Search

Many theoretical methods have been applied to research user behaviour and requirements. However, the uncertainty associated with customer characteristics often biases the conclusions drawn from customer research and affects the effectiveness of product design. In this paper, Bayesian networks (BN) are introduced into the research on customer behaviour analysis based upon theory of planned behaviour (TPB), and an analysis model driven by customer research data is established from the perspective of user behaviour intention to guide design optimisation. Combining the User background Factor with the TPB Factor, the model analyses the uncertainty of the association between the two, and corrects the errors in the designer's prior knowledge through structural learning. By a case study the paper finds that the evaluations that enhance customers' subjective norms and perceived behavioural control lead to a greater probability of purchase or use. In addition, customers with specific characteristics are more inclined to generate behaviour intention. The paper finally provides a design optimisation plan based upon the result of the research and discusses about the advantages of the research approaches and the directions of future researches. [ABSTRACT FROM AUTHOR]

Background: A significant proportion of individuals with symptoms of sexually transmitted infection (STI) delay or avoid seeking healthcare, and digital diagnostic tools may prompt them to seek healthcare earlier. Unfortunately, none of the currently available tools fully mimic clinical assessment or cover a wide range of STIs. Methods: We prospectively invited attendees presenting with STI-related symptoms at Melbourne Sexual Health Centre to answer gender-specific questionnaires covering the symptoms of 12 common STIs using a computer-assisted self-interviewing system between 2015 and 2018. Then, we developed an online symptom checker (iSpySTI.org) using Bayesian networks. In this study, various machine learning algorithms were trained and evaluated for their ability to predict these STI and anogenital conditions. We used the Z-test to compare their average area under the ROC curve (AUC) scores with the Bayesian networks for diagnostic accuracy. Results: The study population included 6,162 men (median age 30, IQR: 26–38; approximately 40% of whom had sex with men in the past 12 months) and 4,358 women (median age 27, IQR: 24–31). Non-gonococcal urethritis (NGU) (23.6%, 1447/6121), genital warts (11.7%, 718/6121) and balanitis (8.9%, 546/6121) were the most common conditions in men. Candidiasis (16.6%, 722/4538) and bacterial vaginosis (16.2%, 707/4538) were the most common conditions in women. During evaluation with unseen datasets, machine learning models performed well for most male conditions, with the AUC ranging from 0.81 to 0.95, except for urinary tract infections (UTI) (AUC 0.72). Similarly, the models achieved AUCs ranging from 0.75 to 0.95 for female conditions, except for cervicitis (AUC 0.58). Urethral discharge and other urinary symptoms were important features for predicting urethral gonorrhoea, NGU and UTIs. Similarly, participants selected skin images that were similar to their own lesions, and the location of the anogenital skin lesions were also strong predictors. The vaginal discharge (odour, colour) and itchiness were important predictors for bacterial vaginosis and candidiasis. The performance of the machine learning models was significantly better than Bayesian models for male balanitis, molluscum contagiosum and genital warts (P < 0.05) but was similar for the other conditions. Conclusions: Both machine learning and Bayesian models could predict correct diagnoses with reasonable accuracy using prospectively collected data for 12 STIs and other common anogenital conditions. Further work should expand the number of anogenital conditions and seek ways to improve the accuracy, potentially using patient collected images to supplement questionnaire data. [ABSTRACT FROM AUTHOR]

Rapid urbanization presents significant challenges to biodiversity through habitat degradation, fragmentation, and loss. This study focuses on Shenzhen, China, a highly urbanized region experiencing substantial land use changes and facing a considerable risk of biodiversity decline, to investigate the dynamics of habitat quality over two critical periods: 2010–2015 and 2015–2020. Using the InVEST (Integrated Valuation of Ecosystem Services and Trade-offs) model for habitat quality assessment and Bayesian networks to analyze causal relationships, this research offers an innovative comparison between habitat recovery and degradation across these two phases. Results indicate that from 2010 to 2015, localized habitat recovery was achieved on 0.53% of the land area due to restoration policies, yet the overall trend remained negative. During the 2015–2020 period, habitat degradation intensified (7.19%) compared to recovery (5.7%); notably, 70.6% of areas that had been previously restored are now experiencing degradation once again. This re-degradation highlights the instability of earlier restoration efforts under ongoing urban pressure. By integrating spatial analysis with Bayesian network modeling, this study provides offers a nuanced understanding of where and why initial recovery efforts were unsuccessful, identifying areas susceptible to persistent degradation. The research emphasizes that urban expansion—particularly the development of construction land, was the primary driver of habitat degradation, while ecological sensitivity played a crucial role in determining the long-term success of recovery efforts. This approach provides valuable insights for designing more effective, sustainable conservation strategies in rapidly urbanizing regions. [ABSTRACT FROM AUTHOR]

