Journal Article10.1007/S10489-018-1255-6
Differential evolution algorithm directed by individual difference information between generations and current individual information
Li Tian,Zhichao Li,Xuefeng Yan +2 more
15
TL;DR: DI-DE is compared with 28 excellent algorithms on three well-known benchmark sets of low dimensionality and one large scale benchmarks set (CEC LSGO 2013) and experimental results demonstrate the competitive performance of DI-DE.
read more
Abstract: In differential evolution (DE) algorithm, numerous adaptive methods based on superior individual information in the current generation have been proposed. However, the individual difference between two generations, which represents whether the corresponding parameters and mutation strategy are suitable for this individual, has not been utilized. Considering that different (superior or inferior) individuals need different parameters and strategies, a new DE variant (DI-DE), which is directed by individual difference information between generations and individual information in the current generation to obtain optimal control parameters and an offspring generation strategy, is proposed. In DI-DE, every individual possesses its own parameters and strategy. First, individuals are distinguished as superior or inferior depending on their fitness values in the current generation. The parameters are tuned in accordance with the information on superior individuals. In addition, the conception of potential individuals is proposed for superior and inferior individuals on the basis of the individual difference information between two generations. By learning from the current and past information, the suitable mutation strategy is adjusted for superior and inferior individuals on the basis of the experience of potential individuals to help them become potential individuals in the next generation. DI-DE is compared with 28 excellent algorithms on three well-known benchmark sets (CEC2005, CEC2013, and CEC2014) of low dimensionality and one large scale benchmarks set (CEC LSGO 2013). Experimental results demonstrate the competitive performance of DI-DE. Finally, DI-DE is applied to optimize the operation conditions of PX oxidation process.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
A fitness-based adaptive differential evolution algorithm
Xuewen Xia,Ling Gui,Yinglong Zhang,Xing Xu,Fei Yu,Hongrun Wu,Bo Wei,Guoliang He,Yuanxiang Li,Yuanxiang Li,Kangshun Li,Kangshun Li +11 more
TL;DR: The effectiveness and efficiency of the newly introduced adaptive strategies are further confirmed by a set of experiments and the comprehensive performance of FADE is extensively evaluated by comparisons between it and other eight state-of-art DE variants based on CEC2013 and CEC2017 test suites.
81
A population state evaluation-based improvement framework for differential evolution
TL;DR: Zhang et al. as mentioned in this paper proposed a population state evaluation (PSE)-based improvement framework that can be freely embedded into various existing DE variants and population-based metaheuristic algorithms.
57
Robust controllability and stabilization of switched Boolean control networks subject to multi-bit function perturbations
Xinrong Yang,Haitao Li +1 more
TL;DR: In this paper , a multi-bit perturbed controllability matrix method was proposed to solve the problem of robust control of switched Boolean control networks (SBCNs) with multi bit function perturbations.
34
An efficient differential evolution with fitness-based dynamic mutation strategy and control parameters
Shubham Gupta,Rong Su +1 more
TL;DR: In this paper , an efficient framework of the differential evolution (DE) algorithm named EFDE is proposed with a novel fitness-based dynamic mutation strategy and control parameters, which avoids the burden of selecting appropriate mutation strategy for a given optimization problem.
34
NFDDE: A novelty-hybrid-fitness driving differential evolution algorithm
Xuewen Xia,Lei Tong,Yinglong Zhang,Xing Xu,Honghe Yang,Ling Gui,Yuanxiang Li,Yuanxiang Li,Kangshun Li,Kangshun Li +9 more
TL;DR: In the new proposed DE, named as NFDDE, both fitness and novelty values of individuals are considered when choosing individuals to create mutant vectors, and some individuals with lower novelty are deleted when the population has converged to a certain extent.
31
References
Differential Evolution – A Simple and Efficient Heuristic for Global Optimization over Continuous Spaces
Rainer Storn,Kenneth Price +1 more
TL;DR: In this article, a new heuristic approach for minimizing possibly nonlinear and non-differentiable continuous space functions is presented, which requires few control variables, is robust, easy to use, and lends itself very well to parallel computation.
Individual Comparisons by Ranking Methods
TL;DR: The comparison of two treatments generally falls into one of the following two categories: (a) a number of replications for each of the two treatments, which are unpaired, or (b) we may have a series of paired comparisons, some of which may be positive and some negative as mentioned in this paper.
14.5K
On a Test of Whether one of Two Random Variables is Stochastically Larger than the Other
Henry B. Mann,D. R. Whitney +1 more
TL;DR: In this paper, the authors show that the limit distribution is normal if n, n$ go to infinity in any arbitrary manner, where n = m = 8 and n = n = 8.
No free lunch theorems for optimization
TL;DR: A framework is developed to explore the connection between effective optimization algorithms and the problems they are solving and a number of "no free lunch" (NFL) theorems are presented which establish that for any algorithm, any elevated performance over one class of problems is offset by performance over another class.
The Use of Ranks to Avoid the Assumption of Normality Implicit in the Analysis of Variance
TL;DR: The use of ranks to avoid the assumption of normality implicit in the analysis of variance has been studied in this article, where the use of rank to avoid normality is discussed.