Bayesian Network-based Framework Research Articles

Data-Driven Fatigue Failure Probability Updating of OSD by Bayesian Backward Propagation

This study introduces a data-driven approach for updating the fatigue failure probability of the orthotropic steel deck (OSD) using Bayesian backward propagation. The OSD in steel bridges is considered as a parallel system composed of two critical fatigue-prone components, namely, the rib-to-diaphragm and rib-to-deck joints. A probabilistic model for fatigue reliability is established based on the equivalent structural stress method and limit state function. The system-level fatigue reliability model is then constructed, taking into account the correlations between limit states of individual components through Bayesian network forward propagation. The key advantage of the Bayesian network-based framework is its ability to perform backward propagation, allowing for the updating of failure probabilities for critical components when the system-level failure of the OSD is observed. Consequently, the proposed approach enables the identification of vulnerable components through data-driven fatigue failure probability updating. Finally, the approach is applied to a real instrumented steel bridge to determine the time-dependent fatigue failure probability at both the system and component levels over its service life. The results show that the component-level fatigue failure probability model will underestimate the fatigue life in comparison to the system-level model. Meanwhile, the proposed method could identify vulnerable components by quantifying the fatigue failure probability of in-service steel bridges.

A Bayesian network-based framework for SHM data fusion supporting bridge management

Guidelines for Risk Classification and Management, Safety Assessment and Monitoring of Bridges, issued in 2020 by the Italian Ministry of Sustainable Mobility, promote the use of Structural Health Monitoring (SHM) systems for risk assessment of bridges. Prestressed or ordinary reinforced concrete bridges are designed to maintain their functionality over a long period of time. However, during their service life, such structures may be exposed to ever- increasing traffic volumes, extreme weather conditions and/or marine environments and so on. Therefore, constant maintenance and timely interventions are crucial to ensure the functionality of the transportation network. The current management process is mainly based on visual inspections, while the aggregation of information coming from multiple sources is still a major challenge. In this context, the main objective of the present work is to develop a general Bayesian framework capable of processing the different sources of information based on a Bayesian network (BN), a probabilistic graphical model that represents a set of variables and their conditional dependencies. A BN is a useful tool for the management of bridges since it allows the prediction of damage states and failure conditions based on the knowledge by visual inspections and SHM. The combined use of SHM and Bayesian approaches can reduce the overall risk of failure increasing the efficiency of the infrastructure system. The procedure is exemplified and validated with reference to a simply supported post-tensioned case study bridge.

A hybrid behavior- and Bayesian network-based framework for cyber–physical anomaly detection

In recent years, the increasing Internet connectivity and heterogeneity of industrial protocols have been raising the number and nature of cyber-attacks against Industrial Control Systems (ICS). Such cyber-attacks may lead to cyber anomalies and further to the failure of physical components, thus leading to cyber–physical attacks. In this paper, we present a novel unsupervised cyber–physical anomaly detection framework based on a hybrid “multi-formalism” approach that combines the outcomes of multiple unsupervised behavior-based anomaly detectors through a Bayesian network-based probabilistic modeling of the ICS. More precisely, the framework consists of two behavior-based anomaly detection modules that monitor separately and simultaneously the behavior of cyber and physical data acquired from the ICS. The outputs of such modules are filtered and combined through a Bayesian network-based modeling in order to improve the trustworthiness of the detected anomalies and to provide the detection probability of cyber, physical, and cyber–physical anomalies, taking into account possible cascading effects over the cyber–physical process. The outcomes achieved through the implementation of our framework on the hardware-in-the-loop Water Distribution Testbed (WDT) dataset show very high detection performance with a strong ability to reject false positive events and to isolate and localize the anomalies over the cyber–physical process.

Corrosion fatigue crack growth prediction of bridge suspender wires using Bayesian gaussian process

This paper proposes a Bayesian gaussian process-based corrosion fatigue damage assessment framework for bridge suspender wires. Prior statistical parameters in the fatigue life prediction model are obtained by corrosion fatigue crack growth test under different stress ratios. A numerical simulation method of corrosion fatigue crack growth is developed combined with ABAQUS and FRANC3D. Following this, a Bayesian network-based framework is established by integrating fatigue crack growth model, stress concentration factor and observed fatigue crack length information to reduce the uncertainties. The uncertainties exist in stress concentration factor are quantified by gaussian process regression-based surrogate model, and the pit geometry of length, width and depth are selected as three-dimensional input. Markov Chain Monte Carlo simulation is used to obtain the posterior distribution of parameters in the Bayesian network. The results show that the fatigue crack growth predictions agree well with experimental observations. The proposed method can simplify the complicated modeling process of stress concentration factor under the influence of corrosion pit, and can effectively update the model parameters to accurately predict the corrosion fatigue crack of bridge suspender wires.