Simple Summary: This study developed and evaluated Bayesian Network models for lung cancer risk prediction using a decade of data from 38,944 high-risk individuals in Denmark. The models were trained and validated on datasets with varying sizes and levels of missing data to reflect real-world screening scenarios. The results showed that a model trained on a small, complete dataset (AUC 0.78) performed similarly on a larger dataset with 21% missing data (AUC 0.78), but performance decreased when 39% of data were missing (AUC 0.67). The laboratory results and smoking data were the most informative variables, significantly outperforming models based only on age and smoking status (AUC 0.70). These findings suggest that BN models can maintain strong predictive performance despite incomplete data and highlight the value of including standard laboratory results in future LC screening programs. Background/Objectives: Lung cancer (LC) is the leading cause of cancer mortality, making early diagnosis essential. While LC screening trials are underway globally, optimal prediction models and inclusion criteria are still lacking. This study aimed to develop and evaluate Bayesian Network (BN) models for LC risk prediction using a decade of data from Denmark. The primary goal was to assess BN performance on datasets varying in size and completeness, simulate real-world screening scenarios, and identify the most valuable data sources for LC screening. Methods: The study included 38,944 patients evaluated for LC, with 11,284 (29%) diagnosed. Data on comorbidities, medications, and general practice were available for the entire cohort, while laboratory results, smoking habits, and other variables were only available for subsets. The cohort was divided into four subsets based on data availability, and BNs were trained and validated across these subsets using cross-validation and external validation. To determine the optimal combination of variables, all possible data combinations were evaluated on the samples that contained all the variables (n = 5587). Results: A model trained on the small, complete dataset (AUC 0.78) performed similarly on a larger dataset with 21% missing data (AUC 0.78). Performance dropped when 39% of data were missing (AUC 0.67), resulting in informative variables missing completely in the dataset. Laboratory results and smoking data were the most informative, significantly outperforming models based only on age and smoking status (AUC 0.70). Conclusions: BN models demonstrated moderate to strong predictive performance, even with incomplete data, highlighting the potential value of incorporating laboratory results in LC screening programs. [ABSTRACT FROM AUTHOR]

Analysis of fossil assemblage structure can help illuminate the processes shaping the assembly of ecological communities. Using Bayesian network analysis methods, we investigated patterns of association between presences and abundances of 12 large-bodied mammal clades at Pleistocene fossil localities and their dependence on local environment types, global temperature estimates, locality ages and large-scale geographic positions. The dependencies among the clades seem to be structured by the degree of generalism in carnivores and omnivores, inter-specific competition-driven ecological differentiation among the carnivores, and local environmental preferences in herbivores. With the exception of hominids, we do not find significant dependencies among the external variables (gross geographic position, age, mean global temperature) and the clades under investigation. We do not find evidence of exclusion between any two clades, which would indicate predation effects or competition at a family or higher level. The network of dependencies among mammalian clades shows a remarkable lack of change over time, pointing to emergent invariability of taxonomic assemblies at the family or higher level despite significant environmental changes. [ABSTRACT FROM AUTHOR]

The impact of climate conditions on infrastructure is a major concern for the sustainability of built environment. Two main issues that add uncertainty and complexity in climate-change impact are of interest: multiple hazard types and non-stationarity of climate actions. This paper proposes an approach using dynamic Bayesian networks to assess the reliability of a building system considering both gradual and extreme climate factors over the service life of the asset. The methodology is illustrated on a case study that examine an HVAC system, considering overheating fault and degradation risk. Compared to conventional Markov model, the results show stochastic dependence in the degradation process at different time instants and hence affect the variability of degradation. The proposed approach includes economic-based impact analysis to determine costs and payoffs accrued as the consequences. By integrating climate stress and shock and accounting for dynamic changes of the hazard, this method helps decision-makers in identifying and prioritizing adaptation strategies for building system under climate change. [ABSTRACT FROM AUTHOR]

The failure probability of a pipeline is a quantification of the likelihood of an accident occurring in the pipeline, which is an indispensable part of the pipeline risk assessment process. To solve the problems of strong subjectivity, low feasibility, and low accuracy in the existing pipeline failure probability calculation methods, a three-layer Bayesian network topology model of "pipeline failure–failure cause–influencing factor" is proposed, with the pipeline failure as the subnode, the type of pipeline failure as the intermediate node, and the factors affecting the pipeline failure as the parent node of the network. Based on data fitting and fuzzy theory analysis methods, the functional relationship between the impact factor and the failure frequency of various pipelines is quantified. Using the mean value theorems for definite integrals and the analytic hierarchy process, the conditional probability of the directed edge in the network is calculated. The proposed function relationship provides a method to calculate the prior probability according to the parameters of the pipeline and its surroundings and a new idea to train the network model even without sufficient data. [ABSTRACT FROM AUTHOR]

Objectives. The purpose of this study is to determine the causal relationships among positive and negative cyberloafing dimensions, safety behaviors and occupational incidents among hospital employees during the COVID-19 pandemic. Methods. Data were obtained from 210 healthcare employees working in public hospitals in Turkey. The data were analyzed using Bayesian network analysis. This study examines the factors that have the most significant impact on occupational incidents through Bayesian belief updating. Results. The findings demonstrated that 28.7% of the sample experienced occupational incidents. Safety behaviors had the strongest impact on occupational incidents. When recovery (66.2%) and developmental cyberloafing (53.1%) are high, and deviant (64.3%) and addictive cyberloafing (35.6%) are low, the probability of safety behaviors increases (79.6%) and occupational incidents decrease. The development dimension of positive cyberloafing and the deviance dimension of negative cyberloafing had the greatest impact on hospital employees’ safety behaviors and occupational incidents. Conclusions. Minor/positive cyberloafing behaviors have a high impact on safety behaviors and occupational incidents, whereas major/negative cyberloafing behaviors have a low impact. Therefore, the hospital administration should specifically control deviant and addictive cyberloafing behaviors. Furthermore, the analysis results recommend that managers consider allowing some positive cyberloafing behaviors to reduce occupational incidents. [ABSTRACT FROM AUTHOR]

