1 Nick Jennings
Professor of Computer Science, University of Southampton, UK
NEGOTIATION TECHNOLOGIES (abstract)
2 Hai Zhuge
Professor and director of the Key Lab of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences
DYNAMIC INHERITANCE IN SOFT-DEVICES WITHIN THE KNOWLEDGE GRID (abstract)
3 Chengqi Zhang
Faculty of Information Technology University of Technology, Sydney, Australia
AGENTS AND DATA MINING: MUTUAL ENHANCEMENT BY INTEGRATION (abstract)
4 Mircea Gh. Negoita
Professor in The School of Information Technology, Wellington Institute of Technology (WelTec), New Zealand and the Director of Centre for Computational Intelligence at WelTec
ARTIFICIAL IMMUNE SYSTEMS - A NEW EMERGENT TECHNOLOGY INVOLVED IN AUTONOMOUS INTELLIGENT SYSTEMS AND DATA MINING (abstract)
5 Pericles A. Mitkas
Associate Professor and the Associate Chairman of the Department of Electrical and Computer Engineering at the Aristotle University of Thessaloniki, Greece
KNOWLEDGE DISCOVERY FOR TRAINING INTELLIGENT AGENTS: METHODOLOGY, TOOLS AND APPLICATIONS (abstract)
6 Leonid I. Perlovsky
Dr. Leonid Perlovsky is Principal Research Physicist and Technical Advisor at the Air Force Research Laboratory/SNHE
EVOLVING AGENTS: COMMUNICATION AND COGNITION (abstract)
Nick Jennings
Professor of Computer Science, University of Southampton, UK
NEGOTIATION TECHNOLOGIES
Abstract. Negotiation is a key form of interaction in a wide variety of areas (including multi-agent systems, the Grid, pervasive computing, and the Semantic Web). Given this ubiquity, automated negotiation technologies exist in many different forms, each of which has different characteristics and properties. Against this background, this talk discusses work on a variety of models, covering bi-lateral encounters, auctions and argumentation-based negotiation.
 |
Nick Jennings is Professor of Computer Science in the 5*-rated School of Electronics and Computer Science at Southampton University where he carries out basic and applied research in agent-based computing. He is Deputy Head of School (Research), Head of the Intelligence, Agents, Multimedia Group (which consists of some 120 research staff and postgraduate students) and is also the Chief Scientific Officer for Lost Wax. He has published over 250 articles and 6 books on various facets of agent-based computing and holds 2 patents (3 more pending). He is in the top 100 or so most cited computer scientists (out of 750,000) according to the CiteSeer digital library and has received a number of awards for his research: the Computers and Thought Award (the premier award for a young AI scientist) in 1999 (this is the only time in the Award's 30 year history that it has been given to someone based in Europe), an IEE Achievement Medal in 2000, and the ACM Autonomous Agents Research Award in 2003. He is a Fellow of the British Computer Society, the Institution of Electrical Engineers, and the European artificial intelligence association (ECCAI) and a member of the UK Computing Research Committee (UKCRC). |
Hai Zhuge
Professor and director of the Key Lab of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences
DYNAMIC INHERITANCE IN SOFT-DEVICES WITHIN THE KNOWLEDGE GRID
Abstract. Inheritance is a natural phenomenon in the biological world. Soft-devices, people and roles constitute a virtual world in the Knowledge Grid environment, which is an intelligent and sustainable interconnection environment that enables people or roles to effectively capture, publish, share and manage knowledge resources. It also provides on-demand services to support innovation, cooperative teamwork, problem solving, and decision making. It uses epistemology and ontology to reflect human cognition characteristics; exploits social, ecological and economic principles; and adopts the techniques and standards developed during work toward the next-generation web. Dynamic clustering of soft-devices is the key feature of the Knowledge Grid. Different from previous software inheritance mechanisms, inheritance in soft-devices is dynamic in nature. This keynote address introduces the methodology of the Knowledge Grid and presents the theory and approach for dynamic inheritance in soft-devices in the Knowledge Grid environment.
