Bayesian Network Method Research Articles

Using Bayesian Networks for Cognitive Assessment of Student Understanding of Buoyancy: A Granular Hierarchy Model

ABSTRACT Cognitive diagnostic assessment based on Bayesian networks (BN) is developed in this paper to evaluate student understanding of the physical concept of buoyancy. we propose a three-order granular-hierarchy BN model which accounts for both fine-grained attributes and high-level proficiencies. Conditional independence in the BN structure is tested and utilized to validate the proposed model. The proficiency relationships are verified and the initial Q-matrix is refined. Then, an optimized granular hierarchy model is constructed based on the updated Q-matrix. All variants of the constructed models are evaluated on the basis of the prediction accuracy and the goodness-of-fit test. The experimental results demonstrate that the optimized granular-hierarchy model has the best prediction and model-fitting performance. In general, the BN method not only can provide more flexible modeling approach, but also can help validate or refine the proficiency model and the Q-matrix and this method has its unique advantage in cognitive diagnosis.

Risk and Reliability Assessment of Metal Lathe Machining Operation with DBN‐FFTA Hybrid Approach

A metal lathe is a high‐performance tool used in the field of metalworking to remove excess material and shape metal parts. However, engaging in metal turning operations carries risks that can lead to serious accidents and physical harm. It is crucial to ensure that these systems are functioning correctly, as any malfunction or flaw can lead to dangerous situations. To maintain safety in industrial environments, it is important to assess the risks and reliability of the equipment. A study was conducted using a method called fuzzy fault tree analysis (FFTA), combined with fuzzy logic, to determine the probability of basic events. Bayesian networks (BNs) were utilized to update probabilities and overcome limitations of the fault tree (FT). A Dynamic Bayesian Network (DBN) was employed to estimate the reliability of a metal lathe in a specific scenario. The FT identified 57 root events and estimated the probability of workpiece FLY‐OUTS as 0.03174329 using the FT method and 0.031505849 using the BN method. Based on the predictions of the DBN, system reliability decreased by 19.89% after 24 months. The FT diagram comprehensively captured all the factors associated with FLY‐OUTS, highlighting that improper closing of the part on the tool was a significant contributing factor. The study concludes by proposing safety measures for turning operations based on the identified critical events.

Teoria da Objetificação: Aplicabilidade em uma Amostra no Rio Grande do Sul/Brasil

Abstract The applicability of objectification theory on undergraduate female students from Rio Grande do Sul was analyzed, examining if the constructs of self-objectification, self-surveillance, appearance anxiety and body shame worked to predict disordered eating and depressive symptomatology. Participants were female undergraduate students from Rio Grande do Sul. Two quantitative, cross-sectional studies were conducted. On the first one (n = 622), the psychometric characteristics of the adapted instruments (English-Portuguese) were evaluated. On the second one, only data provided by Psychology students (n = 371) was used to test the framework using the innovative method of Bayesian Networks. Results indicate that the tested variables predict outcomes related to depression and eating disorders, partially explaining the gender disparity in the development of these pathologies. Objectification theory is useful to understand how the phenomenon can affect the mental health of Brazilian women.

A continuous Bayesian network regression model for estimating seismic liquefaction‐induced settlement of the free‐field ground

AbstractThe Bayesian network (BN) method has been successfully applied to evaluate earthquake liquefaction‐induced settlement of free‐field ground in recent years due to several specific advantages. However, the existing BN models need to discretize all continuous variables, and therefore, they can only predict the range value of the settlement (i.e., classification). Thus, information loss is inevitable in the process of discretization, which will largely reduce the prediction accuracy of the model. To realize the application of the BN method in the regression prediction of seismic liquefaction‐induced settlement, this study proposes a hybrid modelling method combining a hill‐climbing algorithm and domain knowledge to construct the structure of a continuous BN regression model based on historical liquefaction‐induced settlement data, and then the conditional linear Gaussian approach is used to learn the conditional probability distributions of parameters. A five‐fold cross‐validation test is used to demonstrate better generalization performance and advantages (such as considering model uncertainty and prior knowledge) of the continuous BN regression model compared with a discrete BN classification model, simplified methods such as the Tokimatsu & Seed and Ishihara & Yoshimine methods, and an artificial neural network model. Their advantages and disadvantages are discussed. In addition, the other two continuous BN models using the Arias intensity and cumulative absolute velocity instead of the peak ground acceleration perform slightly worse than the proposed continuous BN model, and the reason for this difference is discussed.

