Soft evidential update for probabilistic multiagent systems

Multiply sectioned Bayesian networks (MSBNs) extend Bayesian networks (BNs) to graphical models that provide a coherent framework for probabilistic inference in cooperative multiagent distributed interpretation systems. Observation plays an important role in the inference with graphical models. Since observation of each observable variable has a cost, it would be helpful if we can find the most relevant variables to observe. In a probabilistic model, a Markov boundary of a variable provides a minimal set of variables that shields the variable from the influence of all other variables. However, the concept cannot be used directly for observation. First, it is generally intractable to verify conditional independencies in a probabilistic model. Second, the Markov boundary members may not be observable. Third, it is defined only for a single variable. Finally, it is not unique. By revising the concept to address these issues, we introduce the concept of observable Markov boundary of a set of nodes defined on d-separation of graphical models. The observable Markov boundary captures all relevant variables to observe for probabilistic inference with graphical models. In an MSBN, the observable Markov boundary of a set of nodes may span across all Bayesian subnets. We present an algorithm for cooperative computation of the observable Markov boundary of a set of nodes in an MSBN without revealing subnet structures.

Minimum training sample size requirements for achieving high prediction accuracy with the BN model: A case study regarding seismic liquefaction

Error handling in multimodal voice-enabled interfaces of tour-guide robots using graphical models

Analysis for warning factors of type 2 diabetes mellitus complications with Markov blanket based on a Bayesian network model

Climate and land-use changes are posing increasing threats to freshwater-related ecosystem services, acting both on the supply and demand sides. These changes disrupt critical processes such as nutrient cycling, sediment transport, and water flow regulation, leading to declining water quality and reduced ecosystem resilience. There is an urgent need for a deeper understanding of the dynamics of these threats, which can help enhance water management, environmental protection, and human well-being. To effectively tackle these risks, it is essential to quantitatively combine physical hazards and vulnerabilities by pinpointing hotspots where multiple stressors greatly increase the risk of water quality degradation. In response to this challenge, Bayesian network models offer a promising decision-support tool for evaluating adaptation options for water resource management, as they can integrate both quantitative and qualitative data. Building upon this approach, we developed a Spatial Bayesian Network (SBN) model to predict the probability of potential risks to water quality at the river basin scale in Italy and support the goal of achieving good chemical and ecological status according to the Water Framework Directive. This integrated model incorporates the complex relationships between land use change, climate change indicators (e.g., flood and drought intensity), and their combined impacts on water degradation. First, the baseline model uses historical patterns of climate change metrics from the CMCC DSS dataset and land use indicators from the Corine Land Cover as inputs to generate probabilistic predictions of potential risks to water quality. Then, the relationships between these variables are captured in their conditional probabilities, allowing for quantifying interactions and identifying key stressors, paving the way for scenario analysis. Finally, different future scenarios will be developed to predict the changes in water quality, considering projected climate data and socio-economic conditions. The outcome of this analysis contributes to developing an integrated management strategy that will help water managers make decisions and ultimately improve the resilience of freshwater ecosystems while supporting the implementation of adaptation strategies to address such problems.Keywords: Water Framework Directive, Water quality, Climate change, Land-use/ land-cover change Bayesian Network (BN) model

Stroke is a major chronic non-communicable disease with high incidence, high mortality, and high recurrence. To comprehensively digest its risk factors and take some relevant measures to lower its prevalence is of great significance. This study aimed to employ Bayesian Network (BN) model with Max-Min Hill-Climbing (MMHC) algorithm to explore the risk factors for stroke. From April 2019 to November 2019, Shanxi Provincial People's Hospital conducted opportunistic screening for stroke in ten rural areas in Shanxi Province. First, we employed propensity score matching (PSM) for class balancing for stroke. Afterwards, we used Chi-square testing and Logistic regression model to conduct a preliminary analysis of risk factors for stroke. Statistically significant variables were incorporated into BN model construction. BN structure learning was achieved using MMHC algorithm, and its parameter learning was achieved with Maximum Likelihood Estimation. After PSM, 748 non-stroke cases and 748 stroke cases were included in this study. BN was built with 10 nodes and 12 directed edges. The results suggested that age, fasting plasma glucose, systolic blood pressure, and family history of stroke constitute direct risk factors for stroke, whereas sex, educational levels, high density lipoprotein cholesterol, diastolic blood pressure, and urinary albumin-to-creatinine ratio represent indirect risk factors for stroke. BN model with MMHC algorithm not only allows for a complicated network relationship between risk factors and stroke, but also could achieve stroke risk prediction through Bayesian reasoning, outshining traditional Logistic regression model. This study suggests that BN model boasts great prospects in risk factor detection for stroke.

