Biography

Professor Uwe Aickelin leads the IMA group (http://ima.ac.uk) and is currently an advanced EPSRC fellow, a member of EPSRC's Complexity SAT and a member of EPSRC's ICT SAT. He holds over GBP 2M EPSRC funding as PI, including current funding in complexity (agent-based simulation for energy - EP/G05956X/1). He is a CI of Nottingham's GBP 13m Digital Economy Hub (EP/G065802/1). He has worked almost his entire research career in cross-disciplinary fields, e.g. leading EPSRC's largest Adventure grant (GR/S47809/01), investigating immunology for robots (EP/E003257/1) and two IDEAS factory projects (EP/G004234/1 and EP/D503949/1). He has also led two EPSRC networks (EP/D036623/1 and GR/S56627/01). Prof Aickelin is a Steering Committee Member of the EPSRC/BBSRC funded Centre for Plant Integrative Biology and he is a Lead Fellow and member of the Director's Group of the EPSRC/ESRC funded Advanced Institute of Management Research.

---

Title of Talk 1: The last 10 years of Artificial Immune System research

Abstract:

• Introduction to 'real' Immune Systems
• What are Artificial Immune Systems?
• Which problems may they be suitable for?
• Some successful Artificial Immune System application examples:
  Time Series prediction (e.g. oil prices), Intrusion Detection (e.g. key logging on computers), Fault Detection (e.g. breakdown of cash dispensers), Preference suggestion (e.g. people who like X might also like Y), Robotic Navigation
• The future: Bio-sensors? Closer collaboration with Clinicians?

---

Title of Talk 2: Anomaly Detection using Dendritic Cells

Abstract:

• How to do interdisciplinary research
• What's in a name? Are you curious?
• Benefits of collaboration
• Problems of collaboration
• Tips and Tricks of collaboration
• The Dendritic Cell Algorithm
• What is Danger Theory?
• A "Danger Theory Algorithm"
• Applying the algorithm
• Experimental results

Biography

Thomas Bartz-Beielstein is a professor for Applied Mathematics at Cologne University of Applied Sciences (CUAS). He is head of the FIWA research team at CUAS, which develops tools from Genetic and Evolutionary Computation (GEC) for applications from finance and water industry. Prof. Bartz-Beielstein has published more than several dozen research papers, presented tutorials and workshops about interactive and automatic tuning of randomized and deterministic algorithms, and has edited several books in the field of GEC, e.g., "Experimental Research in EC" and "Experimental Methods for the Analysis of Optimization Algorithms". His research interests include optimization, simulation, and statistical analysis of complex real-world problems. Prof. Bartz-Beielstein is the driving force in the development of the Sequential Parameter Optimization methodology and the related Toolbox (SPOT). SPOT was applied as a tuner for numerous optimization algorithms such as evolution strategies, differential evolution, or particle swarm optimization.

---

Title of Talk 1: Tuning and Statistical Analysis of Optimization Algorithms - The Sequential Parameter Optimization Toolbox

Title of Talk 2: A hands on tutorial on SPO

Biography

Kalyanmoy Deb is the Deva Raj Chair Professor of Mechanical Engineering at Indian Institute of Technology Kanpur in India. He is also an Adjunct Professor at the Business Technology Department in the Aalto University in Finland. Prof. Deb received his Bachelor's degree in Mechanical Engineering from Indian Institute of Technology Kharagpur in India in 1985. After a short industrial experience of two years, he completed his master's and PhD degrees in Engineering Mechanics from University of Alabama, Tuscaloosa, USA in 1989 and 1991, respectively.

Prof Deb's main research interests are in evolutionary algorithms and their application in optimization and machine learning. He is one of the few researchers having over 23 years of research experience in evolutionary optimization. He is the recipient of the prestigious Shanti Swarup Bhatnagar Prize in Engineering Sciences for the year 2005 in India. He has also received the `Thomson Citation Laureate Award' from Thompson Scientific for having the highest number of citations in Computer Science during the past ten years in India. His 2002 IEEE-TEC NSGA-II paper is now judged as the Most Highly Cited paper and a Current Classic by Thomson Reuters having more than 1,850 citations. He is a fellow of Indian National Academy of Engineering (INAE), Indian National Science Academy, Indian National Academy of Sciences, and International Society of Genetic and Evolutionary Computation (ISGEC). He has received Fredrick Wilhelm Bessel Research award from Alexander von Humboldt Foundation in 2003. He has written two text books on optimization, 11 edited books, and more than 250 international journal and conference research papers. He is associate editor and in the editorial board on 15 major international journals.
More information about his research can be found from http://www.iitk.ac.in/kangal/deb.htm

