Metrics
66 Record Views
Conference proceeding
On combining multiple classifiers by fuzzy templates
1998 Conference of the North American Fuzzy Information Processing Society, NAFIPS : August 20 & 21, 1998, Pensacola Beach, Florida, USA (Cat. No.98TH8353), pp.193-197
Conference of the North American Fuzzy Information Processing Society, NAFIPS (Pensacola Beach, Florida, USA, 08/20/1998–08/21/1998)
1998
Web of Science ID: WOS:000077524200039
Abstract
We study classifier fusion by the fuzzy template (FT) technique. Given an object to be classified, each classifier from the pool yields a vector with degrees of “support” for the classes, thereby forming a decision profile. A fuzzy template is associated with each class as the averaged decision profile over the training samples from this class. A new object is then labeled with the class whose fuzzy template is closest to the objects’ decision profile. We give a brief overview of the field to place the FT approach in a proper group of classifier combination techniques. Experiments with two data sets (satimage and phoneme) from the ELENA database demonstrate the superior performance of FT over: a version of majority voting; aggregation by fuzzy connectives (minimum, maximum, and product); and (unweighted) average.
Related links
Details
- Title
- On combining multiple classifiers by fuzzy templates
- Publication Details
- 1998 Conference of the North American Fuzzy Information Processing Society, NAFIPS : August 20 & 21, 1998, Pensacola Beach, Florida, USA (Cat. No.98TH8353), pp.193-197
- Resource Type
- Conference proceeding
- Conference
- Conference of the North American Fuzzy Information Processing Society, NAFIPS (Pensacola Beach, Florida, USA, 08/20/1998–08/21/1998)
- Publisher
- IEEE; [Piscataway, NJ]
- Copyright
- © IEEE
- Identifiers
- WOS:000077524200039; 99380090647506600
- Academic Unit
- Public Health; Usha Kundu, MD College of Health
- Language
- English