 |
Hai Zhuge is the professor and director of the Key Lab of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences. He leads the China Knowledge Grid Research Group (http://kg.ict.ac.cn/), which has 25 young researchers. He is the chief scientist of the China Semantic Grid project, a five-year national fundamental research plan project. He was the keynote speaker at the 2nd International Conference on Grid and Cooperative Computing (GCC03) and the 5th International Conference on Web-Age Information Management (WAIM04), and the Chair of the 2nd International Workshop on Knowledge Grid and Grid Intelligence (KGGI04). He has organized two journal special issues on the theme of Semantic, Intelligent and Knowledge Grids. He is serving as the Area Editor of the Journal of Systems and Software, the associate editor of Future Generation Computer Systems, and on the editorial boards of the Information and Management, Journal of Computer Science and Technology, and Electronic Commerce Research and Applications. His current research interests are the models, theories, methods and applications of the future interconnection environment. He is the author of two books and over sixty papers appeared mainly in leading international conferences and journals such as Communications of the ACM; IEEE Computer; IEEE Intelligent Systems; IEEE Computing in Science and Engineering; IEEE Transactions on Systems, Man, and Cybernetics; Information and Management; Decision Support Systems; Expert Systems with Applications; Journal of Systems and Software; and Concurrency and Computation: Experience and Practice. Prof. Zhuge is an IEEE Senior Member. |
Chengqi Zhang
Faculty of Information Technology University of Technology, Sydney, Australia
AGENTS AND DATA MINING: MUTUAL ENHANCEMENT BY INTEGRATION
Abstract. In this talk, I will tell a story of synergism of two cutting edge technologies - agents and data mining. By integrating these two technologies, the power for each of them is enhanced. Integrating agents into data mining systems, or constructing data mining systems from agent perspectives, the flexibility of data mining systems can be greatly improved. New data mining techniques can add to the systems dynamically in the form of agents, while the out-of-date ones can also be deleted from systems at run-time. Equipping agents with data mining capabilities, the agents are much smarter and more adaptable. In this way, the burden of the run-time reconfiguration of agents is alleviated. The case study will be given to demonstrate such mutual enhancement.
 |
Prof. Chengqi Zhang received a PhD degree from the University of Queensland, Brisbane in Computer Science and a Doctor of Science (higher doctorate) degree from Deakin University. He is currently a research professor in Faculty of Information Technology at University of Technology, Sydney. His areas of research are Data Mining and Multi-Agent Systems. He has published more than 200 refereed papers, edited nine books, and published three monographs. He has supervised 10 PhD students successfully and currently supervising ten on-going PhD students. He is a Senior Member of the IEEE Computer Society (IEEE), an Associate Editor or a member of the editorial board for five international journals. He has served as General Chair, PC Chair, or Organising Chair for four international Conferences and a member of Program Committees for many international or national conferences. His personal web page is http://www-staff.it.uts.edu.au/~chengqi/. |
Mircea Gh. Negoita
Professor in The School of Information Technology, Wellington Institute of Technology (WelTec), New Zealand and the Director of Centre for Computational Intelligence at WelTec
ARTIFICIAL IMMUNE SYSTEMS - A NEW EMERGENT TECHNOLOGY INVOLVED IN AUTONOMOUS INTELLIGENT SYSTEMS AND DATA MINING
Abstract. Artificial Immune Systems (AIS) are still considered with an attitude of reserve by most practitioners in Computational Intelligence, much more some of them even considering this emergent computing paradigm in an infancy stage. My talk try to prove why AIS are of interest, starting from the real-world of applications asking for a radical change of the information systems framework, namely the component-based framework must be replaced with an agent-based one, where the system complexity requires that any agent to be clearly featured by its autonomy. The AIS methods build adaptive large-scale multi-agent systems that are open to the environment, systems that are not at all fixed just after the design phase, but are real-time adaptive to unpredictable situations and malicious defects. The AIS perform the defence of a complex system against malicious defects achieving its survival strategy by extension of the concept of organization of multicellular organisms to the information systems. The main behavioural features of AIS - as self-maintenance, distributed and adaptive computational systems - are defined and described in relation to the Immune System as an information system. A comparison of AIS methodology with other Intelligent Technologies is another point of the talk. The overview of some actual AIS applications is made using a practical engineering design strategy that views AIS as very effective software with agent-based architecture.
 |
|
Mircea Gh. Negoita received the M. Sc. degree from the Technical University of Bucharest (TUB), Romania and the Ph.D. degree from TUB in 1985.