---

Title of Talk 1: Evolutionary Multi-objective Optimization (EMO) for finding Multiple Pareto-optimal Solutions

Abstract: Multi-objective optimization problems involve multiple conflicting objectives and in principle they give rise to a set of trade-off Pareto-opimal solutions. Due to their population approach and flexibility in their operators, evolutionary algorithms (EAs) were found to be ideal for tackling such problems. In this talk, we shall discuss the essential differences between a single and a multi-objective optimization algorithm and present the key operations needed for finding and maintaining a diverse set of trade-off solutions. Thereafter, we shall present a number of popular evolutionary multi-objective (EMO) algorithms. In comparison to classical methods, EMO methodologies attempt to find a set of representative Pareto-optimal solutions in a single simulation. We shall highlight the scalability property of an EMO algorithm for handling a large number of objectives. We shall conclude this talk by presenting two salient advantages of EMO: (i) EMO for aiding to solve other optimization problems, such as single-objective constraint handling, multimodal optimization etc. and (ii) EMO for knowledge discovery -- a methodology that helps reveal hidden problem properties associated with high-performing solutions in a problem.

---

Title of Talk 2: Evolutionary Multi-Objective Optimization (EMO) for finding Preferred Pareto-optimal Solutions

Abstract: Finding a set of representative trade-off Pareto-optimal solutions is half the story for solving multi-objective optimization problems. For implementation, the user would require a single or a few preferred solutions. Thus, procedures for selecting a few preferred solutions are equally important. In this talk, we shall discuss three different ways of combining an EMO with a multi-criterion decision making task involving a decision-maker: (i) a priori approach in which preference information is utilized before optimization, (ii) a posteriori approach in which preference information is utilized after optimization and (ii) interactive approach in which preference information is utilized during optimization. Different EMO methodologies towards these approaches will be discussed and advantages and disadvantages of these approaches will be highlighted. A recently suggested progressively interactive EMO (PI-EMO) procedure will be presented in detail to show-case a viable interactive EMO approach. This talk should be motivational for researchers and practitioners to put more efforts in developing more efficient interactive EMO procedures.

Biography

Andries Engelbrecht received the Masters and PhD degrees in Computer Science from the University of Stellenbosch, South Africa, in 1994 and 1999 respectively. He is a Professor in computer science at the University of Pretoria, and serves as Head of the department. He also holds the position of South African Research Chair in Artificial Intelligence, and leads the Computational Intelligence Research Group at the University of Pretoria, consisting of 35 Masters and PhD students. His research interests include swarm intelligence, evolutionary computation, artificial neural networks, artificial immune systems, and the application of these Computational Intelligence paradigms to data mining, games, bioinformatics, finance, and difficult optimization problems. He has published over 180 papers in these fields in journals and international conference proceedings, and is the author of the two books, Computational Intelligence: An Introduction and Fundamentals of Computational Swarm Intelligence. In addition to these, he is a co-editor of Foundations on Computational Intelligence.

Prof Engelbrecht is very active in the international community, annually serving as reviewer for over 30 journals and 10 conferences. He is an Associate Editor of the IEEE Transactions on Evolutionary Computation, Journal of Swarm Intelligence, and the IEEE Transactions on Computational intelligence and AI in Games. Additionally, he serves on the editorial board of three other international journals, and is co-guest editor of special issues of the IEEE Transactions on Evolutionary Computation and the Journal of Swarm Intelligence. He served on the international program committee and organizing committee of a number of conferences, organized special sessions, presented tutorials, and took part in panel discussions. As member of the IEEE Computational Intelligence Society, he is a member of the Games technical committee and the Evolutionary Computation Technical Committee. He currently serves as the founding chair of the South African chapter of the IEEE Computational Intelligence Society.

