Abstract Recently, Multi-Database Mining (MDBM) for association rules has been recognized as an important and timely research area in the Knowledge Discovery Database (KDD) community. It consists of mining different databases in order to obtain frequent patterns which are forwarded to a centralized place for global pattern analysis. Various synthesizing models [8, 9,13,14,15,16] have been proposed to build global patterns from the forwarded patterns. It is desired that the synthesized rules from such forwarded patterns must closely match with the mono-mining results, ie., the results that would be obtained if all the databases are put together and mining has been done. When the pattern is present in a site but fails to satisfy the minimum support threshold value, it is not allowed to take part in the pattern synthesizing process. Therefore this process can lose some interesting patterns which can help the decision maker to make the right decisions. To adress this problem, we propose to integrate the users knowledge in the local and global mining process. For that we describe the users beliefs and expectation by the rule schemas multi-level and integrate them in both the local association rules mining and in the synthesizing process. In this situation we get true global patterns of select items as there is no need to estimate them. Furthermore, a novel Condensed Patterns Tree (CP-TREE)structure is defined in order to store the candidates patterns for all organization levels which can improve the time processing and reduce the space requirement. In addition CP-TREE structure facilitate the exploration and the projection of the candidates patterns in differents levels. finally We conduct some experimentations in real world databases which are the production field and demonstrate the effectivlness of the CP-TREE structure on time processing and space requirement.

References

[1] Guillet F., Olaru A., and Marinica C., Local Mining of Association Rules with Rule Schemas, in proceeding of IEEE Symposium on Computational Intelligence and Data Mining, Nashville, pp. 118-124, 2009.

[2] Jaroszewicz S. and Simovici D., Support Approximations using Bonferroni-Type Inequalities, in Proceedings of 6th European Conference on Principles of Data Mining and Knowledge Discovery, Finland, pp. 212-223, 2002.

[3] Khiat S., Belbachir H., and Rahal S., Probabilistic Models for Local Patterns Analysis, Journal of Information Systems Processing, vol. 10, no. 1, pp. 145-161, 2014.

[4] Liu B., Wynne H., Ke W., and Shu C., Visually Aided Exploration of Interesting Association Rules, Springer, 1999.

[5] Pavlov D., Mannila H., and Smyth P., Probabilistics Models for Query Approximation with Large Sparse Binary Data Sets, in Proceeding of 16th Conference on Uncertainty in Artificial Intelligence, San Francisco, pp. 465- 472, 2000

[6] Rakesh A., Imielinski T., and Swami A., Mining Association Rules between Sets of Large Databases, ACM SIGMOD Record, vol. 22, no. 2, pp. 207-216, 1993.

[7] Ramkumar T. and Srinivasan R., Modified Algorithms for Synthesizing High-Frequency Rules from Different Data Sources, Springer, 2008.

[8] Ramachandrarao P., Animesh A., and Witold P., Advanced Information and Knowledge Processing, Springer, 2010.

[9] Senhadji S., Khiat S., and Belbachir H., Association Rule Mining and Load Balancing Strategy in Grid Systems, The International Arab Journal of Information Technology, vol. 11, no. 4, pp. 338-344, 2014.

[10] Thirunavukkarasu R. and Rengaramanujam S., The Effect of Correction Factor in Synthesizing Global Rules in a Multi-databases Mining Scenario, Journal of Computer Science, vol.6, no. 3, pp. 33-38, 2009.

[11] Yun U., Efficient Mining of Weighted Interesting Patterns with a Strong Weight and/or Support Affinity, Information Sciences, vol. 177, no. 17, pp. 3477-3499, 2007.

[12] Zhang S. and Wu X., Synthesizing High- Frequency Rules from Different Data Sources, IEEE Transaction Knowledge Data Eng, vol. 15, no. 2, pp. 353-367, 2003.

[13] Zhang S., Wu X., Zhang C., Multi-Database Mining, IEEE Computational Intelligence Bulletin , vol. 2, no. 1, pp. 5-13, 2003.

[14] Zhang C., Meiling L., Wenlong N., and Shichao Z., Identifying Global Exceptional Patterns in Multi-database Mining, IEEE Computational Intelligence Bulletin, vol. 3, no. 1, pp. 19-24, 2004.

[15] Zhang S., Zhang C., and Yu J., An Efficient Strategy for Mining Exceptions in Multi- Databases , An International Journal Information Science, vol. 165, no. 1-2, pp. 1-20, 2004.

[16] Zhang S., Chengqi Z., and Jeffrey X., Identifying Interesting patterns in multi-databases, Springer, 2005. 680 The International Arab Journal of Information Technology, Volume 14, No. 5, September 2017 Salim Khiat He is Doctor in computer science since 2015 in University of science and technology Mohamed Boudiaf Oran USTOMB Algeria. He teaches courses in undergraduate and graduate composition, at National School Polytechnic Oran Algeria. He is memberships in Signal, System and Data Laboratory (LSSD). His current research interests include the databases, multi- database mining for software engineering, Ontology, grid and cloud computing. Hafida Belbachir He Received PH.D degree in Computer Science from University of Oran, Algeria in 1990. Currently, she is a professor at the Science and Technology University USTO in Oran, where she heads the Database System Group in the LSSD Laboratory. Her research interests include Advanced Databases, DataMining and Data Grid. Sid Rahal He is Doctor in computer science since 1989 in Pau University France. He is memberships in professional activities are: - Member in LSSD (Laboratory Signal, System and Data) -Interest in Databases, Data Mining, Agent and expert systems.