Discovery of Production Rules with Fuzzy Hierarchy

In this paper a novel algorithm is proposed that integrates the process of fuzzy hierarchy generation and rule discovery for automated discovery of Production Rules with Fuzzy Hierarchy (PRFH) in large databases.A concept of frequency matrix (Freq) introduced to summarize large database that helps in minimizing the number of database accesses, identification and removal of irrelevant attribute values and weak classes during the fuzzy hierarchy generation.Experimental results have established the effectiveness of the proposed algorithm.

Authors:

• Fadl M. Ba-Alwi
• Kamal K. Bharadwaj

Keywords:

• Data Mining
• Degree of subsumption
• Freq matrix
• Fuzzy hierarchy.

References:

[1] F. M. Ba-Alwi and K. K. Bharadwaj, "Automated discovery of
hierarchical ripple-down rules (HRDRs)", Proc of In the Twenty-third
IASTED International Conference on Artificial Intelligence and
Applications (AIA 2005), Innsbruck, Austria, February 14-16, 2005.
[2] S. Levachkine and A. Guzmán-Arenas, "Hierarchies measuring
qualitative variables", Springer-Verlag Berlin Heidelberg 2004, A.
Gelbukh (Ed.): CICLing 2004, 2004, pp. 262-274.
[3] B. Liu, M. Hu and W. Hsu, "Multi-Level organization and
summarization of the discovered rules", Boston, USA, SIGKDD-
2000, Aug 20-23, 2000.
[4] G. W. Mineau and R. Godin, "Automatic structuring of knowledge
bases by conceptual clustering", IEEE Transactions on Knowledge
and Data Engineering, vol. 7(5), 1995, pp. 824-828.
[5] N. K. Jain, K. K. Bharadwaj and N. Marranghello, "Extended of
hierarchical censored production rules (EHCPRs) system: An
approach toward generalized knowledge representation", Journal of
Intelligent Systems, UK, vol. 9(3,4), 1999, pp. 259-295.
[6] E. Tsiporkova and S. Garrett, "On different modes of inheritance in
fuzzy class hierarchies ",CIMCA'99, Vienna, 1999.
[7] G. Chen, Q. Wei, E. Kerre and G. Wets, "Overview of fuzzy
associations mining", in Proc of ISIS2003, Jeju, Korea, September
2003.
[8] Q. Wei and G. Chen, "Mining generalized association rules with
fuzzy taxonomic structures", in Proc of the North America Fuzzy
Information Processing Society (NAFIPS99), New York, 1999, pp.
477-481.
[9] F. Boussemart, C. Lecoutre, S. Merchez and E. Grégoire, "Fuzzy
hierarchies", CP99 Post-Conference Workshop on MODELLING
AND SOLVING SOFT CONSTRAINTS, Alexandria, Virginia, USA,
October 16, 1999.
[10] R. Srikant, Q. Vu and R. Agrawal, "Mining association rules with
item constraints", in Proc of the Third International Conf on
Knowledge Discovery and Data Mining (KDD97), 1997, pp. 67-73.
[11] M. Suan, "Semi-Automatic taxonomy for efficient information
searching", Proceeding of the 2nd International Conference on
Information Technology for Application (ICITA- 2004), 2004.
[12] K. K. Bharadwaj and N. K. Jain, "Hierarchical censored production
rules (HCPRs) Systems", Data and Knowledge Engineering, North
Holland, vol. 8, 1992, pp. 19-34.
[13] F. Hussain, H. Liu, E. Suzuki and H. Lu, "Exception rule mining with
a relative interestingness measure", Knowledge Discovery and Data
Mining, Lecture Notes in Artificial Intelligence (PAKDD), Terano,
T., Liu, H. & Chen, A.L.P. (Eds.), Kyoto, Japan. Springer-Verlag, vol.
1805, April 2000, pp. 86-97.
[14] C. Westphal and T. Blaxton, "Data mining solution, methods and
tools for solving real-world problems", Wiley Computer Publishing,
1998.
[15] J. Domingo-Ferrer and V. Torra, "Approximating fuzzy measures by
hierarchically decomposable ones", ISIF 2002, pp. 191-198.
[16] H. Suryanto and P. Compton, "Learning classification taxonomies
from a classification knowledge based system", In Staab, S.,
Maedche, A., Nedellec, C. & Wiemer-Hastings, P. (Eds.), Proceedings
of the Workshop on Ontology Learning, 14 Conference on Artificial
Intelligence (ECAI'00), Berlin, August 20-25, 2000.
[17] Z. Ding and Y. Peng, "A probabilistic extension to ontology language
owl", in Proc of the Hawai-i International Conf. on System Sciences,
2004.