Multi-criteria decision making based on DSmT-AHP

Jean Dezert (1) , Jean-Marc Tacnet (2) , Mireille Batton-Hubert (3) , Florentin Smarandache (4)

1 ONERA - The French Aerospace Lab [Châtillon]
2 UR ETGR (ETNA) - Érosion torrentielle, neige et avalanches
3 Mines Saint-Étienne MSE - École des Mines de Saint-Étienne
4 Department of Mathematics and Statistics [Albuquerque]

In this paper, we present an extension of the multi- criteria decision making based on the Analytic Hierarchy Process (AHP) which incorporates uncertain knowledge matrices for generating basic belief assignments (bba's). The combination of priority vectors corresponding to bba's related to each (sub)- criterion is performed using the Proportional Conflict Redistribu- tion rule no. 5 proposed in Dezert-Smarandache Theory (DSmT) of plausible and paradoxical reasoning. The method presented here, called DSmT-AHP, is illustrated on very simple examples.

Mots clés: Analytic Hierarchy Process; AHP; DSmT; Information Fusion; Decision Making; Multi-Criteria

Domaines: Intelligence artificielle [cs.AI]

Jean Dezert, Jean-Marc Tacnet, Mireille Batton-Hubert, Florentin Smarandache. Multi-criteria decision making based on DSmT-AHP. Workshop on the Theory of Belief Functions, April 1- 2, 2010 Brest, France, Apr 2010, Brest, France. Paper no 132. ⟨hal-00471855⟩