Representation learning algorithms are often used to extract essential features from high-dimensional datasets. These algorithms commonly assume that such features are independent. However, multimodal datasets containing complementary information often have causally related features. Consequently, there is a need to discover features purporting conditional independencies. Bayesian networks (BNs) are probabilistic graphical models that use directed acyclic graphs (DAGs) to encode the conditional independencies of a joint distribution. To discover features and their conditional independence structure, we develop pimaDAG, a variational autoencoder framework that learns features from multimodal datasets, possibly with known physics constraints, and a BN describing the feature distribution. Our algorithm introduces a new DAG parameterization, which we use to learn a BN simultaneously with a latent space of a variational autoencoder in an end-to-end differentiable framework via a single, tractable evidence lower bound loss function. We place a Gaussian mixture prior on the latent space and identify each of the Gaussians with an outcome of the DAG nodes; this identification enables feature discovery with conditional independence relationships obeying the Markov factorization property. Tested against a synthetic and a scientific dataset, our results demonstrate the capability of learning a BN on simultaneously discovered key features in a fully unsupervised setting. [ABSTRACT FROM AUTHOR]

BACKGROUND: The morbidity and mortality of heart disease are increasing in middle-aged and elderly people in China. It is necessary to explore relationships and interactive associations between heart disease and its risk factors in order to prevent heart disease. OBJECTIVE: To establish a Bayesian network model of heart disease and its influencing factors in middle-aged and elderly people in China, and explore the applicability of the elite-based structure learner using genetic algorithm based on ensemble learning (EN-ESL-GA) algorithm in etiology analysis and disease prediction. METHODS: Based on the 2013 national tracking survey data from China Health and Retirement Longitudinal Study (CHARLS) database, EN-ESL-GA algorithm was used to learn the Bayesian network structure. Then we input the data and the learned network structure into the Netica software for parameter learning and inference analysis. RESULTS: The Bayesian network model based on the EN-ESL-GAalgorithm can effectively excavate the complex network relationships and interactive associations between heart disease and its risk factors in middle-aged and elderly people in China. CONCLUSIONS: The Bayesian network model based on the EN-ESL-GA algorithm has good applicability and application prospect in the prediction of diseases prevalence risk. [ABSTRACT FROM AUTHOR]

Serious crime modelling typically needs to be undertaken securely behind a firewall where police knowledge and capabilities remain undisclosed. Data informing an ongoing incident are often sparse; a large proportion of relevant data only come to light after the incident culminates or after police intervene—by which point it is too late to make use of the data to aid real-time decision-making for the incident in question. Much of the data that are available to the police to support real-time decision-making are highly confidential and cannot be shared with academics, and are therefore missing to them. In this paper, we describe the development of a formal protocol where a graphical model is used as a framework for securely translating a base model designed by an academic team to a fully embellished model for use by a police team. We then show, for the first time, how libraries of these models can be built and used for real-time decision support to circumvent the challenges of data missingness seen in such a secure environment through the ability to match ongoing plots to existing models within the library.The parallel development described by this protocol ensures that any sensitive information collected by police and missing to academics remains secured behind a firewall. The protocol nevertheless guides police so that they are able to combine the typically incomplete data streams that are open source with their more sensitive information in a formal and justifiable way. We illustrate the application of this protocol by describing how a new entry—a suspected vehicle attack—can be embedded into such a police library of criminal plots. [ABSTRACT FROM AUTHOR]

There is a widespread belief in the Bayesian network (BN) community that while the overall accuracy of the results of BN inference is not sensitive to the precision of parameters, it is sensitive to the structure. We report on the results of a study focusing on the parameters in a companion paper, while this paper focuses on the BN graphical structure. We present the results of several experiments in which we test the impact of errors in the BN structure on its accuracy in the context of medical diagnostic models. We study the deterioration in model accuracy under structural changes that systematically modify the original gold standard model, notably the node and edge removal and edge reversal. Our results confirm the popular belief that the BN structure is important, and we show that structural errors may lead to a serious deterioration in the diagnostic accuracy. At the same time, most BN models are forgiving to single errors. In light of these results and the results of the companion paper, we recommend that knowledge engineers focus their efforts on obtaining a correct model structure and worry less about the overall precision of parameters. [ABSTRACT FROM AUTHOR]

There is a widely spread belief in the Bayesian network (BN) community that the overall accuracy of results of BN inference is not too sensitive to the precision of their parameters. We present the results of several experiments in which we put this belief to a test in the context of medical diagnostic models. We study the deterioration of accuracy under random symmetric noise but also biased noise that represents overconfidence and underconfidence of human experts.Our results demonstrate consistently, across all models studied, that while noise leads to deterioration of accuracy, small amounts of noise have minimal effect on the diagnostic accuracy of BN models. Overconfidence, common among human experts, appears to be safer than symmetric noise and much safer than underconfidence in terms of the resulting accuracy. Noise in medical laboratory results and disease nodes as well as in nodes forming the Markov blanket of the disease nodes has the largest effect on accuracy. In light of these results, knowledge engineers should moderately worry about the overall quality of the numerical parameters of BNs and direct their effort where it is most needed, as indicated by sensitivity analysis. [ABSTRACT FROM AUTHOR]

The work presented here marks a further advance in expert uncertainty quantification. In a recent probabilistic evaluation of ice sheet process contributions to sea level rise, tail dependence was elicited and propagated through an uncertainty analysis for the first time. The elicited correlations and tail dependencies concerned pairings of three processes: Accumulation, Discharge and Run-off, which operate on major ice sheets in the West and East Antarctic and in Greenland. The elicitation enumerated dependencies between these processes under selected global temperature change scenarios over different future time horizons. These expert judgments allowed us to populate a Paired Copula Bayesian network model to obtain the estimated contributions of these ice sheets for future sea level rise. Including positive central tendency dependence and tail dependence increases the fatness of the upper tails of projected sea level rise distributions, an amplification important for designing and evaluating possible mitigation strategies. Detailing and jointly computing distributional dependencies and tail dependencies can be crucial components of good practice for assessing the influence of uncertainties on extreme values when modelling stochastic multifactorial processes. [ABSTRACT FROM AUTHOR]

