Evolutionary Multiobjective Optimization Based Multimodal Optimization: Fitness Landscape Approximation and Peak Detection

Research output: Contribution to journalArticle

Standard

Harvard

APA

Vancouver

Author

Bibtex

@article{04de6a3bc5714e95a540764188a41edf,
title = "Evolutionary Multiobjective Optimization Based Multimodal Optimization: Fitness Landscape Approximation and Peak Detection",
abstract = "Recently, by taking advantage of evolutionary multiobjective optimization techniques in diversity preservation, the means of multiobjectivization has attracted increasing interest in the studies of multimodal optimization. While most existing work of multiobjectivization aims to find all optimal solutions simultaneously, in this paper, we propose to approximate multimodal fitness landscapes via multiobjectivization, thus providing an estimation of potential optimal areas. To begin with, a multimodal optimization problem is transformed into a multiobjective optimization problem by adding an adaptive diversity indicator as the second optimization objective, and an approximate fitness landscape is obtained via optimization of the transformed multiobjective optimization problem using a multiobjective evolutionary algorithm. Then, on the basis of the approximate fitness landscape, an adaptive peak detection method is proposed to find peaks where optimal solutions may exist. Finally, local search is performed inside the detected peaks on the approximate fitness landscape. To assess the performance of the proposed algorithm, extensive experiments are conducted on 20 multimodal test functions, in comparison with three state-of-the-art algorithms for multimodal optimization. Experimental results demonstrate that the proposed algorithm not only shows promising performance in benchmark comparisons, but also has good potential in assisting preference based decision-making in multimodal optimization.",
keywords = "multimodal optimization , multiobjective optimization , niching, fitness landscape approximation , peak detection , decision-making , preference, multiobjectivization",
author = "Ran Cheng and Miqing Li and Ke Li and Xin Yao",
year = "2018",
month = "10",
doi = "10.1109/TEVC.2017.2744328",
language = "English",
volume = "22",
pages = "692 -- 706",
journal = "IEEE Transactions on Evolutionary Computation",
issn = "1089-778X",
publisher = "Institute of Electrical and Electronics Engineers (IEEE)",
number = "5",

}

RIS

TY - JOUR

T1 - Evolutionary Multiobjective Optimization Based Multimodal Optimization: Fitness Landscape Approximation and Peak Detection

AU - Cheng, Ran

AU - Li, Miqing

AU - Li, Ke

AU - Yao, Xin

PY - 2018/10

Y1 - 2018/10

N2 - Recently, by taking advantage of evolutionary multiobjective optimization techniques in diversity preservation, the means of multiobjectivization has attracted increasing interest in the studies of multimodal optimization. While most existing work of multiobjectivization aims to find all optimal solutions simultaneously, in this paper, we propose to approximate multimodal fitness landscapes via multiobjectivization, thus providing an estimation of potential optimal areas. To begin with, a multimodal optimization problem is transformed into a multiobjective optimization problem by adding an adaptive diversity indicator as the second optimization objective, and an approximate fitness landscape is obtained via optimization of the transformed multiobjective optimization problem using a multiobjective evolutionary algorithm. Then, on the basis of the approximate fitness landscape, an adaptive peak detection method is proposed to find peaks where optimal solutions may exist. Finally, local search is performed inside the detected peaks on the approximate fitness landscape. To assess the performance of the proposed algorithm, extensive experiments are conducted on 20 multimodal test functions, in comparison with three state-of-the-art algorithms for multimodal optimization. Experimental results demonstrate that the proposed algorithm not only shows promising performance in benchmark comparisons, but also has good potential in assisting preference based decision-making in multimodal optimization.

AB - Recently, by taking advantage of evolutionary multiobjective optimization techniques in diversity preservation, the means of multiobjectivization has attracted increasing interest in the studies of multimodal optimization. While most existing work of multiobjectivization aims to find all optimal solutions simultaneously, in this paper, we propose to approximate multimodal fitness landscapes via multiobjectivization, thus providing an estimation of potential optimal areas. To begin with, a multimodal optimization problem is transformed into a multiobjective optimization problem by adding an adaptive diversity indicator as the second optimization objective, and an approximate fitness landscape is obtained via optimization of the transformed multiobjective optimization problem using a multiobjective evolutionary algorithm. Then, on the basis of the approximate fitness landscape, an adaptive peak detection method is proposed to find peaks where optimal solutions may exist. Finally, local search is performed inside the detected peaks on the approximate fitness landscape. To assess the performance of the proposed algorithm, extensive experiments are conducted on 20 multimodal test functions, in comparison with three state-of-the-art algorithms for multimodal optimization. Experimental results demonstrate that the proposed algorithm not only shows promising performance in benchmark comparisons, but also has good potential in assisting preference based decision-making in multimodal optimization.

KW - multimodal optimization

KW - multiobjective optimization

KW - niching

KW - fitness landscape approximation

KW - peak detection

KW - decision-making

KW - preference

KW - multiobjectivization

U2 - 10.1109/TEVC.2017.2744328

DO - 10.1109/TEVC.2017.2744328

M3 - Article

VL - 22

SP - 692

EP - 706

JO - IEEE Transactions on Evolutionary Computation

JF - IEEE Transactions on Evolutionary Computation

SN - 1089-778X

IS - 5

ER -