الفهرس 
AcknowledgementOnly 14 pages are availabe for public view
 |  | from | 163 |  |  |
| | | from | 163 | | |
Abstract
Data mining is the process of discovering previously unknown and potentially interesting patterns in databases. Though most knowledge discovery methods have been developed for supervised data, the task of finding knowledge from unsupervised data often arises in real-world problems. In addition, techniques for unsupervised knowledge discovery are essentially different and still much less developed than those for supervised discovery. This paper introduces a novel framework for extracting a set of comprehensible rules from unsupervised database. The proposed framework depends on three techniques namely; clustering technique, fuzzification technique, and inductive learning technique. Clustering technique uses a k-means for clustering unsupervised database. Consequently the input database is converted into supervised database. Fuzzification technique transforms the continuous attributes of database into linguistic terms. This transformation leads to reduction of search space. Decision tree used as a inductive learning algorithm for extracting a set of accurate rules from supervised database.