Most intelligent manufacturing systems involve gained information. Inference knowledge (or rules) can be elicited through the gained information that is usually modeled as a set of data with a numeric type or semantic form. While the induction groups of algorithm are being used to acquire knowledge automatically, with respect to decision tree generation, the technique that deals with the representation of numeric data in the dataset may strongly affect the outputs. In this paper, we present a mechanism that combines the utilization of membership function and the IDS algorithm to generate decision rules from a set of data. Based on the presented mechanism, the research also develops an IDS Rule Generation System (IDSRGS) that can be used in any domain to support the generation of a decision tree and correspondingly exact/approximate rules. An example used to demonstrate the prototype system is also delineated.
展开▼
