From: earlcox@earlcoxreports.com   
      
   Changing the shape (type, width, skew, rate of change (slope)) and the   
   overlap of fuzzy sets will change the semantics of the rules that use the   
   fuzzy sets. Even a small change can have a profound impact on the resulting   
   classification system (see The Fuzzy Systems Handbook (2nd Ed.) for a   
   detailed discussion of these issues).   
      
   Since the shape reflects the meaning of the fuzzy set, the shape is dictated   
   by the needs of the model. Understanding how a fuzzy set encodes the   
   semantics of the terms underlying each variable will, more or less,   
   automatically tell you how to design the fuzzy sets.   
      
   Earl   
      
      
   "Peter Rijnbeek"  wrote in message   
   news:camsg9$186$1@brutus.eur.nl...   
   > Can anyone explain me what the effect of the shape of a fuzzy set is on   
   the   
   > performance of a fuzzy rule in a classification task? How do you decide   
   > which shape is best for your problem?   
   >   
   > Thanks Peter   
   >   
   >   
      
   --- SoupGate-Win32 v1.05   
    * Origin: you cannot sedate... all the things you hate (1:229/2)