Reflections on Bayesian Network models for road tunnel safety design: A case study from Norway

Borg, Audun; Bjelland, Henrik; Njå, Ove

doi:10.1016/j.tust.2014.05.004

Cited by 24 publications

(3 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To evaluate a given BBN model, this methodology employs some edge-based scoring and searching algorithms, which are described in detail by reference [17]. Moreover, the Bayesian network method has been applied by many researchers in the modeling of road safety [37,[39][40][41][42]. There are also several studies where BBN is applied to analyze maritime accidents [43][44][45][46].…”

Section: Literature Reviewmentioning

confidence: 99%

Towards Sustainable Road Safety in Saudi Arabia: Exploring Traffic Accident Causes Associated with Driving Behavior Using a Bayesian Belief Network

et al. 2022

View full text Add to dashboard Cite

Understanding the causes and effects of road accidents is critical for developing road and action plans in a country. The causation hypothesis elucidates how accidents occur and may be applied to accident analysis to more precisely anticipate, prevent, and manage road safety programs. Driving behavior is a critical factor to consider when determining the causes of traffic accidents. Inappropriate driving behaviors are a set of acts taken on the roadway that can result in aberrant conditions that may result in road accidents. In this study, using Al-Ahsa city in Saudi Arabia’s Eastern Province as a case study, a Bayesian belief network (BBN) model was established by incorporating an expectation–maximization algorithm. The model examines the relationships between indicator variables with a special focus on driving behavior to measure the uncertainty associated with accident outcomes. The BBN was devised to analyze intentional and unintentional driving behaviors that cause different types of accidents and accident severities. The results showed when considering speeding alone, there is a 26% likelihood that collision will occur; this is a 63% increase over the initial estimate. When brake failure was considered in addition to speeding, the likelihood of a collision jumps from 26% to 33%, more than doubling the chance of a collision when compared to the initial value. These findings demonstrated that the BBN model was capable of efficiently investigating the complex linkages between driver behavior and the accident causes that are inherent in road accidents.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Towards Sustainable Road Safety in Saudi Arabia: Exploring Traffic Accident Causes Associated with Driving Behavior Using a Bayesian Belief Network

et al. 2022

View full text Add to dashboard Cite

show abstract

“…The number of fixation is defined as the total number of fixation points and was once called a fixation point, which is a sign of the importance of the region. The more the number of fixations, the more the test concerned about this area [25]. Fixation duration refers to the time for which drivers fixate on a fixed area.…”

Section: Drivers' Dynamic Visual Mode and Parameters Selectionmentioning

confidence: 99%

Study on Driver's Fixation Variation at Entrance and Inside Sections of Tunnel on Highway

Yan

Hou

Wang

et al. 2014

Advances in Mechanical Engineering

View full text Add to dashboard Cite

How drivers' visual characteristics change as they pass tunnels was studied. Firstly, nine drivers' test data at tunnel entrance and inside sections using eye movement tracking devices were recorded. Then the transfer function of BP artificial neural network was employed to simulate and analyze the variation of the drivers' eye movement parameters. The relation models between eye movement parameters and the distance of the tunnels were established. In the analysis of the fixation point distributions, the analytic coordinates of fixations in visual field were clustered to obtain different visual area of fixations by utilizing dynamic cluster theory. The results indicated that, at 100 meters before the entrance, the average fixation duration increased, but the fixations number decreased substantially. After 100 meters into the tunnel, the fixation duration started to decrease first and then increased. The variations of drivers' fixation points demonstrated such a pattern of change as scatter, focus, and scatter again. While driving through the tunnels, drivers presented a long time fixation. Nearly 61.5% subjects' average fixation duration increased significantly. In the tunnel, these drivers pay attention to seven fixation points areas from the car dashboard area to the road area in front of the car.

show abstract

“…Due to the ability to deal with few data, and continuously update the probability, Bayesian approaches can be used to monitor the hazard state of workers (Luo et al , 2014). Other safety-related topics include lifecycle safety control (Zhang et al , 2013), safety design (Borg et al , 2014) and extracting recurrent scenarios from narrative texts for accident diagnosis (Abdat et al , 2014), all proved the utility of Bayesian approaches.…”

Section: Resultsmentioning

confidence: 99%

Applications of Bayesian approaches in construction management research: a systematic review

Hon

Sun

Xia

et al. 2021

ECAM

View full text Add to dashboard Cite

PurposeBayesian approaches have been widely applied in construction management (CM) research due to their capacity to deal with uncertain and complicated problems. However, to date, there has been no systematic review of applications of Bayesian approaches in existing CM studies. This paper systematically reviews applications of Bayesian approaches in CM research and provides insights into potential benefits of this technique for driving innovation and productivity in the construction industry.Design/methodology/approachA total of 148 articles were retrieved for systematic review through two literature selection rounds.FindingsBayesian approaches have been widely applied to safety management and risk management. The Bayesian network (BN) was the most frequently employed Bayesian method. Elicitation from expert knowledge and case studies were the primary methods for BN development and validation, respectively. Prediction was the most popular type of reasoning with BNs. Research limitations in existing studies mainly related to not fully realizing the potential of Bayesian approaches in CM functional areas, over-reliance on expert knowledge for BN model development and lacking guides on BN model validation, together with pertinent recommendations for future research.Originality/valueThis systematic review contributes to providing a comprehensive understanding of the application of Bayesian approaches in CM research and highlights implications for future research and practice.

show abstract

Reflections on Bayesian Network models for road tunnel safety design: A case study from Norway

Cited by 24 publications

References 19 publications

Towards Sustainable Road Safety in Saudi Arabia: Exploring Traffic Accident Causes Associated with Driving Behavior Using a Bayesian Belief Network

Towards Sustainable Road Safety in Saudi Arabia: Exploring Traffic Accident Causes Associated with Driving Behavior Using a Bayesian Belief Network

Study on Driver's Fixation Variation at Entrance and Inside Sections of Tunnel on Highway

Applications of Bayesian approaches in construction management research: a systematic review

Contact Info

Product

Resources

About