MASSON: Knowledge Discovery in Databases (KDD) System
Welcome to the home page of MASSON. MASSON is a knowledge discovery system in object-oriented databases which are currently being developed in University of Houston. We are currently experimenting Query Discovery application to MASSON by using Genetic Programming as a search engine. For this purpose, we have partially built an object-oriented personal database based on Object-Oriented Functional Data Model (OOFDM). This was implemented by CLOS (Common Lisp Object System). In this application, a set of objects (or database instances) are given to the system, then the system will find commonalities for a set of objects belonging to an database. The commonalities are described by object-oriented queries that compute this set of objects. A new navigational query operators are used as a description language. We used genetic programming to generate many different queries and to search an interesting query or a set of queries that describe the given object set.
Publications
- T.W. Ryu and C.F. Eick, "MASSON: Discovering Commonalities of a Set of Objects Using Genetic Programming" in the Proc. of Genetic Programming 1996 Conference (GP'96) at Stanford University in California, U.S.A., July 28-31, 1996.
- T.W. Ryu and C.F. Eick, "Deriving Queries From Results Using Genetic Programming" in the Proc. of The Second International Conference on Knowledge Discovery and Data Mining (KDD'96) at Portland, Oregon, U.S.A., August 2-4, 1996.
- T.W. Ryu and C.F. Eick, "Automated Discovery of Discriminant Rules for a Group of Objects in Databases," in the Proc. of Conference on Automated Learning and Discovery (CONALD'98) at Carnegie Mellon University, Pittsburgh, U.S.A., June 11-13, 1998.
- T.W. Ryu and C.F. Eick, "Similarity Measures for Multi-valued Attributes for Database Clustering," to appear in SMART ENGINEERING SYSTEM DESIGN Neural Networks, Fuzzy Logic, Evolutionary Programming, Data Mining and Rough Sets (ANNIE'98) at St. Louis, Missouri, U.S.A., November 1 - 4, 1998.
- T.W. Ryu and C.F. Eick, "Discovering Discriminant Characteristic Queries from Databases through Clustering" to appear in Fourth International Conference on Computer Science and Informatics (CS&I'98) at Research Triangle Park, NC, U.S.A., October 23-28, 1998.
- T.W. Ryu and C.F. Eick, "A Unified Similarity Measure for Attributes with Set or Bag of Values for Database Clustering" to appear in The Sixth International Workshop on Rough Sets, Data Mining and Granular Computing (RSDMGrC'98) at Research Triangle Park, NC, U.S.A., October 23-28, 1998.
!! Always under Construction !! Last updated: 08/24/1998