Search

Despite increasing digitalization and automation, complex production processes often require human judgment/decision-making adaptability. Humans can abstract and transfer knowledge to new situations. People in production are an irreplaceable resource. This paper presents a new concept for digitizing human expertise and their ability to make knowledge-based decisions in the production area based on ontologies and causal Bayesian networks for further research. Dedicated approaches for the ontology-based creation of Bayesian networks exist in the literature. Therefore, we first comprehensively analyze previous studies and summarize the approaches. We then add the causal perspective, which has often not been an explicit subject of consideration. We see a research gap in the systematic and structured approach to ontology-based generation of causal graphs (CGs). At the current state of knowledge, the semantic understanding of a domain formalized in an ontology can contribute to developing a generic approach to derive a CG. The ontology functions as a knowledge base by formally representing knowledge and experience. Causal inference calculations can mathematically imitate the human decision-making process under uncertainty. Therefore, a systematic ontology-based approach to building a CG can allow digitizing the human ability to make decisions based on experience and knowledge.

Despite increasing digitalization and automation, complex production processes often require human judgment/decision-making adaptability. Humans can abstract and transfer knowledge to new situations. People in production are an irreplaceable resource. This paper presents a new concept for digitizing human expertise and their ability to make knowledge-based decisions in the production area based on ontologies and causal Bayesian networks for further research. Dedicated approaches for the ontology-based creation of Bayesian networks exist in the literature. Therefore, we first comprehensively analyze previous studies and summarize the approaches. We then add the causal perspective, which has often not been an explicit subject of consideration. We see a research gap in the systematic and structured approach to ontology-based generation of causal graphs (CGs). At the current state of knowledge, the semantic understanding of a domain formalized in an ontology can contribute to developing a generic approach to derive a CG. The ontology functions as a knowledge base by formally representing knowledge and experience. Causal inference calculations can mathematically imitate the human decision-making process under uncertainty. Therefore, a systematic ontology-based approach to building a CG can allow digitizing the human ability to make decisions based on experience and knowledge. [ABSTRACT FROM AUTHOR]

This paper aims to investigate the differences between conference papers and journal papers in the field of computer science based on Bayesian network. This paper investigated the differences between conference papers and journal papers in the field of computer science based on Bayesian network, a knowledge-representative framework that can model relationships among all variables in the network. We defined the variables required for Bayesian networks modeling, calculated the values of each variable based Aminer dataset (a literature data set in the field of computer science), learned the Bayesian network and derived some findings based on network inference. The study found that conferences are more attractive to senior scholars, the academic impact of conference papers is slightly higher than journal papers, and it is uncertain whether conference papers are more innovative than journal papers. The study was limited to the field of computer science and employed Aminer dataset as the sample. Further studies involving more diverse datasets and different fields could provide a more complete picture of the matter. By demonstrating that Bayesian networks can effectively analyze issues in Scientometrics, the study offers valuable insights that may enhance researchers' understanding of the differences between journal and conference in computer science. Academic conferences play a crucial role in facilitating scholarly exchange and knowledge dissemination within the field of computer science. Several studies have been conducted to examine the distinctions between conference papers and journal papers in terms of various factors, such as authors, citations, h-index and others. Those studies were carried out from different (independent) perspectives, lacking a systematic examination of the connections and interactions between multiple perspectives. This paper supplements this deficiency based on Bayesian network modeling. [ABSTRACT FROM AUTHOR]

Web services (WS) are the preferred approach in realizing the service-oriented computing paradigm. However, this comes with challenges such as complexity and uncertainty that hinder their practical application. Bayesian networks (BNs) are one of the techniques used to address these challenges. The objective of this mapping study was to determine what is known about the use of Bayesian networks in web services research. To do this, we identified and selected rigorously 69 articles (out of the 532 identified) published on the subject in 2001–2021. We then classified and analyzed these articles by Web service themes (Service Composition, Service Management, Service Engineering), Objectives (Description, Prediction, Prescription), Types of BN (Basic, Combined, Extended), and Evaluation methods (Proof of concept, Experiment, No evaluation). In doing so, we hope to provide a clear understanding of the subject. We also identify and suggest avenues for future research. Thus, the review results can help researchers and practitioners interested by the application of BNs in WS research. [ABSTRACT FROM AUTHOR]

