Hybrid Features and Classifier for Classification of ECG Signal

In this research, we have proposed an efficient technique to classify beat from ECG database. The proposed technique is composed into three stages, 1) pre processing 2) Hybrid feature extraction 3) hybrid feature classifier. The beat signals are initially taken from the physiobank ATM and in the pre-processing stage the beat signals are made suitable for feature extraction. For efficient feature extraction we use hybrid feature extractor. The hybrid feature extraction is done in three steps, i) Morphological based feature extraction ii) Haar wavelet based feature extraction iii) Tri-spectrum based feature extraction. Once the feature is extracted the hybrid classifier is used to classify the beat signal as normal or abnormal. Beat classification studies are conducted on the MIT-BIH Arrhythmia Database using three efficient features like as morphological, wavelet and trispectrum. The beat classification system based morphological information gives an accuracy of 68%, wavelet information gives an accuracy of 78%, trispectrum information gives an accuracy of 70%, combined morphological with wavelet information gives an accuracy of 77%, combined morphological with trispectral information gives an accuracy of 70%. By combining the evidence from both the morphological, wavelet and trispectrum features, an accuracy of 91% is obtained, indicating that ECG beat information is present in the hybrid features.