Vol.26, No.3, 2020, pp.501-512, doi:10.32604/iasc.2020.013926
OPEN ACCESS
ARTICLE
Niche Genetic Algorithm for Solving Multiplicity Problems in Genetic Association Studies
  • Fu-I Chou1, Wen-Hsien Ho2,3, Chiu-Hung Chen4,*
1 Department of Automation Engineering, National Formosa University, Taiwan, R.O.C.
2 Department of Healthcare Administration and Medical Informatics, Kaohsiung Medical University, Kaohsiung, Taiwan, R.O.C.
3 Department of Medical Research, Kaohsiung Medical University Hospital, Kaohsiung, Kaohsiung, Taiwan, R.O.C.
4 Department of Mechanical and Computer-Aided Engineering, Feng Chia University, No. 100 Wenhwa Rd., Seatwen, Taichung, Taiwan 407, R.O.C.
* Corresponding Author: Chiu-Hung Chen, cchung688@gmail.com; chiuhchen@fcu.edu.tw
Abstract
This paper proposes a novel genetic algorithm (GA) that embeds a niche competition strategy (NCS) in the evolutionary flow to solve the combinational optimization problems that involve multiple loci in the search space. Unlike other niche-information based algorithms, the proposed NCSGA does not need prior knowledge to design niche parameters in the niching phase. To verify the solution capability of the new method, benchmark studies on both the travelling salesman problem (TSP) and the airline recovery scheduling problem were first made. Then, the proposed method was used to solve single nucleotide polymorphism (SNP) barcodes generation problems in a genetic association study. Experiments showed that the proposed NCS-based solver substantially improves solution quality by maintaining multiple optima.
Keywords
genetic algorithm, combinational optimization, travelling salesman problem, genetic association, single nucleotide polymorphism.
Cite This Article
Chou, F., Ho, W., Chen, C. (2020). Niche Genetic Algorithm for Solving Multiplicity Problems in Genetic Association Studies. Intelligent Automation & Soft Computing, 26(3), 501–512.
This work is licensed under a Creative Commons Attribution 4.0 International License , which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.