Reliability estimation measure: Generic Discounting Approach

Ahmed Samet (1) , Eric Lefevre (2) , Imen Hammami (3) , Sadok Ben Yahia (4)

1 ICube - Laboratoire des sciences de l'ingénieur, de l'informatique et de l'imagerie
2 LGI2A - Laboratoire de Génie Informatique et d'Automatique de l'Artois
3 Lab-STICC_TB_CID_TOMS
4 UTM - Université de Tunis El Manar

In the belief function theory, several measures of uncertainty have been introduced. One of their possible use is unreliable source discounting before the fusion stage. Two different measures of uncertainty exist which are the intrinsic and extrinsic ones. The intrinsic measure makes it possible to assess the source's confusion whereas the extrinsic one measures the contradiction between sources. In this paper, we associate both measures in order to estimate the global reliability of a source. This method, named Generic Discounting Approach (GDA), is proposed in two different versions: Weighted GDA and Exponent GDA. Those reliability measures are integrated into a classifier. The method was tested, against to some pioneer approaches, on several UCI datasets as well as on an urban image classification problem and showed very encouraging results.

Mots clés: Belief function theory; Discounting; Classification; Conflict management; Source confusion

Domaines: Intelligence artificielle [cs.AI]

Ahmed Samet, Eric Lefevre, Imen Hammami, Sadok Ben Yahia. Reliability estimation measure: Generic Discounting Approach. International Journal of Pattern Recognition and Artificial Intelligence, 2015, 29 (07), pp.1559011. ⟨10.1142/S0218001415590119⟩. ⟨hal-03354137⟩