Title: Evaluation of a new heart beat classification method based on ABC algorithm, comparison with GA, PSO and ACO classifiers
Authors: Selim Dilmac; Ali Nizam; Mehmet Korurek
Addresses: Department of Electronics and Communication Engineering, Istanbul Technical University, Istanbul, Turkey ' Department of Computer Engineering, Fatih Sultan Mehmet Waqf University, Istanbul, Turkey ' Department of Electronics and Communication Engineering, Istanbul Technical University, Istanbul, Turkey
Abstract: In this paper, we proposed a new method modified artificial bee colony (MABC) algorithm and it is applied to ECG signal analysis for heart beat classification. MITBIH database ECG data is used. In this dataset, MABC algorithm can reach high classification success rate, even with the low values of colony size and other control parameters such as MCN and limit. The classification success rate result of MABC is compared with results of three other classifiers: GA, PSO and ACO. In classification problem, choosing distinctive features has important effect to get a high classification success rate. By using the right features on analysed dataset, high system classification success rate (98.73%) is achieved by MABC, similar to other compared classifiers. MABC and ACO has high sensitivity for all beat types while GA and PSO have lower classification success rates for some beat types.
Keywords: modified ABC; artificial bee colony optimisation; MABC; data clustering; ECG arrhythmia; heart beat classification; swarm intelligence; ant colony optimisation; ACO; PSO; particle swarm optimisation; genetic algorithms; electrocardiograms.
International Journal of Reasoning-based Intelligent Systems, 2014 Vol.6 No.3/4, pp.98 - 108
Available online: 09 Dec 2014 *Full-text access for editors Access for subscribers Purchase this article Comment on this article