Evolutionary synthesis of micromachines using supervisory multiobjective interactive evolutionary computation

Authors:
Raffi Kamalian;Ying Zhang;Hideyuki Takagi;Alice M. Agogino
Affiliations:
Faculty of Design, Kyushu University, Fukuoka, Japan;BEST Lab, University of California, Berkeley, CA;Faculty of Design, Kyushu University, Fukuoka, Japan;BEST Lab, University of California, Berkeley, CA
Venue:
ICMLC'05 Proceedings of the 4th international conference on Advances in Machine Learning and Cybernetics
Year:
2005

Citing 3
Cited 1

Simulated annealing: theory and applications

Simulated annealing: theory and applications
Genetic Algorithms in Search, Optimization and Machine Learning

Genetic Algorithms in Search, Optimization and Machine Learning
Formal engineering design synthesis

Formal engineering design synthesis

Interactive Multiobjective Evolutionary Algorithms

Multiobjective Optimization

Quantified Score

Hi-index	0.00

Visualization

Abstract

A novel method of Interactive Evolutionary Computation (IEC) for the design of microelectromechanical systems (MEMS) is presented. As the main limitation of IEC is human fatigue, an alternate implementation that requires a reduced amount of human interaction is proposed. The method is applied to a multi-objective genetic algorithm, with the human in a supervisory role, providing evaluation only every nth-generation. Human interaction is applied to the evolution process by means of Pareto-rank shifting for the fitness calculation used in selection. The results of a test on 13 users shows that this IEC method can produce statistically significant better MEMS resonators than fully automated non-interactive evolutionary approaches.