Reliability Estimation of Low-Voltage Power Distribution Systems

Many accidents always happen in the electricity distribution sector, which requires the use of control strategies in this field. Therefore, this study presented a risk assessment method based on a fuzzy Bayesian network (FBN) and William Fine method in low-voltage power distribution systems to reduce the structural uncertainties of the studies and examined the reliability of these systems to achieve proper performance in emergencies. The first step is to develop a fault tree (FT) and event tree (ET) in bow tie (BT) format. In this study, fuzzy theory and expert judgment were used to qualitatively analyze the root events affecting the system failure and determine the relevant probabilities. Then, deductive and inductive reasoning was done after determining the likelihood of basic events (BEs) and establishing the Bayesian network (BN). Then, the final risk was estimated using William Fine’s method and fuzzy logic. The results of a case study in a low-voltage power distribution system showed that there were 36 BEs and 20 intermediate events (IEs) for system failure, and the reliability of the system was obtained as 0.96654476 and 0.96654476 based on the FT and FBN, respectively. According to the results of BE25 (no installation of the earth) and BE18 (contact of metal objects with the live wire), the most critical events were based on FBN. The results showed that FBN simulation and its combination with static methods such as BT and William Fine provide a suitable method for the accurate identification of distribution systems. Therefore, the approach of the present study can help the decision makers and analysts of the electricity industry to prevent possible failures due to system changes.

Proposal of STRIM Improving Rule Induction Method and its Application to Datasets Generated via Partial Correspondence Hypothesis

Various data mining models and/or methods have been proposed to date. A statistical test rule induction method (STRIM) has been proposed as one of them, that induces if-then rules hidden in a dataset known as the decision table generated based on a simple hypothesis. This study improves the previous data generation model using a hypothesis similar to human rating and the rule induction method to adapt to real-world datasets. Specifically, 1) the hypothesis is expanded from a complete correspondence hypothesis to a partial correspondence hypothesis. 2) The previous rule induction method is developed into a Bayesian STRIM, that infers and/or explores the causes based on the results. The applied rule induction method’s validity and usefulness are confirmed using a verification system. The relationship and difference between Bayesian STRIM against a maximum a posteriori probability estimate and a Bayesian network method are also studied in the rule induction problem.

Accident analysis and risk prediction of tank farm based on Bayesian network method

In recent decades, many attempts have been made to establish the cause-effect relationship model of accidents, while little work has been carried out to comprehensively consider the interdependence between the causal factors and their complex interactions with the accident outcomes. In this study, a novel accident analysis approach based on Bayesian networks (BNs) was proposed to achieve quantitative accident analysis and dynamic risk prediction of accident types and consequences. To develop the BN-based accident analysis model, a total of 1144 accident cases occurred in tank farm of China from 1960 to 2018 were collected. The BN model that can comprehensively characterize the dependencies among accident elements was established through structural learning based on accident case analysis and parameter learning based on EM algorithm. The reliability and validity of the BN model were verified by k-fold cross-validation method and comparison of predicted data with real data, and the results showed that the BN model had good classification and prediction performance. Furthermore, the established BN model was applied to the accident occurred in Huangdao, China. The analysis results show that not only the accident outcome can be accurately predicted, but also the hidden correlation can be deeply explored through the established BN model. The proposed method and findings can provide technical reference for accident investigation and analysis, and provide decision support for accident prevention and risk management.

A human-in-the-loop based Bayesian network approach to improve imbalanced radiation outcomes prediction for hepatocellular cancer patients with stereotactic body radiotherapy.

