ICHEA – a constraint guided search for improving evolutionary algorithms

Sharma, Anuraganand and Sharma, Dharmendra P. (2012) ICHEA – a constraint guided search for improving evolutionary algorithms. [Conference Proceedings]

PDF - Published Version Restricted to Registered users only Download (242kB) | Request a copy

Abstract

Many science and engineering applications require finding solutions to optimization problems by satisfying a set of constraints. These problems are typically NP-complete and can be formalized as constraint satisfaction problems (CSPs). Evolutionary algorithms (EAs) are good solvers for optimization problems ubiquitous in various problem domains. EAs have also been used to solve CSPs, however traditional EAs are ‘blind’ to constraints as they do not exploit information from the constraints in search for solutions. In this paper, a variation of EA is proposed where information is extracted from the constraints and exploited in search. The proposed model (ICHEA for Intelligent Constraint Handling Evolutionary Algorithm) improves on efficiency and is independent of problem characteristics. This paper presents ICHEA and its results from solving continuous CSPs. The results are significantly better than results from other existing approaches and the model shows strong potential. The scope is to finding at least one solution that satisfies all the constraints rather than optimizing the solutions.

Item Type:	Conference Proceedings
Additional Information:	Published in Neural Information Processing: ICONIP 2012
Uncontrolled Keywords:	computational neuroscience - fuzzy inference system - intrusion detection - nonlinear systems - self-organizing maps
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science Q Science > QA Mathematics > QA76 Computer software
Divisions:	Faculty of Science, Technology and Environment (FSTE) > School of Computing, Information and Mathematical Sciences
Depositing User:	Anuraganand Sharma
Date Deposited:	04 Oct 2013 01:16
Last Modified:	08 Jul 2020 03:11
URI:	https://repository.usp.ac.fj/id/eprint/6847

Actions (login required)

View Item