查看文章

This work investigates and compares a set of efficient techniques to extract and select striking features from the ECG data applicable in automatic cardiac beat classification. Each method was applied to a pre-selected data segment from the MIT-BIH (Massachusetts Institute of Technology/Beth Isrel Hospital) database. The classification and optimization of different heart beat methods were performed based upon the extracted features (morphological and statistical feature). The morphological features were found as the most important for arrhythmia classification. However, because of ECG signal variability in different patients, the statistical approach is favoured for a precise and robust feature extraction. Among all these feature extraction, feature selection, classification and optimization techniques, SVM based PSO gives higher classification accuracy with curse of dimensionality.