Optimizing Freeway Traffic Sensor Locations by Clustering Global-Positioning-System-Derived Speed Patterns

Kianfar, Jalil; Edara, Praveen

doi:10.1109/tits.2010.2051329

Cited by 37 publications

(16 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Count‐based methods mainly address those applications, such as origin–destination (O–D) estimation , freeway bottleneck identification , and freeway incident detection . Travel time estimates always require data from speed‐based methods.…”

Section: Introductionmentioning

confidence: 99%

Analysis of factors that influence the sensor location problem for freeway corridors

Dong

Jia

et al. 2013

J of Advced Transportation

View full text Add to dashboard Cite

SUMMARYThe use of traffic sensors to acquire real-time traffic information for intelligent transportation systems is becoming increasingly common. It is a challenge to determine where these sensors should be located to maximize the benefit of their use. This paper aims to illuminate the interaction of the sensor location problem (SLP) and its influencing factors, and to reveal the influencing mechanisms between those factors and the optimal sensor numbers. Firstly, we sum up the factors that influence the SLP for freeway corridors in detail and present the mathematical formulation of each factor. Then, given the parameters, which are derived from those influencing factors, the maximum integration value model (MIVM) and simplified MIVM are proposed for addressing the SLP. Finally, a real world case study, in which the simplified MIVM is used, is presented to illustrate how these factors influence the optimal sensor numbers and the maximum integration value, and also leads to the typical influencing patterns of those factors for freeway corridors. The results of the case study also demonstrate the effectiveness of the model and problem solving scheme. What is more, the suggestions for using the findings hereof in practical applications are put forward.

show abstract

Section: Introductionmentioning

confidence: 99%

Analysis of factors that influence the sensor location problem for freeway corridors

Dong

Jia

et al. 2013

J of Advced Transportation

View full text Add to dashboard Cite

show abstract

“…Among these works, Kianfar et al [7] proposed optimizing traffic sensor locations for freeway bottleneck identification. Gupta et al [10] stated there is a minimum number of sensors required for the desired level of coverage and connectivity, assuming sensors are stochastically deployed along the roadsides.…”

Section: Related Workmentioning

confidence: 99%

“…For cost efficiency and flexibility, it is rarely practical to equip all these on-road sensors with cables or fibers, so wireless sensors enjoy a boost in type and quantity. Therefore, a typical On-Road Sensor Network (ORSN) is formed by a majority of wireless sensors communicating through radio links and certain sensors serving as data collectors and relaying collected data to a remote data center through radio or cable/fiber [7]. It boasts properties like flexible and easy deployment, two-way communication, and is distinguished from regular wireless sensor networks by its linear-like topology [8].…”

Section: Introductionmentioning

confidence: 99%

A Fault Tolerance Mechanism for On-Road Sensor Networks

Feng

Guo

Sun

et al. 2016

Sensors

View full text Add to dashboard Cite

On-Road Sensor Networks (ORSNs) play an important role in capturing traffic flow data for predicting short-term traffic patterns, driving assistance and self-driving vehicles. However, this kind of network is prone to large-scale communication failure if a few sensors physically fail. In this paper, to ensure that the network works normally, an effective fault-tolerance mechanism for ORSNs which mainly consists of backup on-road sensor deployment, redundant cluster head deployment and an adaptive failure detection and recovery method is proposed. Firstly, based on the N − x principle and the sensors’ failure rate, this paper formulates the backup sensor deployment problem in the form of a two-objective optimization, which explains the trade-off between the cost and fault resumption. In consideration of improving the network resilience further, this paper introduces a redundant cluster head deployment model according to the coverage constraint. Then a common solving method combining integer-continuing and sequential quadratic programming is explored to determine the optimal location of these two deployment problems. Moreover, an Adaptive Detection and Resume (ADR) protocol is deigned to recover the system communication through route and cluster adjustment if there is a backup on-road sensor mismatch. The final experiments show that our proposed mechanism can achieve an average 90% recovery rate and reduce the average number of failed sensors at most by 35.7%.

show abstract

“…Melo et al (2006) applied the semi-supervised K-Means clustering technique to classify highway lanes. Kianfar and Edara (2010) used it to optimize sensor locations on freeways by clustering speed and travel-time data obtained from the GPS-equipped probe vehicles. Wang et al (2013) incorporated it into the Delphi method to categorize the level-of-service for Beijing's urban expressways.…”

Section: Literature Reviewmentioning

confidence: 99%

Real-time identification of probe vehicle trajectories in the mixed traffic corridor

Tang

2015

Transportation Research Part C: Emerging Technologies

View full text Add to dashboard Cite

Optimizing Freeway Traffic Sensor Locations by Clustering Global-Positioning-System-Derived Speed Patterns

Cited by 37 publications

References 20 publications

Analysis of factors that influence the sensor location problem for freeway corridors

Analysis of factors that influence the sensor location problem for freeway corridors

A Fault Tolerance Mechanism for On-Road Sensor Networks

Real-time identification of probe vehicle trajectories in the mixed traffic corridor

Contact Info

Product

Resources

About