Bayesian Network Research Articles

Overcoming Catastrophic Forgetting in Continual Fine-Grained Urban Flow Inference

Citywide fine-grained urban flow inference (FUFI) problem aims to infer the high-resolution flow maps from the coarse-grained ones, which plays an important role in sustainable and economic urban computing and intelligent traffic management. Previous models tackle this problem from spatial constraint, external factors, and memory cost. However, utilizing the new urban flow maps to calibrate the learned model is very challenging due to the “catastrophic forgetting” problem and is still under-explored. In this article, we make the first step in FUFI and present CUFAR—Continual Urban Flow inference with augmented Adaptive knowledge Replay—a novel framework for inferring the fine-grained citywide traffic flows. Specifically, (1) we design a spatial-temporal inference network that can extract better flow map features from both local and global levels; (2) then, we present an augmented adaptive knowledge replay (AKR) training algorithm to selectively replay the learned knowledge to facilitate the learning process of the model on new knowledge without forgetting. We apply several data augmentation techniques to improve the generalization capability of the learning model, gaining additional performance improvements. We also propose a knowledge discriminator to avoid the “negative replaying” issue introduced by noisy urban flow maps. Extensive experiments on two large-scale real-world FUFI datasets demonstrate that our proposed model consistently outperforms strong baselines and effectively mitigates the forgetting problem.

Dynamic model-based intelligent fault diagnosis method for fault detection in a rod fastening rotor

A complete fault sample database is of great significance for the intelligent fault diagnosis method of rod fastening rotor. However, the lack of fault samples makes the fault diagnosis results unbelievable. To solve this issue, the dynamic model-based intelligent fault diagnosis method is established for a rod fastening rotor, and the fault sample database is enriched by numerical simulations. First, the lumped parameter model of the rod fastening rotor system is constructed and further updated using Euclidean Distance between measurement and numerical simulation of the intact system. Second, mathematical models of various fault types are incorporate into the updated model to obtain numerical simulation fault samples. Thirdly, the utilization of numerical simulation fault samples is severed as training data to the artificial intelligence (AI) models and the unknown measurement test samples will be finally classified. In this paper, Support Vector Machine, Random Forest, Bayesian Network and Decision Tree are selected as the typical AI models. Subsequently, the feasibility of classification is validated by the test bench of the rod fastening rotor system, and the problem of insufficient fault samples can be solved.

Adverse events analysis of Relugolix (Orgovyx®) for prostate cancer based on the FDA Adverse Event Reporting System (FAERS).

Due to the limitations of clinical trials, some delayed and rare adverse events (AEs) may remain undetected, and safety information can be supplemented through post-market data analysis. This study aims to comprehensively analyze the AEs associated with Relugolix (Orgovyx®) using data from the FAERS database, and gain a better understanding of the potential risks and side effects of Relugolix (Orgovyx®) therapy. Data of Relugolix (Orgovyx®) were collected from the FAERS database covering the period from the fourth quarter of 2020 to the third quarter of 2023. Disproportionality analysis was performed by calculating the reporting odds ratios (ROR), proportional reporting ratio (PRR), Bayesian analysis confidence propagation neural network (BCPNN), and the multi-item gamma Poisson shrinker (MGPS) to detect positive signals. Totally, 5,382,189 reports were collected from the FAERS database, 4,397 reports of Relugolix (Orgovyx®) were identified as the 'primary suspected (PS)' AEs. Relugolix (Orgovyx®) induced AEs occurred in 26 organ systems. 58 significant disproportionality preferred terms (PTs) satisfying with the four algorithms were retained at the same time. Unexpected significant AEs such as Pollakiuria, and Prostatic specific antigen increased also occur. The median time of onset was 60 days. The majority of the AEs occurred within the first 30 days after Relugolix (Orgovyx®) initiation. Common AEs included Hot flush, Fatigue, Asthenia, Constipation, and Myalgia. These AEs should be focused on when using the drug to avoid serious consequences. In addition, the study results also suggested that the drug may exist Pollakiuria, Prostatic specific antigen increased and other AEs not mentioned in the manual, to supplement the AEs in the manual. This study is helpful for clinicians and pharmacists to improve their understanding of Relugolix (Orgovyx®) related AEs, and take timely prevention and treatment measures to ensure drug safety for patients.

