An approach for ECG classification based on wavelet feature extraction and decision tree

Automatic analysis of cardiac arrhythmias is very important for diagnosis of cardiac abnormities. This paper presents a novel approach that classifies ECG signals with the combination of Wavelet transform and Decision tree classification. This approach has two aspects. In the first aspect, we utilize the wavelet transform to extract the ECG signals wavelet coefficients as the first features and utilize the combination of principal component analysis (PCA) and independent component analysis (ICA) to remove the first features relativity and search this features independence as the new features, then we add the RR interval as the final features. In the second aspect, we utilize the ID3 algorithm which is one of analysis decision tree methods as the classifier to recognize the different heartbeat arrhythmias. We utilize the MIT-BIH Arrhythmia Database to create the classification and test the classification. The results confirm its high reliability and high accuracy is very well.