威尼斯娱人城官网

Title：Interactive Evolutionary Computation

Speaker： TAKAGI, Hideyuki, Professor
Time： 13：00 to 15：00, Mar 27, 2017
Place：F310, School of Mechanical Engineering
Host：Peng Zhike, Professor

Abstract: Firstly, we emphasize how human factor is important for computational intelligence and show the concept of humanized computational intelligence. Next, we show Interactive Evolutionary Computation (IEC) is one of realization approach of the humanized computational intelligence. Finally, we outline what is IEC.

Secondly, we categorize IEC applications areas into three: artistic applications, engineering applications, and others and introduces many IEC applications including creating artistic graphics, industrial design, and music, designing noise reduction filters and image enhancement filters, hearing-aid fitting and cochlear implant fitting, media database retrieval, data mining, robotics, intrusion detection system, geology, and others. Objective of this introduction is to let audience understand IEC's applicability in wide variety of areas and let them learn how to apply IEC in their areas.

Thirdly, we introduce some research for reducing the fatigue of IEC users who have to cooperate with tireless computer for long time. Some of them are improving IEC user interface, accelerating IEC search, introducing human evaluation models and combining the model evaluation and human evaluation, introducing several types of EC algorithms into IEC, and others.

Finally, we introduce unique research to use IEC as a tool for human science. IEC is a technique to optimize a target system based on human evaluation. We may obtain information of the IEC user by analyzing the target system optimized by the human as the same as reverse-engineering. Here we introduce such new approaches including research on measuring human mind, looking for unknown audio-psychophysiological knowledge, and extended IEC which optimizes a target system based on human physiological feedback. IEC tutorial paper and slides are downloadable from //www.design.kyushu-u.ac.jp/~takagi/ .

Biography:  高木英行(TAKAGI, Hideyuki) received the degrees of Bachelor and Master from Kyushu Institute of Design in 1979 and 1981, and the degree of Doctor of Engineering from Toyohashi University of Technology in 1991. He was a researcher at Panasonic Central Research labs in 1981 - 1995, and was/is Associate Professor of Kyushu Institute of Design in 1995 - 2003 and that of Kyushu University since 2003. He was a visiting researcher at UC Berkeley in 1991-1993 hosted by Prof. L. A. Zadeh.

He had worked on neuro-fuzzy systems in 1987 - early 1990's and extended his interests to fusing neuro-fuzzy-genetic algorithms and human factors. Now, he aims humanized computational intelligence and is focusing on interactive evolutionary computation (IEC) as a tool for this research direction. Well cited his IEC papers and others can be found at Google Scholar Citations.

He has been a volunteer for IEEE Systems, Man, and Cybernetics (SMC) Society. Some of his contributions are: Vice President in 2006 - 2009: a member of Administrative Committee/Board of Governors in 2001 - 2010, and 2016 - 2018: Chair of SMC Japan Chapter in 2015 - 2018: Technical Committee (TC) Coordinator in 2004-2005: Chair of TC on Soft Computing in 1998-2004 and since 2008: Distinguished Lecturer in 2006 - 2011: Associate Editor of IEEE Transactions on SMC, Part B previously and Cybernetics now since 2001. 

See further detail at his web page at //www.design.kyushu-u.ac.jp/~takagi/ .