Los Angeles, CA
March 31, 2009 to April 2, 2009
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/CSIE.2009.294
Data mining is a process to discover useful, possibly unexpected, patterns from the large set of data and widely used in the large information processing applications. Classification is used to classify the data into a set of classes based on some attributes for further processing. Real world application contains very large,imprecise and noisy data. In this case, the knowledge representation need some linguistic term instead of discrete value. In such a scenario fuzzy logic based processing is a natural choice. In this paper, we propose an algorithm for classification using fuzzy approach,which performs class dependent fuzzy discretization.The continuous numeric data is converted in linguistic form which helps in fuzzy classification. The proposed method is compared with standard non-fuzzy discretization techniques where class-attribute relationship is not considered and intervals are predefined. Simulation results show the improved performance of the proposed method.
Data Mining (DM), Fuzzy based Classification, Interval discretization, Fuzzy discretization
Rupa G. Mehta, Dipti P. Rana, Mukesh A. Zaveri, "A Novel Fuzzy Based Classification for Data Mining Using Fuzzy Discretization", CSIE, 2009, 2009 WRI World Congress on Computer Science and Information Engineering, CSIE, 2009 WRI World Congress on Computer Science and Information Engineering, CSIE 2009, pp. 713-717, doi:10.1109/CSIE.2009.294