Optimized Fuzzy Decision Tree Data Mining for Engineering Applications

Abstract

Manufacturing organizations are striving to remain competitive in an era of increased competition and every-changing conditions. Manufacturing technology selection is a key factor in the growth of an organization and a fundamental challenge is effectively managing the computation of data to support future decision-making. Classification is a data mining technique used to predict group membership for data instances. Popular methods include decision trees and neural networks. This paper investigates a unique fuzzy reasoning method suited to engineering applications using fuzzy decision trees.

The paper focuses on the inference stages of fuzzy decision trees to support decision-engineering tasks. The relaxation of crisp decision tree boundaries through fuzzy principles increases the importance of the degree of confidence exhibited by the inference mechanism. Industrial philosophies have a strong influence on decision practices and such strategic views must be considered. The paper is organized as follows: introduction to the research area, literature review, proposed inference mechanism and numerical example. The research is concluded and future work discussed.