01334306

Component

Computer algorithms used to identify recurrent bottlenecks have been studied since the wide deployment of loop detecting systems in the US. Such algorithms automatically analyze the archived loop detector data, and identify potential recurrent bottleneck and their characteristics such as activation rate, location, time of day, for further investigation. In a highway congestion mitigation project, such automatic algorithms can save a lot of resources and labor hours for initial screening of bottlenecks on a large freeway network, when compared with traditional driving and traffic video inspection methods. Representative bottleneck identification algorithms include Chen's, Ban's and Jin's algorithms. From practitioners' point of view, it is necessary to understand the strengths and conditions of these algorithms against real-world loop detector data with quality issues. However, the lack of effective evaluation method makes such analysis difficult. In this paper, a new evaluation method is proposed based on a novel set of indexes defined on the spatial-temporal diagram. With these indexes, Chen's, Ban's and Jin's algorithms are calibrated and evaluated using field data for two freeway corridors (US 12/14 and I-894) in the State of Wisconsin, USA. Ground truth data for this study come from the manual inspection of 287,055 traffic video snapshots. The 5-min loop detector data are used as inputs to all three algorithms. The evaluation results show different characteristics of tested algorithms against noisy loop data. Chen's method cannot handle detector data noises effectively, while Ban's method and Jin's method have some capabilities to reduce the impact of some data quality issues of loop detectors. In addition, a simple speed cleaning method is proposed for Chen's and Ban's algorithms and its effectiveness is also evaluated in this study. The paper is concluded by summarizing the characteristics of each algorithm, limitations of this evaluation study and future work.

01329018

11-3965

English

17p

2011

Transportation Research Board 90th Annual Meeting

DVD

Figures; Photos; References (22) ; Tables (1)

Algorithms; Bottlenecks; Data quality; Detection and identification; Loop detectors; Planning; Traffic congestion; Traffic surveillance; Video cameras

Real world data

Wisconsin

Highways; Operations and Traffic Management; Planning and Forecasting; I72: Traffic and Transport Planning

Transportation Research Board Annual Meeting 2011 Paper #11-3965

TRIS, TRB

Feb 17 2011 6:42PM