Bayesian methodology incorporating expert judgment for ranking countermeasure effectiveness under uncertainty: Example applied to at grade railroad crossings in Korea

Washington, Simon; Oh, Juhwan

doi:10.1016/j.aap.2005.08.005

Cited by 51 publications

(21 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Pawlovich et al (2006) employed a Bayesian approach to assess impacts of road design measures on crash frequencies and rates. And Washington and Oh (2006) developed a Bayesian methodology for incorporating expert judgment in ranking countermeasure effectiveness under uncertainty.…”

Section: Introductionmentioning

confidence: 99%

A multivariate Poisson-lognormal regression model for prediction of crash counts by severity, using Bayesian methods

Kockelman²,

Damien

2008

Accident Analysis & Prevention

329

134

View full text Add to dashboard Cite

The following paper is a pre-print and the final publication can be found in Accident Analysis and Prevention, 40 (3):964-975, 2008. Presented at the 86 th Annual Meeting of the Transportation Research Board, January 2007 ABSTRACT Numerous efforts have been devoted to investigating crash occurrence as related to roadway design features, environmental and traffic conditions. However, most of the research has relied on univariate count models; that is, traffic crash counts at different levels of severity are estimated separately, which may neglect shared information in unobserved error terms, reduce efficiency in parameter estimates, and lead to potential biases in sample databases. This paper offers a multivariate Poisson-lognormal (MVPLN) specification that simultaneously models injuries by severity. The MVPLN specification allows for a more general correlation structure as well as overdispersion. This approach addresses some questions that are difficult to answer by estimating them separately. With recent advancements in crash modeling and Bayesian statistics, the parameter estimation is done within the Bayesian paradigm, using a Gibbs Sampler and the Metropolis-Hastings (M-H) algorithms for crashes on Washington State rural two-lane highways.The estimation results from the MVPLN approach did show statistically significant correlations between crash counts at different levels of injury severity. The non-zero diagonal elements suggested overdispersion in crash counts at all levels of severity. The results lend themselves to several recommendations for highway safety treatments and design policies. For example, wide lanes and shoulders are key for reducing crash frequencies, as are longer vertical curves. KEY WORDS INTRODUCTIONRoadway safety is a major concern for the general public and public agencies. Roadway crashes claim many lives and cause substantial economic losses each year. In the U.S. traffic crashes bring about more loss of human life (as measured in human-years) than almost any other causefalling behind only cancer and heart disease (NHTSA, 2005). The situation is of particular interest on rural two-lane roadways, which experience significantly higher fatality rates than urban roads. The annual cost of traffic crashes is estimated to be $231 billion, or $820 per capita in 2000(Blincoe et al., 2000. These costs do not include the cost of delays imposed on other travelers, which also are significant, particularly when crashes occur on busy roadways. Schrank and Lomax (2002) estimate that over half of all traffic delays are due to non-recurring events, such as crashes, costing on the order of $1,000 per peak-period driver per year, particularly in urban areas. Thus, while vehicle and roadway design are improving, and growing congestion may be reducing impact speeds, crashes are becoming more critical in many ways, particularly in societies that continue to motorize. Given the importance of roadways safety, there has been considerable crash prediction research (see, e.g., Hauer, 1986Hauer, , 1997Hauer,...

show abstract

Section: Introductionmentioning

confidence: 99%

A multivariate Poisson-lognormal regression model for prediction of crash counts by severity, using Bayesian methods

Kockelman²,

Damien

2008

Accident Analysis & Prevention

329

134

View full text Add to dashboard Cite

show abstract

“…The proposed approach is similar to that suggested by El Faouzi (2006), Melcher et al (2001) and Washington and Oh (2006), but different in how prior knowledge and data likelihood functions are developed.…”

Section: Bayesian Data Fusionmentioning

confidence: 91%

Estimating countermeasure effects for reducing collisions at highway–railway grade crossings

Saccomanno

Park

2007

Accident Analysis & Prevention

View full text Add to dashboard Cite

“…The next steps, defining criteria for usability/risk thresholds (2) and generating ideas for improved usability/risk control (3), are undertaken with different instruments, according to different clauses of IEC 62366 (for usability engineering) and ISO 14971 (for risk management), but with the same goal of simulating (4) and evaluating (5) the new degree of usability respectively the new residual risk after implementation of design improvements/countermeasures. The last elements of each iteration loop in IEC 62366 as well as ISO 14971, include identification (6) and evaluation (7) of new usability problems or risks, arising from implemented modifications of the foregoing steps as well, as a decision on whether to start a new iteration or interrupt and end with the usability and risk management procedure (8). Comparing the two processes, it becomes clear that UE is a means of the risk management process.…”

Section: Usability Engineering and Risk Management Processmentioning

confidence: 99%

A new knowledge-based risk control method for risk sensitive devices

Plogmann¹,

Janß²,

Jansen-Troy³

et al. 2013

Safety and Security Engineering V

View full text Add to dashboard Cite

Medical engineering is always closely linked to the well-being of the human. This close relation can strike out at two directions: although medical devices are intentionally designed to support diagnosis and therapy, they can also cause serious adverse events and harm patients, users and third parties. Therefore, according to ISO 14971, risk management -including risk identification, risk evaluation, risk control and market surveillance -is an important and inevitable chapter in medical device development. Unfortunately, the risk control process, which implies selection and application of countermeasures (generally through inherent, protective or descriptive safety measures), is not yet supported systematically and methodically. Therefore the Chair of Medical Engineering at the RWTH Aachen University has developed a methodological approach to generate appropriate countermeasures for given risks, helping to mitigate previously identified technical and human-induced errors or hazards in products and processes.The methodology uses a knowledge-base, reorganizing prior experience, from by now fourteen risk analyses of medical systems, comprising research and industrial risk assessments. Case-tailored categories from error-taxonomies allow the user to hark back to his antecessors' knowledge in a user-friendly manner. The methods' basic structure is built on the Theory of Inventive Problem Solving (TRIZ) and can be fed with further data in the future. Purely technical and system-inherent, as well as Human-Machine-Interaction errors, have been organized in thirteen error categories, filing 61 individual failure modes, which represent the former (root) causes and failures from the analyzed risk analysis data base. The different possible combinations of cause and failure are displayed in a 2-D matrix, indexing a total of 41 abstract principles of risk control that suggest tailor-made solutions for a specific problem.Evaluation of the method took place with different test groups, each time in comparison to conventional brainstorming as the state-of-the-art reference. Reassessment of risk priority numbers (after applying countermeasures) by a blind expert, shows a noticeable benefit, gained by the new method. Keywords: healthcare/medical systems, risk control in risk management, system safety, theory of inventive problem solving (TRIZ), human factors.

show abstract

Bayesian methodology incorporating expert judgment for ranking countermeasure effectiveness under uncertainty: Example applied to at grade railroad crossings in Korea

Cited by 51 publications

References 10 publications

A multivariate Poisson-lognormal regression model for prediction of crash counts by severity, using Bayesian methods

A multivariate Poisson-lognormal regression model for prediction of crash counts by severity, using Bayesian methods

Estimating countermeasure effects for reducing collisions at highway–railway grade crossings

A new knowledge-based risk control method for risk sensitive devices

Contact Info

Product

Resources

About