Article ID: | iaor20071527 |
Country: | China |
Volume: | 14 |
Issue: | 3 |
Start Page Number: | 201 |
End Page Number: | 205 |
Publication Date: | Jun 2005 |
Journal: | Systems Engineering and Theory Methodology Applications |
Authors: | Wang Zhengou, Ni Chunpeng |
Keywords: | neural networks, decision theory |
This paper presents a new data classifying method based on a combination of neural networks and decision trees. The method firstly ranks attributes based on the importance of the attributes, and then prunes the attributes using a Radial Basis Function neural network, and finally builds a decision tree and extracts rules. Compared with traditional data classifying methods using decision tree, the present method can find the minimal decision tree directly without pruning, which raises the efficiency of building decision tree and improves the prediction precision of the rules produced. The method is suitable for large scale and high dimension data classifying problem.