Ensemble learning on heartbeat type classification

Ensemble learning, known as multiple classifier system, combines the predictions from multiple base classifiers (or learners) altogether to conclude a final decision. It has been proven that ensemble learning is a simple, useful and effective meta-classification methodology. SBCB (Selecting Base Classifiers on Bagging) is a selective based ensemble learning algorithm [1] which is able to select an optimal set of classifiers among all candidates through an optimization process, based on the criteria of accuracy and diversity. In this paper, the use of SBCB algorithm to effectively deal with the classification of heartbeat on ECG signal is presented as a case study. The automatic identification of different heartbeat types is conducive to arrhythmia detection, heart disease diagnosis and so on. The comparison of SBCB and classical classification algorithms were designed and conducted in this paper. The empirical results reveal the effectiveness of SBCB algorithm to classify the type of heartbeat based on ECG signal. In additional, the integration of SBCB algorithm to an ECG diagnostic system was reviewed and presented in this paper.