The Ninth International Conference on Simulated Evolution And Learning (SEAL'2012)

Prof. Hisao Ishibuchi,
Professor, Osaka Prefecture University, Japan.

Title: Evolutionary Multiobjective Optimization and Fuzzy Rule-Based Classifier Design.

Abstract
The tutorial talk will include only basic ideas on
- Evolutionary multiobjective optimization
- Fuzzy rule-based classifiers
- Evolutionary design of fuzzy rule-based classifiers
- Evolutionary multiobjective design of fuzzy rule-based systems.
Biography
Prof. Hisao Ishibuchi received the BS and MS degrees from Kyoto University in 1985 and 1987, respectively. He received the Ph. D. degree from Osaka Prefecture University in 1992. Since 1987, he has been with Osaka Prefecture University as a research associate (1987-1993), an assistant professor (1993), an associate professor (1994-1999) and a full professor since 1999. His research interests include evolutionary multiobjective optimization, multiobjective memetic algorithms, fuzzy genetics-based machine learning, fuzzy rule-based classification and evolutionary games. He received a Best Paper Award from GECCO 2004, HIS-NCEI 2006, FUZZ-IEEE 2009, WAC 2010, SCIS & ISIS 2010 and FUZZ-IEEE 2011. He also received a 2007 JSPS Prize from the Japan Society for the Promotion of Science. He is the IEEE CIS Vice-President for Technical Activities (2010-2011 & 2012-2013), the Program Chair of IEEE CEC 2010, a Program Co-Chair of FUZZ-IEEE 2011, the General Chair of ICMLA 2011, a Technical Co-Chair of FUZZ-IEEE 2012, SEAL 2012 and IEEE CEC 2013, and a Program Co-Chair of FUZZ-IEEE 2013 and IEEE CEC 2014. He is also an associate editor of IEEE T-SMC Part B (2002-), IEEE TFS (2004-), IEEE CI Magazine (2005-) and IEEE TEC (2007-). According to Google Scholar, the total number of citations of his papers is more than 11,000 and his h-index is 47 (as of August 24, 2012).
Prof. Akira Namatame,
Professor of Computer Science Department and Academic Dean at National Defense Academy of Japan
Email: nama@nda.ac.jp
Web: www.nda.ac.jp/~nama

Title: Optimal Network Design with Evolutionary Algorithm.

Abstract
In this tutorial I present a general framework for designing optimal complex networks using evolutionary algorithm. A networked society implies the increase of interdependency, creating challenges for managing risks. The qualification of risks lies in their systemic nature. A risk to one subsystem may present an opportunity to another subsystem. A systemic risk is the possibility that an event will trigger a loss of confidence in a substantial portion of the system serious enough to have adverse consequences on system performance. A systemic risk therefore impacts the integrity of the whole systems.
The network is only as strong as its weakest link, and trade-offs are most often connected to a function that models system performance management. There is a class of problems, ranging from risk spreading to the control of cascade failure, that are naturally defined as network optimization problems. Other efforts like improving the robustness of systems also involve optimization problems and reveal enhanced system properties shaped by optimizing the underlying network topology. We propose a heuristic optimization approach using generic algorithm (GA) to design optimal networks that may fit to many network requirements. Other issues such as network robustness and network resilience defined as multi-criteria optimization problems of the underlying network topology.
Biography
Dr. Akira Namatame is a Professor of Computer Science Department and Academic Dean at National Defense Academy of Japan. He is well-known as an international research leader in the field of multi-agent modeling and complex systems, and in the past ten years he has given over 30 invited talks in these areas. His research interests include multi-agent systems, complex networks, evolutionary computation, and game theory. He is the editor-in-chief of Springer's Journal of Economic Interaction and Coordination. He has published more than 230 refereed scientific papers, together with eight books on multi-agent systems, collective systems and game theory.

Prof Zhun Fan
Professor, School of Electronics and Information Engineering
Tongji University, Shanghai, China
Email:zfan@tongji.edu.cn

Title: Mechatronic Design Automation Using Evolutionary Approaches'
Abstract
Evolutionary computation has been applied in an increasingly wider range of automated design applications. This tutorial will focus on automatic design of dynamical systems, and in particular, mechatronic systems. Mechatronic systems have become so ubiquitous recently that their automated design deserves much more attention. Automatic design of mechatronic systems has a stem, and a close affiliation with automatic design of electronic systems, so called Electronic Design Automation (EDA). This tutorial therefore introduces the concept of Mechatronic Design Automation (MDA), and presents the work of over ten years on the topic of applying evolutionary approaches for automatic design of a large variety of mechatronic systems. The principal methodology, so called BGGP, combines the capability of Bond Graph (BG) to model and represent multi-domain physics of a typical mechatronic system, and Genetic Programming (GP) as a strong search and optimization tool to explore the open-ended design space in terms of both topology and parameters. The method is also capable of co-evolving the continuous dynamic controller and the plant embodiment, expanding it to a wider range of applications. Recently, the method had another important extension to involve treatment of discrete events, thus enabled it to automatic design of hybrid dynamical systems. The resulting method, hBGGP, integrates hybrid Bond Graph (hBG) and Genetic Programing (GP), and can be used to design a more complete range of mechatronic systems. A series of design case studies are presented to illustrate the effectiveness and efficiency of the methodologies. In a special group of applications – automatic design of micro-electro-mechanical Systems (MEMS), the issues of hierarchical design and robust design are addressed. Future research directions, which will incorporate strengths of other state-of-the-art evolutionary techniques, will also be discussed, to boost the research field of Mechatronic Design Automation.
Biography
Zhun Fan obtained his PhD from Michigan State University in 2004. He has been working at Technical University of Denmark as an Assistant Professor and Associate Professor, and is Principal Investigator for a number of projects sponsored by the Danish Research Agency of Science Technology and Innovation. He is now working as a project researcher in the BEACON Center for Study of Evolution in Action. His research interests include design automation and optimization for mechatronic systems, evolutionary computation, robotics, MEMS, and computer vision.  He has published more than 80 technical papers, co-edited two conference proceedings. He is a senior member of IEEE, and member of ACM and ASME

