Real-Time Estimation of Accident Likelihood for Safety Enhancement

Oh, Jun Seok; Oh, Cheol; Ritchie, Stephen G.; Chang, Myungsoon

doi:10.1061/(asce)0733-947x(2005)131:5(358)

Cited by 105 publications

(82 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A couple of studies show that a major factor leading to an accident is the variation of speed. It was found that reducing the speed variation increases safety and reduces the likelihood of an accident (8,9). Thus, vehicle speed and the variance in speed between vehicles may also be effective MOEs in the study of safety.…”

Section: Safety Effectsmentioning

confidence: 99%

Evaluation of Effectiveness of Automated Work Zone Information Systems

Chu

Kim

Chung

et al. 2005

Transportation Research Record: Journal of the Transportation R

View full text Add to dashboard Cite

With the advancement of the Intelligent Transportation Systems (ITS) technologies, some Automated Workzone Information Systems (AWIS) have been developed and deployed in the field with the purpose of providing useful real-time traffic information to motorists as they approach or pass through a work zone. Several evaluation studies have been conducted in order to answer the question if AWIS can provide the expected benefits. These evaluation studies paid more attention to the evaluation of system functionality and reliability. This paper focuses on the evaluation of the effectiveness of an AWIS system, called CHIPS, deployed in southern California. We conducted studies on traffic diversion, safety effects, and driver survey in order to show its effectiveness. Evaluation results showed most driver survey respondents liked the system, which was found to be effective in diverting traffic and promoting smoother traffic flow during congested periods.3

show abstract

Section: Safety Effectsmentioning

confidence: 99%

Evaluation of Effectiveness of Automated Work Zone Information Systems

Chu

Kim

Chung

et al. 2005

Transportation Research Record: Journal of the Transportation R

View full text Add to dashboard Cite

show abstract

“…The authors also proposed a methodology to identify crash-prone conditions in real time, for potential use in proactive traffic management. Oh et al (2001) showed that five minutes standard deviation of 30-second speed measurements was the best indicator of "disruptive" traffic flow leading to a crash as opposed to "normal" traffic flow. They used the Bayesian classifier to categorize the two possible traffic flow conditions.…”

Section: Studies Establishing Statistical Linksmentioning

confidence: 99%

Transferability and Robustness of Predictive Models to Proactively Assess Real-Time Freeway Crash Risk

Shew

View full text Add to dashboard Cite

Transferability and Robustness of Predictive ModelsTo Assess Real-Time Freeway Crash Risk Cameron Hunter ShewThis thesis describes the development and evaluation of real-time crash risk assessment models for four freeway corridors, US-101 NB (northbound) and SB (southbound) as well as I-880 NB and SB. Crash data for these freeway segments for the 16-month period from January 2010 through April 2011 are used to link historical crash occurrences with real-time traffic patterns observed through loop detector data.The analysis techniques adopted for this study are logistic regression and classification trees, which are one of the most common data mining tools. The crash risk assessment models are developed based on a binary classification approach (crash and non-crash outcomes), with traffic parameters measured at surrounding vehicle detection station (VDS) locations as the independent variables. The classification performance assessment methodology accounts for rarity of crashes compared to non-crash cases in the sample instead of the more common pre-specified thresholdbased classification.Prior to development of the models, some of the data-related issues such as data cleaning and aggregation were addressed. Based on the modeling efforts, it was found that the turbulence in terms of speed variation is significantly associated with crash risk on the US-101 NB corridor. The models estimated with data from US-101 NB were evaluated based on their classification performance, not only on US-101 NB, but also on the other three freeways for transferability assessment. It was found that the predictive model derived from one freeway can be readily applied to other freeways, although the classification performance decreases. The models which transfer best to other roadways were found to be those that use the least number of VDSs-that is, using one upstream and downstream station rather than two or three.The classification accuracy of the models is discussed in terms of how the models can be used for real-time crash risk assessment, which may be helpful to authorities for freeway segments with newly installed traffic surveillance apparatuses, since the real-time crash risk assessment models from nearby freeways with existing infrastructure would be able to provide a reasonable estimate of crash risk. These models can also be applied for developing and testing variable speed limits (VSLs) and ramp metering strategies that proactively attempt to reduce crash risk.The robustness of the model output is assessed by location, time of day and day of week. The analysis shows that on some locations the models may require further learning due to higher than expected false positive (e.g., the I-680/I-280 interchange on US-101 NB) or false negative rates. The approach for post-processing the results from the model provides ideas to refine the model prior to or during the implementation.Keywords: Real-time crash risk, data mining, classification tree, proactive traffic management, loop detector data, transferability, robustness v...

show abstract

“…Disaggregate traffic data have been used in only a limited number of studies (Abdel-Aty et al, 2007;Kockelman and Ma, 2007;Lee et al, 2003Lee et al, , 2002Madanat and Liu, 1995). While detailed vehicle movement data in a section would be the best data source, traffic data from several consecutive detectors in a section can be a good surrogate to identifying traffic dynamics that may lead to accidents (Oh et al, 2001). …”

Section: State Of the Artmentioning

confidence: 99%

“… geometric elements (Garber and Wu, 2001;Karlaftis and Golias, 2002;Knuiman et al, 1993;Lundy, 1965;Miaou et al, 1992;Okamoto and Koshi, 1989;Shankar et al, 1995;Vogt and Bared, 1998;Wong and Nicholson, 1992),  prevailing traffic conditions (Carson and Mannering, 2001;Chang and Chen, 2005;Frantzeskakis and Iordanis, 1987;Garber and Wu, 2001;Hall and Pendleton, 1989;Lave, 1985;Oh and Chang, 1999;Oh et al, 2000),  weather (Chang and Chen, 2005;Fridstrom and Ingebrigtsen, 1989;Ivey et al, 1981;Jovanis and Delleur, 1981),  roadway environment in terms of lighting conditions, warning signs, pavement characteristics, and so on (Carson and Mannering, 2001;Karlaftis and Tarko, 1998;Lee and Mannering, 2002;Martin, 2002, Taylor et al, 2000, and…”

Section: Crash Counts-related Modelsmentioning

confidence: 99%

“…Nowadays, most freeways are equipped with continuous surveillance systems making disaggregate traffic data readily available; these have been used in some studies (Abdel-Aty et al, 2007;Kockelman and Ma, 2007;Lee et al, 2002Lee et al, , 2003Madanat and Liu, 1995). While detailed vehicle movement data in a section would be the best data source, traffic data from several consecutive detectors in a section can be a good surrogate to identifying traffic dynamics that may lead to accidents (Oh et al, 2001). In this chapter we focus on examining the effects of various traffic parameters collected real-time both at -and prior to -the time of the accident on type of crash.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Incident occurrence and response on urban freeways

Christoforou¹

View full text Add to dashboard Cite

Real-Time Estimation of Accident Likelihood for Safety Enhancement

Cited by 105 publications

References 8 publications

Evaluation of Effectiveness of Automated Work Zone Information Systems

Evaluation of Effectiveness of Automated Work Zone Information Systems

Transferability and Robustness of Predictive Models to Proactively Assess Real-Time Freeway Crash Risk

Incident occurrence and response on urban freeways

Contact Info

Product

Resources

About