本論文提出族群大小可變之人工蜂群演算法(APSABC)，隨著搜
尋結果改變族群大小提升人工蜂群演算法的搜尋能力。
群體大小可變之目的在於更有效的運用運算資源，相較固定群
體大小之人工蜂群演算法有更好的效能。利用最佳解引導與隨機個
體平均方式產生新個體。最佳解引導加強最佳解周圍的搜尋能力，
而隨機個體平均開拓其他區域搜尋，在陷入區域最佳解時能有機會
跳脫區域最佳解。
本論文採用 CEC2015 測試函數，其中包括單模態函數、多模態
函數、混合函數及合成函數。分析 APSABC 與其他 ABC 之效能，
證實本論文提出的方法具有有效的搜尋能力。

This thesis presents a novel adaptive population size of artificial bee colony algorithm (APSABC). The algorithm changes the population size to improve the search ability of the artificial bee colony algorithm.
The purpose of adaptive population size is to use computing resources more effectively, and it has better performance than the original artificial bee colony algorithm, which has fixed population size. New bees are generated using optimal solution guidance and random bee average. The best solution guides the search ability around the best solution. The random bees develop other areas and have the opportunity to jump off the local best solution.
In this study, the CEC2015 test functions, included unimodal functions, multimodal functions, hybrid functions and composition functions, are used to test the performance of APSABC and other ABC algorithms. The experiment results show that the proposed method has effective search ability than other algorithms.

致謝 I
摘要 III
ABSTRACT V
目錄 VII
圖目錄 IX
表目錄 XI
符號表 XIII
第一章 緒論 1
1-1 綜述 1
1-2 動機與目的 2
1-3 文獻與方法回顧 3
1-3-1 粒子群最佳化演算法 4
1-3-2 蟻群最佳化演算法 5
1-3-3 人工蜂群演算法 6
1-4 研究方法 7
1-5 論文架構 8
第二章 基本理論探討 11
2-1 最佳化問題 11
2-2 群智慧演算法 13
2-2-1 粒子群演算法 13
2-2-2 蟻群最佳化演算法 16
2-2-3 人工蜂群演算法 19
2-3 人工蜂群演算法之改良 22
第三章 族群大小可變之人工蜂群演算法 27
3-1 族群大小調整機制 27
3-1-1 個體增加 28
3-1-2 個體減少 28
3-2 族群大小可變之人工蜂群演算法 29
第四章 實驗結果 31
4-1 測試函數 31
4-2 實驗參數設定 33
4-3 實驗結果與比較 34
4-4 族群大小調整結果 47
4-5 實驗總結 49
第五章 結論與未來展望 51
5-1 結論 51
5-2 未來工作 51
參考文獻 53
作者簡歷 55

[1]L. C. Lai, Y. C. Chang, J. T. Jeng, G. M. Huang, W. N. Li, and Y. S. Zhang, “A PSO method for optimal design of PID controller in motion planning of a mobile robot,” in Proc. 2013 International Conference on Fuzzy Theory and Its Applications (iFUZZY), pp. 134-139, Taipei, 2013.
[2]J. Oinuma, K. Arakawa, and H. Harashima, “Evaluation of genetic algorithm for interactive evolutionary face image beautifying system,” in Proc. 2014 6th International Symposium on Communications, Control and Signal Processing (ISCCSP), pp. 594-597, Athens, 2014.
[3]R. K. Panda and B. B. Choudhury, “An Effective Path Planning of Mobile Robot Using Genetic Algorithm,” in Proc. 2015 IEEE International Conference on Computational Intelligence & Communication Technology, pp. 287-291, Ghaziabad, 2015.
[4]D. Misra, S. Deb, and S. Joardar, “Efficient design of quadrature mirror filter bank for audio signal processing using Craziness based Particle Swarm Optimization Technique,” in Proc. 2015 International Conference on Computer, Communication and Control (IC4), pp. 1-5, Indore, 2015.
[5]A. Colorni, M. Dorigo, and V. Maniezzo, “Distributed optimization by ant colonies,” in Proc. 1st European Conference on Artificial Life, pp.134-142, Paris, 1991.
[6]J. Kennedy and R. Eberhart, “Particle swarm optimization,” in Proc. 1995 IEEE International Conference on Neural Networks, pp.1942-1948 vol.4, Perth, WA, 1995.
[7]D. Karaboga, “An idea based on honeybee swarm for numerical optimization[R],” Technical Report TR06, Erciyes University, Engineering Faculty, Computer Engineering Department, 2005.
[8]S. T. Hsieh, T. Y. Sun, C. C. Liu, and S. J. Tsai, “Efficient Population Utilization Strategy for Particle Swarm Optimizer,” IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), vol. 39, no. 2, pp. 444-456, April 2009.
[9]W. N. Chen et al., “Particle Swarm Optimization With an Aging Leader and Challengers,” IEEE Transactions on Evolutionary Computation, vol. 17, no. 2, pp. 241-258, April 2013.
[10]M. Mavrovouniotis and S. Yang, “Ant colony optimization with self-adaptive evaporation rate in dynamic environments,” in Proc. 2014 IEEE Symposium on Computational Intelligence in Dynamic and Uncertain Environments (CIDUE), pp. 47-54, Orlando, FL, 2014.
[11]U. Cekmez, M. Ozsiginan, and O. K. Sahingoz, “Multi colony ant optimization for UAV path planning with obstacle avoidance,” in Proc. 2016 International Conference on Unmanned Aircraft Systems (ICUAS), pp. 47-52, Arlington, VA, 2016.
[12]Chun-Ling Lin, S. T. Hsieh, and Shih-Yuan Chiu, “Work-in-progress: Adaptive population artificial bee colony for numerical optimization,” in Proc. 2015 1st International Conference on Industrial Networks and Intelligent Systems (INISCom), pp. 168-171, Tokyo, 2015.
[13]J. Liu, Y. Zhang, and S. Bai, “An Adaptive Artifical Bee Colony Algorithms Based on Global Best Guide,” in Proc. 2017 13th International Conference on Computational Intelligence and Security (CIS), pp. 211-215, Hong Kong, 2017.
[14]S. T. Hsieh, H. W. Cheng, C. L. Lin, and T. Y. Sun, “Biologically Adaptive Artificial Bee Colony for Numerical Optimization,” in Proc. 2017 Fifth International Symposium on Computing and Networking (CANDAR), pp. 187-193, Aomori, 2017.
[15]S. T. Hsieh and C. L. Lin, “Innovative R peak detecting algorithm using enhanced artificial bee colony,” in Proc. 2018 IEEE International Conference on Applied System Invention (ICASI), pp. 570-573, Chiba, 2018.
[16]J. J. Liang, B.Y. Qu, P. N. Suganthan, and Q. Chen, “Problem Definitions and Evaluation Criteria for the CEC 2015 Competition on Learning based Real-Parameter Single Objective Optimization,” Tech. Rep. 201411A, Computational Intelligence Laboratory, Zhengzhou University, Zhengzhou China and Technical Report, Nanyang Technological University, Singapore, Nov. 2014.