New developments for determinacy analysis: diclique-based approach
WSEAS Transactions on Information Science and Applications
Machine learning task as a diclique extracting task
FSKD'09 Proceedings of the 6th international conference on Fuzzy systems and knowledge discovery - Volume 1
| Hi-index | 0.00 |
In this paper an algorithm named MONSA for closed sets mining is presented. It does not use such kind of techniques as in ChARM by Zaki and Hsiao. MONSA is an exact depth-first search algorithm extracting only frequent closed sets using several new very effective pruning techniques to be free from repetitive and empty patterns. MONSA does not depend on the initial order of objects. In MONSA there is active only one branch which is under construction. The purpose of this paper is to describe the approach used in MONSA and the correspondence of its basics and concepts to the approach by Zaki and Hsiao. A full example of the algorithm's work is presented. By the algorithm the intersections (closed sets) and IF...THEN rules on the subsets of source data set simultaneously are found. MONSA treats not only binary data, but a larger set of discrete values.