Optimized beamforming vector and antenna selection using autoencoder with Bayesian RNN and hybrid heuristic algorithm for MIMO systems

SummaryWireless communication systems depend on channel state information (CSI). However, the CSI collection is a significant barrier to achieving high performance. Present wireless communication models mainly rely on many antennas and related signal dispensation for increasing effectiveness. User mobility, the usage of greater frequencies, and a better number of antennas contribute to beamforming and beam management in these networks. Therefore, an improved hybrid heuristic algorithm is proposed here for providing optimized Joint beam forming and antenna selection (JBAS) in a multi‐input multi‐output (MIMO) model. The major novelty of the research work is to jointly perform the beam forming and antenna selection in MIMO that effectively enhanced the performance of the wireless transmission system. The major intention of this paper is to optimize the beamforming vectors and antennae by using the designed algorithm, where the spectral efficiency gets maximized. Initially, the data is collected by varying the number of users, locations, and sampling points, which is optimally selected by developing the hybrid reptile search‐based lion optimization algorithm (HRS‐LOA). Once it is collected, the relevant CSI is considered. This state of information is fed as input to the Auto Encoder with Bayesian Recurrent Neural Network (AE‐BRNN). Finally, through the network, the optimized value of the beamforming vector and antenna is obtained, which is useful to increase the sum rate/spectral efficiency. From the numerical results, the recommended model attained a spectral efficiency of 30 bits/s/Hz, which is higher than the BWO‐AE‐BRNN with 13%, RSO‐AE‐BRNN with 16%, RSA‐AE‐BRNN with 17%, and LA‐AE‐BRNN with 40% respectively.

Bayesian neural networks modeling for tool wear prediction in milling Al 6061 T6 under MQL conditions

Bayesian neural networks modeling for tool wear prediction in milling Al 6061 T6 under MQL conditions

A modified A* algorithm combining remote sensing technique to collect representative samples from unmanned surface vehicles.

Ensuring representativeness of collected samples is the most critical requirement of water sampling. Unmanned surface vehicles (USVs) have been widely adopted in water sampling, but current USV sampling path planning tend to overemphasize path optimization, neglecting the representative samples collection. This study proposed a modified A* algorithm that combined remote sensing technique while considering both path length and the representativeness of collected samples. Water quality parameters were initially retrieved using satellite remote sensing imagery and a deep belief network model, with the parameter value incorporated as coefficient Q in the heuristic function of A* algorithm. The adjustment coefficient k was then introduced into the coefficient Q to optimize the trade-off between sampling representativeness and path length. To evaluate the effectiveness of this algorithm, Chlorophyll-a concentration (Chl-a) was employed as the test parameter, with Chaohu Lake as the study area. Results showed that the algorithm was effective in collecting more representative samples in real-world conditions. As the coefficient k increased, the representativeness of collected samples enhanced, indicated by the Chl-a closely approximating the overall mean Chl-a and exhibiting a gradient distribution. This enhancement was also associated with increased path length. This study is significant in USV water sampling and water environment protection.

Identification of Risk Factors for Bus Operation Based on Bayesian Network

Public transit has been continuously developing because of advocacy for low-carbon living, and concerns about its safety have gained prominence. The various factors that constitute the bus operating environment are extremely complex. Although existing research on operational security is crucial, previous studies often fail to fully represent this complexity. In this study, a novel method was proposed to identify the risk factors for bus operations based on a Bayesian network. Our research was based on monitoring data from the public transit system. First, the Tabu Search algorithm was applied to identify the optimal structure of the Bayesian network with the Bayesian Information Criterion. Second, the network parameters were calculated using bus monitoring data based on Bayesian Parameter Estimation. Finally, reasoning was conducted through prediction and diagnosis in the network. Additionally, the most probable explanation of bus operation spatial risk was identified. The results indicated that factors such as speed, traffic volume, isolation measures, intersections, bus stops, and lanes had a significant effect on the spatial risk of bus operation. In conclusion, the study findings can help avert dangers and support decision-making for the operation and management of public transit in metropolitan areas to enhance daily public transit safety.