---

Title of Talk 1: An Introduction to Particle Swarm Optimization

Abstract: Particle swarm optimization (PSO) has been introduced in 1995 by Kennedy and Eberhart as a new population-based, stochastic optimization method. Since then, PSO research has grown exponentially and has established PSO as an effective, powerful, yet simple optimization method. Many variations of the basic PSO have been developed, and theoretical studies conducted to understand the dynamics of particles. This talk will start with a gentle introduction to PSO, having as its objective to provide the attendee with an overview of PSO and its basic variations. A significant problem with the standard PSO will be illustrated, and a few results from studies of particle trajectories will be presented. From these results guidelines to initialize PSO control parameters will be discussed. The focus of this talk will be on the application of PSO to unconstrained optimization problems.

In a little more detail, the following topics will be discussed:

1. The foundations of PSO, followed by the standard PSO.
2. The need for social network structures.
3. The importance of the PSO control parameters (inertia, acceleration coefficients, velocity clamping).
4. Basic variations to PSO aimed at improving convergence speed and accuracy.
5. A review of theoretical analyses of particle trajectories, leading to some guidelines to initialize the values of control parameters.
6. Premature convergence of PSO and identification of a problem with the standard PSO that may lead to premature convergence.

---

Title of Talk 2: Particle Swarm Optimization as a Universal Optimizer

Abstract: The first PSO algorithms proposed in 1995 by Kennedy and Eberhart, and the first variations of the PSO were applicable to unconstrained optimization problems where the parameters to be optimized are real-valued. This talk makes the claim that PSO can be seen as a universal optimizer, showing that later adaptations of PSO make it applicable to a wide range of optimization problems. The talk will show how PSO can be adapted, without changing the foundational principles of PSO, to solve the following classes of problems:

1. Constrained optimization problems
2. Multi-objective optimization problems
3. Locating multiple solutions
4. Dynamically changing optimization problems
5. Binary-valued optimization problems 6. Large-scale optimization problems

The talk will end with a short discussion of recent developments in PSO.

Biography

Garrison W. Greenwood received the Ph.D. degree in electrical engineering from the University of Washington, Seattle. After spending more than a decade in industry designing multiprocessor embedded system hardware, he entered academia where he is now a professor in the Department of Electrical and Computer Engineering at Portland State University, Portland, Oregon USA. In 1999 and 2000 he was a National Science Foundation Scholar-in-Residence at the National Institutes of Health in Bethesda, Maryland USA.

Dr. Greenwood has served as an organizing committee member on many international conferences and was the General Chair of the 2004 Congress on Evolutionary Computation. From 2006 through 2009 he was the Vice-President of Conferences for the IEEE Computational Intelligence Society. Currently he serves as a member of the IEEE Computational Intelligence Society's Games Technical Committee and the Evolutionary Computation Technical Committee (which he chaired during 2004 and 2005). He is the current Editor-in-Chief of the IEEE Transactions on Evolutionary Computation. Dr. Greenwood is a member of the Tau Beta Pi Engineering Honor Society, the Eta Kappa Nu Electrical Engineering Honor Society and is a registered professional engineer in the State of California USA. His research interests are evolvable hardware, adaptive systems, and game theory with an emphasis on N-person social dilemmas. Dr. Greenwood is the co-author of the book Introduction to Evolvable Hardware: A Practical Guide for Designing Self-Adaptive Systems, Wiley-IEEE Press, 2006.

---

Title of Talk: Evolvable Hardware: Using Nature to Help Design and Maintain Complex Systems

Abstract: The complexity of electronic and computer systems continues to increase at a phenomenal rate. While this complexity increase enables us to produce impressive engineering systems such as high-performance aircraft and cars, mobile phones and "intelligent" homes, there are negative aspects to this increased complexity: how to design, manage and reason about such complex systems. Moreover, as complexity increases so do the chances of faults and errors occurring in these systems. For non-maintainable systems, those that are not easily repaired such as satellites, deep-sea probes or long-range spacecraft, faults and errors can damage the system making the system useless. Are there different ways to produce our current and future complex engineering systems?

Biological systems are many orders of magnitude more complex than anything we can currently produce, which suggests we might want to look to nature for some answers. Evolvable hardware (EHW) is a dynamic field that brings together reconfigurable hardware, computational intelligence, fault tolerance and autonomous systems. EHW uses simulated evolution to search for new hardware configurations. The evolution is performed by a variety of different stochastic search algorithms, such as genetic algorithms, but other computational intelligence methods such as fuzzy systems and neural networks are also beginning to appear. EHW techniques have been successfully used for both original system design and online adaptation of existing systems. It is in latter application area that has generated the most interest. EHW allows systems to self-adapt to compensate for failures or unanticipated changes in the operational environment. This capability has attracted the attention of the National Aeronautics and Space Administration (NASA) because operating in extreme physical environments, coupled with the need for high reliability, is the norm for systems deployed by this agency.

This talk on EHW is presented in two parts: Part I covers the basic concepts of EHW and discusses some previous applications. Part II discusses implementation issues and describes the latest innovation in the EHW field, metamorphic systems.

Biography

Professor Hisao Ishibuchi received the BS and MS degrees in precision mechanics from Kyoto University, Japan, in 1985 and 1987, respectively. He received the Ph. D. degree from Osaka Prefecture University, Japan, in 1992. Since 1987, he has been with Osaka Prefecture University, Japan, where he was a research associate (1987-1993), an assistant professor (1993), and an associate professor (1994-1999). Currently he is a professor (1999-) and the Head of Computational Intelligence Research Center (2006-).

His research interests include evolutionary multiobjective optimization, fuzzy rule-based classification, and multiobjective genetic fuzzy systems. He have proposed a number of hybrid computational intelligence techniques such as fuzzy regression analysis by neural networks with fuzzy connection weights, learning of neural networks form fuzzy if-then rules, genetic algorithm-based fuzzy rule selection, multiobjective genetic local search, and multiobjective fuzzy genetics-based machine learning. He received Best Paper Award from GECCO 2004, HIS-NCEI 2006 and FUZZ-IEEE 2009. He also received 2007 JSPS PRIZE from the Japan Society for the Promotion of Science.

He is the Vice-President for Technical Activities (2010-2011) of the IEEE Computational Intelligence Society. He is working as an associate editor for a number of international journals such as IEEE Trans. on SMC Part B (2002-), IEEE Trans. on Fuzzy Systems (2004-), IEEE CI Magazine (2005-), International Journal of Metaheuristics (2007-), and IEEE Trans. on Evolutionary Computation (2007-). He is also an area editor of Soft Computing (2007-), the Program Chair of CEC 2010, and a Program Co-Chair of FUZZ-IEEE 2011.

---

Title of Talk 1: Evolutionary Design of Accurate and Interpretable Fuzzy Rule-Based Systems

Abstract: One advantage of fuzzy systems based on fuzzy rules is their high approximation ability. As multilayer feedforward neural networks, fuzzy systems are universal approximators of non-linear functions. Since the early 1990s, a large number of evolutionary learning methods of fuzzy systems have been proposed to fully utilize their high approximation ability [1]. Another advantage of fuzzy systems is their high interpretability. Fuzzy rules are often written in the if-then form using linguistic terms such as "small" and "large". Those fuzzy systems are linguistically interpretable for human users.

High approximation ability and high interpretability, however, conflict with each other in the design of fuzzy systems. Accurate fuzzy systems are often too complicated to be interpretable whereas interpretable fuzzy systems are often too simple to be accurate. Thus the design of fuzzy systems can be viewed as finding a good compromise (i.e., tradeoff) between accuracy and interpretability. One approach to fuzzy system design is to integrate accuracy and interpretability into an integrated function to which single-objective evolutionary algorithms are applied. In some studies, accuracy maximization is performed under constraint conditions on interpretability. Another approach is to formulate fuzzy system design as multi-objective optimization problems where multi-objective evolutionary algorithms are used to search for non-dominated fuzzy systems with respect to accuracy and interpretability [2].

In this talk, first fuzzy rule generation methods are briefly explained. Next single-objective evolutionary approaches to fuzzy system design are discussed. Then single-objective approaches are generalized to multi-objective approaches. Finally hot issues in the field of evolutionary multi-objective fuzzy system design are explained [3].

References

1. F. Herrera, "Genetic fuzzy systems: Taxonomy, current research trends and prospects," Evolutionary Intelligence, 1:27-46 (2008). See also his GFS Webpage http://sci2s.ugr.es/gfs.
2. H. Ishibuchi and Y. Nojima, "Analysis of interpretability-accuracy tradeoff of fuzzy systems by multiobjective fuzzy genetics-based machine learning," International Journal of Approximate Reasoning 44:4-31 (2007).
3. H. Ishibuchi, Y. Kaisho, and Y. Nojima, "Design of linguistically interpretable fuzzy rule-based classifiers: A short review and open questions," Journal of Multiple-Valued Logic and Soft Computing (in press).

---

Title of Talk 2: How to Combine Local Search with Evolutionary Algorithms for Multi-objective Combinatorial Optimization

Abstract: Evolutionary algorithms have high global search ability to escape from local optima. High global search ability, however, is often incompatible with high convergence ability. Thus hybridization with local search has been examined in many studies under the name of "memetic algorithms" [1]. Such a hybrid algorithm often outperforms pure evolutionary algorithms. Hybridization with local search has been also examined for multi-objective optimization since the mid-1990s [2]. Local search, however, is basically a single-objective optimization technique. Thus its utilization for multi-objective optimization is not straightforward. Traditionally two ideas were used in hybrid multi-objective evolutionary algorithms: One is the use of scalarizing functions with different weight vectors, and the other is the use of Pareto dominance relation.

In addition to local search implementation for multi-objective optimization, there exist a number of important issues in the design of hybrid multi-objective evolutionary algorithms. One is the balance between evolutionary search and local search [3]. This issue includes the timing of local search (i.e., when local search should be applied), the frequency of local search (i.e., how often local search should be applied), and the length of local search (i.e., how many neighbors should be examined by local search). Another important issue is the selection of solutions to which local search is applied [4].

In this talk, first a basic structure of hybrid algorithms for multi-objective optimization is explained. Next it is demonstrated that the performance of hybrid multi-objective evolutionary algorithms strongly depends on the balance between evolutionary search and local search. Then the important of starting solution selection for local search are demonstrated. Finally, various structures of hybrid multi-objective evolutionary algorithms are explained.

References

1. Y. S. Ong, M. Lim, and X. Chen, "Memetic computation - Past, present & future," IEEE Computational Intelligence Magazine 5:24-31 (2010).
2. H. Ishibuchi and T. Murata, "Multi-objective genetic local search algorithm," Proc. of 1996 IEEE International Conference on Evolutionary Computation, pp.119-124 (1996).
3. H. Ishibuchi, T. Yoshida, and T. Murata, "Balance between genetic search and local search in memetic algorithms for multiobjective permutation flowshop scheduling," IEEE Trans. on Evolutionary Computation 7:204-223 (2003).
4. H. Ishibuchi, Y. Hitotsuyanagi, Y. Wakamatsu, and Y. Nojima, "How to choose solutions for local search in multiobjective combinatorial memetic algorithms," Proc. of 11th International Conference on Parallel Problem Solving from Nature - PPSN XI (in press).

Biography

Yaochu Jin received the B.Sc., M.Sc., and Ph.D. degrees from Zhejiang University, Hangzhou, China the Dr.-Ing. degree from Ruhr University Bochum, Germany.

He is currently a Professor of Computational Intelligence and Head of the Nature-Inspired Computing and Engineering (NICE) Group, Department of Computing, University of Surrey, UK. Before joining Surrey, he had been a Principal Scientist and Project Leader with the Honda Research Institute Europe in Germany since 2003. His research interests include computational approaches to understanding evolution, learning and development in biology, and biological approaches to solving complex real-world problems. He has (co)edited four books and three conference proceedings, authored a monograph, and (co)authored over 100 peer-reviewed journal and conference papers. Dr. Jin is an Associate Editor of BioSystems, the IEEE Transactions on Neural Networks, the IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews, and the IEEE Computational Intelligence Magazine. He was a past Associate Editor of the IEEE Transactions on Control Systems Technology, and is currently an editorial member of Soft Computing, Memetic Computing and Swarm Intelligence Research. Dr. Jin has given plenary / keynote talks on international conferences on various topics, including morphogenetic robotics, analysis and synthesis of gene regulatory networks, evolutionary aerodynamic design optimization and multi-objective machine learning. He is a Senior Member of IEEE.

---

Title of Talk: Evolutionary Multi-objective Machine Learning

Abstract: Machine learning is inherently a multi-objective task. Traditionally, however, either only one of the objectives is adopted as the cost function or multiple objectives are aggregated to a scalar cost function. This can be mainly attributed to the fact that most conventional learning algorithms can only deal with a scalar cost function. Over the last decade, efforts on solving machine learning problems using the Pareto-based multi-objective optimization methodology have gained increasing impetus, particularly due to the great success of multi-objective optimization using evolutionary algorithms and other population-based stochastic search methods.

