Nodes In Bayesian Network Research Articles

Risk analysis of underground debris flows in mines based on a coupled weighted Bayesian network

Mines mined by the natural caving method are prone to underground debris flow disasters, resulting in mud gushing blocking roadways, equipment damage and even casualties, which seriously affect the safe operation of mines. To carry out a risk analysis of underground debris flows in mines, quantify the interactions among risk factors in the process of disasters, and identify the main disaster-causing paths, DEMATEL-ISM was used to analyze 18 risk factors related to material sources, geology, water sources and processes. A multilevel network structure model was constructed, and the model was mapped to a Bayesian network (BN). Based on the N-K model, the degree of risk coupling was calculated, the nodes in the BN were coupled and weighted, and diagnostic reasoning for underground debris flows was realized based on posterior probability. The results showed that the risk of debris flow increases with increasing coupling factor. The factors of water source, geology and ore drawing ranked at the top in terms of the probability change rate of the BN nodes, and a main disaster-causing path was obtained by diagnostic reasoning, which provides a theoretical basis for the formulation of underground debris flow prevention and control measures.

An international relations quantitative evaluation model (IRQEM) based on an integrated method.

International relations (IR) have great uncertainty and instability. Bad IR or conflicts will bring about heavy economic losses and widespread social unrest domestically and internationally. The accurate prediction for bilateral relations can support decision making for timely responses, which will be used to find ways to maintain development in the complex international situation. An international relations quantitative evaluation model (IRQEM) is proposed by integrating a variety of research models and methods like the interpretative structural modeling method (ISM), Bayesian network (BN) model, the Bayesian search (BS), and the expectation-maximization (EM) algorithm, which is novel for IR research. Factors from several different fields are identified as BN nodes. Each node is assigned different state values. The hierarchical structure of these BN nodes is obtained by ISM. The data collection of 192 cases is used to construct the BN model by GeNIe 4.0. The IRQEM can be used to evaluate the influence of emergencies on IR. The critical factors of IR also can be explored through our proposed model. Results show that the prediction of bilateral relations under emergencies can be realized by updating the indicator set when emergencies occur. The capability to anticipate threats of IR changes is advanced by optimizing the reporting information of IR forecasting through a combination of qualitative and quantitative methods, charts, and texts. Relevant analysis results can provide support for national security decision making.

A Possibility Evaluation Model for Road Transportation of Hazardous Chemicals Based on Bow-tie Theory and Bayesian Model

This paper collected 1115 road transportation accidents of hazardous chemicals in China from 2013 to 2021, and constructed a total of 120 accident chains, among which the most common accident chain was "impact → rear-end collision → fuel tank damage → leakage", with a total of 195 times. Based on the analysis of historical accident data, the occurrence mechanism of road transportation accidents of hazardous chemicals was discussed. Based on the bow-tie theory, the bow-tie diagram was established to realize the construction of qualitative reasoning bow-tie diagram for multi-disaster coupling accidents in road transportation of hazardous chemicals. The mapping rules between Bow-tie model and Bayesian network were established, and the structure of Bayesian network for road transportation of hazardous chemicals was constructed. The prior probability and conditional probability of Bayesian network nodes are determined by multi-source data, and the real-time accident probability evaluation is realized by combining quantitative and qualitative methods. Finally, a real time evaluation of the possibility of multi-disaster coupling accidents is realized every 30 seconds through a numerical example, which reflects the influence law of multi-disaster coupling scenarios on risks.

An Index Model for the Evaluation of the Performance of Lock Navigation Scheduling Rules Considering the Perspective of Stakeholders

The lock navigation scheduling problem involves multiple stakeholder groups. The game relationship between stakeholders directly affects the sustainable development of regional society and economy. Considering the objectivity and accuracy of social network analysis (SNA) for relationship identification, indicator screening, and system construction, it completes the stakeholder extraction and evaluation index system construction. Considering that the conditional probability of nodes in Bayesian networks (BN) can flexibly and intuitively characterize the direction and strength of the factors’ roles in a complex scenario, this study proposes an index model for the evaluation of the performance of lock navigation scheduling rules. Firstly, build the BN topology under the efficiency, safety, and fairness criteria. Subsequently, an improved composite index method is combined with the BN to determine the evaluation index from the stakeholder perspective. This study takes the Three Gorges locks maintenance scenario as an example. The index evaluation model can accurately identify the direction, trend, and magnitude of the performance of the scheduling rules on the efficiency, safety, and fairness criteria under navigational constraints, realizing the dynamic and quantitative evaluation of the performance of lock navigation scheduling rules during the observation period.