A novel Tree-augmented Bayesian network for predicting rock weathering degree using incomplete dataset

The precise forecasting of the weathering degree of surrounding rock holds paramount importance for the scientific design and secure execution of tunnel engineering. The apparent features of the surrounding rock serve as critical indicators for evaluating its weathering degree. This paper endeavors to quantify the rock apparent features based on an improved Computer vision model and establish a multi-source heterogeneous dataset encompassing 10 parameters, thereby facilitating data-driven predictions of the weathering degree. Specifically, the rock appearance parameters are quantified and segmented by an improved Tunnel face feature segmentation (TFFSeg) model, which is tailored to the unique characteristics of groundwater, fractures, and interlayers. Concurrently, the TFFSeg model exhibits significantly enhanced performance for these rock features compared to other widely employed Computer vision methods. Subsequently, this multi-source dataset is further enriched by incorporating rock physical and mechanical parameters as well as tunnel design parameters. Nevertheless, the issue of data incompleteness persists within this dataset. To achieve precise prediction of the weathering degree based on this incomplete dataset, a novel Tree-augmented Bayesian network (TAN-BN) is designed, which is capable of learning from incomplete datasets. The predictive outcomes demonstrate that the proposed TAN-BN surpasses other currently utilized meta models and ensemble models, such as ANN, GBRT, and Naive BN. Finally, sensitivity analysis is conducted to determine the importance rankings of the 10 parameters, offering valuable insights for on-site evaluation of the rock weathering degree at the tunnel face.

Demodulating Optical Wireless Communication of FBG Sensing with Turbulence-Caused Noise by Stacked Denoising Autoencoders and the Deep Belief Network

Free-space optics communication (FSO) can be used as a transmission medium for fiber optic sensing signals to make fiber optic sensing easier to implement; however, interference with the sensing signals caused by the optical turbulence and scattering of airborne particles in the FSO path is a potential problem. This work aims to deep denoise sensed signals from fiber Bragg grating (FBG) sensors based on FSO link transmission using advanced denoising deep learning techniques, such as stacked denoising autoencoders (SDAE). Furthermore, it will demodulate the sensed wavelength of FBGs by applying the deep belief network (DBN) technique. This is the first time the real FBG sensing experiment has utilized the actual noise interference caused by the environmental turbulence from an FSO link rather than adding noise through numerical processing. Consequently, the spectrum of the FBG sensors is clearly modulated by the noise and the issue with peak power variation. This complicates the determination of the center wavelengths of multiple stacked FBG spectra, requiring the use of machine learning techniques to predict these wavelengths. The results indicate that SDAE is efficient in denoising from the FBG spectrum, and DBN is effective in demodulating the central wavelength of the overlapped FBG spectrum. Thus, it is beneficial to implement an FSO link-based FBG sensing system in adverse weather conditions or atmospheric turbulence.

A Hybrid Approach for Intrusion Detection by Dragonfly Optimization and Bayesian Neural Network Methodologies

The technique of keeping an eye out for malicious activity or policy violations on a computer network or system is known as intrusion detection. It entails examining system logs, network traffic, and other data sources to spot potential security breaches, misuse, and illegal access. Network-based and host-based intrusion detection systems (IDS) are the two types available. The former analyzes network traffic and packets, while the latter concentrates on specific hosts or devices. This paper investigates how to improve intrusion detection systems in cyber security by combining dragonfly optimization (DFO) and Bayesian neural network (BNN) methodologies. The NSL-KDD dataset, which is tested and trained in the system, is the source of the dataset used in the study. By utilizing the optimization skills of DFO and the probabilistic reasoning powers of BNN, the hybrid technique improves the accuracy and flexibility of detecting and addressing network intrusions. This research illustrates the effectiveness of the suggested methodology in navigating dynamic network environments and identifying emerging dangers through a thorough examination. In addition to improving detection performance, the integration of BNN and DFO gives enterprises insightful information about infiltration patterns and the ability to take proactive measures to thwart hostile activity. The created model's enhanced intrusion detection performance is demonstrated by the experimental findings. These results are validated in terms of accuracy, precision, recall, execution time, and F1 score by comparing them with models that are currently in use.

