Histogram distance-based Bayesian Network structure learning: A supervised classification specific approach

Sierra, Basilio; Lazkano, Elena; Jauregi, E.; Irigoien, Itziar

doi:10.1016/j.dss.2009.07.010

Cited by 26 publications

(17 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Fig.1 An example of a Bayesian Networks BNs are founded on the concept of conditional independence among variables [16]. This concept makes possible a factorization of the probability distribution of the n-dimensional random variable (X1, … , Xn) in the following way:…”

Section: The Bayesian Networkmentioning

confidence: 99%

An economic early warning approach based on Bayesian Networks mechanism?

Pang

Bao

Jiang

2010

2010 Sixth International Conference on Natural Computation

View full text Add to dashboard Cite

Economic early warning (EEW) helps decision-making by judging the tendency of economic development. Active research has investigated process modeling and the methodologies of EEW. However, in real-world, features have complex relationships, and one feature is always decided by the others. Traditional EEW methods need the feature independent assumption. This paper tries to create an EEW Based on Bayesian Networks, which considers the cause and consequence to overcome this problem. The experiment indicates that our method has achieved a satisfying performance: precision of 85.71% in open test in EEW, which is a desirable precision in EEW.

show abstract

Section: The Bayesian Networkmentioning

confidence: 99%

An economic early warning approach based on Bayesian Networks mechanism?

Pang

Bao

Jiang

2010

2010 Sixth International Conference on Natural Computation

View full text Add to dashboard Cite

show abstract

“…The design of a BN model involves determining the network structure and its parameters. Structure learning involves figuring out a proper DAG, confirming the association relationship between variables (nodes) . The network structure can be developed by creating directed edges from one node (fault causes) to another node (its consequence).…”

Section: Safety Risk Analysis Approachmentioning

confidence: 99%

“…Structure learning involves figuring out a proper DAG, confirming the association relationship between variables (nodes). (41) The network structure can be developed by creating directed edges from one node (fault causes) to another node (its consequence). Indeed, FTs or ETs, some the most commonly used techniques for risk and reliability studies, can provide a logic diagram that displays the interrelationships between a potential critical event and the causes in a system.…”

Section: Fbn Model Constructionmentioning

confidence: 99%

Towards a Fuzzy Bayesian Network Based Approach for Safety Risk Analysis of Tunnel‐Induced Pipeline Damage

et al. 2015

View full text Add to dashboard Cite

Tunneling excavation is bound to produce significant disturbances to surrounding environments, and the tunnel-induced damage to adjacent underground buried pipelines is of considerable importance for geotechnical practice. A fuzzy Bayesian networks (FBNs) based approach for safety risk analysis is developed in this article with detailed step-by-step procedures, consisting of risk mechanism analysis, the FBN model establishment, fuzzification, FBN-based inference, defuzzification, and decision making. In accordance with the failure mechanism analysis, a tunnel-induced pipeline damage model is proposed to reveal the cause-effect relationships between the pipeline damage and its influential variables. In terms of the fuzzification process, an expert confidence indicator is proposed to reveal the reliability of the data when determining the fuzzy probability of occurrence of basic events, with both the judgment ability level and the subjectivity reliability level taken into account. By means of the fuzzy Bayesian inference, the approach proposed in this article is capable of calculating the probability distribution of potential safety risks and identifying the most likely potential causes of accidents under both prior knowledge and given evidence circumstances. A case concerning the safety analysis of underground buried pipelines adjacent to the construction of the Wuhan Yangtze River Tunnel is presented. The results demonstrate the feasibility of the proposed FBN approach and its application potential. The proposed approach can be used as a decision tool to provide support for safety assurance and management in tunnel construction, and thus increase the likelihood of a successful project in a complex project environment.

show abstract

“…Table II. For all the twenty five indexes we calculate the "histogram's distance" [20,21] three dimensional space describes with reasonable accuracy the "map" of the twenty five indexes. The resulting Sheppard plots, represented in figures 26-29, show that a good distribution of points around the 45 degree line is obtained for the indices [22].…”

Section: Mds Analysis Based On Histogramsmentioning

confidence: 99%