Temporal data mining unearths patterns from sequential or ordered data. Semantics of these patterns can be different depending on the underlying data, technique used and the purpose of data mining. Patterns included in this paper are taken from three different domains and their structure and semantics are different. First type, which we call temporal patterns, includes a set of states and relationships among the states. Second type, called sequential patterns includes a set of ordered states. Finally, the third type called episodes is a partially ordered set of event types. To index a database of these patterns, Signature based techniques were considered to be a viable option as signatures could accommodate multiple state values as well as the relationship among the states. In this paper we compared the different implementations of signature files when used indexes for database of temporal patterns on various criteria listed in the paper. Further, based on the semantics of sequential patterns and episodes, and the results obtained above, we suggested which implementations would be suitable for databases of other two types of patterns.

1. A. Carlson, S. Estepp, M. Fowler. “Temporal Patterns”(AT&T Martin Fowler and Policy Management Systems Corporation, August 1998)
2. A. Nanopoulos, M. Zakrzewicz, T. Morzy, and Y. Manolopoulos, “Efficient storage and querying of sequential patterns in database systems,” Information and Software Technology, vol. 45, pp. 23-34, 2003.
3. A. Tuzhilin and B. Liu, “Querying multiple sets of discovered rules,” Proc. ACM SIGKDD ’02, pp. 52-60, 2002.
4. Agrawal R, Srikant R 1995 Mining sequential patterns. In Proc. 11th Int. Conf. on Data Engineering, (Washington, DC: IEEE Comput. Soc.)
5. C. Faloutsos and S. Christodoulakis. Signature files: An access method for documents and its analytical performance evaluation. ACM Transactions on Office Informations Systems, 2(4):267– 288, October 1984.
6. C.M. Antunes and A.L. Oliveira, “Temporal data mining: An overview,” Proc. ACM SIGKDD Workshop Temporal Data Mining, pp. 1-13, 2001.
7. E. Winarko and J.F. Roddick, “A signature-based indexing method for efficient content-based retrieval of relative temporal patterns”,IEEE Trans. on Knowledge and Data Engineering, VOL. 20, NO. 6, JUNE 2008.
8. F. Ho¨ppner, “Learning Temporal Rules from State Sequences,”Proc. IJCAI Workshop Learning from Temporal and Spatial Data,pp. 25-31, 2001.
9. Faloutsos C, Christodoulakis S (1984) Signature files: an access method for documents and its analytical performance evaluation. ACM Trans Office Inform Sys 2(4):267–288
10. J. F. Roddick and M. Spiliopoulou, “A survey of temporal knowledge discovery paradigms and methods,” IEEE Trans. Knowledge and Data Eng., vol. 14, no. 4, pp. 750-767, Mar./Apr. 2002.
11. J. Xiao, Y. Zhang, X. Jia, and T. Li, “Measuring similarity of interests for clustering web-users,” Proc. 12th Australasian Database Conf. (ADC ’01), M. Orlowska and J. Roddick, eds., pp. 107-114, 2001.
12. L. Geng and H.J. Hamilton, “Interestingness Measures for datamining: A survey,” ACM Computing Surveys, vol. 38, no. 3, 2006.
13. M. Zakrzewicz, “Sequential index structure for content-based retrieval,” Proc. Fifth Pacific-Asia Conf. Knowledge Discovery and Data Mining (PAKDD ’01), pp. 306-311, 2001.
14. Mannila H, Toivonen H, Verkamo A I 1997 Discovery of frequent episodes in event sequences. DataMining Knowledge Discovery 1: 259–289
15. Laxman S, Sastry P S, Unnikrishnan K P 2004b Fast algorithms for frequent episode discovery in event sequences. In Proc. 3rd Workshop on Mining Temporal and Sequential Data, Seattle, WA.
16. R. Fagin, J. Nievergelt, N. Pippenger, H.R. Strong, “Extendible hashing – a fast access method for dynamic files. ACM Trans Database Sys 4(3):315–344.
17. Ritambhra Korpal, Arpita Gopal “Extendible Signature Hashing based Indexing for Efficient Content-based Retrieval of Temporal Patterns” IJCSA Issue 2010, ISSN 0974-0767;178-183
18. Ritambhra Korpal, Arpita Gopal “Signature Trees as Index for Database of Temporal Patterns”, in press.
19. S. Helmer and G. Moerkotte, “A performance study of four index structures for set-valued attributes of low cardinality,” VLDB J., vol. 12, no. 3, pp. 244-261, 2003.
20. T. Imielinski and A. Virmani, “Association rules . . . and what’s next? Towards second generation data mining systems,” Proc. Second East European Symp. Advances in Databases and Information Systems (ADBIS ’98), pp. 6-25, 1998.
21. Y. Chen, “Building signature trees into OODBs,” J. Information Science and Eng., vol. 20, no. 2, pp. 275-304, 2004.
22. Y. Chen, Y. Chen, “On the Signature Tree Construction and Analysis, IEEE Trans. On Knowledge and Data Engineering, VOL. 18, NO. 9, SEPTEMBER 2006.
23. Y. Ishikawa, H. Kitagawa, and N. Ohbo, “Evaluation of signature files as set access facilities in OODBs,” Proc. ACM SIGMOD ’93, P. Buneman and S. Jajodia, eds., pp. 247-256, 1993.

Temporal Patterns sequential patterns episode Signature Files Sequential Signature Files Bit Slice Signature Files Extendible Signature Hashing Signature Trees