AAAA, Alife, Adaptive Behavior, Agents, and Ant Colony Optimization

Vasant Honavar honavar@cs.iastate.edu Karthik Balakrishnan balak_k@yahoo.com

Recent advancements and applications of Artificial life, Adaptive behavior, Agents and Ant Colony Optimization

This special track brings together novel contributions in the closely related areas of Artificial Life, Adaptive Behavior, Agents, and Ant Colony Optimization. From artificial models of biological systems, to the synthesis of "life" on artificial media; from self-organizing, self-replicating, and self-learning structures, to bio-inspired adaptive robots and mobile agents; from collective behaviors and swarm intelligence, to communication, coordination, and collaboration in multi-agent teams/colonies; from organization of agent societies, to applications of ant colony systems in combinatorial optimization -- this area deals with algorithmic, synthetic, empirical, and theoretical advances in artificial systems inspired by evolution, biology, and life.

DNA, DNA and Molecular Computing

Natasha Jonoska jonoska@math.usf.edu

Computation with DNA and other molecules. The molecules encode solutions to a problem and are selected and recombined to form other solutions.

ES, Evolution Strategies

Guenter Rudolph rdo@parsytec.de

Evolution Strategies are characterized by using real (floating point) encodings, sophisticated mutation and recombination operators, and deterministic selection. Papers in this deme would include theoretical studies of ES (ideally complemented with experiments), improvements and modifications to the algorithms, and applications to benchmarking problems (test function suites, TSP, graph coloring, graph partitioning, etc.).

EP, Evolutionary Programming

Guenter Rudolph rdo@parsytec.de

Originally proposed to work on finite state machines, lately EP is characterized by using floating point encodings and relying on mutation to explore the search space. Papers in this deme would include theoretical studies of EP (ideally complemented with experiments), improvements and modifications to the algorithms, and applications to benchmarking problems (test function suites, TSP, graph coloring, graph partitioning, etc.).

ROB, Evolutionary Robotics

Mitchell A. Potter mpotter@aic.nrl.navy.mil Alan C. Schultz schultz@aic.nrl.navy.mil

Automatic design of autonomous robots using evolutionary algorithms.

Overlapping and complementary approaches to using evolutionary algorithms in the areas of robotics have been seen in recent years. In this special program track, we would like to explore some of these approaches, and hopefully better understand their similarities and differences. Topics of interest include, but are not limited to, the use of evolutionary algorithms in: development and design of robots, robotic learning, robotic control, coordination of multiple robots, perception and multi-sensor integration, and testing and evaluation of robotic systems.

SCH, Evolutionary Scheduling and Routing

http://www.asap.cs.nott.ac.uk/new/gecco2002cfp.shtml

Edmund Burke ekb@cs.nott.ac.uk

This track is concerned with all aspects of evolutionary and metaheuristic research in scheduling and routing. A particular aim of the track is to consider evolutionary research in the field within the context of research in other meta-heuristics and other approaches from Artificial Intelligence and Operations Research. Specific aims of the track include (but are not limited) to the following themes:

Scheduling Problems and Applications

Meta-heuristic Approaches to Scheduling and Routing Problems

Vehicle Routing

Travelling Salesman and Related Problems

EH, Evolvable Hardware

Julian Miller j.miller@cs.bham.ac.uk

Using evolutionary algorithms to design hardware (mechanical systems, electronic circuits, antennas, etc.)

GP, Genetic Programming

Riccardo Poli rpoli@essex.ac.uk

Genetic Programming is the automatic induction of computer programs and other variable-size structures from a high-level statement of a problem through evolutionary algorithms.

LCS, Learning Classifier Systems

Larry Bull larry.bull@uwe.ac.uk

Learning classifier systems are adaptive rule-based systems that use an evolutionary algorithm and/or heuristics to search the space of possible rules.

This deme is not about decision trees, neural networks, or other machine learning systems for categorization of data (Although, of course, classifier systems can be use to categorize data, and comparisons and CS-ML hybrids are welcome).

RWA, Real World Applications

David Davis david.davis@nutechsolutions.com Rajkumar Roy R.Roy@cranfield.ac.uk

Application of any evolutionary algorithm to problems in the real world (as opposed to benchmarking problems and test function suites). The papers in this deme will be peer-reviewed in the same blind reviewing process of the rest of the conference, and will be published in the conference proceedings that will be distributed commercially by Morgan Kaufmann Publishers. Selected papers of this track will be invited to submit a revised and enhanced version to a special issue of the 'Applied Soft Computing' Journal.

  See E.C.I. (Evolutionary Computing in Industry)
for details on a separate industrial special track.  

use evolutionary algorithms and related search techniques to address problems in software engineering

provide definitions of representations, fitness/cost functions, operators, and search strategies for software engineering problems

develop and extend the emerging community working on Search-Based Software Engineering

introduce researchers in evolutionary computation to problems in software engineering

increase awareness and uptake of evolutionary computation technology within the software engineering community.

Topics of interest include requirements engineering, system and software design, implementation, system and software integration, quality assurance and testing, project management, maintenance, change management, optimisation and transformation as well as development processes.