Relay protection rejection and misoperation exist in the existing distribution network, which will affect the fault diagnosis results. To diagnose faults in distribution networks, this paper presents a fault diagnosis method for the distribution network based on the D-S evidence theory Bayesian network. First, the collected relay protection information is divided into two categories, protection information and circuit breaker information; the corresponding Bayesian network model is established based on their respective action logic, and the corresponding component failure probability is obtained by Bayesian backward inference. Second, the fault probabilities obtained from the two Bayesian networks are fused by the D-S evidence theory, and the obtained fault probabilities are used to diagnose the faulty component. Then, using the Bayesian network corresponding to the faulty component to perform Bayesian forward inference, the protection devices and circuit breakers are identified for misoperation or rejection to achieve the fault diagnosis of the distribution network. Finally, the correctness and reliability of the proposed diagnosis method are verified through the analysis of arithmetic cases. [ABSTRACT FROM AUTHOR]

Copyright of Bulletin of the L.N. Gumilyov Eurasian National University. Technical science & Technology series is the property of L.N. Gumilyov Eurasian National University and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

As the lifeblood of national energy, oil and gas pipelines are vulnerable to corrosion, third-party damage, and natural disasters. Among these, third-party damage accidents have a high probability and serious consequences. However, China lacks a mature and unified pipeline accident database, making it difficult to assess and manage the risk of such incidents. To address this issue, this paper identifies 20 key risk factors for third-party damage to oil and gas pipelines through literature and case studies. The paper then proposes a multistate probabilistic assessment model using the Decision-Making Trial and Evaluation Laboratory (DEMATEL), interpretative structural modeling method (ISM), Røed method, and Bayesian network (BN). Real case studies demonstrate that the model not only predicts the probability of third-party damage risks but also clearly identifies key influencing factors and causal chains in the risk system. This provides a new approach for assessing third-party damage risks to oil and gas pipelines and offers a scientific basis for decision-making in managing actual pipelines. Practical Applications: The high probability and serious consequences of third-party damage accidents of oil and gas pipelines have caused certain hidden dangers to social security, environment, and economy, and put forward higher requirements for pipeline operation and management. In order to scientifically manage and effectively control the occurrence of third-party damage accidents of oil and gas pipelines, this paper, in the absence of an applicable pipeline failure database. Based on expert knowledge, a model that can be used for the assessment and prediction of third-party damage probability of oil and gas pipelines is constructed. Through the application of real cases, it is shown that the model can be used not only to predict the probability of third-party damage of oil and gas pipelines, but also to identify the key influencing factors and key causal chains leading to third-party damage. The results of the study not only provide theoretical support for pipeline management in reality, but also provide new ideas for risk assessment of oil and gas pipelines that lack actual data. [ABSTRACT FROM AUTHOR]

The daily production and life of human beings are inseparable from electricity. As the power supplier, electric power enterprises provide power demand for the majority of users. In the new era, electric power enterprises are also facing market-oriented reform. The focus of reform is electric power marketing. The formulation of electric power marketing strategy needs scientific decision-making analysis as guidance. With the increase of power demand, the scale of power grid is also expanding continuously. With the introduction of new energy equipment, the power system is becoming more and more complex, and it is difficult for relevant staff to effectively monitor and analyze the system. Combined with the above situation, this paper combined Bayesian network to build a power marketing decision analysis system, and combined Bayesian algorithm to test the power marketing real-time cost control system. The experimental results showed that the average judgment accuracy was 91.90 %, and the average warning time was 0.39 s. From the above data, it can be seen that this algorithm can play a good optimization effect on the performance of the system. In this paper, the elasticity test of the power system was also carried out from the aspect of wind speed, and the results showed that the maximum elasticity value can reach 0.94. It can be seen that the elasticity effect of the power system is good as a whole under different wind speeds. [ABSTRACT FROM AUTHOR]

Weak thruster fault detection problem is investigated for Autonomous Underwater Vehicle (AUV) with being less than 10% loss of effectiveness fault in a thruster. For the weak thruster fault, the fault features are small in general, meanwhile the fault features are also difficult to be distinguished from the external disturbances including measurement noise. In this paper, a weak thruster fault detection method is developed based on Bayesian network and hidden Markov model. In the proposed method, the fault features are enhanced at first and then the fault detection is achieved based on the occurrence probability. Specifically, Bayesian network is applicable to enhance weak signals, but the prior knowledge is difficult to obtain for an AUV. To solve this problem, this paper introduces sparse decomposition into Bayesian network to enhance the weak thruster fault features. And then, a hidden Markov model is established to provide the likelihood probability between the observation sequence and the predict one. The fault detection is achieved according to comparing the probability and the threshold. Finally, pool-experimental results on an AUV are presented to verify the effectiveness of the developed fault detection method. [ABSTRACT FROM AUTHOR]

