KSII Transactions on Internet and Information Systems (TIIS)

Korean Society for Internet Information (한국인터넷정보학회)
권호 표지
DOI QR코드

DOI QR Code

Effect of Changing the Basis in Genetic Algorithms Using Binary Encoding

  • Kim, Yong-Hyuk (Department of Computer Science and Engineering, Kwangwoon University) ;
  • Yoon, You-Rim (School of Computer Science and Engineering, Seoul National University)
  • Published : 2008.08.25
Download PDF
⟨ Previous Next ⟩

Abstract

We examine the performance of genetic algorithms using binary encoding, with respect to a change of basis. Changing the basis can result in a change in the linkage structure inherent in the fitness function. We test three simple functions with differing linkage strengths and analyze the results. Based on an empirical analysis, we show that a better basis results in a smoother fitness landscape, hence genetic algorithms based on the new encoding method provide better performance.

Keywords

Cited by

  1. 신장 트리 기반 표현과 MAX CUT 문제로의 응용 vol.18, pp.12, 2008, https://doi.org/10.5302/j.icros.2012.18.12.1096
  2. A Mathematical Design of Genetic Operators onGLn(ℤ2) vol.2014, pp.None, 2008, https://doi.org/10.1155/2014/540936
  3. GA-optimized Support Vector Regression for an Improved Emotional State Estimation Model vol.8, pp.6, 2008, https://doi.org/10.3837/tiis.2014.06.014
  4. Linkage-Based Distance Metric in the Search Space of Genetic Algorithms vol.2015, pp.None, 2015, https://doi.org/10.1155/2015/680624
  5. An Edge-Set Representation Based on a Spanning Tree for Searching Cut Space vol.19, pp.4, 2008, https://doi.org/10.1109/tevc.2014.2338076
  6. Epistasis-Based Basis Estimation Method for Simplifying the Problem Space of an Evolutionary Search in Binary Representation vol.2019, pp.None, 2008, https://doi.org/10.1155/2019/2095167
  7. Towards a Better Basis Search through a Surrogate Model-Based Epistasis Minimization for Pseudo-Boolean Optimization vol.8, pp.8, 2008, https://doi.org/10.3390/math8081287