Managing Ship’s Ballast Water: A Feasibility Assessment of Mobile Port-Based Treatment

The International Maritime Organization (IMO) has adopted the Ballast Water Management Convention (BWMC), which requires vessels to manage their ballast water according to specific standards. While most vessels have to install a management system onboard, in some cases, a mobile solution, for example a system fitted in a container, might be a more viable solution. These mobile systems are an excellent solution as a contingency measure as well, that is when onboard systems malfunction. Research on the topic is rather scant. To that extent, this paper proposes a Bayesian network-based framework to model and assess the feasibility of mobile ballast water treatment solutions. The results based on input from experts indicate that mobile systems are a highly feasible solution. The operational and logistical feasibility of the system are the most important parameters and are areas where the manufacturers and service providers should pay more attention. With compliance deadlines approaching, malfunctions of installed systems increasing and the technology for port-based solutions becoming more mature, there will be increased focus on port-based systems. Our results can, therefore, provide valuable insights to regulators, ship and port operations and we hope that they can spark further academic research on this area.

Bayesian Network-Based Framework for Cost-Implication Assessment of Road Traffic Collisions

Investigating the cost-implications of road traffic collision factors is an important endeavour that has a direct impact on the economy, transport policies, cities and nations around the world. A Bayesian network framework model was developed using real-life road traffic collision data and expert knowledge to assess the cost of road traffic collisions. Findings of this study suggest that the framework is a promising approach for assessing the cost-implications associated with road traffic collisions. Moreover, adopting this framework with other computational intelligence approaches would have a positive impact towards achieving the Sustainable Development Goals in terms of road safety.

Dynamic reliability analysis for residual life assessment of corroded subsea pipelines

ABSTRACT Failure threats in subsea pipelines are hard to inspect, but parameters influencing them are easier to observe. Hence, nowadays, Bayesian network models became more relevant, as the model can be updated with the sparse observations while considering the underlying uncertainty. This holds for failure threat assessment of subsea pipelines, specifically for a highly random corrosion mechanism, which has not been captured in the current traditional assessments appropriately. However, a number of researchers stated that it is difficult to build the Conditional Probability Table (CPT) of the Bayesian networks. In such cases, it has been suggested to employ expert knowledge to determine the conditional probability distributions, which involves some uncertainties and high data deviation. This paper focusses on developing a dynamic Bayesian network-based framework to minimise the inputs from the expert domain in the CPT development, while providing an efficient option to analyse the pipeline residual life due to corrosion threat.

Bayesian network-based framework for exposure-response study design and interpretation

Conventional environmental-health risk-assessment methods are often limited in their ability to account for uncertainty in contaminant exposure, chemical toxicity and resulting human health risk. Exposure levels and toxicity are both subject to significant measurement errors, and many predicted risks are well below those distinguishable from background incident rates in target populations. To address these issues methods are needed to characterize uncertainties in observations and inferences, including the ability to interpret the influence of improved measurements and larger datasets. Here we develop a Bayesian network (BN) model to quantify the joint effects of measurement errors and different sample sizes on an illustrative exposure-response system. Categorical variables are included in the network to describe measurement accuracies, actual and measured exposures, actual and measured response, and the true strength of the exposure-response relationship. Network scenarios are developed by fixing combinations of the exposure-response strength of relationship (none, medium or strong) and the accuracy of exposure and response measurements (low, high, perfect). Multiple cases are simulated for each scenario, corresponding to a synthetic exposure response study sampled from the known scenario population. A learn-from-cases algorithm is then used to assimilate the synthetic observations into an uninformed prior network, yielding updated probabilities for the strength of relationship. Ten replicate studies are simulated for each scenario and sample size, and results are presented for individual trials and their mean prediction. The model as parameterized yields little-to-no convergence when low accuracy measurements are used, though progressively faster convergence when employing high accuracy or perfect measurements. The inferences from the model are particularly efficient when the true strength of relationship is none or strong with smaller sample sizes. The tool developed in this study can help in the screening and design of exposure-response studies to better anticipate where such outcomes can occur under different levels of measurement error. It may also serve to inform methods of analysis for other network models that consider multiple streams of evidence from multiple studies of cumulative exposure and effects.