Imbalanced outcome is one of common characteristics of oncology datasets. Current machine learning approaches have limitation in learning from such datasets. Here, we propose to resolve this problem by utilizing a human-in-the-loop (HITL) approach, which we hypothesize will also lead to more accurate and explainable outcome prediction models. A total of 119 HCC patients with 163 tumors were used in the study. 81 patients with 104 tumors from the University of Michigan Hospital treated with SBRT were considered as a discovery dataset for radiation outcomes model building. The external testing dataset included 59 tumors from 38 patients with SBRT from Princess Margaret Hospital. In the discovery dataset, 100 tumors from 77 patients had local control (LC) (96% of 104 tumors) and 23 patients had at least one grade increment of ALBI (I-ALBI) during six-month follow up (28% of 81 patients). Each patient had a total of 110 features, where 15 or 20 features were identified by physicians as expert knowledge features (EKFs) for LC or I-ALBI prediction. We proposed a HITL based Bayesian network (HITL-BN) approach to enhance the capability of selecting important features from imbalanced data in terms of accuracy and explainability through humans' participation by integrating feature importance ranking and Markov blanket algorithms. A pure data-driven Bayesian network (PD-BN) method was applied to the same discovery dataset of HCC patients as a benchmark. In the training and testing phases, the areas under receiver operating characteristic curves of the HITL-BN models for LC or I-ALBI prediction during SBRT are 0.85 (95% confidence interval: 0.75-0.95) or 0.89 (0.81-0.95) and 0.77 or 0.78, respectively. They significantly outperformed the during-treatment PD-BN model in predicting LC or I-ALBI based on the discovery cross-validation and testing datasets from the Delong tests. By allowing the human expert to be part of the model building process, the HITL-BN approach yielded significantly improved accuracy as well as better explainability when dealing with imbalanced outcomes in the prediction of post-SBRT treatment response of HCC patients when compared to the PD-BN method.

The perspective of a smart city by endorsing the nexus Bermuda triangle with the risk assessment of polluted water reuse in integrated water and food security management: the case of Semnan, Iran

AbstractLocated in a semi-arid and arid zone, Iran is suffering from growing challenges of water scarcity. In the paradigm of a circular economy, the reuse of treated wastewater in agriculture is currently regarded as a possible solution for alleviating the issues of water scarcity and pollution. Accordingly, this research aims to assess the use of polluted water in the integrated management of water resources in Semnan. The research used the Water Evaluation and Planning System (WEAP) software package to model and analyze the water sector. Also, the Bayesian network method was used to assess the risk of using polluted water and its effects on humans and plants. The research explored two general scenarios for the study site of Semnan. The first scenario assumes the increase in population, crops (food), and industries, and the second has the same assumptions plus an increase in agricultural efficiency (food production). Based on the results, the agricultural, urban, and industrial water demands are 37, 0.06, and 0.01 million m3 in the base year, respectively. The water demand in the next years will be higher due to population growth. Finally, it is safer to use the wastewater of both treatment plants of the region (Mehdishahr and Semnan) in the industry than in other sectors. Additionally, the wastewater of the Mehdishahr Sewage Treatment Plant is more reliable than that of the Semnan Sewage Treatment Plant.

Enhancing BNN structure learning of hybrid modeling strategy for free formulated mechanism complex systems

Modeling of large and complex industrial processes such as chemical processes has always been an ongoing research topic. Hybrid modeling approaches draw more and more attentions due to its ability to combine the benefits of both mechanism(first-principle) models and data-based models in the term of the balance between accuracy and cost. However, there is an insurmountable problem in the application of hybrid modeling, that is, when the accurate formulated mechanism information of the system is difficult to obtain, the hybrid modeling strategy is often difficult to obtain the desired results in existing hybrid modeling strategies. In order to solve the contradiction between the need for accurate formulated mechanism and the reality that obtaining them in a large actual process is difficult or even impossible, we utilized the directed graph and the method of Bayesian Neural Network(BNN)-Structure Learning to combine the mechanism information and data information into a hybrid information graph, which is called BNN-Data Augmented Graph(BNN-DAG) to form a hybrid model without accurate first-principles formulas. On the basis of the hybrid information graph, the system is first partitioned into small blocks according to the demand of the target variables, then an appropriate modeling method is utilized based on the requirements of the object. Then, the selected modeling method is implemented into blocks and contributes to a complete predictive model, so that the complex system can still be modeled with a certain accuracy without the mechanism information expressed by accurate formulas. The method in this manuscript is validated on a Tennessee Eastman(TE) benchmark process and a Hydrogenation Fractionation Unit(HFU) in a real plant. The prediction results are compared with the currently popular deep learning methods. It is proved that under the framework of the method in this manuscript, it is possible to obtain a system prediction model with the same or higher accuracy as the existing deep learning methods but with a relatively a low cost. Under the framework, the interpretability of the prediction model could be obtained clearly. Also, the improvement is beneficial to the application in the actual industrial process.

