Electrocardiogram Classification Method Based on SVM

摘要

Heart disease is one of the main diseases threatening human beings health, and electrocardiogram is the important basis of diagnosing cardiovascular disease. Because of distinctiveness and variability of QRS wave, many present ECG classification techniques are difficult to realize. Although many methods could work successfully in recognizing certain types of ECG signals, the recognition rate usually can not be substantially promoted throughout all kinds of ECG signals. In this paper, 1-vs-rest algorithm of SVM is used for ECG classification. The algorithm for ECG classification is tested with the data of MIT-BIH.Finally a high recognize rate is obtained.