LUNCHEON PLENARY 

Monday, Noon - 1:30 p.m. 

(Pavilion Salon C)

Soft Computing: A Common Framework Approach to Represent Meta_Heuristics

Dr. Piere P. Bonissone, General Electric Global Research Center, Niskayuna, NY USA

Overview: Meta-heuristics are heuristic procedures used to tune, control, guide, allocate computational resources or reason about object-level problem solvers in order to improve their quality, performance, or efficiency. Offline meta-heuristics define the best structural and/or parametric configurations for the object-level model, while on-line heuristics generate run-time corrections for the behavior of the same object-level solvers.

Soft Computing is a framework in which we encode domain knowledge to develop such meta-heuristics. We explore the use of meta-heuristics in three application areas: a) control; b) optimization; and c) classification.

In the context of control problems, we describe the use of evolutionary algorithms to perform offline parametric tuning of fuzzy controllers, and the use of fuzzy supervisory controllers to perform on-line mode-selection and output interpolation.

In the area of optimization, we illustrate the application of fuzzy controllers to manage the transition from exploration to exploitation of evolutionary algorithms that solve the optimization problem.

In the context of discrete classification problems, we have leveraged evolutionary algorithms to tune knowledge-based classifiers and maximize their coverage and accuracy.

Biography:
Education: PhD EECS, 1979, UC Berkeley; MS ME, 1979, UC Berkeley; MS in EECS, 1978, UC Berkeley; BS in EE/ME, 1975, University of Mexico City (UNAM).

Experience: A computer scientist at the General Electric Global Research center (GE-GR) since 1979, Dr. Bonissone has carried out research and projects in Artificial Intelligence, expert systems, simulation, fuzzy sets, and Soft Computing. Dr. Bonissone has led many projects in Fuzzy Logic Control and Soft Computing, ranging from the control of turbo-shaft engines to the use of Fuzzy Logic in dishwashers, locomotives, and power supplies. He has also developed case-based and fuzzy-neural systems to accurately estimate the value of single-family residential properties when used as mortgage collaterals. He has extensive experience in data mining and analysis, which he used to develop a profitability model to identify preferred customers for GE Financial Assurance - Long Term Care. Currently he is leading a large internal project that uses fuzzy-rule based and fuzzy case-based reasoning to partially automate the underwriting process of life insurance applications. Recently he has led a Soft Computing (SC) group in the development of SC application to diagnostics and prognostics of processes and products, including the prediction of paper-web breakage in paper mills.

Academic Experience: Dr. Bonissone is an Adjunct Professor of ECSE Dept. at the Rensselaer Polytechnic Institute (RPI), Troy, NY, where he teaches the course ``Fuzzy Sets and Expert Systems in Computer Engineering'' (course taught since 1982). Since 1993 he has been the Editor-in-Chief of the International Journal of Approximate Reasoning (North-Holland).
Honors and Awards: In 1986, he received the King-Sun Fu Award from the North American Fuzzy Information Processing Society for his contributions to the field of fuzzy sets and approximate reasoning. In 1989 he received the Dushman Award GE CRD for his work on reasoning with uncertainty. In 1993 he received the Coolidge Fellowship Award from GE CRD for overall technical accomplishments. In 1996 he became a Fellow of the American Association for Artificial Intelligence (AAAI). In 1999 he received the Dushman Award from GE CRD for his work on medical equipment diagnostics
Papers and Patents: Dr. Bonissone has co-edited four books: Expert Systems in Structural Safety Assessment (Springer-Verlag 1989), Uncertainty in Artificial Intelligence 6 (North-Holland 1991), Uncertainty in Artificial Intelligence 7 (Morgan Kaufmann 1991), and the Handbook of Fuzzy Computation (Institute of Physics Publishing, 1998). He has published more than 100 articles in the area of expert systems, approximate reasoning, fuzzy sets, pattern recognition, decision analysis, and soft computing. He received 29 patents (and 19 more pending) from the U.S. Patent Office for his work on reasoning with uncertainty and fuzzy control, automated decision making with soft constraints, etc.

Professional Activities: Program and Conference Chair of the Uncertainty in AI conference (1989 & 1990). He has been the keynote speaker of many important conferences in the Artificial Intelligence and Soft Computing field, such as AAAI’91, IEEE ICNN ’92, IEEE WCCI’94, FNS’98, ECAI’2000, to name a few. He is in the Editorial board of Fuzzy Sets and Systems (North-Holland) and the International Journal of Uncertainty, Fuzziness and Knowledge-based Systems (World Scientific)

IEEE Activities:
- Program Chair of the 1993 IEEE International Conference on Fuzzy Systems
- Conference Chair of the 1994 IEEE International Conference on Fuzzy Systems
- Co-treasurer of the 1997 IEEE International Conference on Fuzzy Systems
- Technical Co-Chair of the 2002 IEEE International Conference on Fuzzy Systems
- Co-treasurer of the 2002 World Congress on Computational Intelligence
- Vice-President Finance for the IEEE Neural Networks Council (1993-2000).
- President Elect of the IEEE Neural Networks Council (2001)
- President of the IEEE Neural Network Society (2002)
- Currently Past President of the IEEE Neural Network Society