Research Area:  Metaheuristic Computing
Fruit fly optimization algorithm (FOA) is a kind of swarm intelligence optimization algorithm, which has been widely applied in science and engineering fields. The aim of this study is to design an improved FOA, namely evolution FOA (EFOA), which can overcome some shortcomings of basic FOA, including difficulty in local optimization, slow convergence speed, and lack of robustness. EFOA applies a few new strategies which adaptively control the search steps and swarm numbers of the fruit flies. The evolution mechanism used in EFOA can preserve dominant swarms and remove inferior swarms. Comprehensive comparison experiments are performed to compare EFOA with other swarm intelligence algorithms through 14 benchmark functions and a constrained engineering problem. Experimental results suggest that EFOA performs well both in global search ability and in robustness, and it can improve convergence speed.
Keywords:  
Fruit fly optimization algorithm
swarm intelligence
engineering field
slow convergence speed
lack of robustness
global search ability
Author(s) Name:  Xuan Yang, Weide Li, Lili Su, Yaling Wang & Ailing Yang
Journal name:  Neural Computing and Applications
Conferrence name:  
Publisher name:  Springer
DOI:  10.1007/s00521-019-04512-2
Volume Information:  32, pages 9897–9914
Paper Link:   https://link.springer.com/article/10.1007/s00521-019-04512-2