Survival prediction for gallbladder carcinoma after curative resection: Comparison of nomogram and Bayesian network models

Aim. It is essential to understand the extent to which job characteristics impact work-related musculoskeletal disorders (WMSDs), and to calculate the probability that an employee will suffer from a musculoskeletal disorder given their working conditions. The objective of this research is to identify the relationships between WMSDs and working characteristics, by developing a Bayesian network (BN) model to calculate the probability that an employee suffers from a musculoskeletal disorder. Methods. A conceptual model was constructed based on a BN. This was then statistically tested and corrected to establish a BN model. Results. Experiments verified that the BN model achieves a better diagnostic performance than artificial neural network, support vector machine and decision tree approaches, and is robust in diagnosing WMSDs given working characteristics. Conclusion. It was verified that working characteristics, such as working hours and pace, impact the incidence rate of WMSDs, and a BN model was developed to probabilistically diagnose WMSDs.

Intelligent vehicles should be able to detect various obstacles and also identify their types so that the vehicles can take an appropriate level of protection and intervention. This article presents a method of detecting and classifying multiclass obstacles for intelligent vehicles. A stereovision-based method is used to segment obstacles from traffic background and measure three-dimensional geometrical features. A Bayesian network (BN) model has been established to further classify them into five classes, including pedestrian, cyclist, car, van, and truck. The BN model is trained using substantial data samples. The optimized structure of the model is determined from the necessary path condition method with a presupposition constraint (NPC+PC). The conditional probability table of the discrete nodes and the conditional probability distribution of the continuous nodes are determined from expectation maximization (EM) training algorithm with consideration of prior domain knowledge. Experiments were conducted using the object detection data set on the public KITTI benchmark, and the results show that the proposed BN model exhibits an excellent performance for obstacle classification while the full pipeline of the method including detection and classification is in the upper middle level compared with other existing methods.

BackgroundThis study aims to establish a Bayesian network risk prediction model for gastric cancer using data mining methods. It explores both direct and indirect factors influencing the incidence of gastric cancer and reveals the interrelationships among these factors.MethodsData were collected from early cancer screenings conducted at the People’s Hospital of Lincang between 2022 and 2023. Initial variable selection was performed using Least Absolute Shrinkage and Selection Operator (Lasso) and Sliding Windows Sequential Forward Selection (SWSFS), and the screened variables and demographic characteristics features were used as variables for constructing the Bayesian network (BN) model. Subsequently, the performance of the models was evaluated, and the optimal model was selected for network mapping and Bayesian inference using the best model.ResultsThe incidence rate of gastric cancer in this region’s high-risk population was determined to be 7.09%. The BN model constructed from the set of variables consisting of Lasso’s selection variables and demographic characteristics had better performance. A total of 12 variables were incorporated into the BN model to form a network structure consisting of 13 nodes and 18 edges. The model shows that age, gender, ethnicity, current address, upper gastrointestinal symptoms (nausea, acid reflux, vomiting), alcohol consumption, smoking, SGIM gastritis, and family history are important risk factors for gastric cancer development.ConclusionThe Bayesian network model provides an intuitive framework for understanding the direct and indirect factors contributing to the early onset of gastric cancer, elucidating the interrelationships among these factors. Furthermore, the model demonstrates satisfactory predictive performance, which may facilitate the early detection of gastric cancer and enhance the levels of early diagnosis and treatment among high-risk populations.

