Multi-Relational Sequential Pattern Mining Based on Iceberg Concept Lattice

Abstract:

Multi-Relational Sequential mining is one of the areas of data mining that rapidly developed in recent years. However, the performance issues of traditional mining methods are not ideal. To effectively mining the pattern, we proposed an algorithm based on Iceberg concept lattice, adopting optimization methods of partition and merger to just mining the frequent sequences. Experimental results show this algorithm effectively reduced the time complexity of multi-relational sequential pattern mining.

• Periodical: Applied Mechanics and Materials (Volume 109)
• Pages: 729-733
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.109.729
• Online since: October 2011
• Authors: Jiang Yin, Yun Li, Cen Cheng Shen, Bo Liu
• Keywords: Iceberg Concept Lattice, Multi-Relation, Sequential Pattern

References

[1] R. Agrawal, R. Srikant. Mining Sequential Pattern. In: Pro. of the 11st Int. Conf. on Data Engineering, Taipei, March 1995, pp.3-14.

[2] L Getoor. Multi-relational data mining using probabilistic relational models: research summary[C]. In: Proceedings of the First Workshop on Multi-relational Data Mining, (2001).

DOI: 10.1007/978-3-662-04599-2_13

[3] S Wrobel. Inductive Logic Programming for Knowledge Discovery in Databases[C]. In.

[1] 2001: 74~101.

[4] He Jun, Liu hongyan, Du xiaoyong, mining of multi-relational association rules[J]. Journal Of Software, 2007, 18(11): 2752-2765.

[5] Dehaspe L, de Raedt L. Mining association rules in multiple relations. In: Dzeroski S, Lavrac N, eds. Proc. of the 7th Int'l Workshop on Inductive Logic Programming. LNAI 1297, Berlin: Springer-Verlag, 1997. 125−132.

DOI: 10.1007/3540635149_40

[6] Dehape L. Frequent pattern discovery in first-order logic [Ph.D. Thesis]. Belgium: Katholieke Universiteit Leuven, (1998).

[7] Nijssen S, Kok J. Faster association rules for multiple relations. In: Nebel B, ed. Proc. of the 17th Int'l Joint Conf. on Artificial Intelligence (IJCAI 2001), Vol. 2. 2001. 891−896.

[8] Jensen VC, Soparkar N. Frequent itemset counting across multiple tables. In: Terano T, Liu H, Chen ALP, eds. Proc. of the 4th Pacific-Asia Conf. of Knowledge Discovery and Data Mining, Current Issues and New Applications. LNCS 1805, Berlin: Springer-Verlag, 2000. 49−61.

DOI: 10.1007/3-540-45571-x_8

[9] Ng EKK, Fu AW, Wang K. Mining association rules from stars. In: Kumar V, Tsumoto S, eds. Proc. of the 2002 IEEE Int'l Conf. on Data Mining (ICDM 2002). Los Alamitos: IEEE Computer Society, 2002. 322−329.

DOI: 10.1109/icdm.2002.1183919

[10] G Stumme, R Taouil, Y Bastide, et al. Computing iceberg concept lattices with titanic[J] . Journal on Knowledge and Data Engineering, 2002, 42( 2 ): 189-222.

DOI: 10.1016/s0169-023x(02)00057-5

[11] ZAK IM. SPADE: An efficient algorithm for mining frequent sequences[J]. Machine Learning, 2001, 41( 1 /2 ): 31- 60.