Knowledge-Inducing interactive genetic algorithms based on multi-agent

Authors:
Yi-nan Guo;Jian Cheng;Dun-wei Gong;Ding-quan Yang
Affiliations:
School of Information and Electronic Engineering, China University of Mining and Technology, Xuzhou, China;School of Information and Electronic Engineering, China University of Mining and Technology, Xuzhou, China;School of Information and Electronic Engineering, China University of Mining and Technology, Xuzhou, China;School of Information and Electronic Engineering, China University of Mining and Technology, Xuzhou, China
Venue:
ICNC'06 Proceedings of the Second international conference on Advances in Natural Computation - Volume Part I
Year:
2006

Citing 4
Cited 3

Multiobjective Satisfaction within an Interactive Evolutionary Design Environment

Evolutionary Computation
Knowledge-based fast evaluation for evolutionary learning

IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews
A multiagent genetic algorithm for global numerical optimization

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
A multiagent evolutionary algorithm for constraint satisfaction problems

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics

Path planning method for robots in complex ground environment based on cultural algorithm

Proceedings of the first ACM/SIGEVO Summit on Genetic and Evolutionary Computation
Cooperative interactive cultural algorithms adopting knowledge migration

Proceedings of the first ACM/SIGEVO Summit on Genetic and Evolutionary Computation
Adaptive evaluation strategy based on surrogate model

HCI'07 Proceedings of the 12th international conference on Human-computer interaction: interaction design and usability

Quantified Score

Hi-index	0.00

Visualization

Abstract

Interactive genetic algorithms lack a common model to effectively integrate different assistant evolution strategies including knowledge-based methods and fitness assignment strategies.Aiming at the problems,knowledge-based interactive genetic algorithm based on multi-agent is put forward in the paper combined with the flexibility of multi-agent systems.Five kinds of agents are abstracted based on decomposed-integral strategy of MAS.A novel implicit knowledge model and corresponding inducing strategy are proposed and realized by knowledge-inducing agent.A novel substitution strategy for evaluating fitness by an online model instead of human is proposed and implemented in fitness-estimation agent.State-switch conditions of above agents are given using agent-oriented programming. Taking fashion design system as a testing platform, the rationality of the model and the effective of assistant evolution strategies proposed in the paper are validated. Simulation results indicate this algorithm can effectively alleviate users' fatigue and improve the speed of convergence.