An Adaptive Parameter Optimization Deep Learning Model for Energetic Liquid Vision Recognition Based on Feedback Mechanism.

The precise detection of liquid flow and viscosity is a crucial challenge in industrial processes and environmental monitoring due to the variety of liquid samples and the complex reflective properties of energetic liquids. Traditional methods often struggle to maintain accuracy under such conditions. This study addresses the complexity arising from sample diversity and the reflective properties of energetic liquids by introducing a novel model based on computer vision and deep learning. We propose the DBN-AGS-FLSS, an integrated deep learning model for high-precision, real-time liquid surface pointer detection. The model combines Deep Belief Networks (DBN), Feedback Least-Squares SVM classifiers (FLSS), and Adaptive Genetic Selectors (AGS). Enhanced by bilateral filtering and adaptive contrast enhancement algorithms, the model significantly improves image clarity and detection accuracy. The use of a feedback mechanism for reverse judgment dynamically optimizes model parameters, enhancing system accuracy and robustness. The model achieved an accuracy, precision, F1 score, and recall of 99.37%, 99.36%, 99.16%, and 99.36%, respectively, with an inference speed of only 1.5 ms/frame. Experimental results demonstrate the model's superior performance across various complex detection scenarios, validating its practicality and reliability. This study opens new avenues for industrial applications, especially in real-time monitoring and automated systems, and provides valuable reference for future advancements in computer vision-based detection technologies.

Fault diagnosis method of rolling bearing of BN ball mill based on AESL-GA

Aiming at the shortcomings of incomplete and inaccurate knowledge-based Bayesian network (BN) construction methods, a BN structure construction method based on knowledge guidance and data mining is proposed. Aiming at the problem of inaccurate single signal fault diagnosis results and the uncertainty problem in fault information, the current signal and the vibration signal are fused to establish the feature nodes of the BN network, and the fault feature parameters of the two signals are extracted respectively. The feature basket is selected using the discrimination index method and used as the node of the BN structure feature layer. The initial BN structure constructed by expert knowledge is combined with the adaptive elite structure genetic algorithm (AESL-GA) for structural optimization. By adaptively restricting the search space in the evolution process, reducing the number of free parameters, improving its global search ability, and obtaining the optimal BN structure. The method is verified by the measured data of the ball mill rolling bearing of Jinchuan Company and the Paderborn University data set, which proves the effectiveness of the proposed method.

Risk Assessment of Polar Drillship Operations Based on Bayesian Networks

Risk Assessment of Polar Drillship Operations Based on Bayesian Networks

Grey Bayesian network model for electromagnetic pulse vulnerability assessment of engine system

Firstly, in view of the uncertainty of electromagnetic pulse vulnerability assessment of engine system caused by limited experimental data and incomplete information, a grey Bayesian network model is proposed by introducing interval grey numbers in grey system theory to characterize the uncertainty of sensitivity threshold and fault logic relationship of engine system components, so as to improve the processing ability of Bayesian network for uncertain information. Secondly, taking broadband high-power microwave as an example, the interval grey number failure probability of engine system and the posterior failure probability of sensor interval grey number are calculated. The former represents the survivability of the engine system as a whole under strong electromagnetic pulse, and the latter reflects the vulnerability order of each sensor under the condition of engine system failure. The evaluation conclusion can provide a reference for the design of vehicle electromagnetic protection.

