Bilkent University
Department of Computer Engineering
S E M I N A R
Fuzzy clustering-based discretization for Rule-based Classification
Dr. Keivan Kianmehr
University of Calgary
A rule-based classification approach that integrates fuzzy class association rules and support vector machines will be presented. A fuzzy discretization technique based on fuzzy c-means clustering algorithm is employed to transform the training set, particularly quantitative attributes, to a format appropriate for association rule mining. A hill-climbing procedure is adapted for automatic thresholds adjustment and fuzzy class association rules are mined accordingly. The compatibility between the generated rules and fuzzy patterns is considered to construct a set of feature vectors, which are used to generate a classifier. The reported test results show that compatibility rule-based feature vectors present a highly qualified source of discrimination knowledge that can substantially impact the prediction power of the final classifier. In order to evaluate the applicability of the proposed method, it has been utilized for the popular task of gene expression classification and the results have been validated and well received by our collaborators from the school of Medicine at the University of Calgary.
DATE: 10 May, 2010, Monday @ 13:40
PLACE: EA 409