Rock mass quality prediction on tunnel faces with incomplete multi-source dataset via tree-augmented naive Bayesian network

Rock mass quality serves as a vital index for predicting the stability and safety status of rock tunnel faces.In tunneling practice,the rock mass quality is often assessed via a combination of qualitative and quantitative parameters.However,due to the harsh on-site construction conditions,it is rather difficult to obtain some of the evaluation parameters which are essential for the rock mass quality prediction.In this study,a novel improved Swin Transformer is proposed to detect,segment,and quantify rock mass characteristic parameters such as water leakage,fractures,weak interlayers.The site experiment results demonstrate that the improved Swin Transformer achieves optimal segmentation results and achieving accuracies of 92%,81%,and 86%for water leakage,fractures,and weak interlayers,respectively.A multisource rock tunnel face characteristic(RTFC)dataset includes 11 parameters for predicting rock mass quality is established.Considering the limitations in predictive performance of incomplete evaluation parameters exist in this dataset,a novel tree-augmented naive Bayesian network(BN)is proposed to address the challenge of the incomplete dataset and achieved a prediction accuracy of 88%.In comparison with other commonly used Machine Learning models the proposed BN-based approach proved an improved performance on predicting the rock mass quality with the incomplete dataset.By utilizing the established BN,a further sensitivity analysis is conducted to quantitatively evaluate the importance of the various parameters,results indicate that the rock strength and fractures parameter exert the most significant influence on rock mass quality.

Evaluating the Efficacy of Latent Variables in Mitigating Data Poisoning Attacks in the Context of Bayesian Networks:An Empirical Study

Bayesian networks are a powerful class of graphical decision models used to represent causal relationships among variables.However,the reliability and integrity of learned Bayesian network models are highly dependent on the quality of incoming data streams.One of the primary challenges with Bayesian networks is their vulnerability to adversarial data poisoning attacks,wherein malicious data is injected into the training dataset to negatively influence the Bayesian network models and impair their performance.In this research paper,we propose an efficient framework for detecting data poisoning attacks against Bayesian network structure learning algorithms.Our framework utilizes latent variables to quantify the amount of belief between every two nodes in each causal model over time.We use our innovative methodology to tackle an important issue with data poisoning assaults in the context of Bayesian networks.With regard to four different forms of data poisoning attacks,we specifically aim to strengthen the security and dependability of Bayesian network structure learning techniques,such as the PC algorithm.By doing this,we explore the complexity of this area and offer workablemethods for identifying and reducing these sneaky dangers.Additionally,our research investigates one particular use case,the“Visit to Asia Network.”The practical consequences of using uncertainty as a way to spot cases of data poisoning are explored in this inquiry,which is of utmost relevance.Our results demonstrate the promising efficacy of latent variables in detecting and mitigating the threat of data poisoning attacks.Additionally,our proposed latent-based framework proves to be sensitive in detecting malicious data poisoning attacks in the context of stream data.

Bayesian network-based survival prediction model for patients having undergone post-transjugular intrahepatic portosystemic shunt for portal hypertension

BACKGROUND Portal hypertension(PHT),primarily induced by cirrhosis,manifests severe symptoms impacting patient survival.Although transjugular intrahepatic portosystemic shunt(TIPS)is a critical intervention for managing PHT,it carries risks like hepatic encephalopathy,thus affecting patient survival prognosis.To our knowledge,existing prognostic models for post-TIPS survival in patients with PHT fail to account for the interplay among and collective impact of various prognostic factors on outcomes.Consequently,the development of an innovative modeling approach is essential to address this limitation.AIM To develop and validate a Bayesian network(BN)-based survival prediction model for patients with cirrhosis-induced PHT having undergone TIPS.METHODS The clinical data of 393 patients with cirrhosis-induced PHT who underwent TIPS surgery at the Second Affiliated Hospital of Chongqing Medical University between January 2015 and May 2022 were retrospectively analyzed.Variables were selected using Cox and least absolute shrinkage and selection operator regression methods,and a BN-based model was established and evaluated to predict survival in patients having undergone TIPS surgery for PHT.RESULTS Variable selection revealed the following as key factors impacting survival:age,ascites,hypertension,indications for TIPS,postoperative portal vein pressure(post-PVP),aspartate aminotransferase,alkaline phosphatase,total bilirubin,prealbumin,the Child-Pugh grade,and the model for end-stage liver disease(MELD)score.Based on the above-mentioned variables,a BN-based 2-year survival prognostic prediction model was constructed,which identified the following factors to be directly linked to the survival time:age,ascites,indications for TIPS,concurrent hypertension,post-PVP,the Child-Pugh grade,and the MELD score.The Bayesian information criterion was 3589.04,and 10-fold cross-validation indicated an average log-likelihood loss of 5.55 with a standard deviation of 0.16.The model’s accuracy,precision,recall,and F1 score were 0.90,0.92,0.97,and 0.95 respectively,with the area under the receiver operating characteristic curve being 0.72.CONCLUSION This study successfully developed a BN-based survival prediction model with good predictive capabilities.It offers valuable insights for treatment strategies and prognostic evaluations in patients having undergone TIPS surgery for PHT.

