Automated characterization and classification of coronary artery disease and myocardial infarction by decomposition of ECG signals: A comparative study.

•Classification of three types of ECG beats are proposed.•Normal, CAD and MI are three classes considered in this work.•DCT, DWT and EMD decomposition methods are employed on ECG beat.•Decomposed signals are fed to Locality Preserving Projections method.•KNN classifier yielded 98.5% accuracy with seven features for DCT method.