The Method of Improving the Structure of the Decision Tree Given by the Experts
This paper presents the problem of sequential decision making in the pattern recognition task. This task can be presented using a decision tree. In this case, it is assumed that the structure of the decision tree is determined by experts. The classification process is made in each node of the tree. This paper proposes a way to change the structure of the decision tree to improve the quality of classification. The split criterion is based on the confusion matrix. The obtained results were verified on the basis of the example of the computer-aided medical diagnosis.
KeywordsDecision Tree Internal Node Confusion Matrix Acute Abdominal Pain Neutral Network
Unable to display preview. Download preview PDF.
- 1.Berger, J.: Statistical Decision Theory and Bayesian Analysis. Springer, New York (1993)Google Scholar
- 4.Duda, R.O., Hart, P.E., Stork, D.G.: Pattern Classification. John Wiley and Sons (2000)Google Scholar
- 9.Mitchell, T.M.: Machine Learning. McGraw-Hill Comp., Inc., New York (1997)Google Scholar
- 10.Mui, J., Fu, K.S.: Automated classification of nucleated blood cells using a binary tree classifier. IEEE Trans. Pattern Anal. Mach. Intell. PAMI-2, 429–443 (1980)Google Scholar
- 12.Quinlan, J.R.: Induction on Decision Tree. Machine Learning 1, 81–106 (1986)Google Scholar
- 14.Getting Started with SAS Enterprise Miner 6.1, http://support.sas.com/documentation/onlinedoc/miner