Application of Bayesian Analysis Based on Neural Network and Deep Learning in Data Visualization

This study aims to explore the application of Bayesian analysis based on neural networks and deep learning in data visualization.The research background is that with the increasing amount and complexity of data,traditional data analysis methods have been unable to meet the needs.Research methods include building neural networks and deep learning models,optimizing and improving them through Bayesian analysis,and applying them to the visualization of large-scale data sets.The results show that the neural network combined with Bayesian analysis and deep learning method can effectively improve the accuracy and efficiency of data visualization,and enhance the intuitiveness and depth of data interpretation.The significance of the research is that it provides a new solution for data visualization in the big data environment and helps to further promote the development and application of data science.

BN-GEPSO:Learning Bayesian Network Structure Using Generalized Particle Swarm Optimization

At present Bayesian Networks(BN)are being used widely for demonstrating uncertain knowledge in many disciplines,including biology,computer science,risk analysis,service quality analysis,and business.But they suffer from the problem that when the nodes and edges increase,the structure learning difficulty increases and algorithms become inefficient.To solve this problem,heuristic optimization algorithms are used,which tend to find a near-optimal answer rather than an exact one,with particle swarm optimization(PSO)being one of them.PSO is a swarm intelligence-based algorithm having basic inspiration from flocks of birds(how they search for food).PSO is employed widely because it is easier to code,converges quickly,and can be parallelized easily.We use a recently proposed version of PSO called generalized particle swarm optimization(GEPSO)to learn bayesian network structure.We construct an initial directed acyclic graph(DAG)by using the max-min parent’s children(MMPC)algorithm and cross relative average entropy.ThisDAGis used to create a population for theGEPSO optimization procedure.Moreover,we propose a velocity update procedure to increase the efficiency of the algorithmic search process.Results of the experiments show that as the complexity of the dataset increases,our algorithm Bayesian network generalized particle swarm optimization(BN-GEPSO)outperforms the PSO algorithm in terms of the Bayesian information criterion(BIC)score.

基于AESL-GA的BN球磨机滚动轴承故障诊断方法

针对基于知识的贝叶斯网络(BN)构建方法存在不完全和不精确的缺点,提出一种基于知识引导和数据挖掘的BN结构构建方法。针对单一信号故障诊断结果不精确的问题和故障信息中存在的不确定性问题,将电流信号与振动信号融合建立BN的特征节点,分别提取2种信号的故障特征参数,利用区分度指标法进行特征筛选,将其作为BN结构特征层的节点。将专家知识构建的初始BN结构结合自适应精英结构遗传算法(AESL-GA)进行结构优化,通过自适应限制进化过程中的搜索空间,减少自由参数的数量,提高其全局搜索能力,得到最优BN结构。通过MQY5585溢流型球磨机滚动轴承实测数据和Paderborn University轴承数据集对所提方法进行验证,结果证明了所提方法的有效性。

