Measuring feature uncertainty by using similarity

Authors:
Barna Cornel
Affiliations:
"Aurel Vlaicu" University, Arad, Romania
Venue:
FS'06 Proceedings of the 7th WSEAS International Conference on Fuzzy Systems
Year:
2006

Citing 4
Cited 0

Modified product fusion

Pattern Recognition Letters
Logic-Based Granular Prototyping

COMPSAC '02 Proceedings of the 26th International Computer Software and Applications Conference on Prolonging Software Life: Development and Redevelopment
Knowledge-Based Clustering: From Data to Information Granules

Knowledge-Based Clustering: From Data to Information Granules
Reconstruction problem and information granularity

IEEE Transactions on Fuzzy Systems

Quantified Score

Hi-index	0.02

Visualization

Abstract

This article proposes a measurement of the uncertainty used in feature labeling which takes into consideration the similarity between the analyzed characteristic and a prototype, and the dissimilarity between the same characteristic and the nearest neighboring prototype. Using the similarity and not the equivalent relationship, the method is more general, the transitivity not being requested.