Localized Corrosion in Seawater: A Bayesian Network-Based Review

This paper reviews the localized corrosion of passive Ni-Fe-Cr-Mo-N alloys immersed in seawater using a Bayesian network (BN) method. Making alloy performance decisions using data from the literature on seawater is challenging because a large body of data is generated using various methods in various natural conditions. There is a significant scatter in the data and cross-comparison of data from different techniques is difficult. The BN approach serves to integrate diverse sources of knowledge and data in this area and evaluate the data in a probabilistic manner. The paper shows that the predicted probability of localized corrosion agrees reasonably well with field data. The challenges and opportunities to improve the BN model are discussed.

Hepatobiliary calculi associated with ceftriaxone treatment: An analysis of FAERS data from 2004 to 2021

IntroductionThe role of gender, age, dose and other factors in the adverse reaction process of pseudocholelithiasis caused by ceftriaxone is controversial. In this study, we further explored potential risk factors using the FAERS database. MethodsThe reported odds ratio (ROR) and the information component (IC) of specific candidate factors were calculated by using the ROR method and the Bayesian confidence promotion neural network (BCPNN) method respectively to detect potential risk factors in adverse events(AEs) of ceftriaxone and hepatobiliary calculi(HBC). One candidate factor will be considered as a suspicious signal, or potential risk factors if its lower limit of 95% confidence interval of ROR (ROR025) is greater than 1 and its lower limit of 95% confidence interval of IC (IC025) is greater than 0. ResultsA total of 764 AEs of HBC were used to this analysis to evaluate candidate risk factors: Age group, Gender, Dose. Child (1–12 years): male ROR025 = 6.64, IC025 = 2.42, female ROR025 = 6.66, IC025 = 2.40. Adolescent group (12–18 years): male ROR025 = 5.47, IC025 = 2.08; elderly (≥65 years): female ROR025 = 1.25, IC025 = 0.22. ConclusionsGender was not detected as a risk factor for HBC caused by ceftriaxone. However, Male infants, male children, female children, adolescent male, and elderly female were potential risk factors for HBC caused by ceftriaxone based on criteria ROR025 > 1 and IC025 > 0.

Application of an information fusion method to the incipient fault diagnosis of the drilling permanent magnet synchronous motor

The signal of incipient fault in the drilling permanent magnet synchronous motor (DPMSM) is not obvious, and it is easy to be submerged by noise. Moreover, the sensitivity of signals to different faults varies, and the fault features of different fault severity are different. Therefore, the diagnostic accuracy is generally low with a single signal for the incipient fault of the DPMSM. A data-driven information fusion method for the incipient fault diagnosis of the DPMSM is presented. Firstly, the empirical wavelet transform (EWT) method is used for signal analysis. Then, the singular value decomposition (SVD) method and the principal component analysis (PCA) method are used to extract the fault feature of the vibration signal and the torque signal, respectively. Finally, the Bayesian network (BN) method is applied to the fault diagnosis with the vibration signal method and torque signal method, and the improved evidence theory method based on the Dempster-Murphy rule is used as an information fusion method to improve diagnostic accuracy. The diagnostic accuracy of the three methods is compared and discussed, the information fusion method has stable and highest diagnostic accuracy for faults with different severity under different load conditions.Note to Practitioners—This article was inspired by the field experience of the maintenance engineers. Our maintenance engineers have found that the diagnosis method based on a single signal is not stable for the DPMSM faults. For different types of faults, the diagnostic accuracy of the vibration signal method is better for mechanical faults, while the diagnosis effect of the torque signal method is better for excitation faults. For different fault severity, the vibration signal method can hardly correctly diagnose the incipient faint faults, while the diagnosis effect of the torque signal method is better for the incipient faults. For faults under different load conditions, the diagnostic accuracy of the two methods decreases with the up in load condition. Based on the above findings, we want to explore the relationship between the diagnostic accuracy of the two methods and the fault type, fault severity, and load condition, and hope to find a better and more stable diagnostic method for engineering applications. Based on this study, the practitioners can select appropriate fault diagnosis methods according to fault type, fault severity, and load condition.