强降雨情景下附着式升降脚手架事故致因IFRAM-BN模型

强降雨事件频发造成附着式升降脚手架事故剧增,为提高强降雨情景下施工安全性,降低事故发生率,提出一种基于改进的功能共振分析模型(IFRAM)和贝叶斯网络(BN)相结合的事故致因分析模型。首先,从定性角度,利用IFRAM识别事故机制并深度挖掘系统功能共振情况;其次,将IFRAM映射至BN定量分析模型,并引入联系云优化计算各根节点的先验概率;最后,以西安“9·10”事故为例,进行实证研究并提出相应预防措施。结果表明:事故在安全状态为Ⅳ级时,发生的可能性最大。工人违规操作、未进行旁站等强制性监督、强降雨等是导致爬架事故的核心致因;强降雨环境→雨后架体载荷超载等致因组合是诱发爬架事故的关键。

基于STPA-BN的船舶航行人为风险因素分析与评估

人为因素是引发船舶事故的最主要因素之一,为了研究船舶人为风险因素的因果关系,从中国海事局发布的船舶事故报告出发,引入系统理论过程分析-贝叶斯网络(STPA-BN)模型对船舶航行人为风险因素进行分析和评估。采用系统理论过程分析(STPA)方法识别出船舶航行中存在的不安全控制行为,结合事故报告内容提取出12种人为风险因素,利用风险因素的内在因果关系和结构学习功能构建贝叶斯网络拓扑结构;将事故报告量化,并对网络进行参数学习,对模型进行验证。在此基础上,利用贝叶斯网络(BN)的推理功能得到船舶航行中7种突出的人为风险因素和3条事故核心致因链,为保障船舶安全航行与船员培训提供数据支持。

少量样本下基于PCA-BNs的多故障诊断

针对一些工业设备因有标签故障样本数据少而导致诊断准确率低的问题,提出了一种PCA-BNs主成分分析和斯网络(principal component analysis-Bayesian networks, PCA-BNs)结合的多故障网络模型的建模方法。通过PCA对时序信号进行降维,得到相互独立的故障特征,提高提取故障关键信息的能力;利用融合单故障贝叶斯网络构建多故障贝叶斯网络结构的方法,解决BN建模过程耗时的问题;通过高斯分布与极大似然估计结合的方法确定网络参数,提高少量数据BN建模的精度,实现在少量样本下的故障诊断。试验结果表明,基于PCA-BNs的故障诊断方法在少量样本条件下,能实现高精度的故障诊断,并且有效缩减了算法运行时间。

基于FDHHFLTS-BN的海底管道泄漏失效风险定量分析

为预防海底油气管道泄漏失效事故,提出基于自由双层次犹豫模糊语言术语集(FDHHFLTS)和贝叶斯网络(BN)的FDHHFLTS-BN风险分析方法,用于分析海底油气管道泄漏失效事故概率及事故的关键风险因素。将故障树模型转换为BN结构,由专家根据FDHHFLTS评估基本事件发生可能性;采用最佳最差法(BWM)确定专家权重,结合相似性聚合方法(SAM)聚合专家意见;依据构建的BN模型,正向推理得到事故发生概率,反向推理得到后验概率,并进行敏感性分析。将该方法应用于实例分析,结果表明:分析段海底管道泄漏事故的概率值为P=6.20×10^(-3);焊缝施工缺陷、材料施工缺陷和渔具作用等为事故发生的关键因素;与传统方法对比分析结果证明,所提方法在确定海底管道风险方面具有一定的优势。

基于改进BNN-LSTM的风电功率概率预测

针对确定性的风电功率预测难以提供预测结果的波动区间和支撑风险决策的问题,以贝叶斯网络为基础,通过将先验分布置于LSTM网络层权重参数之上,构建了贝叶斯LSTM神经网络(BNN-LSTM)。以时间卷积神经网络(TCNN)处理风电功率预测的历史时序数据,提取时序数据的关联特征。使用互信息熵方法分析了风电功率的气象数据集,剔除关联性小的变量,对气象数据集进行降维处理。并采用嵌入(embedding)结构学习风电功率时间分类特征。随后将TCNN处理后的时序数据、降维后的气象数据以及时间分类特征数据一起送入BNN-LSTM预测模型,通过在某风电数据集不同算法的概率预测指标pinball损失和Winkler评分的对比验证,可知,本文所提方法能从可对风电功率波动做出较为准确的响应,预测效果更好。

