Welcome to the InfoSci Platform
Reference Hub1
An Improved Second Order Training Algorithm for Improving the Accuracy of Fuzzy Decision Trees

An Improved Second Order Training Algorithm for Improving the Accuracy of Fuzzy Decision Trees

Swathi Jamjala Narayanan, Rajen B. Bhatt, Ilango Paramasivam
Copyright: © 2016 |Volume: 5 |Issue: 4 |Pages: 25
ISSN: 2156-177X|EISSN: 2156-1761|EISBN13: 9781466693234|DOI: 10.4018/IJFSA.2016100105
Cite Article Cite Article

MLA

Narayanan, Swathi Jamjala, et al. "An Improved Second Order Training Algorithm for Improving the Accuracy of Fuzzy Decision Trees." IJFSA vol.5, no.4 2016: pp.96-120. http://doi.org/10.4018/IJFSA.2016100105

APA

Narayanan, S. J., Bhatt, R. B., & Paramasivam, I. (2016). An Improved Second Order Training Algorithm for Improving the Accuracy of Fuzzy Decision Trees. International Journal of Fuzzy System Applications (IJFSA), 5(4), 96-120. http://doi.org/10.4018/IJFSA.2016100105

Chicago

Narayanan, Swathi Jamjala, Rajen B. Bhatt, and Ilango Paramasivam. "An Improved Second Order Training Algorithm for Improving the Accuracy of Fuzzy Decision Trees," International Journal of Fuzzy System Applications (IJFSA) 5, no.4: 96-120. http://doi.org/10.4018/IJFSA.2016100105

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

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.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.