Performance Analysis of ECG Arrhythmia Classification based on Different SVM Methods
Sumanta Kuila1, Sayandeep Maity2, Suman Kumar Mal3, Subhankar Joardar4

1Sumanta Kuila*, Dept. of Computer Sc. & Engineering, Haldia Institute of Technology, Haldia, (West Bengal), India.
2Sayandeep Maity, Dept. of Computer Sc. & Engineering, Haldia Institute of Technology, Haldia, (West Bengal), India.
3Suman Kumar Mal, Dept. of Computer Sc. & Engineering , Haldia Institute of Technology, Haldia, (West Bengal), India.
4Subhankar Joardar, Dept. of Computer Sc. & Engineering, Haldia Institute of Technology, Haldia, (West Bengal), India.

Manuscript received on September 06, 2020. | Revised Manuscript received on September 18, 2020. | Manuscript published on October 10, 2020. | PP: 45-49 | Volume-9 Issue-12, October 2020 | Retrieval Number: 100.1/ijitee.L79171091220 | DOI: 10.35940/ijitee.L7917.1091220
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: Heart arrhythmias are the different types of heartbeats which are irregular in nature. In Tachycardia the heartbeat works too fast and in case of Bradycardia it works too slow. In the study of different cardiac conditions automatic detection of heart arrhythmia is done by the classification and feature extraction of Electrocardiogram(ECG) data. Various Support Vector Machine based methods are used to analyze and classify ECG signals for arrhythmia detection. There are several Support Vector Machine (SVM) methods used to classify the ECG data such as one against all, one against one and fuzzy decision function. This classification detects the existence of the arrhythmia and it helps the physicians to treat the heart patient with more accurate way. To train SVM, the MIT BIH Arrhythmia database is used which works with the heart disorder like sinus bradycardy, old inferior myocardial infarction, coronary artery disease, right bundle branch block. All three methods are implemented in proper way, and their rate of accuracy with SVM classifier is optimal when it is processed with the one-against-all method. The data sets of ECG arrhythmia are usually complex in nature, so for the SVM based classification one-against-all method has great impact and will fetch better result. 
Keywords: Arrhythmia, Classification, Electrocardiogram, Feature Extraction, MIT BIH Arrhythmia Database, Support Vector Machine, QRS Complex.