Document Type
Article
Publication Date
2015
Publication Title
IEEE Transactions on Systems, Man, and Cybernetics: Systems
Abstract
This paper introduces a Markov model for evolutionary algorithms (EAs) that is based on interactions among individuals in the population. This interactive Markov model has the potential to provide tractable models for optimization problems of realistic size. We propose two simple discrete optimization search strategies with population-proportion-based selection and a modified mutation operator. The probability of selection is linearly proportional to the number of individuals at each point of the search space. The mutation operator randomly modifies an entire individual rather than a single decision variable. We exactly model these optimization search strategies with interactive Markov models. We present simulation results to confirm the interactive Markov model theory. We show that genetic algorithms and biogeography-based optimization perform better with the addition of population-proportion-based selection on a set of real-world benchmarks. We note that many other EAs, both new and old, might be able to be improved with this addition, or modeled with this method.
Repository Citation
Ma, Haiping; Simon, Daniel J.; Fei, Minrui; and Mo, Hongwei, "Interactive Markov Models of Evolutionary Algorithms" (2015). Electrical and Computer Engineering Faculty Publications. 390.
https://engagedscholarship.csuohio.edu/enece_facpub/390
Original Citation
H. Ma, D. Simon, M. Fei and H. Mo, "Interactive Markov Models of Optimization Search Strategies," IEEE Transactions on Systems, Man, and Cybernetics: Systems, vol. PP, pp. 1-18, 2015.
DOI
10.1109/TSMC.2015.2507588
Version
Postprint
Publisher's Statement
(c) 2016 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission. See http://www.ieee.org/publications_standards/publications/rights/index.html for more information. This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication.