Making predictions bounded by uncertainty is a crucial component of modern decision support systems. Knowledge graphs provide a structured, semantic-oriented approach to data integration, storage and retrieval; however, they represent data in an absolute way and do not natively support reasoning under uncertain future conditions. In this paper, we present a novel technique for building a probabilistic model from a knowledge graph using a Bayesian network, which is a step towards enabling probabilistic reasoning under uncertainty within a knowledge graph. Our approach supports mixing of continuously and discretely-distributed variables, which is necessary for jointly processing real-world data, but has not typically been supported in prior work. As an interface to the probabilistic model, we propose an extension of the SPARQL query language called Orion DSL, which is currently a working prototype. We also define a custom probabilistic ontology in order to store outputs of the model directly in the knowledge graph alongside the original data, which we refer to as a Probabilistic Knowledge Graph (PKG). The evaluation shows that: (1) the dependencies and distributions of data in a synthetically-generated knowledge graph were accurately captured by the Bayesian model, and (2) an SPARQL query against the PKG to retrieve computed probability distributions was orders of magnitude more performant than a similarly-intentioned query against the base knowledge graph. We anticipate that the models generated by this system will have applications in the areas of predicting missing data, approximate query processing, and utility-based optimization. Future work will involve more detailed explorations of each of these topics as we work towards a PKG-based decision support system. [ABSTRACT FROM AUTHOR]

With the deepening development and utilization of urban underground space, the risk of urban road collapse is becoming increasingly prominent, which is a serious threat to the safety of life and property. Therefore, the risk assessment of urban road collapse has vital significance for the safety management of cities. The main idea is to predict ongoing accidents by analyzing historical accident cases in depth. This paper explores the combination of Interpretative Structural Modeling (ISM) and Bayesian Networks (BNs) to construct a risk assessment model of road collapse. First, the main risk factors of road collapse and their coupling relationships are identified, which is used to increase the low reliability of complex systems. Then, the risk factors of road collapse are logically divided by ISM to obtain the BN hierarchy. Finally, the BN node probabilities are evaluated by the Expectation–Maximization (EM) algorithm using the collected 92 real road collapse accident cases. The model can be used to quantify the coupling strength and influence degree of each risk factor on the occurrence of road collapse accidents, which in turn can predict the probability of road collapse accidents in a given scenario. This study can provide a theoretical basis for urban safety management and reduce the risk of road collapse and potential loss of life and property, which is important for the sustainable development of societies. [ABSTRACT FROM AUTHOR]

Space teleoperation systems, as complex giant systems, feature performance-influencing factors that are interrelated. Accurately describing the dependence between these factors is crucial for constructing a human factor reliability assessment (HRA) model. Moreover, data scarcity has consistently been a challenge in space HRA. There are primarily two types of data in this domain: expert judgment data and empirical data (simulation data, actual reports), each with complementary effects. The expert judgment data, although subjective, are readily accessible, while empirical data provide robust objectivity but are difficult to obtain. Addressing these challenges, this paper constructs an HRA model for space teleoperation that combines Interpretive Structural Modeling (ISM) with a two-stage Bayesian update method. This model reflects the dependencies between factors and accommodates multisource data (expert judgment and experimental data). With more empirical data, the model can be continuously updated and refined to yield increasingly accurate evaluations of human error probability (HEP). The validity of the model was verified through the analysis of 52 space incidents using the N-K model. The study provides a methodological foundation for HRA in other space missions. [ABSTRACT FROM AUTHOR]

High-dimensional data leads to degraded performance of machine learning algorithms and weak generalization of models, so feature selection is of great importance. In a Bayesian network (BN), the Markov blanket (MB) of a target node (T) is the best feature subset of that node. Therefore, this paper proposes Fast Shrinking parents-children learning for Markov blanket-based feature selection (FSMB), which first determines the parents-children of the target node, and then discovers spouses while checking candidate parents-children set. In spouse determination process, a secondary screening strategy is proposed to remove false-positive spouses effectively. In this process, once the spouses of T with respect to T's child are determined, the parents-children set is immediately tested and the false-positive parents-children are removed in time, which not only can avoid the influence of false-positive parents-children on the subsequent spouse discovery, but also do not need to determine the spouses for false-positive parents-children. To verify the effectiveness of FSMB, experiments were performed on eight state-of-the-art MB algorithms on six standard networks and eight real datasets, the results show that FSMB outperforms other algorithms in terms of accuracy and efficiency. [ABSTRACT FROM AUTHOR]