Analysis of rockburst mechanism and warning based on microseismic moment tensors and dynamic Bayesian networks

One of the major factors inhibiting the construction of deep underground projects is the risk posed by rockbursts.A study was conducted on the access tunnel of the Shuangjiangkou hydropower station to determine the evolutionary mechanism of microfractures within the surrounding rock mass during rockburst development and develop a rockburst warning model.The study area was chosen through the combination of field studies with an analysis of the spatial and temporal distribution of microseismic(MS)events.The moment tensor inversion method was adopted to study rockburst mechanism,and a dynamic Bayesian network(DBN)was applied to investigating the sensitivity of MS source parameters for rockburst warnings.A MS multivariable rockburst warning model was proposed and validated using two case studies.The results indicate that fractures in the surrounding rock mass during the development of strain-structure rockbursts initially show shear failure and are then followed by tensile failure.The effectiveness of the DBN-based rockburst warning model was demonstrated using self-validation and K-fold cross-validation.Moment magnitude and source radius are the most sensitive factors based on an investigation of the influence on the parent and child nodes in the model,which can serve as important standards for rockburst warnings.The proposed rockburst warning model was found to be effective when applied to two actual projects.

A reconfigurable dynamic Bayesian network for digital twin modeling of structures with multiple damage modes

Dynamic Bayesian networks(DBNs)are commonly employed for structural digital twin modeling.At present,most researches only consider single damage mode tracking.It is not sufficient for a reusable spacecraft as various damage modes may occur during its service life.A reconfigurable DBN method is proposed in this paper.The structure of the DBN can be updated dynamically to describe the interactions between different damages.Two common damages(fatigue and bolt loosening)for a spacecraft structure are considered in a numerical example.The results show that the reconfigurable DBN can accurately predict the acceleration phenomenon of crack growth caused by bolt loosening while the DBN with time-invariant structure cannot,even with enough updates.The definition of interaction coefficients makes the reconfigurable DBN easy to track multiple damages and be extended to more complex problems.The method also has a good physical interpretability as the reconfiguration of DBN corresponds to a specific mechanism.Satisfactory predictions do not require precise knowledge of reconfiguration conditions,making the method more practical.

基于CIA-ISM-BN煤矿瓦斯爆炸事故分析

为识别动态情景下煤矿瓦斯爆炸事故的影响因素,推断因素之间的因果关系,采用CIA(Cross Impact Analysis)、ISM(Interpretive Structural Model)和BN(Bayesian Network)结合的情景建模方法来构建煤矿井下瓦斯爆炸事故风险评价模型。利用CIA-ISM组合生成不同影响级别下瓦斯爆炸事故影响因素的因果层次网络,并进行情景推断和分析。将层次网络映射到BN模型中,通过概率推理量化复杂依赖关系的层次网络,确定瓦斯爆炸的主要致因和造成的损害。结果表明:(1)重视监管机制、违规生产、管理技术、员工安全教育培训、违章作业和通风环境之间的微循环,可以有效阻断事故演化路径;(2)瓦斯爆炸事故发生下,造成人员伤亡、经济损失和社会影响以及有毒有害等次灾害的概率分别为94.7%,95.0%,24.0%;(3)不健全的监管机制是导致瓦斯爆炸事故发生的根本原因。

基于Stacking策略的集成BN网络目标威胁评估

现有基于贝叶斯网络的威胁评估采用专家经验确定的朴素结构,其推理评估结果精度欠佳。为此,提出一种融合专家经验与数据观测的基于Stacking策略的集成贝叶斯网络(ensemble Bayesian network,EBN)。首先使用不同搜索空间内的评分优化算法获得数据观测模型集并进行模型平均;然后使用专家经验朴素模型对平均网络进行修剪,形成威胁约束集合;最后以动态规划为基础,通过该集合限制节点序图扩展,以求取全局最优威胁评估网络。在作战想定中,EBN模型单目标威胁概率推理精度比朴素贝叶斯模型高出10%,在多目标威胁排序任务中,其Spearman系数分布亦优于朴素模型。

AABN: Anonymity Assessment Model Based on Bayesian Network With Application to Blockchain

Blockchain is a technology that uses community validation to keep synchronized the content of ledgers replicated across multiple users,which is the underlying technology of digital currency like bitcoin.The anonymity of blockchain has caused widespread concern.In this paper,we put forward AABN,an Anonymity Assessment model based on Bayesian Network.Firstly,we investigate and analyze the anonymity assessment techniques,and focus on typical anonymity assessment schemes.Then the related concepts involved in the assessment model are introduced and the model construction process is described in detail.Finally,the anonymity in the MIX anonymous network is quantitatively evaluated using the methods of accurate reasoning and approximate reasoning respectively,and the anonymity assessment experiments under different output strategies of the MIX anonymous network are analyzed.

