期刊名称:Journal of Theoretical and Applied Information Technology
印刷版ISSN:1992-8645
电子版ISSN:1817-3195
出版年度:2013
卷号:51
期号:1
出版社:Journal of Theoretical and Applied
摘要:An improved particle swarm optimization algorithm, which combines the idea of simulated annealing algorithm and opposition-based learning strategy, is presented for NP-hard protein structure prediction based on AB model. Flying grain is used to control the neighborhood structure of particle, so particle can search the global optimum in solution space more finely. An opposition-based learning is used to keep the diversity of swarm and improve the algorithm’s ability to escape from local optima. Furthermore, the Metropolis criterion of simulated annealing algorithm is used to balance the exploitation and exploration ability. Simulation results show that those strategies can improve the performance of the proposed algorithm effectively.
关键词:Particle Swarm Optimization; AB Model; Protein Structure Prediction; Simulated Annealing Algorithm; Opposition-Based Learning; Flying Grain