Exploration of college teacher education path based on cognitive multi-method integration for innovation and entrepreneurship ability cultivation

Abstract In this paper, a cognitive multi-method integration-based approach combined with a genetic algorithm for optimization is used to set the random variables as Bayesian network nodes, and the joint probability distribution is obtained by analyzing the strength of association between the nodes. An independently distributed observation data set with random variables is used to determine the log-likelihood function. After generating the random data, the roulette wheel is used to select the individuals with higher fitness values for transformation, and the excellence of the individuals in the population is improved through cyclic iteration. 20 points improved the educational practice’s 4th test score compared to the pre-training score after the innovation and entrepreneurship training. Therefore, the method of cultivating innovation and entrepreneurial abilities based on cognitive multi-method integration has a positive effect on improving the education level and talent cultivation quality of college teachers.

A Bayesian Network-Based Inhibition Model of the Rainstorm–Landslide–Debris Flow Disaster Chain in Mountainous Areas: The Case of the Greater Bay Area, China

In this study, a Bayesian network (BN)-based inhibition model is developed for the rainstorm–landslide–debris flow (R-L-D) disaster chain in the mountainous area of the Greater Bay Area (GBA), China, using the historical disaster data. Twelve nodes are selected for the inhibition model, which are classified into four types, including Hazardous Factor, Response Operation, Disaster Evolution, and Disaster Result. By combining the proposed inhibition with the scenario analysis method, the probabilities of the BN nodes under different rainfall scenarios are analyzed, and then the inhibitory effects of the environmental geological conditions and rescue speed on the R-L-D disaster chain under the most unfavorable rainfall scenario are investigated. On this basis, an inhibition framework consisting of the early warning, inhibition, and measures layers is proposed for the R-L-D disaster chain. The results reveal that under the most unfavorable rainfall scenarios, where the rainfall intensity is greater than 100 mm/d and the rainfall duration is greater than 24 h, the probability of landslides and debris flow is 0.930 and 0.665, respectively. Improving the environmental geological conditions such as slope, lithology and geological structure can greatly inhibit the occurrence of the R-L-D disaster chain. Moreover, the improvement of geological structure conditions is the most significant, and reduces the probability of landslides and debris flow by 0.684 and 0.430, respectively, as well as reducing the probability of death and direct economic loss by 0.411 and 0.619, respectively. Similarly, increasing the rescue speed leads to a reduction in the probability of death and direct economic loss by 0.201 and 0.355, respectively. This study can provide theoretical and practical insights into the prevention and inhibition of the R-L-D disaster chain.

Risk Analysis of Laboratory Fire Accidents in Chinese Universities by Combining Association Rule Learning and Fuzzy Bayesian Networks

Targeting the challenges in the risk analysis of laboratory fire accidents, particularly considering fire accidents in Chinese universities, an integrated approach is proposed with the combination of association rule learning, a Bayesian network (BN), and fuzzy set theory in this study. The proposed approach has the main advantages of deriving conditional probabilities of BN nodes based on historical accident data and association rules (ARs) and making good use of expert elicitation by using an augmented fuzzy set method. In the proposed approach, prior probabilities of the cause nodes are determined based on expert elicitation with the help of an augmented fuzzy set method. The augmented fuzzy set method enables the effective aggregation of expert opinions and helps to reduce subjective bias in expert elicitations. Additionally, an AR algorithm is applied to determine the probabilistic dependency between the BN nodes based on the historical accident data of Chinese universities and further derive conditional probability tables. Finally, the developed fuzzy Bayesian network (FBN) model was employed to identify critical causal factors with respect to laboratory fire accidents in Chinese universities. The obtained results show that H4 (bad safety awareness), O1 (improper storage of hazardous chemicals), E1 (environment with hazardous materials), and M4 (inadequate safety checks) are the four most critical factors inducing laboratory fire accidents.

