bidirectional Extreme Learning Machine (1-NBELM) to reliably classify normal and coronary artery disease groups. Twenty chaotic and non-linear attributes were hauling out from the Heart Rate Variability (HRV) signal to detect coronary artery disease groups. The HRV data for this study derived from a typical database of Normal Old (ELY), Young (YNG), and Coronary Artery Disease (CAD) people. Fisher, Wilcoxon and Bhattacharya were used to compute the rankings of attributes. GDA then turned the ranking features into a new feature. The Radial Basis Function (RBF) kernel was used to transfer original features to a high-dimensional feature space in GDA and PCA, and then it was deployed to 1-NBELM, which utilized the sigmoidal or multiquadric non-linear activation. Numerical experiments were performed on the combination of database sets as Young-ELY, Healthy-CAD, and Healthy ELY-CAD subjects. The numerical results show that ROC with GDA and 1-NBELM approach achieved an accuracy of 98.12±0.14, 96.21±0.12 and 99.87±0.28 for Young-CAD, Young-ELY and Healthy ELY-CAD groups with the use of sigmoidal and multiquadric activation function. The Fisher with GDA and 1-NBELM and Bhattacharya with GDA and 1-Norm Extreme Learning Machine (1-NELM) approach achieved an accuracy of 99.98±0.21 for all databases.http://www.biomed.bas.bg/bioautomation/2022/vol_26.3/files/26.3_05.pdf1-norm extreme learning machine (1-nelm)generalized discriminant analysis (gda)ranking methodschaos and non-linear features |
spellingShingle | Ram Sewak Singh Demissie Jobir Gelmecha Satyasis Mishra Gemechu Dengia Devendra Kumar Sinha A Novel Machine Learning Approach for Detection of Coronary Artery Disease Using Reduced Non-linear and Chaos Features International Journal Bioautomation 1-norm extreme learning machine (1-nelm) generalized discriminant analysis (gda) ranking methods chaos and non-linear features |
title | A Novel Machine Learning Approach for Detection of Coronary Artery Disease Using Reduced Non-linear and Chaos Features |
title_full | A Novel Machine Learning Approach for Detection of Coronary Artery Disease Using Reduced Non-linear and Chaos Features |
title_fullStr | A Novel Machine Learning Approach for Detection of Coronary Artery Disease Using Reduced Non-linear and Chaos Features |
title_full_unstemmed | A Novel Machine Learning Approach for Detection of Coronary Artery Disease Using Reduced Non-linear and Chaos Features |
title_short | A Novel Machine Learning Approach for Detection of Coronary Artery Disease Using Reduced Non-linear and Chaos Features |
title_sort | novel machine learning approach for detection of coronary artery disease using reduced non linear and chaos features |
topic | 1-norm extreme learning machine (1-nelm) generalized discriminant analysis (gda) ranking methods chaos and non-linear features |
url | http://www.biomed.bas.bg/bioautomation/2022/vol_26.3/files/26.3_05.pdf |
work_keys_str_mv | AT ramsewaksingh anovelmachinelearningapproachfordetectionofcoronaryarterydiseaseusingreducednonlinearandchaosfeatures AT demissiejobirgelmecha anovelmachinelearningapproachfordetectionofcoronaryarterydiseaseusingreducednonlinearandchaosfeatures AT satyasismishra anovelmachinelearningapproachfordetectionofcoronaryarterydiseaseusingreducednonlinearandchaosfeatures AT gemechudengia anovelmachinelearningapproachfordetectionofcoronaryarterydiseaseusingreducednonlinearandchaosfeatures AT devendrakumarsinha anovelmachinelearningapproachfordetectionofcoronaryarterydiseaseusingreducednonlinearandchaosfeatures AT ramsewaksingh novelmachinelearningapproachfordetectionofcoronaryarterydiseaseusingreducednonlinearandchaosfeatures AT demissiejobirgelmecha novelmachinelearningapproachfordetectionofcoronaryarterydiseaseusingreducednonlinearandchaosfeatures AT satyasismishra novelmachinelearningapproachfordetectionofcoronaryarterydiseaseusingreducednonlinearandchaosfeatures AT gemechudengia novelmachinelearningapproachfordetectionofcoronaryarterydiseaseusingreducednonlinearandchaosfeatures AT devendrakumarsinha novelmachinelearningapproachfordetectionofcoronaryarterydiseaseusingreducednonlinearandchaosfeatures |