Abstract

Info

Title:: Fundamental heart sound classification based on optimized back-propagation neural network

Author(s):: XU Chundong; LONG Qinghua; School of Information Engineering, Jiangxi University of Science and Technology, Ganzhou 341000, China

Keywords:: artificial bee colony algorithm back-propagation neural network chaotic system fundamental heart sound classification

Abstract:: For solving the problems of back-propagation (BP) neural network such as highly relying on initial weights, slow convergence and easily falling into local extremum, and the weak development capability and poor local search ability of standard artificial bee colony (ABC) algorithm, a classification method based on improved ABC algorithm is proposed to optimize BP neural network. The adaptive and global optimal strategies are introduced to improve the global search and probability selection algorithm of honey sources in ABC algorithm, and the optimal solution of the current iteration is used to improve the development capability. In addition, chaotic systems are used to generate initial populations, thus enhancing the global convergence of ABC algorithm. Finally, the proposed algorithm is applied in fundamental heart sound recognition. The experimental results show that the classification accuracy of the proposed algorithm is superior to that of the classical classification algorithms. Based on Mel-scale frequency cepstral coefficients, the proposed algorithm can achieve a classification accuracy rate above 94%.