Dr. Swagatam Das
Assistant Professor with the Electronics and Sciences Unit, Indian Statistical Institute, Kolkata
Email:swagatamdas19@yahoo.co.in
Web: http://www.isical.ac.in/~swagatam.das/

Title: "Differential Evolution – After one and a half Decades"


Abstract
Differential Evolution (DE) is arguably one of the most powerful stochastic real-parameter optimization algorithms of current interest. DE operates through similar computational steps as employed by a standard Evolutionary Algorithm (EA). However, unlike traditional EAs, the DE-variants perturb the current-generation population members with the scaled differences of randomly selected and distinct population members. Therefore, no separate probability distribution has to be used for generating the offspring. Since late 1990s, DE started to find several significant applications to the optimization problems arising from diverse domains of science and engineering.
DE operates through the same computational steps as employed by any standard Evolutionary Algorithm (EA). However, unlike traditional EAs, DE employs the difference of the parameter vectors to explore the objective function landscape. In its simplest form, DE adds the scaled, random vector difference to a third randomly selected population vector to create a donor vector corresponding to each population vector (also known as target vector). Next the components of the target and donor vectors are mixed through a crossover operation to produce a trial vector. In the selection stage, the trial (or offspring) vector competes against the population vector of the same index, i.e. the parent vector. Once the last trial vector has been tested, the survivors of all the pair-wise competitions become parents for the next generation in the evolutionary cycle. Compared to several existing EAs, DE is much simpler and straightforward to implement. It takes 4-5 lines to code the main body of the algorithm in any programming language. Simplicity of programming is important for practitioners from other fields, since they may not be experts in programming and are looking for an algorithm that can be simply implemented and tuned to solve their domain-specific problems. Additionally, DE takes very few control parameters (typically the population size Np, the scale factor F, and the crossover rate Cr), which makes it easy to use. Perhaps these issues triggered the popularity of DE among researchers all around the globe within a short span of time.
Growing research interest in DE has already resulted in a lot of variants of the basic algorithm with improved performance. This tutorial will begin with a detailed overview of the basic concepts related to DE and also focus on its algorithmic components and control parameters. It will subsequently discuss some of the significant algorithmic variants of DE for bound constrained single-objective optimization. Application of the DE family of algorithms for multi-objective, constrained, large-scale, dynamic and multi-modal optimization problems will also be presented. Theoretical advances made to understand the search mechanism of DE and the effect of its most important control parameters will be discussed. The talk will finally discuss a few engineering applications of DE and uncover a few problems that pose severe challenge to the state-of-the-art DE algorithms and demand strong research effort from the DE-community in near future.
Biography
Swagatam Das (M'10) received the B.E.Tel.E.,M.E.Tel.E. (control engineering specialization), and Ph.D. degrees from Jadavpur University, Kolkata,India, in 2003, 2005, and 2009, respectively. He was an Assistant Professor with the Department of Electronics and Telecommunication Engineering, Jadavpur University, from 2006 to 2011.He is currently an Assistant Professor with the Electronics and Communication Sciences Unit, Indian Statistical Institute, Kolkata. He has published more than 120 research articles in peer-reviewed journals and international conferences. He coauthored a research monograph on metaheuristic clustering techniques from Springer in 2009. He is the founding Coeditor-in-Chief of Swarm and Evolutionary Computation, an international journal from Elsevier. He serves as an Associate Editor of the IEEE Transactions on Systems, Man, and Cybernetics (Part—A) and Information Sciences (Elsevier). He is an editorial board member of Progress in Artificial Intelligence, International Journal of Artificial Intelligence and Soft Computing, and International Journal of Autonomous and Adaptive Communications Systems. He has been acting as a regular reviewer for journals like Pattern Recognition, IEEE Transactions on Evolutionary Computation, IEEE/ACM Transactions on Computational Biology and Bioinformatics, IEEE Transactions on SMC Part A, B, and C. He has co-authored a research monograph on metaheuristic clustering techniques published by Springer in 2009.