Title :
On filling-in missing attribute values for Bayes and fuzzy classifiers
Author :
Ralescu, Anca ; Visa, Sofia
Author_Institution :
Dept. of Comput. Sci., Univ. of Cincinnati, Cincinnati, OH
Abstract :
Multidimensional classification problems often must address the issue of missing attribute values. The solution for this problem in the case of two frequency based classifiers is discussed here. The Bayes approach of boosting low frequency values, or filling-in missing values is compared to the interpolation operation used in the fuzzy classifiers.
Keywords :
Bayes methods; fuzzy set theory; interpolation; pattern classification; Bayes classifiers; filling-in missing attribute values; frequency based classifiers; fuzzy classifiers; interpolation operation; multidimensional classification problems; Bayesian methods; Computer science; Decision trees; Frequency; Fuzzy sets; Interpolation; Multidimensional systems; Predictive models; Testing; Training data;
Conference_Titel :
Fuzzy Information Processing Society, 2008. NAFIPS 2008. Annual Meeting of the North American
Conference_Location :
New York City, NY
Print_ISBN :
978-1-4244-2351-4
Electronic_ISBN :
978-1-4244-2352-1
DOI :
10.1109/NAFIPS.2008.4531263
