The extreme value theory approach to safety estimation

Songchitruksa, Praprut; Tarko, Andrew P.

doi:10.1016/j.aap.2006.02.003

Cited by 258 publications

(94 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Therefore, it is sometimes difficult to investigate the main causes of collisions just from the numbers of the outcome (i.e., collision) of the process. Finally, this approach of safety analysis is often criticized by many researchers (e.g., Chin and Quek, 1997;Debnath and Chin, 2006;Songchitruksa and Tarko, 2006) as reactive and unethical as it requires sufficiently large number of collisions to take place first, before any preventive or corrective measures are taken.…”

Section: Introductionmentioning

confidence: 99%

Navigational Traffic Conflict Technique: A Proactive Approach to Quantitative Measurement of Collision Risks in Port Waters

Debnath

Chin

2009

J. Navigation

View full text Add to dashboard Cite

Navigational safety analysis relying on collision statistics is often hampered because of low number of observations. A promising alternative approach that overcomes this problem is proposed in this paper. By analyzing critical vessel interactions this approach proactively measures collision risk in port waters. The proposed method is illustrated for quantitative measurement of collision risks in Singapore port fairways, and validated by examining correlations between the measured risks with those perceived by pilots. This method is an ethically appealing alternative to the collisionbased analysis for fast, reliable and effective safety assessment, thus possesses great potential for managing collision risks in port waters.

show abstract

Section: Introductionmentioning

confidence: 99%

Navigational Traffic Conflict Technique: A Proactive Approach to Quantitative Measurement of Collision Risks in Port Waters

Debnath

Chin

2009

J. Navigation

View full text Add to dashboard Cite

show abstract

“…These data limitations motivate the development of surrogate measures of safety and non-crash-based safety estimation approaches. The recently proposed non-crash-based approaches include extreme value theory (EVT) approach (Songchitruksa & Tarko, 2006;Tarko, 2012), probabilistic framework for automated road safety analysis (Saunier & Sayed, 2008), and causal model (Davis et al, 2011). The EVT is of interest in this study because of its capability to estimate the probability of extreme rare events from relatively short time period observations, and this is in line with Threshold Approach for Road Safety Estimation 77 the objective of surrogate measures of safety, which is to use more observable traffic events to predict less frequent crashes.…”

Section: Introductionmentioning

confidence: 99%

Evaluation of Peak Over Threshold Approach for Road Safety Estimation

Zheng

Ismail

Meng

2014

Journal of Transportation Safety & Security

View full text Add to dashboard Cite

Development of non-crash-based safety estimation approaches has drawn considerable research interest, and the application of extreme value theory is one of them. This study proposes the use of extreme value theory based peak over threshold (POT) approach for road safety estimation and compares the POT with the crash-based negative binomial regression approach. The traffic data is from videos recorded at 29 directional segments with time duration of approximately 3 h each. The results show that the best fitted model comes from regression model with R 2 of 0.65, in which the covariate is return levels estimated from POT approach. Meanwhile, the POT estimated crashes also have relatively high R 2 value but with large variances. Both of these imply that POT estimations from short observation time carry useful safety information. Moreover, the POT estimated return levels can be employed as a covariate for building better regression models.

show abstract

“…Traffic conflict collection has been extensively studied since their first conceptualization in the late 1960s, but is still mostly performed manually by on-site observers (6,12,13). The extreme value method is applied in (15) to estimate the frequency of right-angle collisions at signalized intersections, relying on the post-encroachment time, which limits the categories of interaction that can be characterized. Davis et al outlined a causal theory and built a minimal model capable of rigorously representing traffic conflicts and crashes, relying on the description of the evasive action (16).…”

Section: Related Workmentioning

confidence: 99%

Large-Scale Automated Analysis of Vehicle Interactions and Collisions

Saunier

Sayed

Ismail

2010

Transportation Research Record

148

101

View full text Add to dashboard Cite

Road collisions represent a worldwide pandemic which can be addressed through the improvement of existing tools for safety analysis. The paper presents a refined probabilistic framework for the analysis of road user interactions. In particular, the identification of potential collision points is used to estimate collision probabilities and their spatial distribution can be visualized. A probabilistic time to collision is also introduced, and interactions are categorized in four categories: head-on, rear-end, side and parallel. The framework is applied to a large dataset of video recordings containing more than 300 severe interactions and collisions collected in Kentucky. The results demonstrate the usefulness of the approach in studying road user behavior and mechanisms that may lead to collisions.

show abstract

The extreme value theory approach to safety estimation

Cited by 258 publications

References 7 publications

Navigational Traffic Conflict Technique: A Proactive Approach to Quantitative Measurement of Collision Risks in Port Waters

Navigational Traffic Conflict Technique: A Proactive Approach to Quantitative Measurement of Collision Risks in Port Waters

Evaluation of Peak Over Threshold Approach for Road Safety Estimation

Large-Scale Automated Analysis of Vehicle Interactions and Collisions

Contact Info

Product

Resources

About