Adverse reaction of specific acute kidney injury caused by atorvastatin: an actual study based on the database of the US FDA adverse event reporting system

ABSTRACT Introduction Atorvastatin, one of the most widely used drugs, has attracted controversy regarding its potential adverse reactions to acute kidney injury(AKI). This study aims to provide evidence in support of the safe use of atorvastatin. Areas Covered Using the FDA Adverse Event Reporting System (FAERS) database (Q1 2004 to Q1 2024), we extracted reports where atorvastatin was the primary suspect and categorized them into five populations: the general population, acute myocardial infarction (AMI), ischemic stroke (IS), type 2 diabetes mellitus (T2DM), and hyperlipidemia (HLD). We performed subgroup analyses by gender and age strata within these populations, assessing positive signals through disproportionality analysis using four criteria: Ratio of Odds Ratio (ROR), Proportional Reporting Ratio (PRR), Bayesian Confidence Propagation Neural Network (BCPNN), and Empirical Bayes Geometric Mean (EGBM). The statistical analysis evaluated differences between adverse drug reaction (ADR) occurrence and nonoccurrence, as well as between high and low induction time groups. Expert Opinion In the general population, evidence for a positive signal of AKI was insufficient. However, the sub-group analysis revealed a risk in males, with older individuals more often affected in both AMI and IS populations. In T2DM, positive signals were evident in younger age groups. For the HLD population, evidence of a positive AKI signal was insufficient across gender and age strata. Overall, atorvastatin is generally safe, but clinical vigilance for AKI is warranted in T2DM, AMI, and IS populations, particularly in older adults (65+ years).

Clinical adverse events to letairis: a real-world drug safety study based on FDA Adverse Event Reporting System (FAERS)

ABSTRACT Background Letairis (ambrisentan), an endothelin receptor antagonist (ERA), is a critical medication for pulmonary arterial hypertension (PAH). Despite its efficacy, its safety profile is under scrutiny, warranting a detailed analysis. Research design and methods This study leveraged the FDA Adverse Event Reporting System (FAERS) from Q1 2007 to Q4 2023, focusing on Letairis as the primary suspect in adverse events. Employing advanced data mining techniques, such as Reporting Odds Ratio (ROR), Proportional Reporting Ratio (PRR), Bayesian Confidence Propagation Neural Network (BCPNN), and Multi-item Gamma Poisson Shrinker (MGPS), the study aimed to uncover safety signals. Results A total of 43,774 cases were identified, with Letairis implicated in 16,038,963 adverse event reports. There was a notable predominance of female patients (75.30%), with a median age around 64 years. Severe outcomes, including hospitalization (51.63%) and fatalities (20.44%), were prevalent. Signal strength analysis highlighted concerns in infections and infestations, as well as cardiac disorders. Conclusion The analysis underscores the need for vigilant pharmacovigilance and highlights Letairis’s potential to induce serious AEs, particularly in female and elderly populations. These findings are instrumental in guiding clinical practice and future drug safety assessments.

Efficacy and safety of different oral anticoagulants for stroke prevention in older patients with atrial fibrillation: A network meta-analysis.

Various oral anticoagulants have been used for stroke prevention in older patients with atrial fibrillation (AF). However, the optimal anticoagulants for stroke prevention has not yet been developed. We performed a systematic review and network meta-analysis to determine the optimal instructions. We searched for randomized controlled trials (RCTs) from PubMed, Embase, and the Cochrane Library without restriction for publication date or language at January 2024. Any RCTs that compared the effectiveness of a direct oral anticoagulant and a vitamin K antagonist (VKA) for stroke prevention in older patients with AF were included in this network meta-analysis. The Bayesian network meta-analysis used a random effects model and surface under the cumulative ranking curve analysis to rank results. All analyses were done using R software with gemtc package, with statistical significance set at P < .05. We included 7 RCTs (79,003 patients) comparing 8 different instructions including Apixaban 5 mg, Dabigatran 110 mg, Dabigatran 150 mg, Edoxaban 30 mg, Edoxaban 60 mg, Rivaroxaban 15 mg, Rivaroxaban 20 mg, and VKA. Apixaban 5 mg, Dabigatran 110 mg, and Dabigatran 150 mg was more effective than the VKA for reducing stroke or systemic embolism risks, and the difference was statistically significant (P < .05). Apixaban 5 mg, Dabigatran 110 mg, Dabigatran 150 mg, Edoxaban 30 mg, and Edoxaban 60 mg was associated with a reduction of the intracranial hemorrhage rate than the VKA (P < .05). The surface under the cumulative ranking curve shows that Dabigatran 110 mg ranked first for reducing stroke or systemic embolism risks. Edoxaban 60 mg ranked first for major bleeding. Dabigatran 110 mg ranked first for intracranial hemorrhage. Apixaban 5 mg ranked first for all bleeding events. Direct oral anticoagulants were found to have lower rates of thromboembolic events compared to VKAs in older patients with AF. Apixaban 5 mg, Dabigatran 110 mg, Dabigatran 150 mg, Edoxaban 30 mg, and Edoxaban 60 mg were also associated with a reduction of intracranial hemorrhage than VKA.

