Discovering Monthly Fuzzy Patterns

M. Shenify, F. A. Mazarbhuiya

College of Computer Science and IT, Albaha University, Albaha, Saudi Arabia.

DOI: 10.4236/ijis.2015.51004                

Abstract

Discovering patterns that are fuzzy in nature from temporal datasets is an interesting data mining problems. One of such patterns is monthly fuzzy pattern where the patterns exist in a certain fuzzy time interval of every month. It involves finding frequent sets and then association rules that holds in certain fuzzy time intervals, viz. beginning of every months or middle of every months, etc. In most of the earlier works, the fuzziness was user-specified. However, in some applications, users may not have enough prior knowledge about the datasets under consideration and may miss some fuzziness associated with the problem. It may be the case that the user is unable to specify the same due to limitation of natural language. In this article, we propose a method of finding patterns that holds in certain fuzzy time intervals of every month where fuzziness is generated by the method itself. The efficacy of the method is demonstrated with experimental results.

Keywords

Frequent Item Sets, Superimposition of Time Intervals, Fuzzy Time Intervals, Right Reference Functions, Left Reference Functions, Membership Functions

Conflicts of Interest

The authors declare no conflicts of interest.

References

[1]	Agrawal, R., Imielinski, T. and Swami, A.N. (1993) Mining Association Rules between Sets of Items in Large Databases. Proceedings of the 1993 ACM SIGMOD International Conference on Management of Data, 22, 207-216. http://dx.doi.org/10.1145/170035.170072
[2]	Ale, J.M. and Rossi, G.H. (2000) An Approach to Discovering Temporal Association Rules. Proceedings of 2000 ACM Symposium on Applied Computing, Como, 19-21 March 2000, 294-300.
[3]	Mahanta, A.K., Mazarbhuiya, F.A. and Baruah, H.K. (2005) Finding Locally and Periodically Frequent Sets and Periodic Association Rules. Pattern Recognition and Machine Intelligence, 3776, 576-582.
[4]	Mahanta, A.K., Mazarbhuiya, F.A. and Baruah, H.K. (2008) Finding Calendar-Based Periodic Patterns. Pattern Recognition Letters, 29, 1274-1284.
[5]	Antunes, C.M. and Oliviera, A.L. (2001) Temporal Data Mining: An Overview. Workshop on Temporal Data Mining—7th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, 26-29 August 2001, 1-13.
[6]	Ozden, B., Ramaswamy, S. and Silberschatz, A. (1998) Cyclic Association Rules. Proceedings of the 14th International Conference on Data Engineering, Orlando, 23-27 February 1998, 412-421. http://dx.doi.org/10.1109/ICDE.1998.655804
[7]	Li, Y., Ning, P., Wang, X.S. and Jajodia, S. (2001) Discovering Calendar-Based Temporal Association Rules. Elsevier Science, Amsterdam.
[8]	Zimbrado, G., de Souza, J.M., de Almeida, V.T. and de Silva, W.A. (2002) An Algorithm to Discover Calendar-Based Temporal Association Rules with Item’s Lifespan Restriction. Proceedings of the 8th ACM SIGKDD, Alberta, 23 July 2002.
[9]	Subramanyam, R.B.V., Goswami, A. and Prasad, B. (2008) Mining Fuzzy Temporal Patterns from Process Instances with Weighted Temporal Graphs. International Journal of Data Analysis Techniques and Strategies, 1, 60-77. http://dx.doi.org/10.1504/IJDATS.2008.020023
[10]	Jain, S., Jain, S. and Jain, A. (2013) An assessment of Fuzzy Temporal Rule Mining. International Journal of Application or Innovation in Engineering and Management (IJAIEM), 2, 42-45.
[11]	Lee, W.-J., Jiang, J.-Y. and Lee, S.-J. (2008) Mining Fuzzy Periodic Association Rules. Data & Knowledge Engineering, 65, 442-462.
[12]	Klir, J. and Yuan, B. (2002) Fuzzy Sets and Logic Theory and Application. Prentice Hill Pvt. Ltd., Upper Saddle River.
[13]	Dubois, D. and Prade, H. (1983) Ranking Fuzzy Numbers in the Setting of Possibility Theory. Information Sciences, 30, 183-224. http://dx.doi.org/10.1016/0020-0255(83)90025-7
[14]	Baruah, H.K. (1999) Set Superimposition and Its Application to the Theory of Fuzzy Sets. Journal of Assam Science Society, 10, 25-31.