TY - GEN
T1 - Automated diagnosis of tachycardia beats
AU - Desai, Usha
AU - Nayak, C. Gurudas
AU - Seshikala, G.
AU - Martis, Roshan J.
AU - Fernandes, Steven L.
N1 - Publisher Copyright:
© Springer Nature Singapore Pte Ltd. 2018.
PY - 2018/1/1
Y1 - 2018/1/1
N2 - Due to tachycardia, heart generates lethal arrhythmia beats namely atrial flutter (AFL), atrial fibrillation (A-Fib), and ventricular fibrillation (V-Fib). These irregular patterns are very effectively and noninvasively reflected using standard electrocardiogram (ECG). In this study, an automated diagnosis support system (DSS) is developed for accurate discrimination and classification of complete classes of tachycardia beats (atrial as well as ventricular) using higher-order spectra (HOS). In this multiclass diagnosis problem, dimensionality of HOS third-order cumulants is reduced using independent component analysis (ICA) and fed for standard hypothesis test ANOVA (p < 0.05). Finally, statistical significant components are subjected for ensemble classification using random forest (RAF) and rotation forest (ROF) classifiers and to realize best performance tenfold classification is performed. Further, the consistency of classifiers is assessed using Cohen’s kappa matric. Proposed DSS achieved overall classification accuracy of 99.54% using ROF. Our reported results are highest than published in the earlier works.
AB - Due to tachycardia, heart generates lethal arrhythmia beats namely atrial flutter (AFL), atrial fibrillation (A-Fib), and ventricular fibrillation (V-Fib). These irregular patterns are very effectively and noninvasively reflected using standard electrocardiogram (ECG). In this study, an automated diagnosis support system (DSS) is developed for accurate discrimination and classification of complete classes of tachycardia beats (atrial as well as ventricular) using higher-order spectra (HOS). In this multiclass diagnosis problem, dimensionality of HOS third-order cumulants is reduced using independent component analysis (ICA) and fed for standard hypothesis test ANOVA (p < 0.05). Finally, statistical significant components are subjected for ensemble classification using random forest (RAF) and rotation forest (ROF) classifiers and to realize best performance tenfold classification is performed. Further, the consistency of classifiers is assessed using Cohen’s kappa matric. Proposed DSS achieved overall classification accuracy of 99.54% using ROF. Our reported results are highest than published in the earlier works.
UR - https://www.scopus.com/pages/publications/85039460393
UR - https://www.scopus.com/pages/publications/85039460393#tab=citedBy
U2 - 10.1007/978-981-10-5544-7_41
DO - 10.1007/978-981-10-5544-7_41
M3 - Conference contribution
AN - SCOPUS:85039460393
SN - 9789811055430
T3 - Smart Innovation, Systems and Technologies
SP - 421
EP - 429
BT - Smart Computing and Informatics - Proceedings of the 1st International Conference on SCI 2016
A2 - Bhateja, Vikrant
A2 - Das, Swagatam
A2 - Satapathy, Suresh Chandra
PB - Springer Science and Business Media Deutschland GmbH
T2 - 1st International Conference on Smart Computing and Informatics, SCI 2016
Y2 - 3 March 2017 through 4 March 2017
ER -