Modern data-oriented applications often require integrating data from multiple heterogeneous sources. When these datasets share attributes, but are otherwise unlinked, there is no way to join them and reason at the individual level explicitly. However, as we show in this work, this does not prevent probabilistic reasoning over these heterogeneous datasets even when the data and shared attributes exhibit significant mismatches that are common in real-world data. Different datasets have different sample biases, disagree on category definitions and spatial representations, collect data at different temporal intervals, and mix aggregate-level with individual data. In this work, we demonstrate how a set of Bayesian network motifs allows all of these mismatches to be resolved in a composable framework that permits joint probabilistic reasoning over all datasets without manipulating, modifying, or imputing the original data, thus avoiding potentially harmful assumptions. We provide an open source Python tool that encapsulates our methodology and demonstrate this tool on a number of real-world use cases. [ABSTRACT FROM AUTHOR]

Introduction :Managing environmental risks associated with marine installations, such as the breakwaters of the Caspian Sea, plays a critical role in mitigating potential hazards and ensuring sustainable development. The Caspian Sea, a unique and environmentally sensitive region, faces significant ecological risks due to construction and operational activities related to breakwaters. This study aims to model and analyze the environmental risks specifically related to the breakwater located in the Caspian Port. By comprehensively identifying the various activities and processes during both the construction and operation phases, this research seeks to uncover potential hazards and damaging factors. The ultimate objective is to provide a framework for preventing or minimizing these risks, thus contributing to the long-term environmental sustainability of the region. Material and Methods: In this research, the Failure Modes and Effects Analysis (FMEA) method was employed to evaluate the environmental risks. FMEA is a widely used risk assessment tool that helps in determining the severity, likelihood of occurrence, and detectability of risks. Expert opinions were collected to assess these factors for each identified risk. Following this evaluation, the risk priority number (RPN) was calculated, which helped identify the critical risks requiring immediate attention. The highest RPN for non-human-related risks was 384, while for human-related risks, it was 126. These priority levels were further analyzed using Bayesian networks through the Netica software, a tool known for efficiently modeling risk interdependencies. Results and Discussion: The analysis of human-related risks revealed that skin damage posed the highest risk, with a quantitative value of 0.167. Direct auditory impairments were less significant, with a value of 0.004, while indirect human risks included soil pollution (0.125) and noise pollution (0.004). These findings indicate that while direct physical harm to individuals may not be highly prevalent, indirect risks, especially related to environmental degradation, hold substantial importance. On the other hand, in the category of non-human-related risks, the most critical hazard was identified as the depletion of natural resources due to mining activities, with a high quantitative value of 0.764. Water pollution (0.224) and the use of hazardous substances (0.024) were also identified as key risks impacting the environment. The Bayesian network analysis effectively highlighted the interconnections between these risks, revealing how the occurrence of one risk could amplify others, demonstrating a web of interdependent risk factors. Conclusion: The results underscore the significance of understanding the interdependence of risks when addressing environmental challenges in marine construction projects. The use of Bayesian networks in this study clearly demonstrated the mutual influence between different risk factors, emphasizing the need for an integrated risk management approach. By identifying critical risks and understanding their interdependencies, decision-makers can implement targeted and localized solutions to mitigate these risks.

Abstract This study aims to develop a Machine Learning model to assess the risks faced by COVID-19 patients in a hospital setting, focusing specifically on predicting the complications leading to Intensive Care Unit (ICU) admission or mortality, which are minority classes compared to the majority class of discharged patients. We operate within a multiclass framework comprising three distinct classes, and address the challenge of dataset imbalance, a common source of model bias. To effectively manage this, we introduce the Multi-Thresholding meta-algorithm (MTh), an innovative output-level methodology that extends traditional thresholding from binary to multiclass classification. This methodology dynamically adjusts class probabilities using misclassification costs, making it highly effective in imbalanced datasets. Our approach is further enhanced by integrating the simplicity, transparency, and effectiveness of Bayesian networks to create a robust predictive model. Using patient admission data, the model accurately identifies key risk and protective factors for COVID-19 outcomes. Our findings indicate that certain patient characteristics, such as high Charlson Index and pre-existing conditions, significantly influence the risk of ICU admission and mortality. Moreover, we introduce an explanatory model that elucidates the interrelationships among these factors, demonstrating the influence of therapeutic limits on the overall risk assessment of COVID-19 patients. Overall, our research provides a significant contribution to the field of Machine Learning by offering a novel solution for multiclass classification in the context of imbalanced datasets. This model not only enhances predictive accuracy but also supports critical decision-making processes in healthcare, potentially improving patient outcomes and optimizing clinical resource allocation.

Abstract Background A high number of stillborn piglets has a negative impact on production and animal welfare. It is an important contributor to piglet mortality around farrowing and continues to rise with the increase of prolificacy. The objective of this study was to build a predictive model of the stillborn rate. Results This study was performed on two farrow-to-finish farms and one farrow-to-wean farm located in Brittany, France. At each farm, the number of total born (TB), born alive (BA), stillborn piglets (S), the same data at the previous farrowing (TB n− 1, BA n− 1 and S n− 1), backfat thickness just before farrowing and at previous weaning and parity rank were recorded in our dataset of 3686 farrowings. Bayesian networks were used as an integrated modelling approach to investigate risk factors associated with stillbirth using BayesiaLab® software. Our results suggest the validity of a hybrid model to predict the percentage of stillborn piglets. Three significant risk factors were identified by the model: parity rank (percentage of total mutual information: MI = 64%), S n− 1 (MI = 25%) and TB n− 1 (MI = 11%). Additionally, backfat thickness just before farrowing was also identified for sows of parity five or more (MI = 0.4%). In practice, under optimal conditions (i.e., low parity rank, less than 8% of stillborn piglets, and a prolificacy lower than 14 piglets at the previous farrowing), our model predicted a stillborn rate almost halved, from 6.5% (mean risk of our dataset) to 3.5% for a sow at the next farrowing. In contrast, in older sows with a backfat thickness less than 15 mm, more than 15% of stillborn and a prolificacy greater than 18 piglets at the previous farrowing, the risk is multiplied by 2.5 from 6.5 to 15.7%. Conclusion Our results highlight the impact of parity, previous prolificacy and stillborn rate on the probability of stillborn. Moreover, the importance of backfat thickness, especially in old sows, must be considered. This information can help farmers classify and manage sows according to their risk of giving birth to stillborn piglets.