Analyzing connectivity reliability and critical units for highway networks in high-intensity seismic region using Bayesian network

It is important to evaluate the connectivity reliability of highway networks for the emergency response and rehabilitation of transportation systems in high-intensity seismic regions. Given the complexity and uncertainty of seismic damages of highway networks in high-intensity seismic region, this paper describes a Bayesian network (BN) model for evaluating the network connectivity reliability and identifying critical units. The empirical prediction method is employed to compute the connectivity probability of highway units based on the structural damage of units under earthquakes. A success tree is used to construct the network connectivity graph. Then, the network connectivity graph is converted into the BN model by BN method with the connectivity probability of highway units as prior probability. Sensitivity analysis and Bayesian updating are performed in BN to identify critical units and dynamically assess the connectivity reliability of highway network. The proposed model is applied to a highway network composed of G213 and S9 in the Wenchuan Earthquake. The results show that the BN model integrates the structural damage of units with the functional performance of the highway network in high-intensity seismic region. Bayesian updating allows the posterior probability of segments and origin–destination pairs to be computed, providing an online evaluation of the functional performance of the highway network. The identification of critical units at each stage enables seismic reinforcement priority, thus contributing to the rehabilitation on connectivity reliability of network system.

A Risk Treatment Strategy Model for Oil Pipeline Accidents Based on a Bayesian Decision Network Model.

Risk treatment is an effective way to reduce the risk of oil pipeline accidents. Many risk analysis and treatment strategies and models have been established based on the event tree method, bow-tie method, Bayesian network method, and other methods. Considering the characteristics of the current models, a risk treatment strategy model for oil pipeline accidents based on Bayesian decision network (BDNs) is proposed in this paper. First, the quantitative analysis method used in the Event-Evolution-Bayesian model (EEB model) is used for risk analysis. Second, the consequence weights and initial event likelihoods are added to the risk analysis model, and the integrated risk is obtained. Third, the risk treatment strategy model is established to achieve acceptable risk with optimal resources. The risk treatment options are added to the Bayesian network (BN) risk analysis model as the decision nodes and utility nodes. In this approach, the BN risk analysis model can be transformed into a risk treatment model based on BDNs. Compared to other models, this model can not only identify the risk factors comprehensively and illustrate the incident evolution process clearly, but also can support diverse risk treatment strategies for specific cases, such as to reduce the integrated risk to meet acceptable criterion or to balance the benefit and cost of an initiative. Furthermore, the risk treatment strategy can be updated as the risk context changes.

Optimization of Cargo Shipping Adaptability Modeling Evaluation Based on Bayesian Network Algorithm

Through shipping service adaptability measurement, selecting shipping services that are more adaptable to preferences such as low cost, high efficiency, safety, and obvious emission reduction can achieve synergistic optimization of green shipping management. The study takes green shipping service adaptability as the research theme; explores three aspects, i.e., shipping safety, shipping rate and shipping choice preference, related to the evaluation and selection of a green shipping service; constructs the green shipping service adaptability evaluation index system including safety index, freight rate index and choice preference index; and applies fuzzy-exact by processing the historical data from H shipping company in Hainan Province, China. Bayesian net is applied to calculate the shipping safety adaptation degree of the transportation object. The theory of shipping service adaptability proposed in the paper can be applied to the fields of shipping supplier selection and shipping company’s detection of shipping object status. The fuzzy-exact Bayesian network method chosen in the paper can solve the problem of incomplete state coverage of the Bayesian network and correct the situation that some edge probabilities are unreasonable.

