Constructing Optimal Experimental Designs by Meta-heuristic Algorithms

• Main Authors: Ming-Sian Wu, 吳明賢
• Other Authors: Wei-Chung Wang
• Format: Others
• Language: en_US
• Published: 2012
• Online Access: http://ndltd.ncl.edu.tw/handle/22376477568894902849

碩士 === 國立臺灣大學 === 數學研究所 === 100 === Metaheuristic algorithms are widely used in solving many optimal experimental design problems. In this paper, we demonstrate the metaheuristic algorithms to construct four optimal experimental designs. First, we proposed the four examples for optimization design problems and presented the outlines of algorithm for comparison such as bat-inspired algorithm, cuckoo search, genetic algorithm, simulated annealing, artificial bee colony algorithm, firefly algorithm, harmony search and particle swarm optimization. After stated the algorithms, the numerical results of the comparison for the four examples are presented and discussed further. Finally, the conclusion suggested that cuckoo search and particle swarm optimization have the best performance in contrast with the other algorithms from the numerical results. The conclusions are drawn from the specific numerical studies and may not apply to other examples.