IEEE Symposium Series on Computational Intelligence 2009

2009 IEEE Symposium on Intelligent Agents

The intersection between Computational Intelligence and Agent technology opens new significant opportunities in many fields where the representation and management of complex systems play a fundamental role. In the formulation of Agent-based systems, the role of uncertainty is crucial for an efficient and coherent resolution of complex problems. Agents overcome classical programs thanks to their inner capabilities to be autonomous and to adapt their behaviour with the changing of the environment where agents live and interact. This means that inevitably they meet uncertainty during their work, or in many cases, for the high complexity of the problem, the information they handle is (or needs to be) approximate.

IA 2009 will aim to provide a leading international forum to bring together researchers and practitioners from diverse fields, such as computer science, information technology, business, education, human factors, systems engineering, and robotics. The symposium will aim to examine the design principles and performance characteristics of various approaches in intelligent agent technology. In addition, the symposium will aim to increase the cross-fertilization of ideas on the development of autonomous agents and multi-agent systems among different domains. By encouraging idea-sharing and discussions on the underlying logical, cognitive, physical, and sociological foundations as well as the enabling technologies of intelligent agents, IA 2009 will foster the development of novel paradigms and advanced solutions in agent-based computing.

The symposium will bring together researchers from both industry and academia from the various disciplines contributing to the area on intelligent agents. Such disciplines include, but are not limited to:

• Embedded and Robotic Agents
• Mobile Agents
• Autonomous Knowledge and Information Agents
• Agent Systems Modeling and Methodology
• Autonomous Auctions and Negotiation
• Agent-Based Marketplaces
• Agent-Based Distributed Data Mining
• Agents for Intelligent Manufacturing Systems
• Agents for E-Commerce
• Agents for Dialogue Systems
• Environment-aware Agents
• Holonic Agents
• Semantic Web Agents
• Human Agent Interaction
• Agents for Smart Environments
• Middleware Agents
• Agent Interaction Protocols
• Multi-Agent Coordination Techniques
• Multi-Agent Autonomic Architectures
• Multi-Agent Planning and Re-Planning
• Social Interactions in Multi-Agent Systems
• Agents Applications

Special Session on Self-Adaptive Agents
Session Organizers:
Amir Hussain, University of Stirling, UK
Sherief Abdallah, British University in Dubai, UAE
Giancarlo Fortino, University of Calabria, Italy
Muaz Niazi, Foundation University, Pakistan

Recent literature has introduced a number of new terms in self-* agents. (Agents with Self- capabilities by being Self-Adaptive, Self-Organizing, Self-Stabilizing, Self-Healing etc.) The goal of this session is to bring researchers and practitioners together with an interest in agents possessing in-built capabilities of learning, adaptation and organization. These so called Self-Adaptive agents can range from individual agents that may use a variety of techniques to improve their performance in their environments to groups of agents self-organizing to improve collective performance. The key focus of the session will be on "Engineered Emergence" in self-adaptive agents (including self-healing and self-organizing agents). Instead of having uncontrollable properties, which are the norms of current self-organizing systems, engineered emergence in the next generation of self-adaptive agents will involve developing planned self-organization and adaptation to move the ideas from their initial origins in science to engineering.

Themes and topics include, but are not limited to the following:

• Machine Learning (Individual or Collective Learning) for self-adaptation in Agents
• Analysis, design modeling and simulation frameworks for analyzing autonomic agent based systems including evaluation criteria e.g. for dynamic adaptation (performance, availability, power, etc)
• Applications of Self-Adaptive Agents (Business, Self-Adaptive agents using RDBMS, Grid Computing, commercial and mission critical applications benefiting from Self-Adaptive Agents, etc)
• Self-adaptive agents in Physical Systems (Pervasive Computing, Ambient Intelligence, Ambient Assisted Living Systems, etc)
• Application of Self-Adaptive/Organizing/Healing agents in modeling and simulation of natural systems
• Self-Adaptive Agents in Spatial & Amorphous Computing Systems
• Self-Adaptive agents in Communication Networks (dynamic routing, content management and distribution, sensor networks, etc)
• Self-Adaptive Agents using Self-healing capabilities: dynamic fault diagnosis and correction; workload characterization; self-recognition; machine learning strategies; dynamic stability in large-scale networks; dynamic adaptation; architectures for self-healing systems; balancing desirable properties (e.g. optimization versus robustness, etc)
• Agent Oriented Software Engineering (methodologies and tools for designing autonomous agents, autonomic control and self-organization, etc)
• Novel approaches for managing complexity in Self-Organizing/Self Adaptive Agents (economic/market based, nature-inspired, social system based, etc)
• Theoretical approaches to self-adaptive autonomous agents.

A follow-on Journal Special Issue is also planned based on selected expanded and revised versions of best papers. Only papers actually presented at the session will be considered.

Special Session on Agents for Ad Hoc and Sensor Network Activities
Session Organiser:
Rabie A. Ramadan, The German University in Cairo, Egypt

Ad hoc and sensor networks became essential parts of our daily activities. For instance, sensor networks are used to monitor critical infrastructure, habituate areas, and battlefields as well as in rescue operations. At the same time, agent technology has been proven to be efficient in many applications, especially, applications that require smartness and efficient energy usage.
Therefore, this session is targeting new innovative research in the field of ad hoc and sensor networks using single and multi agents. The session includes but not limited to design, theory, applications, and usage of agents for the purpose of ad hoc and sensor networks.

Special Session on Intelligent Agent Applications in Industry and Commerce
Session Organiser:
Faiyaz Doctor, University of Essex, UK

Computational Intelligence (CI) has been growing in significant popularity within the business and commercial world through its interplay with agent based systems and technologies. Techniques such as fuzzy logic, neural networks and evolutionary computation, as well as other optimization and adaptive learning approaches are gathering wider acceptance and providing robust working solutions to complex real world problems. Some of the areas where IA approaches have been applied include: decision support, financial prediction, scheduling and processes optimization, electronic commerce, intelligent engine controllers, building energy management systems, data mining and knowledge discovery applications.

The special session on Applications of Intelligent Agents in Industry and Commerce will aim to provide an international forum to bring together researchers and practitioners from diverse fields, such as computer science, information technology, business, education, human factors, systems engineering, embedded systems and robotics. The session will aim to increase the awareness of IA based approaches in industry and commerce, by examining the design principles and performance characteristics of various applications that have been developed to address a variety of business and commercial problems. Participant submissions should aim to cover the following topics:

• The problem domain and identified commercial and business needs.
• The competitive advantages, value adding potential and selling points of the technology.
• Description of the developed application, IA based technology or approaches.
• The outcome of trials and resulting improvements over existing systems or processes.

In addition the session will aim to promote cross-fertilization of ideas on the development of these systems across different applied domains. By encouraging idea sharing and discussions, our aim is to foster a better understanding of real world problems and the development of novel paradigms to provide working and value-generating solutions.

In addition the session will aim to promote cross-fertilization of ideas on the development of these systems across different applied domains. By encouraging idea sharing and discussions, our aim is to foster a better understanding of real world problems and the development of novel paradigms to provide working and value-generating solutions.

The session will bring together researchers from both industry and academia from the various disciplines involved in developing high quality research and applying IA technologies to commercial and business applications. Areas include, but are not limited to:

• Financial, accounting and risk based applications
• Industrial manufacturing process scheduling, optimization and control systems
• Enterprise knowledge management / knowledge discovery applications
• Recruitment and human resources systems
• Intelligent search and retrieval based applications
• Semantic web based applications
• Decision support systems
• Energy management and control systems
• Embedded systems for optimization, fault detection, and adaptive control
• Ubiquitous and pervasive computing based application

Special Session on: Learning and Adaptivity in Agent Technology
Session organizer:
Abdelhamid Bouchachia, University of Klagenfurt, Austria

Learning and adaptivity and are fundamental issues in developing and implementing reasoning in agent-based applications. Relying on metaphors of nature, these issues are inspired from biological and cognitive plausibilities which are the basis for many computational models such as neural networks, evolutionary computation, probabilistic reasoning and many other softcomputing and machine learning models.

The intelligence of agents is largely attributed to their ability to continually learn and self-adapt to the environment. This becomes crucial when the environment dynamically changes over time. Therefore, agents should self-adjust as new perceptions, facts and forces take place in the system. Because of this dynamicity, agents evolving in a multi-agent infrastructure are required to be not only individually intelligent but also should contribute to the collective intelligence of the system. That is, the collective behavior must emerge via mechanisms of adaptation and self-organization.

The aim of this Special Session is to present the recent advances and to discuss the new directions in this area of research. Accepted papers will be published either in a special issue or a book.

Expected topics include (but not limited to):

• On-line learning algorithms
• Evolution and learning in changing environments
• Learning and Adaptive reasoning
• Reactive agents and adaptivity
• Coordination and self-organization
• Learning and Adaptivity in:
• Revision theory
• Situation theory
• Game theory, etc.
• Perception and evolution
• Adaptivity and learning models in computational intelligence:
• Neural networks
• Evolutionary computation
• Swarm intelligence
• Uncertainty and fuzziness modeling, etc
• Adaptivity and learning in applications
• Smart systems
• Ambient and ubiquitous environments
• Distributed intelligence
• Robotics
• Internet
• E-commerce, etc.

Paper Submission to Special Sessions

To submit manuscripts to special sessions, authors must follow the conference guidelines and instructions. Only papers submitted through the conference submission system will be considered. When submitting a paper for a special session, the title of the special session must be selected as main research area in the conference submission system (selecting other research areas will result in submission to the regular sessions).

The paper submission deadline for the special session is the same of the regular sessions.

Program Chair
Hani Hagras, The German University in Cairo, Egypt and the University of Essex, UK

Program Committee
Waleed Abdulla, University of Auckland, New Zealand
Plamen Angelov, University of Lancaster, UK
Abdelhamid Bouchachia, Klagenfurt University, Austria
Selcuk Candan, Arizona State University, USA
Diane Cook, Washington State University, USA
Kerstin Dautenhahn, University of Hertfordshire, UK
Hakan Duman, British Telecom, UK
Faiyaz Doctor, University of Essex, UK
Barbara Hammer, Clausthal University of Technology, Germany
Mohamed Ibrahim, Heilbronn University, Germany
Achilles Kameas, Hellenic Open University and CTI, Greece
Ryszard Kowalczyk, Swinburne University of Technology, Australia
Chang-Shing Lee, National University of Tainan, Taiwan
Vincenzo Loia, University of Salerno, Italy
Antonio Lopez, University of Oviedo, Spain
Wolfgang Minker, University of Ulm, Germany
Muaz Niazi, Foundation University, Pakistan
Rabie Ramadan, The German University in Cairo, Egypt
Sabrina Senatore, University of Salerno, Italy
Dipti Srinivasan, National University of Singapore, Singapore
Kostas Stathis, Royal Holloway, University of London, UK
Mihaela Ulieru, University of New Brunswick, Canada
Christian Wagner, University of Essex, UK
Michael Weber, University of Ulm, Germany