Authors: Zahra Mahmoodabadi; Saeed Shaerbaf Tabrizi
Addresses: Imamreza University, Daneshgah, Mashhad 91735-553, Iran ' Imamreza University, Daneshgah, Mashhad 91735-553, Iran
Abstract: One of the most critical diseases, which have a considerable mortality rate in the world, is coronary artery disease. To improve the diagnosis of this dangerous disease in the early stages, we proposed a system which uses data mining techniques and an evolutionary algorithm called imperialist competitive algorithm (ICA). Since the convergence speed is one of the important factors in an evolutionary algorithm, a change was made in this algorithm so that the convergence occurs more quickly. The results show that ICA and improved ICA produce the same results in classification accuracy, but the convergence time is different. To compare the efficiency of CA/improved ICA with another evolutionary algorithm, PSO algorithm used to test the proposed system. Results confirm the superiority of ICA in terms of accuracy and convergence speed to PSO in adjusting membership functions problem. The proposed system gets an accuracy of 94.92%, which is high in comparison to similar works.
Keywords: imperialist competitive algorithm; ICA; particle swarm optimisation; PSO; fuzzy logic; coronary artery disease; data mining; convergence speed; heart disease; coronary disease.
International Journal of Telemedicine and Clinical Practices, 2015 Vol.1 No.2, pp.157 - 173
Received: 16 Jul 2014
Accepted: 21 Jul 2014
Published online: 09 Jun 2015 *