Similarity Classifier based on Schweizer & Sklars t-norms

  • Luukka, P. (Laboratory of Applied Mathematics Lappeenranta University of Technology) ;
  • Sampo, J. (Laboratory of Applied Mathematics Lappeenranta University of Technology)
  • Published : 2004.08.25

Abstract

In this article we have applied Schweizer & Sklars t-norm based similarity measures to classification task. We will compare results to fuzzy similarity measure based classification and show that sometimes better results can be found by using these measures than fuzzy similarity measure. We will also show that classification results are not so sensitive to p values with Schweizer & Sklars measures than when fuzzy similarity is used. This is quite important when one does not have luxury of tuning these kind of parameters but needs good classification results fast.

Keywords