Uncertainty and Preference Modelling for Multiple Criteria Vehicle Evaluation

Abstract

A general framework for vehicle assessment is proposed based on both mass survey information and the evidential reasoning (ER) approach. Several methods for uncertainty and preference modeling are developed within the framework, including the measurement of uncertainty caused by missing information, the estimation of missing information in original surveys, the use of nonlinear functions for data mapping, and the use of nonlinear functions as utility function to combine distributed assessments into a single index. The results of the investigation show that various measures can be used to represent the different preferences of decision makers towards the same feedback from respondents. Based on the ER approach, credible and informative analysis can be conducted through the complete understanding of the assessment problem in question and the full exploration of available information.

Prioritizing customer requirements in a product-service system (PSS) context

“…This is a significant problem especially in the case of small and medium enterprises, where large-scale surveys cannot always be afforded (Franceschini and Maisano, 2015). This is in line with the research hints of Xie et al (2010), who highlighted the need to find methods to handle the uncertainty due to incomplete data. The latter aspect is…”

Application of Evidential Reasoning Approach in Enterprise Performance Evaluation System

“…For qualitative attributes, the system acquiescently provides the mapping transformation. 3) Alternatives management sub-module: This sub-module is used to save, update and delete the information of alternatives.4) Evidential reasoning sub-module: it is used to obtain the comprehensive evaluation results by integrating the initial evaluation information according to (2)(3)(4)(5)(6)(7)(8)(9)(10)(11).…”

“…In recent years, this method has been widely used in maritime risk assessment, ship type evaluation, competitiveness comparison, etc. [7][8][9][10][11][12]But the manual calculation task is heavy for decision maker due to the high complexity of ERA. In order to assist corporate investors and operators to make investment and management decisions, an enterprise performance evaluation system should be designed.…”

A Novel D-S Combination Method for Interval-valued Evidences

“…Evidence theory is a convenient framework for modeling imperfection in data and for combining information. As a theory of uncertain information processing, evidence theory has been widely used in data fusion (Sevastianov and Dymova, 2009;Deng et al, 2011), pattern recognition (Perrin et al, 2004;Liu et al, 2008), decision analysis (Kanoksri and Miroslav, 2008;Ludmila and Pavel, 2010), uncertainty quantification (Aven, 2011;Xie et al, 2010) and other fields (He et al, 2007;Basir and Yuan, 2007;Thomas and Olivier, 2011).…”