How to evaluate and predict potential source terms quickly and effectively is very important for emergency response. In this paper, the traditional forward analysis calculation based on deterministic method was combined with probability theory calculation, and a large number of typical accident sequences were calculated with severe accident analysis software to obtain data of source terms. According to expert knowledge base, probabilistic safety analysis, and other information, a model of nuclear power plant was established based on Bayesian network algorithm, so as to carry out researches on rapid source term calculation and prediction methods. Based on the Bayesian network model of a specific power plant and the pre-calculated source term results of typical accident scenarios, the best available knowledge and observation results of events were used to estimate the relevant typical source terms and their possibilities, which provide a strong basis for effectively grasping and predicting the accident process, quickly predicting source terms and release characteristics of radioactive materials, and quickly and accurately evaluating the radioactive consequences. [ABSTRACT FROM AUTHOR]

Purpose: The use of improvement tools in the construction sector has shown to be an important determinant of quality. Companies endeavoring to enhance their daily practices require assistance, evidence, standards, frameworks and quantitative models from existing experts to help them set out for the road. This paper is aimed to assist construction managers in the selection of tools to increase customer satisfaction. Design/methodology/approach: This piece of research is based on the results of a previous empirical study on the use, within a sample of Mexican firms, of a set of more than 30 tools. It then proposes a Bayesian network (BN) to select them. By analyzing the variables under study, it is possible to establish their interaction and dependencies. The resultant BN comprises 24 nodes, and it is useful for choosing some tools that help to increase customer satisfaction. Findings: Customers and their needs now have become more complicated and harder to meet than in the past. Then, the use of improvement tools that put quality at the heart of the management strategies is crucial for achieving customer satisfaction. In order to reduce prices, keep product quality and meet delivery times, these tools should be used on a daily basis. Along this line of thought, the overall results from the hypothetical scenarios explored in this were positive, reflecting the relevance of the proposed model. In particular, the use of tools for gathering customer needs, the utilization of technology and the implementation of a quality department are relevant for increasing customer satisfaction in the sector. Research limitations/implications: The sample size could be further expanded. The customer satisfaction dimensions could be enhanced. Practical implications: While the sample in which the investigation is based could be expanded along with the number of variables and their states, the BN can help practitioners in the global construction industry to improve their quality practices, to foster loyalty and to grow revenues. Originality/value: Most of the research reported in the area of continuous improvement in construction focuses on qualitative considerations, and it is still scarce in terms of developing mathematical models for selecting existing tools and, ultimately, satisfying customer's requirements. This investigation is aimed to bridge this gap in the literature. [ABSTRACT FROM AUTHOR]

This study examines causal relationships among various short- and long-term interest rates in the Korean financial market to identify transmission channels. Monthly time series data from January 2015 to February 2024 were used, covering nine interest rates, including call rates, commercial paper (CP) rates, bank lending rates, and Treasury bond yields of different maturities. The study employs a Bayesian network to identify an acyclic causal structure between interest rates alongside a vector error correction model (VECM) to capture long-term equilibrium relationships and short-term dynamics. The findings reconfirm the traditional call rate transmission mechanism, aligning with conventional monetary policy views, demonstrating the call rate's significant influence on bank lending rates, which affects corporate bond spreads and CP rates. Additionally, it reveals that 10-year Treasury bond yields form an independent interest rate transmission pathway, a finding not previously identified in the literature. These results underscore the need for coordinated monetary and fiscal policies due to the distinct transmission pathways of Treasury yields for sustainable macroeconomic management and growth. [ABSTRACT FROM AUTHOR]

Studying cloud-to-ground lightning strokes and ground-strike points provides an alternative method of lightning mapping for lightning risk assessment. Various k-means algorithms have been used to verify the ground-strike points from lightning locating systems, producing results with room for improvement. This paper proposes using Bayesian networks (BNs), a model not previously used for this purpose, to classify lightning ground-strike points. A Bayesian network is a probabilistic graphical model that uses Bayes' theorem to represent the conditional dependencies of variables. The networks created for this research were trained from the data using a score-based structure-learning procedure and the Bayesian information criterion score function. The models were evaluated using confusion matrices and kappa indices and produced accuracy values ranging from 86% to 94% and kappa indices of up to 0.76. While BN models do not outperform k-means algorithms, they offer an alternative by not requiring predetermined distances. However, the easy implementation of the k-means approach means that no significant gain is made by implementing the more complex Bayesian network approach. [ABSTRACT FROM AUTHOR]