It has been shown that Pareto-based multi-objective learning approaches are more powerful compared to learning algorithms with a scalar cost function in addressing various topics of machine learning, such as clustering, feature selection, improvement of generalization ability, knowledge extraction, and ensemble generation.

One common benefit of the different multi-objective learning approaches is that a deeper insight into the learning problem can be gained by analyzing the Pareto front composed of multiple Pareto-optimal solutions. This talk provides an overview of recent advances in multi-objective machine learning, focusing on supervised learning. In addition, a number of case studies are provided to illustrate the major benefits of the Pareto-based approach to machine learning, e.g., how to identify interpretable models and models that can generalize on unseen data from the obtained Pareto-optimal solutions.

Biography

Jong-Hwan Kim received his B.S., M.S. and Ph.D. degrees in Electronics Engineering from Seoul National University, Korea, in 1981, 1983 and 1987, respectively. Since 1988, he has been with the Department of Electrical Engineering at KAIST and is currently Professor. Dr. Kim is Director for both of the National Robotics Research Center for Robot Intelligence Technology and the National Research Lab for Intelligent Humanoid Robots. His research interests include computational intelligence and ubiquitous and genetic robotics. Dr. Kim has authored 5 books and 2 edited books, 2 journal special issues and around 300 refereed papers in technical journals and conference proceedings. He currently serves as an Associate Editor of the IEEE T. on Evolutionary Computation and the IEEE Computational Intelligence Magazine. Dr. Kim was one of the co-founders of the Int’l Conf. on Simulated Evolution and Learning in 1996. He was General Chair for the IEEE Congress on Evolutionary Computation, Korea, 2001 and General Chair for the IEEE Int’l Symp. on Computational Intelligence in Robotics and Automation, Korea, 2009. He has been on the program committees and advisory boards of more than 100 int’l conferences. Dr. Kim has delivered around 150 invited talks, keynote speeches and tutorials on computational intelligence and robotics in over 20 countries. His name was included in the Barons 500 Leaders for the New Century in 2000 as the Father of Robot Football. He is the Founder of FIRA and IROC and is currently serving them as President. Dr. Kim was the recipient of the science and technology award from the President of Republic of Korea in 1997 and has been elevated to 2009 IEEE Fellow.

• 1988 - Present -- Dept. of Electrical Engineering, KAIST -- Professor
• 2003 - 2006 -- KAIST Robotics Program -- Head
• 2003 - Present -- Griffith University, Australia -- Adjunct Professor
• 2005 - Present -- De La Salle University, The Philippines -- Honorary Professor
• 2009 - Present -- National Robotics Research Center for RIT -- Director
• 2009 - Present -- National Research Lab for IHR -- Director
• 1997 - Present -- IEEE T. on Evolutionary Computation -- Associate Editor
• 2009 - Present -- IEEE Computational Intelligence Magazine -- Associate Editor
• 1998 - Present -- Fed. of Int'l Robosoccer Association (FIRA) -- President
• 1999 - Present -- Int'l Robot Olympiad Committee (IROC) -- President

---

Title of Talk 1: Intelligence Technology for Cyber-Physical Robot System

Abstract: Human beings will be living in a ubiquitous world in which all IT devices are fully networked so that they can offer us desired services at any place and anytime. This shift has hastened the ubiquitous revolution, which has further manifested itself in the new multidisciplinary research area, ubiquitous robotics. It initiates the third generation of robotics following the first generation of the industrial robot and the second generation of the personal robot. A fairy tale introduced Genie, which upon springing from a lamp served Aladdin. The ubiquitous era brings us to the threshold of the realization of this dream, through ubiquitous robotics. Moreover, the robots shall have their own genome in which a specific personality is encoded. This concept leads to the research on genetic robotics. Cyber-physical robot system combines these new concepts of next generation robotics for the convergence of computational and physical systems.

This talk introduces the recent progress and development of ubiquitous robot, genetic robot and cyber-physical robot system along with the new classification of robot intelligence. Ubiquitous robot is composed of three forms of robots: software robot, embedded robot and mobile robot to represent an amalgamation of the tripartite personification of entities of perception, thinking and action. Genetic robot has its own genetic codes to represent a specific personality. Cyber-physical robot system conjoins and coordinates the software agents and physical robots including SW and HW resources. Special emphasis in this talk is placed on intelligence technology for the cyber-physical robot system to realize cognitive intelligence, social intelligence, behavioral intelligence, ambient intelligence, genetic intelligence and swarm intelligence. This system will provide us with seamless, calm, and context-aware services in a networked environment

---

Title of Talk 2: Evolutionary Multi-objective Footstep Planning for Humanoid Robots

Abstract: This talk presents a novel evolutionary multi-objective footstep planner for humanoid robots. Firstly, recent progress and development of small-sized humanoid robot HanSaRam (HSR) is introduced, which has been in continual development and research by the Robot Intelligence Technology (RIT) Laboratory, KAIST since 2000. Its height and weight are 52.8 cm and 5.3 kg, respectively. It has 27 DOFs that consists of 13 dc motors with harmonic drives for reduction gears in the lower body and 16 RC servo motors (two servo motors in each hand control, 1 DOF per hand) in the upper body. The onboard Pentium III compatible PC, running RT-Linux, calculates the proposed walking pattern every 5 ms in real time. To measure reaction forces on the foot, four force sensing resisters are equipped on each foot. Then, a footstep planner using univector field navigation method is presented to provide a command state (CS) which is to be an input of modifiable walking pattern generator (MWPG), developed at RIT Lab., at each footstep. Then MWPG generates corresponding trajectories of every leg joint of the humanoid robot at each footstep to follow the CS. Multi-objective Quantum-inspired evolutionary algorithm (MQEA) is employed to optimize univector fields satisfying multiple objectives in navigation. To select a preferred one out of various nondominated solutions obtained by MQEA, preference-based selection algorithm is used. The algorithm is based on fuzzy measure and fuzzy integral. The effectiveness of the proposed evolutionary multi-objective footstep planner is demonstrated through computer simulations for a simulation model of the small-sized humanoid robot, HanSaRam-VIII (HSR-VIII).

Biography

Jose A. Lozano received received an M.Sc. degree in mathematics and an M.Sc. degree in computer science from the University of the Basque Country, Spain, in 1991 and 1992 respectively, and the PhD degree in computer science from the University of the Basque Country, Spain, in 1998. Since 2008 he is full professor of the University of the Basque Country, Spain where he leads the Intelligent System Group. He is the coauthor of more than 50 ISI journal publications and co-editor of the first book published about Estimation of Distribution Algorithms. His major research interests include machine learning, pattern analysis, evolutionary computation, data mining, metaheuristic algorithms, and real-world applications. Prof. Lozano is associate editor of IEEE trans. on Evolutionary Computation and member of the editorial board of Evolutionary Computation journal, Soft Computing and other three journals.

---

Title of Talk 1: A Gentle Introduction to Estimation of Distribution Algorithms

Abstract: The talk is devoted to Estimation of Distribution Algorithms (EDAs). Based on Genetic Algorithms, EDAs generalizes Genetic Algorithms by replacing the crossover and mutation operators by learning and sampling the probability distribution of the best individuals of the population at each iteration of the algorithm. Working in such a way, the relationships between the variables involved in the problem domain are explicitly and effectively captured and exploited.

The talk starts presenting an intuitive example of a simple EDA. After that we will introduce probabilistic graphical models as the basic tools used in EDAs to codify probability distributions. Several EDAs classifications would be given and particular instances of EDAs will be presented. The talk will conclude with a practical application where the EDA paradigm excels. During the talk some opportunities to research in this topic will be presented.

---

Title of Talk 2: Solving three bioinformatics problems with EDAs

Abstract: The objective of the talk is to show how EDAs can be used in the solution of real problems. Particularly we concentrate on the solution of problems coming from the field of bioinformatics. We will deal with protein folding under two different models. These two scenarios will drive us to propose two different solutions based on EDAs. A third problem we treat is the selection of tagSNPs in association studies. The solution of these three problems will illustrate several interesting aspect of EDAs: from the use of prior information about the problem to the generation of a model of the problem that is being optimized.

