Cumulative Learning based on Dynamic Clustering of Hierarchical Production Rules(HPRs)

An important structuring mechanism for knowledge bases is building clusters based on the content of their knowledge objects. The objects are clustered based on the principle of maximizing the intraclass similarity and minimizing the interclass similarity. Clustering can also facilitate taxonomy formation, that is, the organization of observations into a hierarchy of classes that group similar events together. Hierarchical representation allows us to easily manage the complexity of knowledge, to view the knowledge at different levels of details, and to focus our attention on the interesting aspects only. One of such efficient and easy to understand systems is Hierarchical Production rule (HPRs) system. A HPR, a standard production rule augmented with generality and specificity information, is of the following form Decision If < condition> Generality Specificity . HPRs systems are capable of handling taxonomical structures inherent in the knowledge about the real world. In this paper, a set of related HPRs is called a cluster and is represented by a HPR-tree. This paper discusses an algorithm based on cumulative learning scenario for dynamic structuring of clusters. The proposed scheme incrementally incorporates new knowledge into the set of clusters from the previous episodes and also maintains summary of clusters as Synopsis to be used in the future episodes. Examples are given to demonstrate the behaviour of the proposed scheme. The suggested incremental structuring of clusters would be useful in mining data streams.

• Kamal K.Bharadwaj
• Rekha Kandwal

• Cumulative learning
• clustering
• data mining
• hierarchical production rules.

[1] Han, J., Kamber, M. "Data mining: Concepts and Techniques"
Academic Press (2001).
[2] Adriaan, P., Zantingre, D. "Data Mining", Addison Wesley, 1999.
[3] Ryszard S. Michalski, Pavel Brazdil: Introduction, Special Issue
on Multistrategy learning, Machine Learning, vol 50, pp 219-222,
2003.
[4] Jain, N.K. ,Bharadwaj, K.K.,: Some Learning Techniques in
Hierarchical Censored Production Rules( HCPRs) System,
International Journal of intelligent systems, John Wiley & sons,
Inc.,vol. 13,pp 319-344,1997.
[5] Marcus A.Maloof and Ryszard S. Michalski : "Learning Evolving
Concepts Using Partial-Memory Approach", Working Notes of the
1995 AAAI Fall Symposium on Active Learning, 1995.
[6] Bharadwaj, K.K., Jain, N.K.: Hierarchical Censored Production
Rules (HCPRs) System, Data and Knowledge Engineering, vol.8
(North Holland), 1992.
[7] Fadl M.Ba-Alwi and K.K.Bharadwaj: "Automated discovery of
hierarchical ripple-down rules(HRDRs)", In the Proc of TwentythirdIASTED
International Conference on Artificial Intelligence
and Applications(AIA 2005),Innsbruck,Austria,February 14-
16,2005.
[8] Fadl M.Ba-Alwi and Bharadwaj, Kamal.K::"Discovery of
Production Rules with Fuzzy Hierarchy",ENFORMATIKA ,vol 1
,2005 ISBN 975-98458-3-0.
[9] Basheer M. Al-Maqaleh and Kamal.K.Bharadwaj::"Genetic
Programming Approach to Hierarchical Production Rule
Discovery",ENFORMATIKA ,vol 6,2005 ISBN 975-98458-5-7.
[10] Rekha Kandwal and Kamal.K.Bharadwaj: " A Cumulative
Learning Approach to Data Mining Employing Censored
Production Rules (CPRs)",to appear in the Proc of 5th International
Enformatika Conference, Prague, Czech Republic, August 26-28,
2005.
[11] Bharadwaj, K.K., Neerja, Goel, G.C.: Hierarchical Censored
Production Rules (HCPRs) Systems Employing the Dampster-
Shafer Uncertainty Calculus, Information and Software
technology, Butterworth-Heinemann Ltd. (U.K.) Vol. 36 No., 155-
164, 1994.
[12] Jose Demisio Simoes da Silva, Bharadwaj K.K., "Integration of
Hierarchical Censored Production Rules (HCRPs) System and
Neural Networks" , SBRN-98, Proceedings of IEEE Computer
Society, Los Alamitos, California, USA, pp73-78, Dec 1998.
[13] Neerja , Bharadwaj K.K., "Fuzzy Hierarchical Censored
Production Rules System" Int. Journal of Intelligent Systems ,
John wiley & sons (New York), vol 11, No.1,pp 1-26 (1996).
[14] Brian Babcock, Shivnath Babu, Mayur data, Rajeev Motwani, and
Jennifer Widom: Models and Issues in data Stream Systems,
Proceeding of 21st ACM Symposium on Principles of Database
Systems (PODS 2002).
[15] Guozhu Dong, Jiawei Han, laks V.S. Lakshmanan, Jian Pei,
Haixun Wang, Philip S. Yu: Online Mining of changes from data
Streams: Research Problems and Preliminary Results, In
Proceedings of the 2003 ACM SIGMOID Workshop on
Management and Processing of data Streams.