Record Details

Hybrid SVM for multiclass arrhythmia classification

DSpace at IIT Bombay

View Archive Info
 
 
Field Value
 
Title Hybrid SVM for multiclass arrhythmia classification
 
Creator JOSHI, AJ
CHANDRAN, S
JAYARAMAN, VK
KULKARNI, BD
 
Subject support vector machines
holder exponent
 
Description Automatically classifying ECG recordings for Malignant Ventricular Arrhythmia is fraught with several difficulties. Even normal ECG signals exhibit only quasi-periodic nature, and contain various irregularities. The key to more accurate detection is the use of position, and amount of local singularities in the signals. In this paper, we propose a Holder-SVM detection algorithm using a novel hybrid arrangement of binary and multiclass SVMs designed to take care of class imbalance rampant in biomedical signals. As a result, we significantly reduce the number of false negatives patients falsely classified as normal. We used the MIT-BIH Arrhythmia database for seven different arrhythmias. We compare our hybrid SVM with a suitable conventional SVM, and show better results. We also use the new arrangement for features proposed earlier, and demonstrate the gain in accuracy. Our concept of hybrid SVM is applicable to a wide variety of multiclass classification problems.
 
Publisher IEEE COMPUTER SOC
 
Date 2011-10-24T10:40:36Z
2011-12-15T09:11:35Z
2011-10-24T10:40:36Z
2011-12-15T09:11:35Z
2009
 
Type Proceedings Paper
 
Identifier 2009 IEEE INTERNATIONAL CONFERENCE ON BIOINFORMATICS AND BIOMEDICINE,287-290
978-0-7695-3885-3
http://dx.doi.org/10.1109/BIBM.2009.73
http://dspace.library.iitb.ac.in/xmlui/handle/10054/15392
http://hdl.handle.net/100/2157
 
Source IEEE International Conference on Bioinformatics and Biomedicine (BIBMW 2009),Washington, DC,NOV 01-04, 2009
 
Language English