An improved TANC classification algorithm based on C4.5

Author

Xiao-qiang Zhao ; Jia-min Yang

Author_Institution

Coll. of Electr. & Inf. Eng., Lanzhou Univ. Of Tech., Lanzhou, China

fYear

2014

fDate

May 31 2014-June 2 2014

Firstpage

4992

Lastpage

4996

Abstract

Tree Augmented Naive Bayes Classification (TANC) is not very well to deal with continuous data and it ignores partial data in the absence of data attribute value and this can reduce the result accuracy. To resolve this problem, an improved algorithm based on C4.5 is proposed in this paper. The proposed algorithm firstly modifies the available training data according to the predictions of C4.5, then continuous data is discretized by dividing many finite intervals of attributes, this modified training data is used to train TANC. In this way it can improve the classification accuracy of the TANC. The experimental results show that the improved algorithm is superior to TANC in terms of classification accuracy.

Keywords

learning (artificial intelligence); pattern classification; C4.5 algorithm; TANC classification algorithm; TANC training; classification accuracy; data attribute value; data discretization; tree augmented naive Bayes classification; Accuracy; Breast; Classification algorithms; Electronic mail; Iris; Prediction algorithms; Training data; C4.5 algorithm; Machine learning; Tree Augmented Naive Bayes; classification;

fLanguage

English

Publisher

ieee

Conference_Titel

Control and Decision Conference (2014 CCDC), The 26th Chinese

Conference_Location

Changsha

Print_ISBN

978-1-4799-3707-3

Type

conf

DOI

10.1109/CCDC.2014.6853067

Filename

6853067