A data-driven approximate causal inference model using the evidential reasoning rule

Chen, Yue; Chen, Yu‐Wang; Xu, Xiaobin; Pan, Changchun; Yang, Jian‐Bo; Yang, Genke

doi:10.1016/j.knosys.2015.07.026

Cited by 50 publications

(21 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, the evidential reasoning (ER) rule has been established to advance the seminal Dempster-Shafer evidence theory [24][25][26][27][28] and the original ER algorithm [29][30][31][32]. Compared with the DC rule, the main advance of the ER rule is to propose a novel concept of weighted evidence (WE) and extend to WE with Reliability (WER) in order to characterize evidence in complement of BBA or BD introduced in the DST.…”

Section: Accepted Manuscript 2 / 18mentioning

confidence: 99%

Data classification using evidence reasoning rule

Zheng

Yang

et al. 2017

Knowledge-Based Systems

Self Cite

175

View full text Add to dashboard Cite

Abstract-In Dempster-Shafer evidence theory (DST) based classifier design, Dempster's combination (DC) rule is commonly used as a multi-attribute classifier to combine evidence collected from different attributes. The main aim of this paper is to present a classification method using a novel combination rule i.e., the evidence reasoning (ER) rule. As an improvement of the DC rule, the newly proposed ER rule defines the reliability and weight of evidence. The former indicates the ability of attribute or its evidence to provide correct assessment for classification problem, and the latter reflects the relative important of evidence in comparison with other evidence when they need to be combined. The ER rule-based classification procedure is expatiated from evidence acquisition and estimation of evidence reliability and weight to combination of evidence. It is a purely data-driven approach without making any assumptions about the relationships between attributes and class memberships, and the specific statistic distributions of attribute data. Experiential results on five popular benchmark databases taken from University of California Irvine (UCI) machine learning database show high classification accuracy that is competitive with other classical and mainstream classifiers.

show abstract

Section: Accepted Manuscript 2 / 18mentioning

confidence: 99%

Data classification using evidence reasoning rule

Zheng

Yang

et al. 2017

Knowledge-Based Systems

Self Cite

175

View full text Add to dashboard Cite

show abstract

“…Each piece of evidence e i can also be associated with a weight w i and a reliability r i respectively. In the ER rule, the weight w i is used to reflect the relative importance of evidence e i , while the reliability r i is regarded as the inherent property of the evidence [15,17].…”

Section: Basics and Strengths Of The Er Rule In Representing And Aggrmentioning

confidence: 99%

“…The ER rule generalizes the Bayesian inference, the seminal Dempster-Shafer (D-S) theory of evidence [18,19] and the ER algorithm [9,10]. Each piece of evidence in the Bayesian inference is formulated by a probability distribution, which can be regarded as a belief distribution without local or global ignorance [15,17]. The ER rule can rigorously combine two pieces of highly or completely conflicting evidence, where Dempster's rule combination was found to generate counter-intuitive results [20,21].…”

Section: Basics and Strengths Of The Er Rule In Representing And Aggrmentioning

confidence: 99%

A Hierarchal Risk Assessment Model Using the Evidential Reasoning Rule

Jiang

Sun

et al. 2017

Systems

Self Cite

View full text Add to dashboard Cite

This paper aims to develop a hierarchical risk assessment model using the newly-developed evidential reasoning (ER) rule, which constitutes a generic conjunctive probabilistic reasoning process. In this paper, we first provide a brief introduction to the basics of the ER rule and emphasize the strengths for representing and aggregating uncertain information from multiple experts and sources. Further, we discuss the key steps of developing the hierarchical risk assessment framework systematically, including (1) formulation of risk assessment hierarchy; (2) representation of both qualitative and quantitative information; (3) elicitation of attribute weights and information reliabilities; (4) aggregation of assessment information using the ER rule and (5) quantification and ranking of risks using utility-based transformation. The proposed hierarchical risk assessment framework can potentially be implemented to various complex and uncertain systems. A case study on the fire/explosion risk assessment of marine vessels demonstrates the applicability of the proposed risk assessment model.

show abstract

“…Each piece of evidence can also be associated with a weight and a reliability respectively. In the ER rule, the weight is used to reflect the relative importance of evidence , while the reliability is regarded as the inherent property of the evidence Chen et al, 2015).…”

Section: Basics and Strengths Of The Er Rule In Representing And Aggrmentioning

confidence: 99%

“…The ER rule generalises the Bayesian inference, the seminal Dempster-Shafer (D-S) theory of evidence (Dempster, 1968;Shafer, 1976) and the ER algorithm (Yang and Singh, 1994;Xu, 2012). Each piece of evidence in the Bayesian inference is formulated by a probability distribution, which can be regarded as a belief distribution without local or global ignorance Chen et al, 2015). The ER rule can rigorously combine two pieces of highly or completely conflicting evidence, where Dempster's rule combination was found to generate counter-intuitive results (Zadeh, 1984;Yager 1987).…”

Section: Basics and Strengths Of The Er Rule In Representing And Aggrmentioning

confidence: 99%

A Hierarchal Risk Assessment Model using the Evidential Reasoning Rule

Jiang

Sun

et al. 2016

Preprint

Self Cite

View full text Add to dashboard Cite

This paper aims to develop a hierarchical risk assessment model using the newlydeveloped evidential reasoning (ER) rule, which constitutes a generic conjunctive probabilistic reasoning process. In this paper, we first provide a brief introduction to the basics of the ER rule and emphasize the strengths for representing and aggregating uncertain information from multiple experts and sources. Further, we discuss the key steps of developing the hierarchical risk assessment framework systematically, including (1) formulation of risk assessment hierarchy, (2) representation of both qualitative and quantitative information, (3) elicitation of attribute weights and information reliabilities, (4) aggregation of assessment information using the ER rule and (5) quantification and ranking of risks using utility-based transformation. The proposed hierarchical risk assessment framework can potentially be implemented to various complex and uncertain systems. A case study on the fire/explosion risk assessment of marine vessels demonstrates the applicability of the proposed risk assessment model.

show abstract

A data-driven approximate causal inference model using the evidential reasoning rule

Cited by 50 publications

References 30 publications

Data classification using evidence reasoning rule

Data classification using evidence reasoning rule

A Hierarchal Risk Assessment Model Using the Evidential Reasoning Rule

A Hierarchal Risk Assessment Model using the Evidential Reasoning Rule

Contact Info

Product

Resources

About