Is Parameters Quantification in Genetic Algorithm Important, How to do it?

Pandey, Hari (2017) Is Parameters Quantification in Genetic Algorithm Important, How to do it? IAES International Journal of Artificial Intelligence (IJ-AI), 6 (3). pp. 112-123. ISSN 2252-8938 DOI https://doi.org/10.11591/ij-ai.v6.i3

[img]
Preview
Text
Paper1111.pdf - Published Version
Available under License Creative Commons Attribution.

Download (468kB) | Preview

Abstract

The term “appropriate parameters” signifies the correct choice of values has considerable effect on the performance that directs the search process towards the global optima. The performance typically is measured considering both quality of the results obtained and time requires in finding them. A genetic algorithm is a search and optimization technique, whose performance largely depends on various factors – if not tuned appropriately, difficult to get global optima. This paper describes the applicability of orthogonal array and Taguchi approach in tuning the genetic algorithm parameters. The domain of inquiry is grammatical inference has a wide range of applications. The optimal conditions were obtained corresponding to performance and the quality of results with reduced cost and variability. The primary objective of conducting this study is to identify the appropriate parameter setting by which overall performance and quality of results can be enhanced. In addition, a systematic discussion presented will be helpful for researchers in conducting parameters quantification for other algorithms

Item Type: Article
Uncontrolled Keywords: Context free grammar, Evolutionary computation, Genetic algorithm Grammar induction, Taguchi design.
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions: Computing and Information Systems
Date Deposited: 31 Oct 2018 13:00
URI: http://repository.edgehill.ac.uk/id/eprint/10805

Archive staff only

Item control page Item control page