Exploring the role of artificial intelligence in building production resilience: learnings from the COVID-19 pandemic

The ever-happening disruptive events interrupt the operationalisation of manufacturing organisations resulting in stalling the production flow and depleting societies with products. Advancements in cutting-edge technologies, viz. blockchain, artificial intelligence, virtual reality, digital twin, etc. have attracted the practitioners’ attention to overcome such saddled conditions. This study attempts to explore the role of artificial intelligence (AI) in building the resilience of production function at manufacturing organisations during a COVID-19 pandemic. In this regard, a decision support system comprising an integrated voting analytical hierarchy process (VAHP) and Bayesian network (BN) method is developed. Initially, through a comprehensive literature review, the critical success factors (CSFs) for implementing AI are determined. Further, using a multi-criteria decision-making (MCDM) based VAHP, CSFs are prioritised to determine the prominent ones. Finally, the machine learning based BN method is adopted to predict and understand the influential CSFs that help achieve the highest production resilience. The present research is one of the early attempts to know the essence of AI and bridge the interplay between AI and production resilience during COVID-19. This study can support academicians, practitioners, and decision-makers in assessing the AI adoption in manufacturing organisations and evaluate the impact of different CSFs of AI on production resilience.

(Retracted) Research on computer network security evaluation based on image recognition and neural network

In today’s social development, the level of informatization has been greatly improved. Computer networks are now used in all aspects of society, especially with the popularity of mobile phones and computers. Basically, a mobile phone is a computer that stores all the information of a person, so it is indispensable for carrying out research on computer network security evaluation. The purpose of this article is to examine the growing state of information security threats in computer networks. Neural network technology, which is considered secure, has high flexibility, fast access to information, strong logic, and low failure. Toward creating a low-cost network topology, we used a low-cost network risk assessment method to assess the security of computer networks based on neural networks, and we evaluated existing risks that are appropriate for future computer security research. The results of the study show that neural networks using the Bayesian network method have a significant impact on network security. Considering the problems that can occur with information security risks, computer security systems based on neural networks have a 30% reduction in information error rate compared with traditional methods, and computer network systems based on neural networks have better learning performance to safeguard network security. Improving the security of information requires further research and evaluation of computer network security based on neural networks.

STS-BN: An efficient Bayesian network method for detecting causal SNPs.

Background: The identification of the causal SNPs of complex diseases in large-scale genome-wide association analysis is beneficial to the studies of pathogenesis, prevention, diagnosis and treatment of these diseases. However, existing applicable methods for large-scale data suffer from low accuracy. Developing powerful and accurate methods for detecting SNPs associated with complex diseases is highly desired. Results: We propose a score-based two-stage Bayesian network method to identify causal SNPs of complex diseases for case-control designs. This method combines the ideas of constraint-based methods and score-and-search methods to learn the structure of the disease-centered local Bayesian network. Simulation experiments are conducted to compare this new algorithm with several common methods that can achieve the same function. The results show that our method improves the accuracy and stability compared to several common methods. Our method based on Bayesian network theory results in lower false-positive rates when all correct loci are detected. Besides, real-world data application suggests that our algorithm has good performance when handling genome-wide association data. Conclusion: The proposed method is designed to identify the SNPs related to complex diseases, and is more accurate than other methods which can also be adapted to large-scale genome-wide analysis studies data.

Failure Risk Assessment of Coal Gasifier Based on the Integration of Bayesian Network and Trapezoidal Intuitionistic Fuzzy Number-Based Similarity Aggregation Method (TpIFN-SAM)

The coal gasifier is the core unit of the coal gasification system. Due to its exposure to high temperatures, high pressures, and aggressive media, it is highly susceptible to serious accidents in the event of failure. Therefore, it is important for the gasifier to perform failure-risk assessment to understand its safety status and provide safety measures. Bayesian networks (BNs) for risk analysis of process systems has received a lot of attention due to its powerful inference capability and its ability to reflect complex relationships between risk factors. However, the acquisition of basic probability data in a Bayesian network is always a great challenge. In this study, an improved Bayesian network integrated with a trapezoidal intuitionistic fuzzy number-based similarity aggregation method (TpIFN-SAM) is proposed for the failure-risk assessment of process systems. This approach used the TpIFN-SAM to collect and aggregate experts’ opinions for obtaining the prior probabilities of the root events in the BN. In the TpIFN-SAM, the intuitionistic fuzzy analytic-hierarchy-process method (IF-AHP) was adopted to assign the expert weights for reducing subjectivity or the bias caused by individual differences. To clarify the suitability of the proposed method, a case study of a coal gasifier was demonstrated, and both prediction and diagnosis analyses of the BN were performed; finally, the weak links of the gasifier were identified.