ECG consists of various waveforms of electric signals of heat. Datamining can be used for analyzing and classifying the waveforms. Conventional studies classifying electrocardiogram have problems like extraction of distorted characteristics, overfitting, etc. This study classifies electrocardiograms by using BP algorithm and SVM to solve the problems. As results, this study finds that SVM provides an effective prohibition of overfitting in neural networks and guarantees a sole global solution, showing excellence in generalization performance.
P. M. Rautaharju, S. H. Zhou, et al., 'Comparability of 12-lead ECGs derived from EASI leads with standard 12-lead ECGS in the classification of acute myocardial ischemia and old myocardial infarction,' Journal of Electrocardiology, Volume 35, Issue 4, Part 2, pp. 35-39, 2002
B. Heden, 'Agreement Between Artificial Neural Networks and Experienced Electro-cardiographer on Electrocardiographic Diagnosis of Healed Myocardial Infarction,' JACC, Vol.28, No.4, pp. 1012-1016, 1996
Z. Dokur and T.Olmez, 'ECG beat classification by a novel hybrid neural network,' Computer Methods and Programs in Biomedicine, Volume 66, Issues 2-3, pp. 167-181, 2001
R. Silipo, M. Goru, et. al., 'Classification of Arrhythmic Events in Ambulatory Electrocardiogram, Using Artificial Neural Networks', Computers and Biomedical research Vol.28, pp. 305-318, 1995
K. Sternickel, 'Automatic pattern recognition in ECG time series', Computer Methods and Programs in Biomedicine, Vol.68, pp. 109-115, 2002
U. Rajendra. Acharya, P. Subbanna Bhat, et al., 'Classification of heart rate data using artificial neural network and fuzzy equivalence relation,' Pattern Recognition', Volume 36, Issue 1, pp. 61-68, 2003