Probabilistic Modeling of Maritime Accident Scenarios Leveraging Bayesian Network Techniques

This paper introduces a scenario evolution model for maritime accidents, wherein Bayesian networks (BNs) were employed to predict the most probable causes of distinct types of maritime incidents. The BN nodes encompass factors such as accident type, life loss contingency, accident severity, quarter and time period of the accident, and type and gross tonnage of the involved ships. An analysis of 5660 global maritime accidents spanning the years 2005 to 2020 was conducted. Using Netica software, a tree augmented network (TAN) model was constructed, thus accounting for interdependencies among risk-influencing factors. To confirm these results, a validation process involving sensitivity analysis and historical accident records was performed. Following this, both forward causal inference and reverse diagnostic inference were carried out on each node variable to scrutinize the accident development trend and evolution process under preset conditions. The findings suggest that the model was competent in effectively predicting the likelihood of various accident scenarios under specific conditions, as well as extrapolating accident consequences. Forward causal reasoning unveiled that general cargo ships with a gross tonnage of 1–18,500 t were most prone to experiencing collision and stranding/grounding accidents in the first quarter. Reverse diagnostic reasoning indicated that, in the early morning hours, container ships, general cargo ships, and chemical ships with a tonnage of 1–18,500 t were less likely to involve life loss in the event of collision accidents.

Dynamic risk analysis of flammable liquid road tanker based on fuzzy Bayesian network

AbstractDue to environmental variability of combustible liquid road transportation, it is difficult to analyze risk accurately. This article proposes a method for real‐time analysis of the risk of flammable liquid road transportation using a fuzzy Bayesian network. This method combines the binary logistic regression model with the bow‐tie model to analyze the influencing factors and accident evolution. Then, a Bayesian network framework is established based on the fault tree model. In the case of limited historical accident statistics, the fuzzy set theory and Leaky Noisy‐OR theory are used to determine the prior probability and conditional probability of Bayesian network nodes, and ALOHA software is used to simulate the dangerous area of the accident to define further the safe evacuation range and emergency rescue material demand. Taking the road transportation of a tanker in Beijing as an example, the accident probability is updated in real time by monitoring the data of transportation nodes, and the change rule of risk level with internal and external conditions at different times is analyzed. The research shows that this method can dynamically describe the road transportation accidents of hazardous chemicals with the GPS data of vehicles.

Revolutionizing steel building project cost overrun risk assessment by Bayesian network

PurposeIn recent years, cost overrun becomes a common problem in steel building construction projects. The average percentage can vary widely depending on the project type, size, complexity and location. The steel structure change ratio in Taiwan is from 1 to 18% in statistics. The contractors always put every possible effort into preventing or mitigating project cost overruns, and one of the approaches is an accurate cost overrun risk estimate. Traditional project cost overrun risk assessment models mainly focus on macro-level evaluation and may not function well for the project-specific level (micro-level). This study creates a network-like connection model between the outcome (i.e. cost overrun risk) and the associated root causes in which the project status evaluation checklists of design, manufacturing, construction and interfaces are used to evaluate the checklists' influences through the Bayesian network (BN) composed by intermediate causes.Design/methodology/approachDue to the constraint of data availability, BN nodes, relationships and conditional probabilities are defined to establish a BN-based steel building project cost overrun assessment model following the knowledge of experts. Because of the complexity of the BN, the construction of the BN structure is first to build BN's fault tree (FT) hierarchy. And then, basic BN framework is constructed by the transformation of the FT hierarchy. Furthermore, some worthwhile additional arcs among BN nodes are inserted if necessary. Furthermore, conditional probability tables (CPTs) among BN nodes are explored by experts following the concept of the ranked node. Finally, the BN-based model was validated against the final cost analysis reports of 15 steel building projects done in Taiwan and both were highly consistent. The overall BN-based model construction process consists of three steps: (1) FT construction and BN framework transformation, (2) CPT computation and (3) model validation.FindingsThis study established a network-like bridge model between the outcome (i.e. cost overrun risk) and the root causes in a network of which cost influences are evaluated through the project-specific status evaluation checklists of design, manufacturing, construction and interfaces. This study overcame several limitations of the previous cost overrun risk assessment models: (1) few past research support assessment of cost overrun based on real-time project-owned data and (2) the traditional causal models inadequately depict interdependencies among influence factors of cost overrun at the network. The main influence factors of the cost overrun risk at the steel building projects in Taiwan were also examined using sensitivity analysis. The main root causes of cost overrun in steel building projects are design management and interface integration.Originality/valueThe proposed model belongs to the project-specific causal assessment model using real-time project-owned status checklist data as input. Such a model was seldom surveyed in the past due to the complicated interdependence among causes in the network. For practical use, a convenient and simple regression equation was also developed to forecast the cost overrun risk of the steel building project based on the root causes as input. Based on the analysis of cost overrun risk and significant influence factors, proper tailor-made preventive strategies are established to reduce the occurrence of cost overrun at the project.

