Key result
An SVM-based ECG pattern recognition technique achieved a QRS complex detection rate of 99.79%, with false positive and false negative rates of 0.86% and 0.21%, respectively.
Why the study?
Does an SVM-based ECG pattern recognition technique accurately detect QRS complexes in single lead ECGs?
Does an SVM-based ECG pattern recognition technique accurately detect QRS complexes in single lead ECGs?
Answers are grounded in this paper and cite their sources.
An SVM-based ECG pattern recognition technique using digital filtering and entropy criteria achieved a 99.79% detection rate for QRS complexes on the standard CSE ECG database.
AbstractThis paper presents simple and reliable method for the detection of QRS complexes (cardiac beat) in single lead Electrocardiograms (ECG) using Support Vector Machine (SVM). Two different preprocessing techniques are applied for the generation of features. First involves digital filtering to remove base line wander and power line interference while the second involves entropy criterion for feature generation. SVM is used as a classifier to classify QRS and non-QRS regions. The results of the validation of the method on the standard CSE ECG database are also presented. Detection rate of 99.79 % is achieved. The percentage of false positive and false negative is 0.86% and 0.21% respectively. The proposed method functions reliably even under the condition of poor signal quality of the ECG. The detection rate depends strongly on the quality of training, data representation and the mathematical basis of the classifier.Indexing terms: ECGEntropyQRS complexSVM Additional informationNotes on contributorsS S MehtaSarabjeet S Mehta was born in Kolkata, India in 1958. He received the BE degree in Electrical Engineeirng and ME degree in Control System from J N Vyas University, Jodhpur, J Rajasthan, India in 1980 and 1987 respectively. He received PhD degree in Electrical Engineering from Indian Institute of Technology, Roorke in 1994. Presently he is Associate Professor and Head, Electrical Engineering Department of MBM Engineering College, J N Vyas University, Jodhpur, Rajasthan, India. His research interest includes pattern recognition, artificial neural networks, biomedical engineering, soft computing and electrical machines. He has published around 52 research papers in the National and International Conferences and Journals. He is member of Indian Society of Technical Education, Institution of Engineers (I), and International Association of Engineers, Hong Kong.N S LingayatNitin S Lingayat was born in Shahapur (Thane), India in 1971. He received BE degree in Electrical Engineering from the University of Poona, Pune in 1992 and the MTech. degree from Indian-Institute of Technology Bombay, Mumbai in 1998. He is Head, Electrical Engineering Department, Institute of Petrochemical Engineering of Dr B A Technological University, Lonere- Maharashtra, India. He is on deputation asa research scholar in Electrical Engineering Department, MBM Engineering College, J N Vyas University, Jodhpur-Rajasthan, India. Presently he is working in the area of biomedical signal processing. He has published around 26 research papers in the National and International Conferences and Journals. He is Life member of Indian Society of Technical Education, Institution of Engineers (I), and International Association of Engineers, Hong Kong.
No takes yet. Share an insight, caveat, or question.
Mehta et al. (2008) studied ECG QRS complex detection. Support Vector Machine (SVM) based ECG Pattern Recognition Technique was evaluated on Detection rate of QRS complexes. An SVM-based ECG pattern recognition technique achieved a QRS complex detection rate of 99.79%, with false positive and false negative rates of 0.86% and 0.21%, respectively.
Synapse has enriched 10 related papers. Consider them for comparative context: