Sheraton Vancouver Wall Centre Vancouver,
British Columbia, Canada 16-21 July 2006
Deadline for submitting special sessions proposals: December 31st, 2005
Submit your special session proposal to: Dr. Carlos A. Coello Coello
Evolutionary Computation in Bioinformatics and Computational Biology
URL: http://coen.boisestate.edu/ssmith/CEC06/
Dr. Kay C. Wiese
Dr. Scott F. Smith
Description of the theme and the topics covered by the session:
Bioinformatics and computational biology present a number of difficult optimization problems with large search spaces. Recent applications of evolutionary computation in this area suggest that they are well-suited to this area of research. This special session will highlight applications of evolutionary computation to a broad range of topics including drug docking, protein folding, sequence alignment, genomics, proteomics, metabolics, medicine, and ecological modeling. Particular interest will be directed towards novel applications of evolutionary computation to problems in these areas.
Swarm Intelligence
Xiaodong Li,
Yuhui Shi,
and Jürgen Branke.
Swarm Intelligence (SI) is an Artificial Intelligence technique involving the study of collective behaviour in decentralized systems. Such systems are made up by a population of simple agents interacting locally with one other and with their environment. Although there is typically no centralized control dictating the behaviour of the agents, local interactions among the agents often cause a global pattern to emerge. Examples of systems like this can be found in nature, including ant colonies, bird flocking, animal herding, honey bees, bacteria, and many more. Swarm-like algorithms, such as Particle Swarm Optimization (PSO) and Ant Colony Optimization (ACO), have already been applied successfully to solve real-world optimization problems in engineering and telecommunication. SI models have many features in common with Evolutionary Algorithms. Like EA, SI models are population-based. The system is initialized with a population of individuals (i.e., potential solutions). These individuals are then manipulated over many iteration steps by mimicking the social behaviour of insects or animals, in an effort to find the optima in the problem space. Unlike EAs, SI models do not explicitly use evolutionary operators such as crossover and mutation. A potential solution simply 'flies' through the search space by modifying itself according to its past experience and its relationship with other individuals in the population and the environment. This special session will highlight the latest development in this rapidly growing research area of Swarm Intelligence. Authors are invited to submit their original and unpublished work in the areas including (but not limited to) the following:
Particle Swarm Optimization
Differential Evolution
Ant Colony Optimization
Culture algorithms
Other nature-inspired computation techniques
Multi-objective Optimization
Constraint Optimization
Optimization in Dynamic Environments
Swarm Intelligence models for evolving Neural Networks
Scheduling - Game Learning
Comparative studies of Swarm Intelligence models
Real world applications
Evolutionary Computation in Cryptology and Computer Security
URL: http://kolmogorov.seg.inf.uc3m.es/
John A Clark
Non-Standard Computation and High Integrity Systems Groups Dept. of
Computer Science University of York, York YO10 5DD,
England Tel: +44 1904 433379 Fax: +44 1904 432767.
Computer Security Group Carlos III University Avda. Universidad, 30 28911
Leganés, Madrid, Spain Tel: +34 91 624 94 99 Fax: +34 91 624 91 29.
Juan M. Estévez-Tapiador
Computer Security Group Carlos III University Avda. Universidad, 30 28911
Leganés, Madrid, Spain Tel: +34 91 624 88 98 Fax: +34 91 624 91 29.
Techniques taken from the field of Evolutionary Computation (especially Genetic Algorithms, Genetic Programming, Artificial Immune Systems, but also others) are steadily gaining ground in the area of cryptology and computer security.
In recent years, algorithms which take advantage of approaches based on Evolutionary Computation have been proposed, for example, in the design and analysis of a number of new cryptographic primitives, ranging from pseudorandom number generators to block ciphers, in the cryptanalysis of state-of-the-art cryptosystems, and in the detection of network attack patterns, to name but a few. There is a growing interest from the cryptographic and computer security communities towards Evolutionary Computation techniques. This has occurred partly as a result of these recent successes, but also because the nature of systems is changing in a way which means traditional computer security techniques will not meet the full range of tasks at hand. The increasing distribution, scale, autonomy and mobility of emerging systems is forcing us to look to nature-inspired computation to help deal with the challenges ahead.
There is a general feeling that the area is ripe for further research; the creation of a body of work has only just begun.
Objectives:
The special session encourages the submission of novel research at all levels of abstraction (from the design of cryptographic primitives through to the analysis of security aspects of systems of systems).
We believe the special session will promote further co-operation between specialists in evolutionary computation (and its current partners such as biology), computer security, cryptography and other disciplines, and will give interested researchers an opportunity to review the current state-of-art of the topic, exchange recent ideas, and explore promising new directions.
Cultural Algorithms and the Emergence of Social Intelligence
Department of Computer Science
Wayne State University
Detroit, Michigan 48202
USA
The special session will survey different culturally motivated approaches to the emergence of socially intelligence within multi-agent systems. Applications in various fields such as anthropology, biology, bioinformatics, engineering, optimization, business and manufacturing systems among others.
Hardware implementations for Genetic Neural and Fuzzy Systems
URL: http://www.isebis.eng.uerj.br/HARD-GNF.html
Nadia Nedjah and Luiza Mourelle
State University of Rio de Janeiro
BRAZIL
Genetic Algorithms (GA), Artificial Neural Networks (ANN) as well as Fuzzy Systems (FS) are becoming omnipresent in almost every intelligent system design. Just to name few, engineering, control, economics and forecasting are some of the scientific fields that enjoy the use of ANN and FS. Unfortunately, the majority of the applications are complex and so require a large computational effort to yield useful and practical results. Therefore, dedicated hardware for evolutionary, neural and fuzzy computation is becoming a key issue for designers. With the spread of reconfigurable hardware such as FPGAs and FPAAs, digital as well as analog hardware implementations of such computation become cost-effective.
The focus of this special session will be on all aspects of for high-speed hardware implementations for genetic algorithms, neural networks and fuzzy controllers. Hybrid implementations using co-design methodology are also welcome. The main topics can be listed as follows:
Recent Developments in Artificial Immune Systems
URL: http://www-users.cs.york.ac.uk/jtimmis/wcci
Dr. Jonathan Timmis
Department of Computer Science and Department of Electronics
University of York
Heslington, York. YO10 5DD
http://www-users.cs.york.ac.uk/jtimmis
Dr. Emma Hart
School of Computing
Napier University
10 Collington Road
Edinburgh. EH10 5DT
http://www.dcs.napier.ac.uk/~emmah
The immune system is a remarkably complex interacting network of cells. There are many day to day challenges facing the immune system, such as the vast array of stimuli that can infect the host, the continual bombardment of such stimuli (there is no resting for the immune system) and the countless interactions that occur with other processes and systems within the host (such as the neural systems and endocrine or hormonal systems). The remarkable ability if the immune system to react to these stimuli (antigens) and remove the majority of them from our system has fascinated researchers over the years. This immune system has inspired researchers in the area of Artificial Immune Systems (AIS) over the past 10 years to develop a wide range of algorithms inspired by various aspects of immunology. Within AIS, there is no one standard AIS algorithm, however, there are a number of basic flavours of AIS algorithms that draw their inspiration from certain processes within the immune system. To date there are clonal selection, immune network, bone marrow and negative selection algorithms. There are many variations on these algorithms, but there is at least some basic acceptance, for example, of what a clonal selection algorithm consists of and how it should work.
The aim of this session is to consolidate state of the art in AIS, but also to encourage the publication of more 'mould breaking' AIS research. Particular encouragement is given to the submission of applications of AIS in industrial settings and advances in theoretical aspects of AIS. To maintain the interdisciplinarity of AIS, the session encourages the submission of immune modelling results using both computational and mathematical modelling techniques that can inform the development of AIS. In addition, we welcome position papers which provide a discussion of current "hot" topics in the area, for example outlining future directions for the area, or discuss the current state-of-the art. Papers are invited for submission on unpublished work in the following (but not restricted to) areas:
Constrained Real Parameter Optimization
URL: http://www.ntu.edu.sg/home/EPNSugan
Prof. Carlos A. Coello Coello (ccoello@cs.cinvestav.mx)
Prof. Kalyanmoy Deb (deb@iitk.ac.in)
Dr Efren Mezura Montes (emezura@computacion.cs.cinvestav.mx)
A/Prof. P. N. Suganthan (epnsugan@ntu.edu.sg)
Most optimization problems have constraints of different types (e.g., physical, time, geometric, etc.) which modify the shape of the search space. During the last few years, a wide variety of metaheuristics have been designed and applied to solve constrained optimization problems. Evolutionary algorithms and most other metaheuristics, when used for optimization, naturally operate as unconstrained search techniques. Therefore, they require an additional mechanism to incorporate constraints into their fitness function.
Historically, the most common approach to incorporate constraints (both in evolutionary algorithms and in mathematical programming) is the penalty functions, which were originally proposed in the 1940s and later expanded by many researchers. Penalty functions have, in general, several limitations. Particularly, they are not a very good choice when trying to solve problem in which the optimum lies in the boundary between the feasible and the infeasible regions or when the feasible region is disjoint. Additionally, penalty functions require a careful fine-tuning to determine the most appropriate penalty factors to be used with our metaheuristics.
In order to overcome the limitations of penalty functions approach, researchers have proposed a number of diverse approaches to handle constraints such as fitness approximation in constrained optimization, incorporation of knowledge such as cultural approaches in constrained optimization and so on. Additionally, the analysis of the role of the search engine has also become an interesting research topic in the last few years. For example, evolution strategies (ES), evolutionary programming (EP), differential evolution (DE) and particle swarm optimization (PSO) have been found advantageous by some researchers over other metaheuristics such as the binary genetic algorithms (GA).
Despite the existence constrained optimization test suites (http://www.cs.cinvestav.mx/~constraint/, http://www.mat.univie.ac.at/~neum/glopt/test.html), there is an obvious need to upgrade the current test suites by considering the types of constraints (equality, inequality, linear, nonlinear, dimensionality, active, etc.), types of objective functions (linear, quadratic, nonlinear, multimodality, separability, etc.), connectivity, relative size of feasible region and so on. In addition, it would be beneficial to evaluate and, if necessary, develop novel performance measures to deal with the diverse characteristics of the constrained optimization problems. We plan to present an extended test suite and standardized evaluation measures for researchers to test their algorithms till the CEC'2006 submission deadline in late January 2006. Along with the papers, we would also optionally like participants to submit their codes and/or executables and we shall put it up on a web-site for anyone to try out. The submitted papers will be peer-reviewed by other authors and reviewers and selected authors will be invited to present their results during CEC-06.
The test functions are available from http://www.ntu.edu.sg/home/EPNSugan. For any further details, please contact the organizers.
Evolutionary Planning and Scheduling
URL: http://www.mosaic.ac/papers/call.php
Dr Keshav Dahal
School of Informatics
University of Bradford
Richmond Road
Bradford, West Yorkshire BD7 1DP
UK
Professor Peter Cowling
MOSAIC Research Group
University of Bradford
Department of Computing
Bradford BD7 1DP
UK
Planning and scheduling problems occur where numerous activities compete for scarce resources (including time). Real-word planning and scheduling problems are generally complex, constrained and multi-objective in nature. Typical examples of such planning and scheduling problems include project planning/scheduling, production planning/scheduling, activities planning, staff rostering, machine scheduling, timetabling, vehicle routing, resource assignment, etc. A sustained research effort over recent years continues to achieve many real world and theoretical successes in the development and application of new techniques for solving planning and scheduling problems. Recently, there has been a high research interest in evolutionary, meta-heuristic and soft computing approaches for solving scheduling problems. This session aims to attract papers on which report on the application of techniques such as these, their refinement for addressing particular planning and scheduling problems, and new theoretical developments. Topics of the interests include, but are not limited to, the following:
Evolutionary Algorithms Based on Probabilistic Models (EAPM)
URL: http://cswww.essex.ac.uk/staff/qzhang/cec06specialsession.htm
Evolutionary algorithms based on probabilistic models (EAPM) have been recognized as a new computing paradigm in evolutionary computation. Instances of EAPMs include, estimation of distribution algorithms, probabilistic model building genetic algorithms, ant colony optimization, cross entropy methods, to name a few. There is no traditional crossover or mutation in EAPMs. Instead, they explicitly extract global statistical information from their previous search and build a probability distribution model of promising solutions, based on the extracted information. New solutions are sampled from the model thus built. EAPMs represent a new systematic way to solve hard search and optimization problems. The last decade has seen growing interest in this area. As an interdisciplinary research area, the development of EAPMs needs joint efforts from the researchers and practitioners in evolutionary computation, machine learning, statistics and simulation. This special session aims at bringing researchers who are interested in EAPM together to review the current state-of-art, exchange the latest ideas and explore future directions. The major topics of interest include, but are not limited to:
Organizers:
Dr. Qingfu Zhang
Prof. José Antonio Lozano
Prof. Pedro Larrañaga
Evolutionary Computation in Finance and Economics
Evolutionary computation is steadily becoming more and more widespread in the fields of finance and economics. It’s been proved to be a powerful tool in domains were analytic solutions are not a good alternative. So far it has been successfully used in financial engineering, risk management, portfolio optimization, industrial organization, auctions, experimental economics, financial forecasting, market simulation or agent-based computational economics among many other areas. Topics suitable for the special session include, but are not limited to the above mentioned. The session is open to any high quality submission from researchers working at the intersection of evolutionary computation and economics and finance.
Pedro Isasi
Departamento de Informática
Universidad Carlos III de Madrid
Av. Universidad 30, Leganés
Madrid 28911
SPAIN
Edward Tsang
Department of Computer Science
University of Essex
Wivenhoe Park, Colchester
CO4 3SQ, UK
David Quintana
Departamento de Informática
Universidad Carlos III de Madrid
Av. Universidad 30, Leganés
Madrid 28911, Spain
Evolutionary Clustering
URL: http://dbk.ch.umist.ac.uk/handl/cec2006.html
The recent surge in post-genomic data has revived the interest in unsupervised classification techniques that permit the automated processing and categorization of large amounts of data in the presence of no or very little training data. Traditional data-mining techniques are not well-suited to the specific difficulties posed by post-genomic data (such as high noise levels, small sample sizes and high dimensionality), and the development of novel, robust and efficient techniques is therefore one of the foremost priorities in (bio)informatics.
This session will cover all evolutionary computation techniques applied to unsupervised classification tasks, such as clustering, bi-clustering and feature selection, including (but not limited to):
Julia Handl
School of Chemistry
University of Manchester
Faraday Building, Sackville Street
PO Box 88, Manchester M60 1QD
UK
J.Handl@postgrad.manchester.ac.uk
Evolutionary Computation and Games
URL: http://www.cse.unsw.edu.au/~blair/wcci06games
Games have proven to be an ideal test domain for the study of evolutionary algorithms, as they provide competitive and dynamic environments that are both interesting to observe and fun to play. Evolutionary techniques have successfully been applied to many different kinds of games and a number of important research issues have been identified and studied. Topics of interest include, but are not limited to:
Evolutionary Computation for Expensive Optimization Problems
Optimization problems where the evaluation of solutions is expensive arise in a variety of contexts. The types of costliness and their effect on how many evaluations/generations can be afforded differ widely, as the following three examples may illustrate. (i) When evolving controllers for a simulated collective of robots, the fidelity of the physics simulator, the noise/stochasticity in the system, and the desire to obtain robots that are robust to rare events may all play a part in making simulation times very long. (ii) When evolving a novel protein with a specific binding target by synthesis of proteins in vitro and their subsequent hybridization and screening, thousands of proteins may be synthesised in parallel but each further "generation" will take another 12 hours to process and will also have financial implications. (iii) When evolving a basic conceptual design for a new building, an architect evaluating the designs will get tired after several hours and will eventually have to stop.
This special session invites contributions in all aspects of applying evolutionary computation to the optimization of expensive functions, to include the following areas.
Intelligent Interface and Interactive Agents Through Evolutionary Computation (IIIATEC)
URL: http://platon.escet.urjc.es/~ovelez/iiiatec06/iiiatec06
The initial point for our approach is the assumption that Evolutionary Computation techniques are especially adequate for the adaptation and learning of Intelligent Interface Agents, because they are inherently based on a distributed paradigm (the natural evolution). With this special sesssion we are trying to approach problems in the Intelligent Interface and Interactive Agents domain from using Evolutionary Computation perspective. We hope Contributions that describe methods and techniques for improving the applicability and effectiveness of Evolutionary Computation techniques when applied to Intelligent Interface and Interactive Agents.
Evolutionary Computation in Dynamic And Uncertain Environments (ECiDUE)
URL: http://www.cs.le.ac.uk/people/syang/ECiDUE06.html
Many real-world optimization problems are subjected to dynamic and uncertain environments that are often impossible to avoid in practice. For instance, the fitness function is uncertain or noisy as a result of simulation/measurement errors or approximation errors (in the case where surrogates are used in place of the computationally expensive high fidelity fitness function). In addition, the design variables or environmental conditions may also perturb or change over time. For these dynamic and uncertain optimization problems, the objective of the evolutionary algorithm is no longer to simply locate the global optimum solution, but to continuously track the optimum in dynamic environments, or to find a robust solution that operates optimally in the presence of uncertainties. This poses serious challenges to conventional evolutionary algorithms.
Handling dynamic and uncertain optimization problems in evolutionary computation has received an increasing research interests over the recent years. A variety of methods have been reported across a broad range of application backgrounds. This special session aims at bringing researchers from academia and industry together to review the latest advances and explore future directions in this field. Topics of interest include but are not limited to:
EC at Work - Generating Value with Evolutionary Computation
URL: http://www.cercia.ac.uk/other/2006/cec/
Evolutionary Computation is increasingly finding applications in business. This special session will provide a common forum for both business and academic people to report and discuss successful applications of EC in business, with an emphasis on a diverse range of projects in which EC is continuously in use to enhance profitability. This is EC coming out of the laboratory and into offices and factories.
By identifying "showcase examples", the session will aid those researchers who wish to see their work in active, commercial use. The case-studies will form a framework for explaining the diversity of EC applications to potential commercial partners and give the academic community information on the difficulties which need to be overcome in order to commercialise EC techniques.
We are inviting submissions that demonstrate solid applications of EC which are making a difference to business, trailblaze innovative use of EC in business and share best practices and experiences in real-world problem solving using EC.
Unlike other sessions in this conference, the applications presented do not have to use newly developed techniques. Instead, the business implementation should be of interest.
We will be looking for papers that show how EC is used to create value in the real world. Also of interest are papers that identify the factors which hinder adoption of EC or enable technical excellence to blossom into business use. We strongly encourage papers with applications based on integration between Evolutionary Computation, Neural Networks, and Fuzzy Logic.
Topics of interest include, but are not limited to:
Differential Evolution
URL: http://www.cs.umsl.edu/~uday/DE-CEC2006/
Differential evolution (DE), an attractive global optimization method with relatively fewer parameters, is a relatively new member of the evolutionary computation family. This method has recently been shown to produce superior results in a wide variety of real-world applications. This special session seeks to bring together researchers and practitioners in this rapidly emerging field.
Topics of interest include, but are not limited to:
Evolutionary Design
The intention of the Special Session is to explore the integration of evolutionary search, exploration and optimization across a wide spectrum of design activities. The session intends to investigate the manner in which evolutionary computation can be utilized to generate design concepts and achieve meaningful designs in addition to more standard evolutionary optimization processes. The support of decision-making and innovation during preliminary design and novel EC strategies and problem representations that best handle design complexity and support people-centred aspects are also of interest. The development and integration of appropriate evolutionary computing strategies will likely focus upon engineering and architectural design. However, papers relating to other areas such as drug design and discovery; software design; the design of foodstuffs etc are also most welcome. Papers which identify and address generic design aspects across several such domains that can particularly benefit from EC application / integration and illustrate EC potential in these areas are particularly encouraged.
The following areas would be of interest although the call is not limited to them:
Quantum Computing and Quantum Computational Intelligence
Historically, classical computer concepts and underlying technologies have been invented by mathematicians and physicists rather than engineers. It were engineers, however, who took basic concepts and ideas and created the practical powerful and inexpensive computers of today. We believe that the same will happen in case of quantum computers. A new area of engineering - quantum computer engineering - will be created to solve many engineering aspects of future quantum circuits and computers. At the present time there are several research groups and conferences in the field of quantum computing, quantum circuits and quantum information that are addressed to physicists, mathematicians and theoretical computer scientists. There is a growing group of researchers with engineering background who do active research in the area of what will become quantum computer engineering. These areas include the following:
Evolutionary Computer Vision
Computer vision is a major unsolved problem in computer science and engineering. Over the last decade there has been increasing interest in using evolutionary computation approaches to solve vision problems. Computer vision provides a range of problems of varying difficulty for the development and testing of evolutionary algorithms.
The theme of the proposed special session is the use of evolutionary computation for solving computer vision and image processing problems. Topics include (but are not limited to):
Evolved Art and Music
URL: http://eldar.mathstat.uoguelph.ca/dashlock/EvoArt/
Evolved Art and Music are an emerging discipline within evolutionary computation. While the representation of artistic or musical objects for evolution is challenging, writing fitness functions that can locate artistically meritorious images or melodies is perhaps the greatest challenge. Many evolutionary artists have solved this problem by using human-in-the-loop fitness. Both effective use of human-in-the-loop and machine computed fitness are welcome in submissions to this session. Researchers who submit to the special session on evolved art and music are also encouraged to submit to the CEC 2006 evolved art contest. The special session and contest are not linked and the contest has no associated publication. Details of CEC 2006 contests are available at:
http://www.hi.is/%7Etpr/cec2006contests/
Evolutionary Multiobjective Optimization
Multiobjective optimization is an area in which evolutionary algorithms have achieved great success. Most real-world problems involve several objectives (or criteria) to be optimized simultaneously, but a single, perfect solution seldom exists for a multiobjective problem. Due to the conflicting nature of at least some of the objectives, only compromise solutions may exist, where improvement in some objectives must always be traded-off against degradation in other objectives. Such solutions are called Pareto-optimal solutions, and there may be many of them for any given problem. Selecting the best compromise solution among them leads to another problem, known as a decision making problem, which must involve additional domain-specific information.
Currently, evolutionary multiobjective optimization (EMO) algorithms tend to emphasize the approximation of the set of Pareto-optimal solutions as a whole. Considering the outcome of EMO runs to be a set of solutions instead of a single best solution raises several challenges from a theoretical standpoint. Fundamental concepts, such as the quality of the sets of solutions produced and optimizer performance in general, have become rather controversial, and have highlighted the need for better experimental methodology in empirical studies and for the design of new EMO algorithms based on stronger theoretical principles.
On the other hand, the selection of a single compromise solution remains a necessary step in real-world problems. Although the articulation of, possibly incomplete, preferences has been considered rather early in EMO history, the integration of EMO algorithms with multi-criterion decision-making approaches has not been very actively pursued. This and other issues, including the handling of large numbers of objectives and the interaction with human operators in interactive optimization remain important avenues for research.
In summary, this special session aims to involve both theoreticians and practitioners in the exchange of recent research and application results in Evolutionary Multiobjective Optimization and related areas, including, but not limited to, the following topics: