Research Seminar - November 14, 2002

Fuzzy Rule Based Classifier

Abstract:

Fuzzy systems based on fuzzy if-then rules are successfully applied to various control problems such as truck backing, broom balancing and so forth. One of the most significant differences between control problems and classification problems is the dimensionality of inputs. While control problems usually involve only a few inputs, real-world pattern classification problems often involve several attributes The aim here is to construct a fuzzy classifier system that can automatically generate fuzzy if-then rule from training patterns for multi-dimensional for pattern classification problems.