Families of the Granules for Association Rules and Their Properties
We employed the granule (or the equivalence class) defined by a descriptor in tables, and investigated rough set-based rule generation. In this paper, we consider the new granules defined by an implication, and propose a family of the granules defined by an implication in a table with exact data. Each family consists of the four granules, and we show that three criterion values, support, accuracy, and coverage, can easily be obtained by using the four granules. Then, we extend this framework to tables with non-deterministic data. In this case, each family consists of the nine granules, and the minimum and the maximum values of three criteria are also obtained by using the nine granules. We prove that there is a table causing support and accuracy the minimum, and generally there is no table causing support, accuracy, and coverage the minimum. Finally, we consider the application of these properties to Apriori-based rule generation from uncertain data. These properties will make Apriori-based rule generation more effective.
KeywordsAssociation rules Rule generation Apriori algorithm Granularity Uncertainty
The authors would be grateful for reviewers’ useful comments. This work is supported by JSPS (Japan Society for the Promotion of Science) KAKENHI Grant Number 26330277.
- 1.Agrawal, R., Srikant, R.: Fast algorithms for mining association rules in large databases. In: Proceedings of VLDB’94, pp. 487–499. Morgan Kaufmann (1994)Google Scholar
- 2.Agrawal, R., Mannila, H., Srikant, R., Toivonen, H., Verkamo, A.I.: Fast discovery of association rules. In: Advances in Knowledge Discovery and Data Mining, pp. 307–328. AAAI/MIT Press (1996)Google Scholar
- 4.Frank, A., Asuncion, A.: UCI machine learning repository. Irvine, CA: University of California, School of Information and Computer Science (2010). http://mlearn.ics.uci.edu/MLRepository.html
- 5.Grzymała-Busse, J.W.: Data with missing attribute values: generalization of indiscernibility relation and rule induction. Trans. Rough Sets 1, 78–95 (2004)Google Scholar
- 11.Pawlak, Z.: Systemy Informacyjne: Podstawy Teoretyczne (in Polish) WNT (1983)Google Scholar
- 13.Sakai, H., Ishibashi, R., Koba, K., Nakata, M.: Rules and apriori algorithm in non-deterministic information systems. Trans. Rough Sets 9, 328–350 (2008)Google Scholar
- 16.Sakai, H., Wu, M., Nakata, M.: The completeness of NIS-Apriori algorithm and a software tool getRNIA. In: Proceedings of International Conference on AAI2014, pp. 115–121 (2014)Google Scholar
- 17.Skowron, A., Rauszer, C.: The discernibility matrices and functions in information systems. In: Słowiński, R. (ed.) Intelligent Decision Support - Handbook of Advances and Applications of the Rough Set Theory, pp. 331–362. Kluwer Academic Publishers, Dordrecht (1992)Google Scholar
- 18.Wu, M., Sakai, H.: getRNIA web software (2013). http://getrnia.org