Decision-Making System for Freeway Incident Response Using Sequential Hypothesis Testing Methods

Madanat, Samer; Cassidy, Michael J.; Teng, Hua Liang; Liu, Pen Chi

doi:10.3141/1554-27

Cited by 4 publications

(2 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some literature was found on modeling of crashes on freeways. A study by Madanat et al used binary logit models to predict the likelihood of vehicle crash incidents on the Borman Expressway (5). Studies conducted by Zeeger et al (6) and Cleveland and Kitamura (7) investigated the relationships between accident frequency, roadway geometry, and roadside conditions.…”

Section: Literature Reviewmentioning

confidence: 99%

Safety Models for Rural Freeway Work Zones

Venugopal

Tarko

2000

Transportation Research Record: Journal of the Transportation R

View full text Add to dashboard Cite

Construction and maintenance work zones have traditionally been hazardous locations within the highway environment. Studies show that the accident rates during road construction are generally higher than during periods of regular traffic operations. The increase in the number of crashes may be attributed to ( a) general disruption to the flowing traffic due to sudden discontinuities caused by closed lanes, ( b) improper lane merging maneuvers, ( c) the presence of heavy construction equipment within the work area, ( d) inappropriate use of traffic control devices, and ( e) poor traffic management. Research was conducted to develop regression models predicting the expected number of crashes at work zones on rural, two-lane freeway segments. Crashes on approaches to work zones and those inside the work zones were analyzed separately. For developing these models, an extensive database was obtained, including freeway data, crash data, and work zone characteristics. Negative binomial models were developed with average daily traffic, the length of the work zones, and the duration of the work projects as exposure-to-risk variables. The cost of the various work projects was found to be a good substitute for some of the exposure-to-risk variables. The investigated variables included the number of on and off ramps, both on approaches and inside the work zones; the type of work; and the intensity of the road work involved. The models may be used to evaluate beforehand the expected number of crashes on the work zone, given the work zone characteristics.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Safety Models for Rural Freeway Work Zones

Venugopal

Tarko

2000

Transportation Research Record: Journal of the Transportation R

View full text Add to dashboard Cite

show abstract

“…Second, occupancies are assumed to follow a Normal distribution. This assumption can make feasible the derivation of a closed-form formula of decision function, and it is generally considered reasonable (17 ). Third, the variance of the difference in the upstream and downstream occupancies before and after incidents is assumed to be the same.…”

Section: Timementioning

confidence: 99%

Developed Incident Detection Algorithm Compared with Neural Network Algorithms

Teng

Martinelli

2003

Transportation Research Record: Journal of the Transportation R

View full text Add to dashboard Cite

The CUSUM (cumulative sum of log-likelihood ratio) algorithm is an optimization-based algorithm that is attractive for many applications because it can minimize detection delay and can explicitly incorporate the characteristics of processes before and after changes. One such application is freeway incident detection, where field-measurable traffic-flow parameters are used to flag incidents in real time in an expedient and reliable manner. In the presented study, the special characteristics of traffic processes associated with incidents are incorporated into the CUSUM algorithm for freeway incident detection. In the algorithm evaluation, the most recently developed neural networks are compared with an enhanced CUSUM algorithm. The neural network algorithms are systematically evaluated first among themselves, and then the best of them is compared with the CUSUM algorithm. The results demonstrate that the CUSUM incident detection algorithm can perform better than the neural network algorithms. The neural network algorithm may show inferior performance because it cannot adjust its decision threshold in real time.

show abstract

Establishing a link between multiple-sensor outputs and non-deterministic decision-making

El-Mahassni

2010

2010 Sixth International Conference on Intelligent Sensors, Sensor Networks and Information Processing

View full text Add to dashboard Cite

Decision-Making System for Freeway Incident Response Using Sequential Hypothesis Testing Methods

Cited by 4 publications

References 5 publications

Safety Models for Rural Freeway Work Zones

Safety Models for Rural Freeway Work Zones

Developed Incident Detection Algorithm Compared with Neural Network Algorithms

Establishing a link between multiple-sensor outputs and non-deterministic decision-making

Contact Info

Product

Resources

About