Abstract Population based incremental learning (PBIL) algorithm has the advantage of simple execution process, quick and accurate solutions to problem. Aiming at the domino phenomenon of convergence from the highest position to the lowest position of binary coding in PBIL algorithm, a zooming algorithm is employed to improve the search efficiency and solution accuracy. The simulation results based on Benchmark functions of different dimensions verify that the proposed hybrid algorithm has the advantage of global convergence, high solution precision and search efficiency.
[1] Balujia S. Population-Based Incremental Learning: A Method for Integrating Genetic Algorithm Search Based Function Optimization and Competitive Learning. Technical Report, CMU-CS-94-163, Pittsburgh, USA: Carnegie Mellon University. Computer Science Department,1994 [2] Rastegar R, Hariri A, Mazoochi M. A Convergence Proof for the Population Based Incremental Learning Algorithm // Proc of the 17th IEEE International Conference on Tools with Artificial Intelligence. Hongkong, China, 2005: 387-391 [3] Zhang Qingbin, Wu Tihua, Liu Bo. A Population-Based Incremental Learning Algorithm with Elitist Strategy // Proc of the 3rd International Conference on Natural Computation. Haikou, China, 2007, Ⅱ: 583-587 [4] Zhou Shude, Sun Zengqi. PBIL Ensemble: Many Better Than One // Proc of the ICSC Congress on Computational Intelligence Methods and Applications. Istanbul, Turkey, 2005: 254-259 [5] Ghebreab S, Jaffe C C, Smeulders A W M. Population Based Incremental Interactive Concept Learning for Image Retrieval by Stochastic String Segmentations. IEEE Trans on Medical Imaging, 2004, 23(6): 676-689 [6] Gallagher M, Frean M. Population-Based Continuous Optimization Probabilistic Modeling and Mean Shift. Evolutionary Computation, 2005, 13(1): 29-42 [7] Yang S Y, Ho S L, Ni G Z, et al. A New Implementation of Population Based Incremental Learning Method for Optimizations in Electromagnetic. IEEE Trans on Magnetics, 2007, 43(4): 1601-1604 [8] Rudnick W M. Genetic Algorithms and Fitness Variance with an Application to Automated Design of Artificial Neural Networks. Ph.D Dissertation. Beaverton, USA: Oregon Graduate Institute of Science and Technology. Klamath Falls, 1992 [9] Kown Y D, Kown H W, Cho S W, et al. Convergence Rate of the Successive Zooming Genetic Algorithm Using Optimal Control Parameters. WSEAS Trans on Computers, 2006, 5(6):1200-1207 [10] Liu Shousheng, Yu Shenglin, Ding Yong, et al. Zooming Genetic Algorithm. Control and Decision, 2002, 17(Z1): 731-734 (in Chinese) (刘守生,于盛林,丁 勇,等.一种变焦遗传算法.控制与决策, 2002, 17(Z1): 731-734) [11] Liu Fucai, Pan Jianghua, Lou Liping, et al. An Improved Zooming Genetic Algorithm. Information and Control, 2004, 33(1): 82-84 (in Chinese) (刘福才,潘江华,路立平,等.一种改进的变焦遗传算法.信息与控制, 2004, 33(1): 82-84) [12] Wang Ling. Intelligent Optimization Algorithms with Applications. Beijing, China: Tsinghua University Press, 2004 (in Chinese) (王 凌.智能优化算法及其应用.北京:清华大学出版社, 2004)
2009, Vol. 22 