Post-earthquake recover strategy for substations based on seismic resilience evaluation

Electrical substations need a sufficient amount of time to repair damaged equipment and restore power after an earthquake. Yet, the devastation and danger inherent in an earthquake requires fastest return to power possible; thus, finding better methods to improve the efficiency of post-earthquake emergency recover is an urgent issue. This paper presents a rapid seismic resilience assessment framework which combines a network model and functional time-varying feature. The authors developed a dual-dimensional functional network model of a typical 220 kV substation built with an emphasis on its connectivity capabilities and the power transmission capacity of its equipment. The model’s rapid function status was evaluated based on its network dependence on Bayesian network nodes. The authors’ post-earthquake iterative analysis focuses on resource constraint and power user importance. This article shows how the authors obtained the stepped functional time-varying function as a basis for quantification in the post-earthquake recovery process and provides a seismic resilience analysis of the electrical substation. The multi-objective heuristic optimization algorithm was developed to determine an optimal post-earthquake multi-level repair strategy for substation post-earthquake recovery and to determine substation’s seismic resilience levels.

A national risk analysis model (NRAM) for the assessment of COVID-19 epidemic.

COVID-19 has caused a critical health concern and severe economic crisis worldwide. With multiple variants, the epidemic has triggered waves of mass transmission for nearly 3 years. In order to coordinate epidemic control and economic development, it is important to support decision-making on precautions or prevention measures based on the risk analysis for different countries. This study proposes a national risk analysis model (NRAM) combining Bayesian network (BN) with other methods. The model is built and applied through three steps. (1) The key factors affecting the epidemic spreading are identified to form the nodes of BN. Then, each node can be assigned state values after data collection and analysis. (2) The model (NRAM) will be built through the determination of the structure and parameters of the network based on some integrated methods. (3) The model will be applied to scenario deduction and sensitivity analysis to support decision-making in the context of COVID-19. Through the comparison with other models, NRAM shows better performance in the assessment of spreading risk at different countries. Moreover, the model reveals that the higher education level and stricter government measures can achieve better epidemic prevention and control effects. This study provides a new insight into the prevention and control of COVID-19 at the national level.

Risk Assessment and Prediction of Underground Utility Tunnels Based on Bayesian Network: A Case Study in Beijing, China

The underground utility tunnels accommodate various types of urban lifelines, which are of great significance for improving the living standards of the citizens. With the rapid development of underground utility tunnels, the large-scale underground utility tunnel systems are gradually becoming the operational lifeblood of China’s large cities. Currently, most of the underground utility tunnels’ risks are estimated and analyzed from a static perspective, and the analysis results are one-sided. This study proposes a dynamic risk evaluation framework. A risk assessment and sensitivity analysis framework based on Bayesian network is established in this study. Combined with the groundwater and electric tunnel risk accident case study, the operation and maintenance data of Beijing Future Science and Technology City from 2010 to 2018 are collected for learning to obtain the conditional probability of the Bayesian network node by using the K2 algorithm. The overall evolution process from the beginning to the end of groundwater tunnel accidents is clearly described and displayed. Through sensitivity analysis and critical path analysis, the critical points of an accident and the probabilities of risk occurrence are identified and predicted. This proposed framework could facilitate the underground utility tunnel management for controlling risk resources, mitigating risk damage and reducing risk losses.