Introduction: Domino effects are a chain of low-probability and high-consequence accidents in which a primary event (fire or explosion) in one unit causes secondary events in adjacent units. Bayesian networks have been used to model the propagation patterns of domino effects and to estimate the probability of these effects at different levels. The unique modeling and flexible structure provided by Bayesian networks allow the analysis of domino effects through a probabilistic framework, taking synergistic effects into account. Material and Methods: Firstly, collecting the basic information related to the location of the storage tanks and determining the scenario of the accidents were done. Furthermore, the values of the heat radiation as escalation vectors in case of a fire in one tank were determined using ALOHA software. The received heat flux values were compared with the heat radiation threshold of 15 kw/m2 and the escalation probability of the primary unit and the propagation of the initial scenario to nearby storage tanks were determined using Bayesian networks. Results: The analysis of the heat flux values showed that among the 8 studied storage tanks, two storage tanks had the highest potential for spreading domino effects due to their location in a tank farm. Also, the implementation of Bayesian networks in GeNIe revealed that, compared to other storage tanks, the probability of domino effects propagating to other nodes is higher when a primary fire accident occurs in the two mentioned tanks, while considered as primary units. Conclusion: Domino effect modeling and appropriate preventative measures can decrease the escalation probability in the process industries. Consideration of the synergistic effects of events at different levels by taking the escalation vectors into account leads to proper risk management and the determination of emergency response measures in storage tank farms.

The article presents a new approach to modeling nonlinear dependencies called composite Bayesian networks. The main emphasis is on integrating machine learning models into Bayesian networks while maintaining their fundamental principles. The novelty of the approach is that it allows us to solve the problem of data inconsistency with traditional assumptions about dependencies. The presented method consists in selecting a variety of machine learning models at the stage of training composite Bayesian networks. This allows you to flexibly customize the nature of the dependencies in accordance with the requirements and dictated characteristics of the modeled object. The software implementation is made in the form of a specialized framework that describes all the necessary functionality. The results of experiments to evaluate the effectiveness of modeling dependencies between features are presented. Data for the experiments was taken from the bnlearn repository for benchmarks and from the UCI repository for real data. The performance of composite Bayesian networks was validated by comparing the likelihood and F1 score with classical Bayesian networks trained with the Hill-Climbing algorithm, demonstrating high accuracy in representing multivariate distributions. The improvement in benchmarks is insignificant since they contain linear dependencies that are well modeled by the classical algorithm. An average 30 % improvement in likelihood was obtained on real UCI datasets. The obtained data can be applied in areas that require modeling complex dependencies between features, for example, in machine learning, statistics, data analysis, as well as in specific subject areas.

Background: A high number of stillborn piglets has a negative impact on production and animal welfare. It is an important contributor to piglet mortality around farrowing and continues to rise with the increase of prolificacy. The objective of this study was to build a predictive model of the stillborn rate. Results: This study was performed on two farrow-to-finish farms and one farrow-to-wean farm located in Brittany, France. At each farm, the number of total born (TB), born alive (BA), stillborn piglets (S), the same data at the previous farrowing (TBn− 1, BAn− 1 and Sn− 1), backfat thickness just before farrowing and at previous weaning and parity rank were recorded in our dataset of 3686 farrowings. Bayesian networks were used as an integrated modelling approach to investigate risk factors associated with stillbirth using BayesiaLab® software. Our results suggest the validity of a hybrid model to predict the percentage of stillborn piglets. Three significant risk factors were identified by the model: parity rank (percentage of total mutual information: MI = 64%), Sn− 1 (MI = 25%) and TBn− 1 (MI = 11%). Additionally, backfat thickness just before farrowing was also identified for sows of parity five or more (MI = 0.4%). In practice, under optimal conditions (i.e., low parity rank, less than 8% of stillborn piglets, and a prolificacy lower than 14 piglets at the previous farrowing), our model predicted a stillborn rate almost halved, from 6.5% (mean risk of our dataset) to 3.5% for a sow at the next farrowing. In contrast, in older sows with a backfat thickness less than 15 mm, more than 15% of stillborn and a prolificacy greater than 18 piglets at the previous farrowing, the risk is multiplied by 2.5 from 6.5 to 15.7%. Conclusion: Our results highlight the impact of parity, previous prolificacy and stillborn rate on the probability of stillborn. Moreover, the importance of backfat thickness, especially in old sows, must be considered. This information can help farmers classify and manage sows according to their risk of giving birth to stillborn piglets. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

