Uncertainty Measure Based on Evidence Theory

Abstract:

Evidence theory is an effective method to deal with uncertainty information. And uncertainty measure is to reflect the uncertainty of an information system. Thus we want to merge evidence theory with uncertainty method in order to measure the roughness of a rough approximation space. This paper discusses the information fusion and uncertainty measure based on rough set theory. First, we propose a new method of information fusion based on the Bayse function, and define a pair of belief function and plausibility function using the fused mass function in an information system. Then we construct entropy for every decision class to measure the roughness of every decision class, and entropy for decision information system to measure the consistence of decision table.

• Periodical: Applied Mechanics and Materials (Volume 329)
• Pages: 344-348
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.329.344
• Online since: June 2013
• Authors: Shao Pu Zhang, Tao Feng
• Keywords: Belief Function, Entropy, Information Fusion, Plausibility Function, Rough Set (RS)

References

[1] Dempster AP Upper and lower probabilities induced by a multivalve mapping. Annals of Mathematical Statistics 38, 325-339 (1967)

DOI: 10.1214/aoms/1177698950

[2] Kryszkiewicz M Rough set approach to incomplete information systems. Information sciences 112, 39-49 (1998)

DOI: 10.1016/s0020-0255(98)10019-1

[3] Pawlak Z Rough sets. Inter. J. Compute. Information Sciences 11, 341-356 (1982)

[4] Pawlak Z Rough sets: Theoretical Aspects of Reasoning about Data. Kluwer Academic Publishers, Boston 16, 36-41 (1991)

[5] Qian YH, Liang JY, Pedrycz W, Dang CY Positive approximation: An accelerator for attribute reduction in rough set theory. Artificial Intelligence 174 (9), 597-618 (2010)

DOI: 10.1016/j.artint.2010.04.018

[6] Shafer G A mathematical theory of evidence. Princeton University Press, Princeton 14, 34-39 (1976)

[7] Smets P Decision making in the TBM: the necessity of the pignistic transformation. International Journal of Approximate reasoning 38(2), 133-147 (2005)

DOI: 10.1016/j.ijar.2004.05.003

[8] Wu WZ, Leung Y Theory and applications of granular labelled partitions in multi-scale decision tables. Information Sciences 181, 3878-3897 (2011)

DOI: 10.1016/j.ins.2011.04.047

[9] Xu WH, Zhang XY, Zhong JM, Zhang WX Attribute reduction in ordered information systems based on evidence theory, Knowledge Information System 25, 169-184 (2010)

DOI: 10.1007/s10115-009-0248-5

[10] Yao YQ, Mi JS, Li ZJ Attribute reduction based on generalized fuzzy evidence theory in fuzzy decision system. Fuzzy Sets and Systems 170, 64-75 (2011)

DOI: 10.1016/j.fss.2011.01.008

[11] Zadeh LA Probability measures of fuzzy events. Journal of Mathematical Analysis and Applications 23, 421-427 (1968)

DOI: 10.1016/0022-247x(68)90078-4