Contribution to Improve Database Classification Algorithms for Multi-Database Mining
1
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
Database classification is an important preprocessing step for the multi-database mining (MDM). In fact,when a multi-branch company needs to explore its distributed data for decision making, it is imperative toclassify these multiple databases into similar clusters before analyzing the data. To search for the bestclassification of a set of n databases, existing algorithms generate from 1 to (n2–n)/2 candidate classifications. Although each candidate classification is included in the next one (i.e., clusters in the current classification aresubsets of clusters in the next classification), existing algorithms generate each classification independently,that is, without taking into account the use of clusters from the previous classification. Consequently, existingalgorithms are time consuming, especially when the number of candidate classifications increases. Toovercome the latter problem, we propose in this paper an efficient approach that represents the problem ofclassifying the multiple databases as a problem of identifying the connected components of an undirectedweighted graph. Theoretical analysis and experiments on public databases confirm the efficiency of ouralgorithm against existing works and that it overcomes the problem of increase in the execution time.
Abstract
Database classification is an important preprocessing step for the multi-database mining (MDM). In fact,when a multi-branch company needs to explore its distributed data for decision making, it is imperative toclassify these multiple databases into similar clusters before analyzing the data. To search for the bestclassification of a set of n databases, existing algorithms generate from 1 to (n2–n)/2 candidate classifications. Although each candidate classification is included in the next one (i.e., clusters in the current classification aresubsets of clusters in the next classification), existing algorithms generate each classification independently,that is, without taking into account the use of clusters from the previous classification. Consequently, existingalgorithms are time consuming, especially when the number of candidate classifications increases. Toovercome the latter problem, we propose in this paper an efficient approach that represents the problem ofclassifying the multiple databases as a problem of identifying the connected components of an undirectedweighted graph. Theoretical analysis and experiments on public databases confirm the efficiency of ouralgorithm against existing works and that it overcomes the problem of increase in the execution time.
참고문헌 (14)
- S. Zhang, "Mining multiple data sources: local pattern analysis", Data Mining and Knowledge Discovery, 12(2-3), pp.121~125 (2006)[DOI]
- S. Zhang, "Multi-database mining", IEEE Computational Intelligence Bulletin, 2(1), pp.5~13 (2003)
- S. Zhang, "Knowledge Discovery in Multiple Databases" (2004), Springer
- A. Adhikari, "Developing Multi-database Mining Applications" (2010), Springer
- X. Wu, "Database classification for multi-database mining", Information Systems, 30(1), pp.71~88 (2005)[DOI]
- H. Li, "An improved database classification algorithm for multi-database mining", Frontiers in Algorithmics, pp.346~357 (2009)
- A. Adhikari, "Efficient clustering of databases induced by local patterns", Decision Support Systems, 44(4), pp.925~943 (2008)[DOI]
- Y. Liu, "Completely clustering for multi-databases mining", Journal of Computational Information Systems, 9(16), pp.6595~6602 (2013)
- H. Liu, "Identifying relevant databases for multidatabase mining", Research and Development in Knowledge Discovery and Data Mining, pp.15~18 (1998)
- H. Liu, "Toward multi-database mining: identifying relevant databases", IEEE Transactions on Knowledge and Data Engineering, 13(4), pp.541~553 (2001)[DOI]
- R. Agrawal, "Parallel mining of association rules", IEEE Transactions on Knowledge and Data Engineering, 8(6), pp.962~969 (1996)[DOI]
- R. Agrawal, "Fast algorithms for mining association rules in large databases", Proceedings of the 20th International Conference on Very Large Data Bases, pp.487~499 (1994)
- J. Han, "Mining frequent patterns without candidate generation: a frequent-pattern tree approach", Data Mining and Knowledge Discovery, 8(1), pp.53~87 (2004)[DOI]
- T. H. Cormen, "Introduction to Algorithms" (1990), MIT Press