Search |  Contact |  SRI Home Do not follow this link, or your host will be blocked from this site. This is a spider trap. Do not follow this link, or your host will be blocked from this site. This is a spider trap. Do not follow this link, or your host will be blocked from this site. This is a spider trap.A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A ASRI International.  333 Ravenswood Avenue.  Menlo Park, CA 94025-3493. SRI International is a nonprofit corporation.

AIC Seminar Series

Evolutionary Synthesis of Micromachines

Raffi KamalianKyushu University, Japan

Notice:  hosted by Eric Yeh

Date:  2005-10-14 at 11:00

Location:  EJ228  (Directions)

   Abstract

Interactive evolutionary computation (IEC) is an optimization method combining human evaluation with evolutionary based optimization such as Genetic Algorithms (GAs). IEC uses human subjective evaluation rather than a conventional numerical computation to determine fitness. Human evaluation is well suited for design or optimization problems where the fitness function can not be computed directly or involves human sensory or aesthetic judgement. IEC has been applied to the fields of signal processing (for example image filtering, hearing aid tuning) and aesthetic design (for example interior layout design, graphic design and even the blending of coffee). A major development in the field of IEC has been to apply this approach to single and multi-objective optimization and synthesis problems as a means of overcoming non-simulatable performance objectives or embedding expert domain knowledge into the evolution process. Our research in the evolutionary sythesis of Micromachines using multi-objective GA. Micromachines, also known as Microelectromechanical Systems (MEMS) is a multi-domain discipline that includes inertial, chemical, biological sensors and optical and RF communication and display optoelectronics. Our research is focused on the design of inertial sensors such as micro accelerometers and gyroscopes - a multiobjective synthesis problem. The incorporation of IEC has allowed us to overcome limitations in the simulation environment and enabled MEMS experts to embed design experience and knowledge to produce designs better suited to the real world environment than output from conventional non-interactive GA approaches. Past research on IEC, MEMS synthesis and Intercative MEMS Synthesis will be covered as well as ongoing research on the use of AI techniques such as Neural Networks to augment IEC.

   Bio for Raffi Kamalian

Raffi Kamalian is a researcher in the Faculty of Design at Kyushu University in Western Japan. He holds a Postdoctoral Fellowship for Foreign Researchers hosted by the Japanese Society for the Promotion of Science. He has a Doctorate Degree from UC Berkeley in Mechanical Engineering with an emphasis in Machine Design and MEMS (Micro Electromechanical Systems, also known as Micromachines). As a researcher in the Berkeley Expert Systems Lab under Professor Alice Agogino, his thesis research focused on the application of evolutionary synthesis algorithms such as Multiobjective Genetic Algorithms, Simulated Annealing and Human Interactive Evolutionary Computation to the design of MEMS sensors.

   Note for Visitors to SRI

Please arrive at least 10 minutes early as you will need to sign in by following instructions by the lobby phone at Building E. SRI is located at 333 Ravenswood Avenue in Menlo Park. Visitors may park in the parking lots off Fourth Street. Detailed directions to SRI, as well as maps, are available from the Visiting AIC web page. There are two entrances to SRI International located on Ravenswood Ave. Please check the Builing E entrance signage.

SRI International
©2014 SRI International 333 Ravenswood Avenue, Menlo Park, CA 94025-3493
SRI International is an independent, nonprofit corporation. Privacy policy