Keynote Speakers of ISKE 2015
Dr. Jun Liu (BSc, MSc, PhD)  (website)
Title: Advanced Rule-Based Systems for Sensing Decision Support
Senior Lecturer in Computer Science：
Artificial Intelligence and Applications Research Group
Computer Science Research Institute
Short Biography of Dr. Jun Liu  (PDF)
Professor Jie Lu (BSc, MAppSc, MEdu, PhD)  (website)
Title: Recommender Systems for e-Business Applications
Abstract and short CV(PDF)
Associate Dean (Research), Faculty of Engineering & Information Technology,
Director of DeSI lab in Centre for Quantum Computation and Intelligent Systems,
Co-Director, Global Big Data Technologies Centre, University of Technology Sydney, Australia
Editor-in-Chief, Knowledge-based Systems
Decision support systems, e-services, e-business, e-government, group decision making, resource planning, database design and development, system modeling, web-based information systems, intelligent decision support systems, fuzzy optimization, fuzzy decision making, business intelligence, personalised recommender systems, system evaluation.
Prof. Patrick S. P. Wang, Fellow IAPR, ISIBM, WASE (PhD)  (website)
Title:IPR and Applications to Interactive Recognition System --- Security, Safer Transportation and Greener World
Thinning Methodologies (Parallel and Sequential)
Words (Characters) Learning/Understanding/Recognition Using Intelligent Techniques
Chinese OCR (Optical Character Recognition)
Invited Keynote Talk : IPR & Applications
Prof. Patrick S. P. Wang, PhD’s Brief Vitae  (PDF)
Prof. Javier Montero(PhD)
Title: A personal view on the evolution of the definition of fuzzy sets
Javier Montero is Full Professor at the Department of Statistics and Operational Research, Faculty of Mathematics, Complutense University of Madrid (Spain). He holds a Ph.D. in Mathematics from Complutense University since 1982 and has been leading research projects since 1987. He is author of more than 100 research papers in refereed journals such as Approximate Reasoning, Computational Intelligent Systems, Computer and Operational Research, European Journal of Operational Research, Fuzzy Sets and Systems, General Systems, Human and Ecological Risk Assesment, IEEE Transactions on Neural Nerworks, IEEE Transactions on Fuzzy Systems, IEEE Transactions on Systems, Man and Cybernetics, IEEE Transactions on Industrial Informatics, Information Sciences, Intelligent Systems, Journal of Algorithms, Knowledge Based Systems, Kybernetes, Kybernetika, Mathware, Multiple Valued Logic, New Mathematics and Natural Computation, Non Linear Analysis, Omega, OR Spectrum, Pure and Applied Geophysics, Remote Sensing, Soft Computing, Top, and Uncertainty, Fuzziness and Knwledge-Based Systems, plus a similar number of refereed papers as book chapters. His research interests are in Aggregation Operators, Preference Representation, Multicriteria Decision Aid, Group Decision Making, System Reliability Theory and Classification problems, mainly viewed as application of Fuzzy Sets Theory. He has been the President of the European Association for Fuzzy Logic and Technology (EUSFLAT), Vice-President of the International Fuzzy Systems Association (IFSA), and Dean at the Faculty of Mathematics, Complutense University of Madrid, with more than 18 years in different academic management positions at the University. He has been also Vice-Rector at his University, and currently he is President Elect of IFSA.
Prof. Takao Terano(PhD)
Dr. Takao TERANO is a professor at Department of Computational Intelligence and System Science, Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology.
He received BA degree in Mathematical Engineering in 1976 and, M. A. degree in Information Engineering in 1978 both from University of Tokyo, and Doctor of Engineering Degree in 1991 from Tokyo Institute of Technology.
His research interests include Agent-based Modeling, Knowledge Systems, Evolutionary Computation, and Service Science.
He is a member of the editorial board of major Artificial Intelligence and System science- related academic societies in Japan and a member of IEEE, AAAI, and ACM.
He is also the president of PAAA.
Taming One Million Learning Agents through a Learning Classifier System Technique
In this presentation, focused on cutting-edge computational techniques, I talk about a Multi-Agent System approach (MAS) using the concepts of Learning Classifier System (LCS).
In our MAS, each agent is designed to learn both as individual and as an organization.
They are distributed across multiple clusters of computing nodes.
One node acts as a manager to distribute knowledge and task between agents living in different clusters.
When an agent finishes its learning loop, it shares its best knowledge to other agents by sending them to the manager.
The manager then may give the agent new task to learn, or it may order the agent to continue learning to improve its current knowledge even more.
The method is applied a distributed video recommendation system. With a benchmark example, we can let one million agents learn adequate recommendation knowledge.
The globally-good knowledge is useful when the system encounters new users, and the locally-good knowledge often offers pleasant surprises to existing users.