期刊名称：International Journal of Advanced Research In Computer Science and Software Engineering
印刷版ISSN：2277-6451
电子版ISSN：2277-128X
出版年度：2013
卷号：3
期号：9
出版社：S.S. Mishra
摘要：An Electroca rdiogram (ECG) is a test that records the electrical activity of the heart to locate the abnormalities. Automatic ECG classification is very useful for the cardiologists in medical diagnosis for effective treatments. In this paper, we propose efficient techniques to automatically classify the ECG signals into normal and arrhythmia affected (abnormal) category. For these categories features such as Linear Predictive coefficients (LPC), Linear predictive cepstral coefficients (LPCC) and Mel-Frequency Cepstral Co-efficients(MFCC) are extracted to exemplify the ECG signal. SVM is the model engaged to capture the distribution of the feature vectors for classification and the performance is calculated. ECG records used in this study are collected from MIT-BIH database. The experimental results demonstrate the efficiency of the proposed method. The proposed method can accurately classify and discriminate the difference between normal ECG signal and arrhythmia affected signal with 94% accuracy
关键词：Electrocardiogram (ECG); Cardiac Arrhythmia; Linear Prediction Coefficients (LPC); Linear Prediction ;Cepstral Coefficients (LPCC); Mel-Frequency Cepstral Co-efficients (MFCC); Support Vector Machine (SVM).