Biography

Dr. Eugene Santos, Jr. received his B.S. ('85) in Mathematics and Computer Science from Youngstown State University, a M.S. ('86) in Mathematics (specializing in Numerical Analysis) from Youngstown State University, as well as Sc.M. ('88) and Ph.D. ('92) degrees in Computer Science from Brown University. He is currently Professor of Engineering in the Thayer School of Engineering at Dartmouth College, Hanover, NH. His areas of research interest include artificial intelligence, intent inferencing, social and cultural modeling, computational social science, automated reasoning, decision science, adversarial reasoning, user modeling, natural language processing, probabilistic reasoning, and knowledge engineering, verification and validation, protein folding, virtual reality, and active user interfaces. He has served on many major conference program committees from intelligent agents to evolutionary computing. He is currently Editor-in-Chief for the IEEE Transactions on Systems, Man, and Cybernetics: Part B, an associate editor for the International Journal of Image and Graphics, and is also on the editorial advisor board for System and Information Sciences Notes and on the editorial boards for Journal of Intelligent Information Systems and Journal of Experimental and Theoretical Artificial Intelligence.

Biography

Associate Professor TAN Kay Chen received the B. Eng degree with First Class Honors in Electronics and Electrical Engineering, and the Ph.D. degree from the University of Glasgow, Scotland, in 1994 and 1997, respectively. He is actively pursuing research in computational and artificial intelligence, with applications to multi-objective optimization, scheduling, automation, data mining, and games.

Dr Tan has published over 90 journal papers, over 100 papers in conference proceedings, co-authored 5 books including Multiobjective Evolutionary Algorithms and Applications (Springer-Verlag, 2005), Modern Industrial Automation Software Design (John Wiley, 2006; Chinese Edition, 2008), Evolutionary Robotics: From Algorithms to Implementations (World Scientific, 2006; Review), Neural Networks: Computational Models and Applications (Springer-Verlag, 2007), and Evolutionary Multi-objective Optimization in Uncertain Environments: Issues and Algorithms (Springer-Verlag, 2009), co-edited 4 books including Recent Advances in Simulated Evolution and Learning (World Scientific, 2004), Evolutionary Scheduling (Springer-Verlag, 2007), Multiobjective Memetic Algorithms (Springer-Verlag, 2009), and Design and Control of Intelligent Robotic Systems (Springer-Verlag, 2009).

Dr Tan has been invited to be a keynote/invited speaker for 15 international conferences. He served in the international program committee for over 100 conferences and involved in the organizing committee for over 20 international conferences, including the General Co-Chair for IEEE Congress on Evolutionary Computation 2007 in Singapore and the General Co-Chair for IEEE Symposium on Computational Intelligence in Scheduling 2009 in Tennessee, USA. Dr Tan is currently a member of Evolutionary Computation Technical Committee in the IEEE Computational Intelligence Society.

Dr Tan has been appointed as the Editor-in-Chief of the IEEE Computational Intelligence Magazine (CIM) starting 2010. He also serves as an Associate Editor / Editorial Board member of over 10 international journals, such as IEEE Transactions on Evolutionary Computation, IEEE Transactions on Computational Intelligence and AI in Games, Evolutionary Computation, European Journal of Operational Research, Journal of Scheduling, and International Journal of Systems Science.

Dr Tan received the Recognition Award (2008) from the International Network for Engineering Education & Research (iNEER) for his outstanding contributions to engineering education and research. He was also a winner of the NUS Outstanding Educator Awards (2004), the Engineering Educator Awards (2002, 2003, 2005), the Annual Teaching Excellence Awards (2002, 2003, 2004, 2005, 2006), and the Honour Roll Awards (2007). Dr Tan is currently a Fellow of the NUS Teaching Academic.

---

Title of Talk: Advances in Evolutionary Multi-objective Optimization

Abstract: Evolutionary algorithms are stochastic search methods that are efficient and effective for solving sophisticated multi-objective (MO) problems. Advances made in the field of evolutionary multi-objective optimization (EMO) are the results of more than two decades worth of intense research, studying various topics that are unique to MO optimization. In this talk, challenges faced in EMO research will be discussed and various EMO features/algorithms will be presented. Some applications of EMO in solving engineering problems will also be discussed.

References

1. Goh, C. K. and Tan, K. C. Evolutionary Multi-objective Optimization in Uncertain Environments: Issues and Algorithms, Springer-Verlag, 2009.
2. Tan, K. C., Khor, E. F. and Lee, T. H. Multiobjective Evolutionary Algorithms and Applications, Springer-Verlag, United Kingdom, 2005.