Pericles A. Mitkas
Associate Professor and the Associate Chairman of the Department of Electrical and Computer Engineering at the Aristotle University of Thessaloniki, Greece
KNOWLEDGE DISCOVERY FOR TRAINING INTELLIGENT AGENTS: METHODOLOGY, TOOLS AND APPLICATIONS
Abstract. In this talk we address a relatively young but important area of research: the intersection of agent technology and data mining. This intersection can take two forms: a) the more mundane use of intelligent agents for improved knowledge discovery and b) the use of data mining techniques for producing smarter, more efficient agents. The talk will focus on the second approach. We argue that knowledge, hidden in voluminous data repositories routinely created and main-tained by today's applications, can be extracted by data mining. The next step is to transform this knowledge into the inference mechanisms or simply the behavior of agents in multi-agent systems. We call this procedure "agent training." We define different levels of agent training and we present a software engineering methodology that combines the application of deductive logic for generating intelligence from data with a process for transferring this knowledge into agents. We also introduce Agent Academy, an integrated open-source framework, which supports data mining techniques and agent development tools. We also provide several examples of multi-agent systems developed with this approach.
 |
Dr. Pericles A. Mitkas received his Diploma of Electrical Engineering from Aristotle University of Thessaloniki in 1985 and an MSc and PhD in Computer Engineering from Syracuse University, USA, in 1987 and 1990, respectively. Between 1990 and 2000 he was a faculty member with the Department of Electrical and Computer Engineering at Colorado State University in USA. Currently, Dr. Mitkas is an Associate Professor and the Associate Chairman of the Department of Electrical and Computer Engineering at the Aristotle University of Thessaloniki, Greece. He is also the Associate Director of the Informatics and Telematics Institute of the Center for Research and Technology - Hellas (CERTH). His research interests include databases and knowledge bases, data mining, software agents, enviromatics and bioinformatics. Dr Mitkas is a senior member of the IEEE Computer Society. His work has been published in over 120 papers, book chapters, and conference publications. He is the co-author of a new book on "Agent Intelligence through Data Mining" by Springer. Dr. Mitkas can be reached by e-mail at: mitkas@eng.auth.gr |
Leonid I. Perlovsky
Dr. Leonid Perlovsky is Principal Research Physicist and Technical Advisor at the Air Force Research Laboratory/SNHE
EVOLVING AGENTS: COMMUNICATION AND COGNITION
Abstract. Computer programming of complex systems is a time consuming effort. Results are often brittle and inflexible. Evolving, self-learning flexible multi-agent systems remain a distant goal. This paper analyzes difficulties toward developing evolving systems and proposes new solutions. The new solutions are inspired by our knowledge of the human mind. The mind develops language and cognitive abilities jointly. Real-time sensor signals and language signals are integrated seamlessly, before signals are understood, at pre-conceptual level. Learning of conceptual contents of the surrounding world depends on language and vice versa. This ability for integrated communication and cognition is a foundation for evolving systems. The paper describes a mathematical technique for such integration: fuzzy dynamic logic and dual cognitive-language models. We briefly discuss relationships between the proposed mathematical technique, working of the mind, applications to understanding-based search engines and evolving multi-agent systems.
 |
Dr. Leonid Perlovsky is Principal Research Physicist and Technical Advisor at the Air Force Research Laboratory/SNHE. Previously, from 1985 to 1999, he served as Chief Scientist at Nichols Research, a $0.5 B high-tech organization, leading the corporate research in information science, intelligent systems, neural networks, optimization, sensor fusion, and algorithm development. In the past he served as professor at Novosibirsk University and New York University. He participated as a principal in commercial startups developing tools for text understanding, biotechnology, and financial predictions. He published about 50 papers in refereed scientific journals and about 230 papers in conferences, delivered invited keynote plenary talks and authored a book "Neural Networks and Intellect: model-based concepts", Oxford University Press, 2001 (currently in the 3rd printing). Dr. Perlovsky serves on multiple IEEE Committees, IEEE World Congress on Computational Intelligence 2006 Operating Committee, as General Chair for IEEE International Conference on Integrating of Knowledge Intensive Multi-Agent Systems (KIMAS), Program Chair for IEEE International Conference on Computational Intelligence Measurement Systems and Applications (CIMSA), Chair IEEE Boston Computational Intelligence Chapter, and as Editor-in-Chief for an Elsevier journal "Physics of Life Reviews". Dr. Leonid Perlovsky can be reached by e-mail at: Leonid.Perlovsky@hanscom.af.mil |
Copyright ©2004 Intelligent Systems Laboratory, SPIIRAS, All rights reserved.