An improved fruit fly optimization algorithm based on knowledge memory

作者：Xuming Han; Qiaoming Liu; Limin Wang; Huimin Lu; Liyuan Zhou; Junhua Wang

来源：International Journal of Computers and Applications, 2020, 42(6): 558-568.

DOI：10.1080/1206212X.2018.1479349

• Fly fruit optimization algorithm
• Knowledge memory
• Function optimization

An improved fruit fly optimization algorithm based on knowledge memory (KM-FOA) is proposed for solving continuous functions problems. It is featured with mechanisms devised for solving the concerned problems: (1) Direction vectors, a novel method, is defined as knowledge. Each fruit fly needs to learn and memorize the direction with the most obvious concentration changes in the search space iteratively; (2) we embedded the direction vectors to guide the procedure of choosing the food. Fruit fly swarm can optimize the search roads on the basis of knowledge. And this approach achieves the goal of locating the global optimal space during early evolution. Furthermore, continuous benchmark functions are used to verify the performance of KM-FOA, and numerical results show that the proposed algorithm not only speeds up the convergence but also has a better convergence precision and better balance searching between global and local. The comparisons among KM-FOA, other improved FOAs and other evolution algorithms also demonstrate that KM-FOA performs much better in solving multi-dimensional function optimization problems.

• 出版日期2020