Rough set extensions in incomplete information systems

Abstract

All eight possible extended rough set models in incomplete information systems are proposed. By analyzing existing extended models and technical methods of rough set theory, the strategy of model extension is found to be suitable for processing incomplete information systems instead of filling possible values for missing attributes. After analyzing the definitions of existing extended models, a new general extended model is proposed. The new model is a generalization of indiscernibility relations, tolerance relations and non-symmetric similarity relations. Finally, suggestions for further study of rough set theory in incomplete information systems are put forward.

References

1. Pawlak Z . Roughsets. International Journal of Computerand Information Sciences, 1982, 11: 341–356. doi:10.1007/BF01001956
2. Pawlak Z . Roughsets: a new approach to vagueness. Fuzzy Logic for the Managementof Uncertainty. New York: John Wiley & Sons, 1992 : 105–118
3. Stefanowski J, Tsoukiès A . On the extension of roughsets under incomplete information. In: Proceedings of the 7th International Workshop on New Directions inRough Sets, Data Mining, and Granular-Soft Computing (RSFDGrC'99).Lecture Notes In Computer Science, Berlin: Springer, 1999, 1711: 73–82
4. Wang G Y . Rough Set Theory and Knowledge Acquisition. Xi'an: Xi'an Jiaotong UniversityPress, 2001, 38–39 (in Chinese)
5. Grzymala-Busse J W . Rough set strategies to data with missing attribute values. In: Proceedings of the Workshop on Foundationsand New Directions in Data Mining, associated with the 3rd IEEE InternationalConference on Data Mining, 2003, 56–63
6. Kryszkiewicz M . Probabilisticapproach to association rules in incomplete databases.In: Proceedings of the First International Conferenceon Web-Age Information Management (WAIM'2000). Lecture Notes in ComputerScience, Berlin: Springer, 2000, 1846: 133–138
7. Grzymala-Busse J W, Hu M . A comparison of several approachesto missing attribute values in data mining. In: Proceedings of the Second International Conference on Rough Setsand Current Trends in Computing (RSCTC'2000). Lecture Notes in ComputerScience, Berlin: Springer, 2001, 2005: 378–385
8. Kryszkiewicz M . Roughset approach to incomplete information systems. Information Sciences, 1998, 112(1): 39–49. doi:10.1016/S0020-0255(98)10019-1
9. Stefanowski J, Tsoukiès A . Incomplete information tablesand rough classification. ComputationalIntelligence, 2001, 17(3): 545–566. doi:10.1111/0824-7935.00162
10. Stefanowski J, Tsoukiès A . Valued tolerance and decisionrules. In: Proceedings of the Second InternationalConference on Rough Sets and Current Trends in Computing (RSCTC'2000).Lecture Notes in Computer Science, Berlin: Springer, 2001, 2005: 212–219
11. Wang G Y . Extension of rough set under incomplete information systems. Journal of Computer Research and Development, 2002, 39(10): 1238–1243 (in Chinese)
12. Grzymala-Busse J W . LERS: a system for learning from examples based on rough sets. In: Slowinski R ed. Intelligent Decision Support, Handbook of Applications and Advancesof the Rough Sets Theory. Kluwer AcademicPublishers, 1992, 3–18
13. Grzymala-Busse J W . A rough set approach to data with missing attribute values. In: Proceedings of the First International Conferenceof Rough Sets and Knowledge Technology (RSKT'2006). Lecture Notesin Computer Science, Berlin: Springer, 2006, 4062: 58–67
14. Wang G Y . Domain-oriented data-driven data mining based on rough sets. In: Proceedings of International Forum on Theoryof GrC from Rough Set Perspective (IFTGrCRSP2006), 2006, 46–46
15. Ziarko W . Variableprecision rough sets model. Journal ofComputer and System Sciences, 1993, 46(1): 39–59. doi:10.1016/0022-0000(93)90048-2