Coastal regions worldwide face increasing threats from climate change-induced hazards, necessitating more accurate and comprehensive vulnerability assessment tools. This study introduces an innovative approach to coastal vulnerability assessment by integrating Bayesian Networks (BN) with the modern coastal vulnerability (CV) framework. The resulting BN-CV model was applied to Queensland's coastal regions, with a particular focus on tide-modified and tide-dominated beaches, which constitute over 85% of the studied area. The research methodology involved beach classification based on morphodynamic characteristics, spatial subdivision of Queensland's coast into 78 sections, and the application of the BN-CV model to analyze interactions between geomorphological features and oceanic dynamics. This approach achieved over 90% accuracy in correlating beach types with vulnerability factors, significantly outperforming traditional CVI applications. Key findings include the identification of vulnerability hotspots and the creation of detailed exposure and sensitivity maps for Gold Coast City, Redland City, Brisbane City, and the Sunshine Coast Regional area. The study revealed spatial variability in coastal vulnerability, providing crucial insights for targeted management strategies. The BN-CV model demonstrates superior precision and customization capabilities, offering a more nuanced understanding of coastal vulnerability in regions with diverse beach typologies. This research advocates for the adoption of the BN-CV approach to inform tailored coastal planning and management strategies, emphasizing the need for regular reassessments and sustained stakeholder engagement to build resilience against climate change impacts. Recommendations include prioritizing adaptive infrastructure in high-exposure areas like the Gold Coast, enhancing flood management in Brisbane, improving socio-economic adaptive capacity in Redland, and maintaining natural defences in Moreton Bay. This study contributes significantly to the field of coastal risk management, providing a robust tool for policymakers and coastal managers to develop more effective strategies for building coastal resilience in the face of climate change. [ABSTRACT FROM AUTHOR]

Learning Bayesian networks from data aims to create a Directed Acyclic Graph that encodes significant statistical relationships between variables and their joint probability distributions. However, when using real-world data with limited knowledge of the original dynamical system, it is challenging to determine if the learned DAG accurately reflects the underlying relationships, especially when the data come from multiple independent sources. This paper describes a methodology capable of assessing the credible interval for the existence and direction of each edge within Bayesian networks learned from data, without previous knowledge of the underlying dynamical system. It offers several advantages over classical methods, such as data fusion from multiple sources, identification of latent variables, and extraction of the most prominent edges with their respective credible interval. The method is evaluated using simulated datasets of various sizes and a real use case. Our approach was verified to achieve results comparable to the most recent studies in the field, while providing more information on the model's credibility. [ABSTRACT FROM AUTHOR]

Breast cancer remains a global health problem requiring effective diagnostic methods for early detection, in order to achieve the World Health Organization's ultimate goal of breast self-examination. A literature review indicates the urgency of improving diagnostic methods and identifies thermography as a promising, cost-effective, non-invasive, adjunctive, and complementary detection method. This research explores the potential of using machine learning techniques, specifically Bayesian networks combined with convolutional neural networks, to improve possible breast cancer diagnosis at early stages. Explainable artificial intelligence aims to clarify the reasoning behind any output of artificial neural network-based models. The proposed integration adds interpretability of the diagnosis, which is particularly significant for a medical diagnosis. We constructed two diagnostic expert models: Model A and Model B. In this research, Model A, combining thermal images after the explainable artificial intelligence process together with medical records, achieved an accuracy of 84.07%, while model B, which also includes a convolutional neural network prediction, achieved an accuracy of 90.93%. These results demonstrate the potential of explainable artificial intelligence to improve possible breast cancer diagnosis, with very high accuracy. [ABSTRACT FROM AUTHOR]

Autonomous Vehicles (AVs) are being promoted as an emerging technology with the potential to improve traffic efficiency and safety. However, the scarcity of publicly available AV crash data contributes to a limited understanding of safety issues for deploying AVs. To gain a deeper understanding of the factors contributing to AV crashes, this study created a unique dataset by combining 445 intersection AV crashes from the California Department of Motor Vehicles with detailed roadway geometric and traffic characteristic data. To address the issue of imbalanced data, the Borderline synthetic minority oversampling technique (BL-SMOTE) was utilized in this study. A framework for analyzing AV crash types at intersections was also developed using the Categorical gradient boosting (Catboost) and Bayesian networks (BNs) models. The results show that inappropriate vehicle maneuvers, such as sudden lane changes or speed control, can increase the likelihood of an AV being involved in a sideswipe crash. Additionally, in scenarios where the AADT of the major road is lower, AVs are more prone to rear-end crashes when proceeding. These findings can provide valuable insights for creating safety management strategies in different situations and improve the development of innovative car warning technologies, such as rear-end collision warnings. [ABSTRACT FROM AUTHOR]

Network analysis is an emerging field for the study of psychopathology that considers constructs as arising from the interactions among their constituents. Pairwise effects among psychological components are often investigated by using this framework. Few studies have applied Bayesian networks, models that include directed interactions to perform causal inference on psychological constructs. Directed graphical models may be less straightforward to interpret in case the construct at hand does not contain symptoms but instead psychometric items from self-report measures. However, they may be useful in validating specific research questions that arise while using standard pairwise network models. In this study, we use Bayesian networks to investigate a well-known psychological construct, empathy from the Interpersonal Reactivity Index, in large two samples of 1973 university students from Belgium. Overall, our results support the hypotheses emphasizing empathic concern (i.e., sympathy) as causally important in the construct of empathy, and overall attribute the primacy of emotional components of empathy over their intellectual counterparts. Bayesian networks help researchers identify the plausible causal relationships in psychometric data, to gain new insight on the psychological construct under examination, help generate new hypotheses and provide evidence relevant to old ones. [ABSTRACT FROM AUTHOR]

One of the most important problems encountered in ceramic tile industry is defective product problem. Defective ceramics lead to loss of income and waste of resources in enterprises. However, it is generally unknown that which factors and production stages cause what kinds of defects. On the other hand, in the literature, the existing modelling studies usually consider the defects seen on industrial ceramics. The defect types of industrial ceramics and those of ceramic tiles are different. This article investigates the reasons behind the defect occurrences on ceramic tiles, along with a comparison between a logistic regression model and a Bayesian network model. The study shows that the Bayesian network model is more successful in estimating the defect types. The constructed Bayesian network model indicates that, in general, the high levels of the production band speed significantly increase the probabilities of all kinds of defects except the deformation defect. Additionally, the high densities of the glaze also increase the occurrence levels of the defects except the deformation defect. Similarly, the high levels of the engobe weight and the engobe density are also among the factors increasing the defect occurrences. [ABSTRACT FROM AUTHOR]