All engineering projects involve risk management applications. Sometimes, risks cannot be effectively managed, leading to catastrophic consequences. Engineers must consciously or unconsciously manage these risks. Regardless of how risks are handled, project risks need to be systematically evaluated. Therefore, risk management procedures must be implemented in every project, particularly in geo-engineering projects, to mitigate undesirable consequences and achieve project objectives. However, the use of risk management procedures in underground excavation projects is not common. Numerous commonly employed underground excavation techniques lack assessment of risks, notably geotechnical risks. Most of them only evaluate rock structures and excavation stability in accordance with the geological structure. This paper combines a universal risk management perspective with the underground engineering discipline. The tunnel engineering design and construction steps were evaluated for uncertainties using Scenario Structuring Modeling techniques to identify both technical and non-technical risks associated with underground excavation. Bayesian Network models were employed to identify connections that contribute to risk. To achieve this, objective and quantitative risk assessment tables have been devised using risk management philosophy, in accordance with tunnel design engineering principles and Turkish procurement laws. The primary objective of this study is to increase awareness of the use of risk management processes in tunnel construction projects and introduce a systematic approach to risk assessment in tunnel engineering projects. As a result, a semi-quantitative risk assessment method based on risk management philosophy is proposed for tunnel design and construction for the first time, evaluating not only geotechnical and engineering risks but also human, financial, and various other sources of risks. [ABSTRACT FROM AUTHOR]

The Cyber Physical System (CPS) is a prime target for cyber attacks due to its heterogeneity and connectivity with physical equipment. This paper proposes a model based on a Hierarchical Bayesian Network (HBN) to increase the CPS’s attack detection ability. Denial of Service (DoS) attacks pose a significant threat to production line availability, business services, and human lives. Therefore, this paper focuses on detecting DoS attacks using the Bayesian network model, an efficient algorithm to detect faults in the networking system based on incomplete recognizing information. The standard Bayesian network model is hierarchically enhanced and optimized with a Bacterial Foraging Optimization (BFO) approach to improve the detection process. The developed, optimized model satisfies security, Quality of Service (QoS) requirements, and time consumption by reducing the constraints to obtain system reliability. The efficiency of the proposed model is evaluated using the NSL-KDD dataset and compared with existing approaches in terms of accuracy, precision, recall, F1-score, ROC, and RMSE. Compared to other existing systems, the proposed model achieves an accuracy of 98.4% in detecting DoS attacks with a reduced RMSE of 0.0617. [ABSTRACT FROM AUTHOR]

In the construction of a telecom-fraud risk warning and intervention-effect prediction model, how to apply multivariate heterogeneous data to the front-end prevention and management of telecommunication network fraud has become one of the focuses of this research. The Bayesian network-based fraud risk warning and intervention model was designed by taking into account existing data accumulation, the related literature, and expert knowledge. The initial structure of the model was improved by utilizing City S as an application example, and a telecom-fraud analysis and warning framework was proposed by incorporating telecom-fraud mapping. After the evaluation in this paper, the model shows that age has a maximum sensitivity of 13.5% to telecom-fraud losses; anti-fraud propaganda can reduce the probability of losses above 300,000 yuan by 2%; and the overall telecom-fraud losses show that more occur in the summer and less occur in the autumn, and that the Double 11 period and other special time points are prominent. The model in this paper has good application value in the real-world field, and the analysis of the early warning framework can provide decision support for the police and the community to identify the groups, locations, and spatial and temporal environments prone to fraud, to combat propaganda and provide a timely warning to stop losses. [ABSTRACT FROM AUTHOR]

Facing the challenges of production management of manufacturing enterprises and the demand for intelligent control of manufacturing system abnormalities, this paper proposes a production abnormal event diagnosis method based on digital twin technology to achieve intelligent tracing of the causes of production abnormal events and improve the problems of poor timeliness and lack of feedback mechanism for the diagnosis of production abnormal events of complex products. First, a complex product production abnormal event diagnosis model is constructed, in which physical production workshop, virtual production workshop, workshop twin data platform and abnormal event diagnosis service system work together. Second, the joint method of Bayesian network (BN) and C5.0 decision tree algorithm (C5.0) is used to achieve the diagnosis of production abnormal events. Finally, the feasibility and effectiveness of the scheme are verified by the arithmetic example of key stations in the bogie production workshop. The diagnostic accuracy of 92.49% of the BN–C5.0 model is higher than that of the conventional C5.0 decision tree model with 79.94% accuracy. The proposed method and mechanism provide a reference model for the application of digital twin to the diagnosis of abnormal production events. [ABSTRACT FROM AUTHOR]