Smart City Construction and Management by Digital Twins and BIM Big Data in COVID-19 Scenario

With the rapid development of information technology and the spread of Corona Virus Disease 2019 (COVID-19), the government and urban managers are looking for ways to use technology to make the city smarter and safer. Intelligent transportation can play a very important role in the joint prevention. This work expects to explore thebuilding information modeling (BIM) big data (BD)processing method ofdigital twins (DTs)of Smart City, thus speeding up the construction of Smart City and improve the accuracy of data processing. During construction, DTs build the same digital copy of the smart city. On this basis, BIM designs the building's keel and structure, optimizing various resources and configurations of the building. Regarding the fast data growth in smart cities, a complex data fusion and efficient learning algorithm, namely Multi-Graphics Processing Unit (GPU), is proposed to process the multi-dimensional and complex BD based on the compositive rough set model. The Bayesian network solves the multi-label classification. Each label is regarded as a Bayesian network node. Then, the structural learning approach is adopted to learn the label Bayesian network's structure from data. On the P53-old and the P53-new datasets, the running time of Multi-GPU decreases as the number of GPUs increases, approaching the ideal linear speedup ratio. With the continuous increase of K value, the deterministic information input into the tag BN will be reduced, thus reducing the classification accuracy. When K = 3, MLBN can provide the best data analysis performance. On genbase dataset, the accuracy of MLBN is 0.982 ± 0.013. Through experiments, the BIM BD processing algorithm based onBayesian Network Structural Learning (BNSL)helps decision-makers use complex data in smart cities efficiently.

A flexible method for parameterizing ranked nodes in Bayesian networks using Beta distributions.

When novice modelers first attempt to build a Bayesian network, they are often impressed with the intuitive graphical structures that capture their causal understanding. This favorable impression evaporates on proceeding to parameterization. Conditional probability tables (CPT) require parameters for often hundreds of very similar scenarios and specifying them in the absence of data can be overwhelming. The problem is even more severe when eliciting parameters from experts with limited time. Often, there is local structure with fewer parameters that better describes the relationship. Such structures include the Noisy OR, decision trees, and equations. These work well for modelers, but can be an issue for experts and particularly groups of experts. An alternative approach is to elicit only a few CPT rows and interpolate the remainder. This is a promising approach, as it can handle unknown structures and multiple experts, but existing techniques can be limited. Here, we present a flexible approach called InterBeta for performing CPT interpolation with ordered nodes. In the simplest case, just two CPT rows are needed, but this can be easily augmented with further information. The basic approach assumes input independence, but allows dependencies to be reintroduced as required, and can also be combined with other local structures such as decision trees or equations, leaving the interpolator to fill in the gaps. We explain the InterBeta method, describe its capabilities and limitations and how it compares to similar approaches and show how it can trade-off elicitation effort against faithfully representing expertunderstanding.

Research on vehicle-cargo matching algorithm based on improved dynamic Bayesian network

The problem of vehicle-cargo matching is a key issue in highway freight logistics transportation, and many investigations have been achieved for this problem. However, current research is limited to ideal environment, small dataset, static matching, and low matching efficiency, etc. Aimed at this, a vehicle-cargo matching algorithm based on improved dynamic Bayesian network is proposed (IDBN) in this paper. First, we define the vehicle-cargo matching degree as two parts, attribute matching degree and environmental influence degree, and quantify the importance of both by AHP (Analytic Hierarchy Process) method. Secondly, we construct the static Bayesian network and the dynamic Bayesian network through mapping vehicles, cargoes, matching combinations and time into Bayesian network nodes. Thirdly, we design an algorithm for the solution of IDBN, where the matching process of each vehicle is viewed as a state and the matching of two adjacent vehicles is switched by state. Fourthly, the model and the algorithm are verified through abundant experiments. It is found that the average success rate of vehicle matching in a single time slice can basically reach more than 80%, and the average success rate of rematching for the failed vehicles can reach 90%, and the matching success rate of vehicles is the highest when the number of cargoes is in the majority. This not only improves the efficiency of vehicle and cargo matching, but also effectively optimizes the subsequent matching process of vehicles that is failed to match. Therefore, theoretical reference can be provided by the proposed IDBN algorithm for the vehicle and cargo matching in small and medium-sized logistics enterprises.

