9th International Conference on Information Technology (ICIT'06)
A comparative analysis of discretization methods for Medical Datamining with Na?ve Bayesian classifier
Bhubaneswar, India
December 18-December 21
ISBN: 0-7695-2635-7
Ranjit Abraham, TocH Institute of Sci. and Tech., Arakkunnam, Kerala,India
Naive Bayes classifier has gained wide popularity as a probability-based classification method despite its assumption that attributes are conditionally mutually independent given the class label. This paper makes a study into discretization techniques to improve the classification accuracy of Na?ve Bayes with respect to medical datasets. Our experimental results suggest that on an average, with Minimum Description Length (MDL) discretization the Na?ve Bayes Classifier seems to be the best performer compared to popular variants of Na?ve Bayes as well as some popular non-Na?ve Bayes statistical classifiers.
Citation:
Ranjit Abraham, Jay B.Simha, S.S Iyengar, "A comparative analysis of discretization methods for Medical Datamining with Na?ve Bayesian classifier," icit, pp.235-236, 9th International Conference on Information Technology (ICIT'06), 2006