Paper Info
Title
Evolutionary synthesis of micromachines using supervisory multiobjective interactive evolutionary computation
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.
Year
DOI
Venue
2005
10.1007/11739685_45
ICMLC
Keywords
Field
DocType
iec method,novel method,evolutionary synthesis,main limitation,fitness calculation,evolution process,mems resonator,interactive evolutionary computation,alternate implementation,human fatigue,multiobjective interactive evolutionary computation,human interaction,statistical significance
Information system,Interactive evolutionary computation,Modern evolutionary synthesis,Microelectromechanical systems,Evolutionary algorithm,Computer science,Control engineering,Human interaction,Artificial intelligence,Precision engineering,Genetic algorithm,Machine learning
Conference
Volume
ISSN
ISBN
3930
0302-9743
3-540-33584-6
Citations 
PageRank 
References 
5
0.56
2
Authors
4
Name
Order
Citations
PageRank
Raffi Kamalian1202.16
Ying Zhang23811.41
Hideyuki Takagi31397190.33
Alice M. Agogino428881.04