A prediction-based adaptive grouping differential evolution algorithm for constrained numerical optimization

Kong, Xiangyong; Ouyang, Haibin; Piao, Xiaoxue

doi:10.1007/s00500-013-1090-y

Cited by 11 publications

(4 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Later research on optimal DE parameter control [59], [60] led to devise robust self-adapting schemes, such as those presented in [61] and [62]. Furthermore, specific mutation operators were introduced in [63], [64]. Also, DE was combined with (adaptive) penalty functions in [65], [66], Lagrangian methods for handling equality constraints in [67], or even ensembles of constraint handling techniques [68].…”

Section: B Methods Based On Differential Evolutionmentioning

confidence: 99%

Memetic Viability Evolution for Constrained Optimization

Maesani

Iacca

Floreano

2016

IEEE Trans. Evol. Computat.

View full text Add to dashboard Cite

The performance of evolutionary algorithms can be heavily undermined when constraints limit the feasible areas of the search space. For instance, while Covariance Matrix Adaptation Evolution Strategy is one of the most efficient algorithms for unconstrained optimization problems, it cannot be readily applied to constrained ones. Here, we used concepts from Memetic Computing, i.e. the harmonious combination of multiple units of algorithmic information, and Viability Evolution, an alternative abstraction of artificial evolution, to devise a novel approach for solving optimization problems with inequality constraints. Viability Evolution emphasizes elimination of solutions not satisfying viability criteria, defined as boundaries on objectives and constraints. These boundaries are adapted during the search to drive a population of local search units, based on Covariance Matrix Adaptation Evolution Strategy, towards feasible regions. These units can be recombined by means of Differential Evolution operators. Of crucial importance for the performance of our method, an adaptive scheduler toggles between exploitation and exploration by selecting to advance one of the local search units and/or recombine them. The proposed algorithm can outperform several state-of-the-art methods on a diverse set of benchmark and engineering problems, both for quality of solutions and computational resources needed.

show abstract

Section: B Methods Based On Differential Evolutionmentioning

confidence: 99%

Memetic Viability Evolution for Constrained Optimization

Maesani

Iacca

Floreano

2016

IEEE Trans. Evol. Computat.

View full text Add to dashboard Cite

show abstract

“…A number of EMOAs have been proposed for finding a set of solutions to approximate the PF in a single run (Deb 2001;Miettinen 1999). They can be roughly divided into three types: the first ones are the algorithms based on domination fitness assignment (Kong et al 2013;Hisao et al 2003;Lu and Yen 2003). NSGA-II (Deb et al 2002) and SPEA-II (Eckart et al 2001) are among the best represented methods; the second ones are the algorithms based on objectives fitness assignment, such as the weighted sum method, Tchebycheff approach (Liu et al 2009;Li and Zhang 2009), and MOEA/D (Zhang and Li 2007).…”

Section: Introductionmentioning

confidence: 98%

A hybrid evolutionary multiobjective optimization algorithm with adaptive multi-fitness assignment

Liu

Tan

2014

Soft Comput

View full text Add to dashboard Cite

There are several studies on hybrid multi-operator recombination methods, while few works have been proposed in the area of combining different fitness assignment in a framework. On the other hand, it is known that fitness assignment has a marked impact on the performance of evolutionary multiobjective optimization algorithm (EMOA). In this paper, a hybrid EMOA is proposed, which divides the population into several smaller subpopulations according to their distribution in the objective space. Each subpopulation is evolved by an individual EMOA, and a hybrid performance measure estimates the performance of these EMOAs. We focus on the fitness assignment and assume that all EMOAs used in the subpopulations adopt the same recombination operator. To evaluate performance of the proposed algorithm, we compare it with MOEA/D-M2M, MOE-A/D, SMS-EMOA and NSGA-II on 16 test instances. Experimental results show that the proposed algorithm performs better than or similar to those compared EMOAs.

show abstract

“…But, an introduction of constraints into the docking problem make these algorithms have focused search with reduced amount of computations. There are many successful constrained evolutionary algorithms for solving problems with steering search (Michalewicz and Schoenauer 1996;Reid 1996;Coello and Montes 2002;Kong et al 2013;Cai et al 2013). So, the design of new perspective of the docking problem with constraints is necessary to have guided search to obtain a group of promising solutions.…”

Section: Introductionmentioning

confidence: 99%

Protein docking using constrained self-adaptive differential evolution algorithm

Sudha¹,

Baskar²,

Krishnaswamy

2019

Soft Comput

View full text Add to dashboard Cite

The objective of protein docking is to achieve a relative orientation and an optimized conformation between two proteins that results in a stable structure with the minimized potential energy. Constrained Self-adaptive Differential Evolution (Cons_SaDE) algorithm is used to find the minimum energy conformation using proposed constraints such as boundary surface complementary interactions, non-bonded inter-atomic allowed distances, and finding of interaction and non-interaction sites. With these constraints, Cons_SaDE is efficient enough to explore the promising solutions by gradually self-adapting the strategies and parameters learnt from their previous experiences. Modified sampling scheme called Rotate Only Representation is used to represent a docking conformation. GROMOS53A6 force field is used to find the potential energy. To test the performance of this algorithm, few bound and unbound complexes from Protein Data Bank (PDB) and few easy, medium and difficult complexes from Zlab benchmark4.0 are used. Buried Surface Area, Root Mean Square Deviation (RMSD) and Correlation Coefficient are some of the metrics applied to evaluate the best docked conformations. RMSD values of the best docked conformations obtained from five popular docking web servers are compared with Cons_SaDE results and nonparametric statistical tests for multiple comparisons with control method are implemented to show the performance of this algorithm. Cons_SaDE has produced good quality solutions for the most of the data sets considered.

show abstract

A prediction-based adaptive grouping differential evolution algorithm for constrained numerical optimization

Cited by 11 publications

References 46 publications

Memetic Viability Evolution for Constrained Optimization

Memetic Viability Evolution for Constrained Optimization

A hybrid evolutionary multiobjective optimization algorithm with adaptive multi-fitness assignment

Protein docking using constrained self-adaptive differential evolution algorithm

Contact Info

Product

Resources

About