Detection of ECG arrhythmia using Zhao-Atlas Mark time-frequency distribution

The heart is one of the most important organs in our body. Because of a problem that occurs in the heart, through the necessary blood flow to tissues and organs cannot be achieved, the quality of life will be affected negatively. In fact, it can even cause paralysis and sudden deaths. Therefore, it is very important for heart diseases to be detected and monitored in advance. In the study, it was purposed to determine ECG arrhythmias. In this context; the data was obtained from the MIT-BIH Arrhythmia database. A total of 214,714 heartbeats were used in the study in order to study a fairly large database. The Zhao-Atlas Mark method is used as the time-frequency distribution method to extract the feature from the ECG signals. In classification, many classifiers were used and it was seen that the best result was taken at the Weighted K-EYK method from K-Nearest Neighbor (K-EYK) classifier. The performance of the system is given as accuracy, sensitivity, specificity, positive predictive value respectively 94.10%, 93.19%, 95.02%, 94.93%.