Information classification algorithm based on decision tree optimization
- 104 Downloads
With the rapid development of information technology, the efficiency of information management has drawn increasing importance with its broadening application. Hence, a new information classification algorithm has proposed in this paper so as to improve information management of the limited resources by reducing its complexity. However, ID3 algorithm is a classical and imprecise algorithm in data mining, because traditional ID3 algorithm selects the attribute that has the maximum information gain according to the data set as that of the split node. Then the data subset is further divided according to the number of attribute values, and the information gain of each subset is calculated recursively. Decision Tree Optimization Ratio is the core approach in this algorithm, whose basic ideas have been introduced and analysed, proving to be more complex. Therefore, the authors propose a relatively precise RLBOR algorithm which takes the number of nodes in the decision tree model into consideration. The experiment show more precise of RLBOR algorithm.
KeywordsID3 algorithm Decision tree model Decision tree optimization ratio Leaf nodes
This work was funded by the National Natural Science Foundation of China under Grant (Nos. 61772152, 61502037), and the Basic Research Project (Nos. JCKY2016206B001, JCKY2014206C002 and JCKY2017604C010).
- 1.Dobra, A., Garofalakis, M., Gehrke, J. and Rastogi, R.: Processing complex aggregate queries over data streams. In: Proc. 2002 ACM Sigmod Int. Conf. Management of Data, Madison, WI, pp. 90–98 (2002)Google Scholar
- 2.Rajgopal Kannan, K., Sarangi, S., Ray, S. and Sitharama Iyengar, S.: Minimal sensor integrity in sensor grids. In: Proc. Int. Conf. Parallel Processing, pp. 21–27 (2002)Google Scholar
- 3.Quinlan, J.R.: Induction of decision trees, Machine Learning, pp. 257–264 (1986)Google Scholar
- 4.Liu, Y., Pi, D., Cheng, Q.: Ensemble kernel method: SVM classification based on game theory. J. Syst. Eng. Electr. 27, 251–259 (2016)Google Scholar
- 11.Ludwig, S.A., Jakobovic, D., Picek, S.: Analyzing gene expression data: fuzzy decision tree algorithm applied to the classification of cancer data, Fuzzy Systems (FUZZ-IEEE). In: 2015 IEEE International Conference on. IEEE, pp. 1–8 (2015)Google Scholar
- 13.Jin, C.X., Li, F.C., Li, Y.: A generalized fuzzy ID3 algorithm using generalized information entropy, knowledge-based systems, pp. 13–21(2014)Google Scholar
- 14.Ahmadi, E., Javadi, H., Khansefid, A., et al.: Fuzzy decision tree learning for preoperative classification of adnexal masses. In: 4th International Conference on Health Informatics (HEALTHINF 2011), Rome, ITALY, pp. 364–375 (2011)Google Scholar
- 17.Vlahovic, N.: An evaluation framework and a brief survey of decision tree tools. In: 39th International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO), Opatija, CROATIA, pp. 1299–1304 (2016)Google Scholar
- 20.Hashemi, S.A.H., Ghodrati Amiri, A.C., Hamedi, F.: Steel buildings damage classification by damage spectrum and decision tree algorithm. J. Rehabil. Civil Eng. 3, 24–42 (2015)Google Scholar
- 21.Hong, J.R., Ding, M.F., Li, X.Y., Wang, L.W.: A new algorithm of decision tree induction. Chin. J. Comput. 18, 470–474 (1995)Google Scholar