Abstract SY17-02: A systems approach to understanding tumor specific drug response

Abstract Systematic characterization of cancer genomes has revealed a staggering complexity of aberrations among individuals, such that the functional importance and physiological impact of most tumor genetic alterations remains poorly defined. A major challenge involves the development of analysis methods to uncover biological insights from the data, including the identification of the key mutations that drive cancer and how these events alter cellular regulation. We have developed Conexic, a novel Bayesian Network-based framework to integrate chromosomal copy number and gene expression data to detect to detect driver genes located in regions that are aberrant in tumors. The underlying assumption is that a driving mutation might be associated with a characteristic gene expression signature representing genes whose expression is modulated by the driver. Thus our score guided approach searches for genes that are both recurrently aberrant and associated with variance of expression patterns across tumor samples. This method not only pinpoints specific regulators within a large aberrant region, but also by associating drivers with gene modules whose expression vary with the driver, provides insight into the physiological roles of drivers and associated genes. We demonstrated the utility of the CONEXIC framework using a melanoma dataset, our analysis correctly identified known drivers in melanoma (such as MITF) and connected these to many of their known targets, as well as the biological processes they regulate. In addition, it predicted multiple tumor dependencies TBC1D16 and RAB27A in melanoma and showed that tumors highly expressing these genes are dependent on the same gene for growth. Additionally, gene expression in the associated modules is altered following knockdown as predicted by our model. The identity of these drivers suggests that abnormal regulation of protein trafficking is important for cell survival in melanoma and highlights the importance of protein trafficking in this malignancy. We also present more recent results of applying CONEXIC to additional cancers, including glioblastoma and ovarian cancers, as well as additional phenotypes including invasion and drug resistance. Together, these results demonstrate the ability of integrative Bayesian approaches to identify novel drivers with biological, and possibly therapeutic, importance in cancer. Citation Format: {Authors}. {Abstract title} [abstract]. In: Proceedings of the 102nd Annual Meeting of the American Association for Cancer Research; 2011 Apr 2-6; Orlando, FL. Philadelphia (PA): AACR; Cancer Res 2011;71(8 Suppl):Abstract nr SY17-02. doi:10.1158/1538-7445.AM2011-SY17-02

A Bayesian network-based framework for semantic image understanding

Current research in content-based semantic image understanding is largely confined to exemplar-based approaches built on low-level feature extraction and classification. The ability to extract both low-level and semantic features and perform knowledge integration of different types of features is expected to raise semantic image understanding to a new level. Belief networks, or Bayesian networks (BN), have proven to be an effective knowledge representation and inference engine in artificial intelligence and expert systems research. Their effectiveness is due to the ability to explicitly integrate domain knowledge in the network structure and to reduce a joint probability distribution to conditional independence relationships. In this paper, we present a general-purpose knowledge integration framework that employs BN in integrating both low-level and semantic features. The efficacy of this framework is demonstrated via three applications involving semantic understanding of pictorial images. The first application aims at detecting main photographic subjects in an image, the second aims at selecting the most appealing image in an event, and the third aims at classifying images into indoor or outdoor scenes. With these diverse examples, we demonstrate that effective inference engines can be built within this powerful and flexible framework according to specific domain knowledge and available training data to solve inherently uncertain vision problems.

A Bayesian Network-Based Framework for Personalization in Mobile Commerce Applications

Providing personalized services for mobile commerce (m-commerce) can improve user satisfaction and merchant profits, which are important to the success of m-commerce. This paper proposes a Bayesian network (BN)-based framework for personalization in m-commerce applications. The framework helps to identify the target mobile users and to deliver relevant information to them at the right time and in the right way. Under the framework, a personalization model is generated using a new method and the model is implemented in an m-commerce application for the food industry. The new method is based on function dependencies of a relational database and rough set operations. The framework can be applied to other industries such as movies, CDs, books, hotel booking, flight booking, and all manner of shopping settings.