Combination of expert decision and learned based Bayesian Networks for multi-scale mechanical analysis of timber elements

Sousa, Hélder S.; Prieto‐Castrillo, Francisco; Matos, José C.; Branco, Jorge M.; Lourenço, Paulo B.

doi:10.1016/j.eswa.2017.09.060

Cited by 12 publications

(4 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In other words, there is no real integration of expert knowledge and statistical data. In addition, the main difficulty of incorporating knowledge and data is that expert knowledge must be consistently integrated with data, that means, expert constraints should be coherent with the conditional independency found in data [36]. On the other hand, although Bayesian Network has an advantage in describing the causality of variables, it cannot define the circular dependency and cannot completely reflect the interaction of variables.…”

Section: Related Workmentioning

confidence: 99%

A Novel Fault Identification Method Driven by Knowledge and Data

Wan

Zhang

2022

IEEE Access

View full text Add to dashboard Cite

In the field of intelligent manufacturing, fault identification is an effective way to improve product service by identifying the cause of failures. For addressing it, the Generalized Bayesian Network (GBN) model is extended based on the traditional Bayesian Network in this paper, which redefines the directed edges and probability parameters among nodes. Compared with Bayesian Network, the GBN model has the ability to simultaneously define causality and correlation of variables. In addition, the structure of network is not only based on statistical data but also driven by expert knowledge. In order to achieve the collaboration of data and knowledge while maintaining the consistency, a hierarchical collaborative framework is designed including the data layer and knowledge layer. Furthermore, a hierarchical multi-objective optimization algorithm, namely Hierarchical Non-dominated Sorting Genetic Algorithm II (HNSGA-II), is advanced to solve the proposed model. Finally, an industrial case study for fault cause identification targeting the product service helps illustrate all details.INDEX TERMS Fault identification, generalized bayesian network (GBN), data and knowledge, hierarchical collaborative framework, hierarchical non-dominated sorting genetic algorithm II (HNSGA-II).

show abstract

Section: Related Workmentioning

confidence: 99%

A Novel Fault Identification Method Driven by Knowledge and Data

Wan

Zhang

2022

IEEE Access

View full text Add to dashboard Cite

show abstract

“…In the last few years, Bayesian Network (BN) has rapidly been adopted across different areas of science [ 25 , 26 , 27 , 28 ]. A BN as a probability-based knowledge representation method is appropriate for the modelling of causal processes with uncertainty [ 29 , 30 ].…”

Section: Introductionmentioning

confidence: 99%

Evaluating the Bovine Tuberculosis Eradication Mechanism and Its Risk Factors in England’s Cattle Farms

Sedighi

Varga²

2021

IJERPH

View full text Add to dashboard Cite

Controlling bovine tuberculosis (bTB) disease in cattle farms in England is seen as a challenge for farmers, animal health, environment and policy-makers. The difficulty in diagnosis and controlling bTB comes from a variety of factors: the lack of an accurate diagnostic test which is higher in specificity than the currently available skin test; isolation periods for purchased cattle; and the density of active badgers, especially in high-risk areas. In this paper, to enable the complex evaluation of bTB disease, a dynamic Bayesian network (DBN) is designed with the help of domain experts and available historical data. A significant advantage of this approach is that it represents bTB as a dynamic process that evolves periodically, capturing the actual experience of testing and infection over time. Moreover, the model demonstrates the influence of particular risk factors upon the risk of bTB breakdown in cattle farms.

show abstract

“…These methods generally do not integrate expert's knowledge for learning the structure of BN. In order to improve these learning algorithm, a priori information such as expert's opinions has been added [6][7][8][9]. The use of a priori information has been mainly proposed in score-based methods in the case of time-fixed covariates in low-dimensional settings but structural restrictions in constraint-based algorithms have been shown as useful [10].…”

Section: Introductionmentioning

confidence: 99%