Optimization of a Low Loss Strategy for Combine Harvesters Based on Bayesian Network

In this study, the Bayesian network was used to optimize the harvesting strategy of the combine harvester for low loss rate. The range analysis and variance analysis of the orthogonal field experiments showed that the feed rate, concave clearance and threshing drum speed were main factors affecting the loss rate. Taken the main factors and loss rate as Bayesian network nodes, the optimal network structure was obtained through scoring search, in which the four scoring functions were respectively combined with hill-climbing method. An optimized harvesting strategy for low loss rate was inferred through the constructed network, and the strategy was implemented in field experiment. The results showed that the average loss rate was reduced by 0.8% compared to that normal harvesting strategy.

Portraying probabilistic relationships of continuous nodes in Bayesian networks with ranked nodes method

This paper advances the use of the ranked nodes method (RNM) to portray probabilistic relationships of continuous quantities in Bayesian networks (BNs). In RNM, continuous quantities are represented by ranked nodes with discrete ordinal scales. The probabilistic relationships of the nodes are quantified in conditional probability tables (CPTs) generated with expert-elicited parameters. When ranked nodes are formed by discretizing continuous scales, ignorance about the functioning of RNM can lead to discretizations that make the generation of sensible CPTs impossible. While a guideline exists on this matter, it is limited by a requirement to define an equal number of ordinal states for all the nodes. This paper presents two novel discretization approaches that consider the functioning of RNM and allow the nodes to have non-equal numbers of ordinal states. In the first one, called the “static discretization approach”, the nodes can be given any desired discretizations that stay unchanged during the use of the BN. In the second one, called the “dynamic discretization approach”, the discretizations are algorithmically updated during the use of the BN to help manage the sizes of the generated CPTs. Both approaches are based on the original idea that, besides the RNM parameters, the nodes probabilistic relationship is defined by initial RNM-compatible discretizations elicited from the domain expert. Overall, the new approaches offer an easier and more versatile way of using RNM to depict the probabilistic relationships of continuous quantities. In doing so, they also facilitate the effective and diverse use of BNs in decision support systems.

A compositional approach to probabilistic knowledge compilation

Bayesian networks (BN) are a popular representation for reasoning under uncertainty. The analysis of many real-world use cases, that in principle can be modeled by BNs, suffers however from the computational complexity of inference. Inference methods based on Weighted Model Counting (WMC) reduce the cost of inference by exploiting patterns exhibited by the probabilities associated with BN nodes. However, these methods require a computationally intensive compilation step in search of these patterns, which effectively prohibits the handling of larger BNs. In this paper, we propose a solution to this problem by extending WMC methods with a framework called Compositional Weighted Model Counting (CWMC). CWMC reduces compilation cost by partitioning a BN into a set of subproblems, thereby scaling the application of state-of-the-art innovations in WMC to scenarios where inference cost could previously not be amortized over compilation cost. The framework supports various target representations that are less or equally succinct as decision-DNNF. At the same time, its inference time complexity O(nexp⁡(w)), where n is the number of variables and w is the tree-width, is comparable to mainstream algorithms based on variable elimination, clustering and conditioning.

Research on Fault Diagnosis of Steam Turbine Based on Bayesian Network

In the fault diagnosis of steam turbine, multiple faults contain number of uncertainties due to the complexity of fault diagnosis knowledge and the strong correlation and coupling between different faults and massive prior knowledge is needed. In this paper, a fault diagnosis method of steam turbine based on Bayesian network is proposed. Various faults and symptoms are parameterized using Bayesian network nodes. Then rough set theory is used to simplify the complex causal relationship between faults and symptoms, and Noisy-Or model is used to simplify the conditional probability parameters. A diagnostic model of the steam turbine was developed using a simplified Bayesian network. The experiment results are shown to validate the practicality and effectiveness of the proposed designs.