Reliability analysis for wireless communication networks via dynamic Bayesian network

The dynamic wireless communication network is a complex network that needs to consider various influence factors including communication devices,radio propagation,network topology,and dynamic behaviors.Existing works focus on suggesting simplified reliability analysis methods for these dynamic networks.As one of the most popular modeling methodologies,the dynamic Bayesian network(DBN)is proposed.However,it is insufficient for the wireless communication network which contains temporal and non-temporal events.To this end,we present a modeling methodology for a generalized continuous time Bayesian network(CTBN)with a 2-state conditional probability table(CPT).Moreover,a comprehensive reliability analysis method for communication devices and radio propagation is suggested.The proposed methodology is verified by a reliability analysis of a real wireless communication network.

System Reliability Analysis Method Based on T-S FTA and HE-BN

For high-reliability systems in military,aerospace,and railway fields,the challenges of reliability analysis lie in dealing with unclear failure mechanisms,complex fault relationships,lack of fault data,and uncertainty of fault states.To overcome these problems,this paper proposes a reliability analysismethod based on T-S fault tree analysis(T-S FTA)and Hyper-ellipsoidal Bayesian network(HE-BN).The method describes the connection between the various systemfault events by T-S fuzzy gates and translates them into a Bayesian network(BN)model.Combining the advantages of T-S fault tree modeling with the advantages of Bayesian network computation,a reliability modeling method is proposed that can fully reflect the fault characteristics of complex systems.Experts describe the degree of failure of the event in the form of interval numbers.The knowledge and experience of experts are fused with the D-S evidence theory to obtain the initial failure probability interval of the BN root node.Then,the Hyper-ellipsoidal model(HM)constrains the initial failure probability interval and constructs a HE-BN for the system.A reliability analysismethod is proposed to solve the problem of insufficient failure data and uncertainty in the degree of failure.The failure probability of the system is further calculated and the key components that affect the system’s reliability are identified.The proposedmethod accounts for the uncertainty and incompleteness of the failure data in complex multi-state systems and establishes an easily computable reliability model that fully reflects the characteristics of complex faults and accurately identifies system weaknesses.The feasibility and accuracy of the method are further verified by conducting case studies.

基于双重约束的最优BN结构学习算法

针对现有基于动态规划的贝叶斯网络结构学习算法复杂度高、无法在合理时间内学习大规模网络的问题,提出基于双重约束的最优贝叶斯网络(Bayesian Network,BN)结构学习算法.首先,利用最大信息系数和马尔科夫毯限制条件独立性(Conditional Independence,CI)测试的候选节点集合和约束集,得到邻居节点集合;其次,利用邻居节点集合约束父节点图的搜索过程,得到候选父节点集合,从候选父节点集合中取出每个节点的最优父集构造初始有向图;再次,利用Tarjan算法计算初始有向图中的强连通分量,得到节点块序;最后,利用节点块序约束节点序图的搜索过程,获得最优的BN结构.实验表明,相比于现有的5种基于动态规划的结构学习算法,本文提出的算法在精度稍微降低的前提下,极大幅度提高了算法的学习效率,如Sachs网络,本文提出的算法相对DPCMB(Dynamic Programming Constrained with Markov Blanket)算法降低了40.3%的时耗,算法精度下降了12.1%.

Differences between journal and conference in computer science:a bibliometric view based on Bayesian network

Purpose:This paper aims to investigate the differences between conference papers and journal papers in the field of computer science based on Bayesian network.Design/methodology/approach: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.Findings: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.Research limitations: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.Practical implications: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.Originality/value: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.