.png){kind=icon}
.png){kind=icon}
Return
Evolutionary programming with a simulated-conformist mutation strategy
.png){kind=icon}
PRE
AI
DOI：10.1007/s00500-016-2365-x.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Evolutionary programming has been widely implemented as a continuous optimization algorithm. Prior studies have come to a bottleneck because most of the evolutionary programming algorithms are unable to robustly solve different types of optimization problems. We argue that such a bottleneck results from the existing mutation strategies' making little use of the population information. Inspired by a psychological model which describes how a person optimizes his/her social activities by conformity behavior, this study proposes a variation vector of the mutation to simulate the conformity behavior with behavior-reference, majority-impact, and distinctive-impact factors. These factors, respectively, correspond with three types of population information for each mutated individual: heuristic information, optimal gradient, and population diversity. We use the proposed vector to design an improved evolutionary programming with a simulated-conformist mutation strategy. The results show that the population information produced by the three factors enhance the robustness of the performance of evolutionary programming in solving both uni- and multimodal functions. The finding is verified by empirical analyses of two sets of benchmark functions proposed in 1998 and 2013. The numerical results indicate that the proposed algorithm performs significantly better on average than the existing EPs and some other algorithms with similar strategies.
Keywords:
Continuous optimization
Evolutionary programming
Simulated-conformist mutation
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
2.5
Papers:
1.0W
Citations:
2.1W