An improved second order training algorithm for improving the accuracy of fuzzy decision trees

被引：3

作者：

Narayanan S.J. ^{[1
]}

Bhatt R.B. ^{[2
]}

Paramasivam I. ^{[1
]}

机构：

[1] School of Computing Science and Engineering, VIT University, Vellore

[2] Robert Bosch Research and Technology Center, Pittsburgh, PA

来源：

International Journal of Fuzzy System Applications | 2016年 / 5卷 / 04期

关键词：

Classification; Fuzzy decision tree; Fuzzy ID3; Levenberg marquardt; Second order training;

D O I：

10.4018/IJFSA.2016100105

中图分类号：

学科分类号：

摘要：

Fuzzy decision tree (FDT) is a powerful top-down, hierarchical search methodology to extract human interpretable classification rules. The performance of FDT depends on initial fuzzy partitions and other parameters like alpha-cut and leaf selection threshold. These parameters are decided either heuristically or by trial-and-error. For given set of parameters, FDT is constructed using any standard induction algorithms like Fuzzy ID3. Due to the greedy nature of induction process, there is a chance of FDT resulting in poor classification accuracy. To further improve the accuracy of FDT, in this paper, the authors propose the strategy called Improved Second Order- Neuro- Fuzzy Decision Tree (ISO-N-FDT). ISO-N-FDT tunes parameters of FDT from leaf node to roof node starting from left side of tree to its right and attains better improvement in accuracy with less number of iterations exhibiting fast convergence and powerful search ability. © 2016, IGI Global.

引用

页码：96 / 120

页数：24

共 56 条

[31]

Narayanan S.J., Paramasivam I., Bhatt R.B., Khalid M., A study on the approximation of clustered data to parameterized family of fuzzy membership functions for the induction of fuzzy decision trees, Cybernetics and Information Technologies, 15, 2, pp. 75-96, (2015)

[32]

Pedrycz W., Sosnowski Z., C-fuzzy decision trees, IEEE Transactions on Systems, Man and Cybernetics. Part C, Applications and Reviews, 35, 4, pp. 498-511, (2005)

[33]

Pulkkinen P., Koivisto H., Fuzzy classifier identification using decision tree and multiobjective evolutionary algorithms, International Journal of Approximate Reasoning, 48, 2, pp. 526-543, (2008)

[34]

Quinlan J.R., Induction of decision trees, Machine Learning, 1, 1, pp. 81-106, (1986)

[35]

Quinlan J.R., C4.5: Programs for Machine Learning, (2014)

[36]

Sanz J., Bustince H., Fernandez A., Herrera F., Iivfdt: Ignorance functions based interval-valued fuzzy decision tree with genetic tuning, International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems, 20, pp. 1-30, (2012)

[37]

Sethi I.K., Entropy nets: From decision trees to neural networks, Proceedings of the IEEE, 78, 10, pp. 1605-1613, (1990)

[38]

Shafer J., Agrawal R., Mehta M., Sprint: A scalable parallel classier for data mining, Proceedings of International Conference on Very Large Data Bases, pp. 544-555, (1996)

[39]

Sztandera L.M., Fuzzy neural trees, Information Sciences, 90, 1, pp. 157-177, (1996)

[40]

Tsang E.C., Wang X.Z., Yeung D.S., Improving learning accuracy of fuzzy decision trees by hybrid neural networks, IEEE Transactions on Fuzzy Systems, 8, 5, pp. 601-614, (2000)

← 1 2 3 4 5 6 →