Periodically asymmetric responses of deep chlorophyll maximum to light and thermocline in a clear monomictic lake: Insights from monthly and diel scale observations

Deep chlorophyll maximum (DCM), a chlorophyll peak in the water column, has important implications for biogeochemical cycles, energy flow and water surface algal blooms in deep lakes. However, how an observed periodically asymmetric DCM response to environmental variables remains unclear, limiting our in-depth understanding and effective eco-environmental management of deep lakes. Based on both monthly field investigations in 2021 and diel continuous observations in 2021–2023 in clear, monomictic Lake Fuxian, Southwest China, the temporal dynamics and drivers of DCM were examined and periodic features of DCM were found, with a formation period (FP, February–July) and a weakening period (WP, August–December). On the monthly scale, although DCM dynamics were partly attributed to thermocline structures, the role of light penetration depths varied with period. In the FP, the influence of light on DCM was direct, i.e., increased depth and thickness but decreased magnitude. Differently, the influence of light mainly occurred by affecting thermocline structures in the WP, where water quality was another important driver. On the diel scale, light was a major reason for a thicker and lower (magnitude) DCM during day than at night, and the response of DCM to environmental factors between the FP and WP differed also more during day. This periodically asymmetric response of daytime DCM not only being caused by light but possibly also related to other physical factors such as lake surface water temperature, wind speed and precipitation. Bayesian network modelling suggested that water darkening and stratification intensification may promote a shallower, thinner and larger (magnitude) DCM in both FP and WP, but achieving such changes in DCM requires different light and thermocline thresholds. Our findings provide new information valuable for modelling DCM and for predicting the related surface algal blooms in deep lakes under climate change and eutrophication.

The virtual driving instructor: Multi‐agent system collaborating via knowledge graph for scalable driver education

AbstractThis work introduces the design, development, and deployment of a virtual driving instructor (VDI) for enhanced driver education. The VDI provides personalized, real‐time feedback to students in a driving simulator, addressing some of the limitations of traditional driver instruction. Employing a hybrid AI system, the VDI combines rule‐based agents, learning‐based agents, knowledge graphs, and Bayesian networks to assess and monitor student performance in a comprehensive manner. Implemented in multiple simulators at a driving school in Norway, the system aims to leverage AI and driving simulation to improve both the learning experience and the efficiency of instruction. Initial feedback from students has been largely positive, highlighting the effectiveness of this integration while also pointing to areas for further improvement. This marks a significant stride in infusing technology into driver education, offering a scalable and efficient approach to instruction.

Approximate inference on optimized quantum Bayesian networks

In recent years, there has been a significant upsurge in the interest surrounding Quantum machine learning, with researchers actively developing methods to leverage the power of quantum technology for solving highly complex problems across various domains. However, implementing gate-based quantum algorithms on noisy intermediate quantum devices (NISQ) presents notable challenges due to limited quantum resources and inherent noise. In this paper, we propose an innovative approach for representing Bayesian networks on quantum circuits, specifically designed to address these challenges and highlight the potential of combining optimized circuits with quantum hybrid algorithms for Bayesian network inference. Our aim is to minimize the required quantum resource needed to implement a Quantum Bayesian network (QBN) and implement quantum approximate inference algorithm on a quantum computer. Through simulations and experiments on IBM Quantum computers, we show that our circuit representation significantly reduces the resource requirements without decreasing the performance of the model. These findings underscore how our approach can better enable practical applications of QBN on currently available quantum hardware.