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.

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.

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.

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.

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.

Bottom hole pressure prediction based on hybrid neural networks and Bayesian optimization

Many scholars have focused on applying machine learning models in bottom hole pressure (BHP) prediction. However, the complex and uncertain conditions in deep wells make it difficult to capture spatial and temporal correlations of measurement while drilling (MWD) data with traditional intelligent models. In this work, we develop a novel hybrid neural network, which integrates the Convolution Neural Network (CNN) and the Gate Recurrent Unit (GRU) for predicting BHP fluctuations more accurately. The CNN structure is used to analyze spatial local dependency patterns and the GRU structure is used to discover depth variation trends of MWD data. To further improve the prediction accuracy, we explore two types of GRU-based structure: skip-GRU and attention-GRU, which can capture more long-term potential periodic correlation in drilling data. Then, the different model structures tuned by the Bayesian optimization (BO) algorithm are compared and analyzed. Results indicate that the hybrid models can extract spatial-temporal information of data effectively and predict more accurately than random forests, extreme gradient boosting, back propagation neural network, CNN and GRU. The CNN-attention-GRU model with BO algorithm shows great superiority in prediction accuracy and robustness due to the hybrid network structure and attention mechanism, having the lowest mean absolute percentage error of 0.025%. This study provides a reference for solving the problem of extracting spatial and temporal characteristics and guidance for managed pressure drilling in complex formations.

Uncertainty quantification of predicting stable structures for high-entropy alloys using Bayesian neural networks

High entropy alloys(HEAs)have excellent application prospects in catalysis because of their rich components and configuration space.In this work,we develop a Bayesian neural network(BNN)based on energies calculated with density functional theory to search the configuration space of the CoNiRhRu HEA system.The BNN model was developed by considering six independent features of Co-Ni,Co-Rh,CoRu,Ni-Rh,Ni-Ru,and Rh-Ru in different shells and energies of structures as the labels.The root mean squared error of the energy predicted by BNN is 1.37 me V/atom.Moreover,the influence of feature periodicity on the energy of HEA in theoretical calculations is discussed.We found that when the neural network is optimized to a certain extent,only using the accuracy indicator of root mean square error to evaluate model performance is no longer accurate in some scenarios.More importantly,we reveal the importance of uncertainty quantification for neural networks to predict new structures of HEAs with proper confidence based on BNN.

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.

An evaluation method of contribution rate based on fuzzy Bayesian networks for equipment system-of-systems architecture

The contribution rate of equipment system-of-systems architecture(ESoSA)is an important index to evaluate the equipment update,development,and architecture optimization.Since the traditional ESoSA contribution rate evaluation method does not make full use of the fuzzy information and uncertain information in the equipment system-of-systems(ESoS),and the Bayesian network is an effective tool to solve the uncertain information,a new ESoSA contribution rate evaluation method based on the fuzzy Bayesian network(FBN)is proposed.Firstly,based on the operation loop theory,an ESoSA is constructed considering three aspects:reconnaissance equipment,decision equipment,and strike equipment.Next,the fuzzy set theory is introduced to construct the FBN of ESoSA to deal with fuzzy information and uncertain information.Furthermore,the fuzzy importance index of the root node of the FBN is used to calculate the contribution rate of the ESoSA,and the ESoSA contribution rate evaluation model based on the root node fuzzy importance is established.Finally,the feasibility and rationality of this method are validated via an empirical case study of aviation ESoSA.Compared with traditional methods,the evaluation method based on FBN takes various failure states of equipment into consideration,is free of acquiring accurate probability of traditional equipment failure,and models the uncertainty of the relationship between equipment.The proposed method not only supplements and improves the ESoSA contribution rate assessment method,but also broadens the application scope of the Bayesian network.

产生“Tuned”模板的Bayesian Networks方法

介绍了Bayesian Networks(简称BNs)产生“Tuned”模板新方法的基本原理以及BNs法与蚁群行为仿真技术和单纯形法组合的方法。通过实际航空影像的实验结果表明,新方法对纹理影像的识别率是令人满意的,同时还将新方法与遗传算法的结果作了对比,结果表明新方法是很有应用前景的。

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。

基于DBN的风电机组变桨系统可靠性动态评估

为了对风电机组变桨系统的潜在风险进行可靠的动态预测,针对变桨系统部件种类多、系统复杂、故障特征提取困难的问题,文章首先对变桨系统故障点和故障传递过程进行归纳分析,建立故障树;然后将其转化为融合Leaky Noisy-Or节点的动态贝叶斯网络(DBN),保证了模型精度并具备了动态预测能力;最后采用5折交叉验证的方式对模型进行寻优并验证。测试结果表明,该方法在对变桨系统进行风险预测、故障致因分析、风险动态演化过程分析方面准确率较高,可指导变桨系统进行预防性维护,在保证风电机组整体安全方面具有工程应用价值。

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。

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。

融合强化学习的DBN跑道侵入风险预测

为解决机场跑道侵入事件风险量化难度大、时效性差、精准性低等问题,提升跑道侵入风险预警能力,构建融合强化学习的动态贝叶斯网络(DBN)风险预测模型。首先,结合因果推断理论与灰色关联分析法分析跑道侵入历史事件,识别跑道侵入事件风险致因;其次,运用贝叶斯网络(BN)理论挖掘各风险因素间的关联性,并利用皮尔逊线性相关系数量化各因素间的关联关系,构建表征风险传播的致因关系网络;然后,利用三角模糊方法与隐马尔可夫模型(HMMs)优化DBN参数学习机制;最后,利用历史数据验证基于融合强化学习的DBN预测结果准确性。结果表明:基于融合强化学习的DBN预测结果与历史数据统计数值的拟合较好,准确率为84%,与单独DBN预测结果相比准确性提升10%;相比于采用度值评价法,通过互信息识别关键节点可有效提升预测准确率和区分度。

Nonlinear inversion of electrical resistivity imaging using pruning Bayesian neural networks

Conventional artificial neural networks used to solve electrical resistivity imaging （ERI） inversion problem suffer from overfitting and local minima. To solve these problems, we propose to use a pruning Bayesian neural network （PBNN） nonlinear inversion method and a sample design method based on the K-medoids clustering algorithm. In the sample design method, the training samples of the neural network are designed according to the prior information provided by the K-medoids clustering results; thus, the training process of the neural network is well guided. The proposed PBNN, based on Bayesian regularization, is used to select the hidden layer structure by assessing the effect of each hidden neuron to the inversion results. Then, the hyperparameter αk, which is based on the generalized mean, is chosen to guide the pruning process according to the prior distribution of the training samples under the small-sample condition. The proposed algorithm is more efficient than other common adaptive regularization methods in geophysics. The inversion of synthetic data and field data suggests that the proposed method suppresses the noise in the neural network training stage and enhances the generalization. The inversion results with the proposed method are better than those of the BPNN, RBFNN, and RRBFNN inversion methods as well as the conventional least squares inversion.

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。

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.