• This study evaluates the changes in the safety perception of shared automated shuttles and the willingness to re-ride (WTR) it. • Survey data from a shared automated passenger shuttle pilot program in Cary, North Carolina, was used. • Findings reveal that shuttle operations, especially timely arrival and drop-off, significantly affect both perceptional change and WTR. • Individuals with initial perceptions of the SAPS as very unsafe or unsafe showed a higher likelihood of perception change. • Further, the primary motivations for WTR were the enjoyable experience and convenience offered by the shuttle. Recognizing the potential transformative impact on transportation systems, safety perceptions of Shared Automated Vehicles (SAVs) have gained significant attention from researchers in recent years. Yet, the critical factors influencing perception changes and the willingness to re-ride (WTR) have not been extensively studied despite their relevance to SAV operations. This study applied Bayesian Networks (BNs) and Text Network (TN) methodologies to analyze survey data from a shared automated passenger shuttle (SAPS) pilot program conducted between March and April 2023, at Fred G. Bond Metro Park in Cary, North Carolina. Participants in the survey provided feedback on their safety perceptions of the SAPS before and after riding, as well as their willingness to ride again. Key findings reveal that shuttle operations, especially timely arrival and drop-off, significantly affect both perceptional change and WTR. Furthermore, users who accessed the shuttle by walking, biking, or public transportation were more likely to positively change their perception and express a willingness to ride the shuttle again. Also, individuals with initial perceptions of the SAPS as very unsafe or unsafe showed a higher likelihood of perception change. Conversely, older respondents were less likely to experience safety perception changes and WTR. Text network analysis further illuminated that the primary motivations for WTR were the enjoyable experience and convenience offered by the shuttle. The study contributes to the growing body of literature on SAVs by providing practical implications for the future development and testing of SAPSs. These insights are invaluable for policymakers and planners in optimizing SAPS operations, providing a deeper understanding of user experiences and expectations. [ABSTRACT FROM AUTHOR]

In the universe, there are up to 2 trillion galaxies with different features ranging from the number of stars, light spectrum, age, or visual appearance. Consequently, automatic classifiers are required to perform this task; furthermore, as shown by some related works, while greater the number of classes considered, the performance of the classifiers tends to decrease. This work is focused on the morphological classification of galaxies. They can be associated with a subset of 10 classes arranged in a hierarchy derived from the Hubble sequence. The proposed method, Bayesian and Convolutional Neural Networks (BCNN), is composed of two main modules. The first module is a convolutional neural network trained with the images of galaxies, and its predictions feed the second module. The second module is a Bayesian network that evaluates the hierarchy and helps to improve the prediction accuracy by combining the predictions of the first module through probabilistic inference over the Bayesian network. A collection of galaxies sourced from the Principal Galaxies Catalog and the APM Equatorial Catalogue of Galaxies are used to perform the experiments. The results show that BCNN performed better than five CNNs in multiple evaluation measures, reaching the scores 83% in hierarchical F-measure, 78% in accuracy, and 67% in exact match evaluation. [ABSTRACT FROM AUTHOR]

In order to solve the problem of evaluating the towing cost of submarine cable paths under arbitrary submarine terrain conditions, this paper adopted the particle swarm optimisation algorithm to plan submarine cable paths, evaluated the towing cost of submarine cable paths from the factors related to the towing cost of submarine cables, established the network structure of submarine cable paths for the evaluation of towing cost, and evaluated it with the static Bayesian network method. After the planning of the submarine cable path, the data related to the planned path were discretised and transformed into observation evidence for Bayesian network evaluation. Then, simulation experiments were conducted to evaluate the towing cost of the submarine cable path. Finally, the results of the simulation experiments were compared with the actual path results to verify the feasibility of Bayesian network application in this field. [ABSTRACT FROM AUTHOR]

Purpose: To this day there is no consensus regarding evidence of usefulness of Intraoperative Neurophysiological Monitoring (IONM). Randomized controlled trials have not been performed in the past mainly because of difficulties in recruitment control subjects. In this study, we propose the use of Bayesian Networks to assess evidence in IONM. Methods: Single center retrospective study from January 2020 to January 2022. Patients admitted for cranial neurosurgery with intraoperative neuromonitoring were enrolled. We built a Bayesian Network with utility calculation using expert domain knowledge based on logistic regression as potential causal inference between events in surgery that could lead to central nervous system injury and postoperative neurological function. Results: A total of 267 patients were included in the study: 198 (73.9%) underwent neuro-oncology surgery and 69 (26.1%) neurovascular surgery. 50.7% of patients were female while 49.3% were male. Using the Bayesian Network´s original state probabilities, we found that among patients who presented with a reversible signal change that was acted upon, 59% of patients would wake up with no new neurological deficits, 33% with a transitory deficit and 8% with a permanent deficit. If the signal change was permanent, in 16% of the patients the deficit would be transitory and in 51% it would be permanent. 33% of patients would wake up with no new postoperative deficit. Our network also shows that utility increases when corrective actions are taken to revert a signal change. Conclusions: Bayesian Networks are an effective way to audit clinical practice within IONM. We have found that IONM warnings can serve to prevent neurological deficits in patients, especially when corrective surgical action is taken to attempt to revert signals changes back to baseline properties. We show that Bayesian Networks could be used as a mathematical tool to calculate the utility of conducting IONM, which could save costs in healthcare when performed. [ABSTRACT FROM AUTHOR]