The intermittence and fluctuation of renewable energy bring significant uncertainty to the power system, which enormously increases the operational risks of the power system. The development of efficient interval prediction models can provide data support for decision making and help improve the economy and reliability of energy interconnection operation. The performance of Bayesian deep learning models and Bayesian shallow neural networks in short-term interval prediction of photovoltaic power is compared in this study. Specifically, an LSTM Approximate Bayesian Neural Network model (ABNN-I) is built on the basis of the deep learning and Monte Carlo Dropout method. Meanwhile, a Feedforward Bayesian Neural Network (ABNN-II) model is introduced by Feedforward Neural Network and the Markov Chain Monte Carlo method. To better compare and verify the interval prediction capability of the ABNN models, a novel clustering method with three-dimensional features which include the number of peaks and valleys, the average power value, and the non-stationary measurement coefficient is proposed for generating sunny and non-sunny clustering sets, respectively. Results show that the ABNN-I model has an excellent performance in the field of photovoltaic short-term interval forecasting. At a 95% confidence level, the interval coverage from ABNN-I to ABNN-II can be increased by up to 3.1% and the average width of the interval can be reduced by 56%. Therefore, with the help of the high computational capacity of deep learning and the inherent ability to quantify uncertainty of the interval forecast from Bayesian methods, this research provides high-quality interval prediction results for photovoltaic power prediction and solves the problem of difficult modeling for over-fitting that exists in the training process, especially on the non-sunny clustering sets.

A Bayesian Network model for risk analysis of deepwater drilling riser fracture failure

Previous work has proposed the ontology-based semi-automatic generation of antipattern Bayesian Network(BN) models. The generated BN model can be used to illustrate the effects of uncertainty on antipatterns using Bayesian propagation. This can guide users in detecting particular antipattern attributes of importance based on uncertain ontological information. However, the proposed approach has been implemented in the Protege ontology editor environment and requires human intervention to specify how the BN model will be generated. The fully automated generation of ontology-based antipattern BN models still remains an open issue. SPARSE is an OWL ontology based intelligent system that assists software project managers in the antipattern detection process. In this paper, we propose the use of the resulting detected antipatterns of SPARSE, their attributes (i.e. causes, symptoms, consequences) and the ontological relationships between these attributes, in order to automatically generate BN models of the detected antipatterns. We illustrate how this approach can be implemented using an example of 8 antipattern attributes of 6 inter-related antipatterns detected using SPARSE.

Multisource geospatial data contains a lot of information that can be used for environment assessment and management. In this paper, four environmental indicators representing typical human activities in Yellow River Delta, China are extracted from multisource geospatial data. By analysing the causal relationship between these human-related indicators and NDVI, a Bayesian network (BN) model is developed. Part of the raster data pre-processed using GIS is used for training the BN model, and the other data is used for model testing. Sensitivity analysis and performance assessment showed that the BN model was good enough to reveal the impacts of human activities on land vegetation. With the trained BN model, the vegetation change under three different scenarios was also predicted. The results showed that multisource geospatial data could be successfully collated using the GIS-BN framework for vegetation detection.

ObjectiveThis study aims to identify relevant risk factors, assess the interactions between variables, and establish a predictive model for ischemic stroke (IS) in patients with cardiac myxoma (CM) using the Bayesian network (BN) approach.MethodsData of patients with CM were collected from three tertiary comprehensive hospitals in Beijing from January 2002 to January 2022. Age, sex, medical history, and information related to CM were extracted from the electronic medical record system. The BN model was constructed using the tabu search algorithm, and the conditional probability of each node was calculated using the maximum likelihood estimation method. The probability of each node of the network and the interrelationship between IS and its related factors were qualitatively and quantitatively analyzed. A receiver operating characteristic (ROC) curve was also plotted. Sensitivity, specificity, and area under the curve (AUC) values were calculated and compared between the BN and logistic regression models to evaluate the efficiency of the predictive model.ResultsA total of 416 patients with CM were enrolled in this study, including 61 with and 355 without IS. The BN model found that cardiac symptoms, systemic embolic symptoms, platelet counts, and tumor with high mobility were directly associated with the occurrence of IS in patients with CM. The BN model for predicting CM-IS achieved higher scores on AUC {0.706 [95% confidence interval (CI), 0.639–0.773]} vs. [0.697 (95% CI, 0.629–0.766)] and sensitivity (99.44% vs. 98.87%), but lower scores on accuracies (85.82% vs. 86.06%) and specificity (6.56% vs. 11.48%) than the logistic regression model.ConclusionCardiac symptoms, systemic embolic symptoms, platelet counts, and tumor with high mobility are candidate predictors of IS in patients with CM. The BN model was superior or at least non-inferior to the traditional logistic regression model, and hence is potentially useful for early IS detection, diagnosis, and prevention in clinical practice.