Behavioral neuropharmacology, a branch of neuroscience, uses behavioral analysis to demonstrate treatment effects on animal models, which is fundamental for pre-clinical evaluation. Typically, this determination is univariate, neglecting the relevant associations for understanding treatment effects in animals and humans. This study implements regression trees and Bayesian networks from a multivariate perspective by using variables obtained from behavioral tests to predict the time spent in the open arms of the elevated arm maze, a key variable to assess anxiety. Three doses of allopregnanolone were analyzed and compared to a vehicle group and a diazepam-positive control. Regression trees identified cut-off points between the anxiolytic and anxiogenic effects, with the anxiety index standing out as a robust predictor, combined with the percentage of open-arm entries and the number of entries. Bayesian networks facilitated the visualization and understanding of the interactions between multiple behavioral and biological variables, demonstrating that treatment with allopregnanolone (2 mg) emulates the effects of diazepam, validating the multivariate approach. The results highlight the relevance of integrating advanced methods, such as Bayesian networks, into preclinical research to enrich the interpretation of complex behavioral data in animal models, which can hardly be observed with univariate statistics. [ABSTRACT FROM AUTHOR]

Using the complementary strengths of Bayesian networks, decision trees, artificial neural networks (ANNs), and Markov models, this endeavor intends to completely revamp clinical decision-making. In order to provide instantaneous access to image-driven insights and clinical decision support systems (CDSS), want to create a revolutionary framework that merges these cutting-edge methods with cloud-enabled technologies. The proposed framework gives a comprehensive perspective of patient data by merging the probabilistic reasoning of Bayesian networks with the interpretability of decision trees, the pattern recognition abilities of ANNs, and the temporal interdependence of Markov models. This helps doctors to make more educated judgments based on a larger spectrum of information, leading to better patient outcomes. Healthcare workers can get to vital data from any place because to the cloud-enabled architecture's seamless scalability and accessibility. This not only increases the efficiency of decision-making, but also improves communication and cooperation between different medical professionals. This uses cutting-edge modeling strategies and cloud computing to pave a new path in clinical decision-making. This system has the potential to greatly enhance healthcare by integrating image-driven insights with CDSS, to the advantage of both patients and healthcare practitioners. [ABSTRACT FROM AUTHOR]

Featured Application: The proposed model can be used to improve symptoms checker tools for mental health disorders, allowing accurate and transparent predictions based on user input. Mental illnesses are becoming one of the most common health concerns among the population. Despite the proven efficacy of psychological treatments, mental illnesses are largely underdiagnosed, particularly in developing countries. A key factor contributing to this is the scarcity of mental health providers capable of diagnosing. In this work, we propose a novel method that combines the general capabilities and accuracy of Large Language models with the explainability of Bayesian Networks. Our system analyzes descriptions of symptoms provided by users and written in natural language and, based on these descriptions, asks questions to confirm or refine the initial diagnosis made by the deep learning model. We trained our model on a large-scale dataset collected from various internet sources, comprising over 2.3 million data points. The initial prediction from the Large Language model is refined through symptom confirmation questions derived from a probabilistic graphical model constructed by experts based on the DSM-5 diagnostic manual. We present results from symptom descriptions sourced from the internet and clinical vignettes extracted from behavioral science exams, demonstrating the effectiveness of our hybrid model in classifying mental health disorders. Our model achieves high accuracy in classifying a wide range of mental health disorders, providing transparent and explainable predictions. [ABSTRACT FROM AUTHOR]

The persistent issue of wrongful convictions in the United States emphasizes the need for scrutiny and improvement of the criminal justice system. While statistical methods for the evaluation of forensic evidence, including glass, fingerprints, and deoxyribonucleic acid, have significantly contributed to solving intricate crimes, there is a notable lack of national‐level standards to ensure the appropriate application of statistics in forensic investigations. We discuss the obstacles in the application of statistics in court and emphasize the importance of making statistical interpretation accessible to non‐statisticians, especially those who make decisions about potentially innocent individuals. We investigate the use and misuse of statistical methods in crime investigations, in particular the likelihood ratio approach. We further describe the use of graphical models, where hypotheses and evidence can be represented as nodes connected by arrows signifying association or causality. We emphasize the advantages of special graph structures, such as object‐oriented Bayesian networks and chain event graphs, which allow for the concurrent examination of evidence of various nature. [ABSTRACT FROM AUTHOR]

The subcellular localization of messenger RNA (mRNA) not only helps us to understand the localization regulation of gene expression but also helps to understand the relationship between RNA localization pattern and human disease mechanism, which has profound biological and medical significance. Several predictors have been proposed for predicting the subcellular localization of mRNA. However, there is still considerable room for improvement in their predictive performance, especially regarding multi-label prediction. This study proposes a novel multi-label predictor, DRpred, for mRNA subcellular localization prediction. This predictor first utilizes Bayesian networks to capture the dependencies among labels. Subsequently, it combines these dependencies with features extracted from mRNA sequences using Word2vec, forming the input for the predictor. Finally, it employs a neural network combining BiLSTM and an attention mechanism to capture the internal relationships of the input features for mRNA subcellular localization. The experimental validation on an independent test set demonstrated that DRpred obtained a competitive predictive performance in multi-label prediction and outperformed state-of-the-art predictors in predicting single subcellular localizations, obtaining accuracies of 82.14%, 93.02%, 80.37%, 94.00%, 90.58%, 84.53%, 82.01%, 79.71%, and 85.67% for the chromatin, cytoplasm, cytosol, exosome, membrane, nucleolus, nucleoplasm, nucleus, and ribosome, respectively. It is anticipated to offer profound insights for biological and medical research. [ABSTRACT FROM AUTHOR]