TRIS Online Record

Printable View

Title	Exploring the Relationship Between Data Aggregation and Predictability to Provide Better Predictive Traffic Information
Accession No	01023231
Authors	Oh, Cheol ; Ritchie, Stephen G ; Oh, Jun-Seok
Journal Title	Transportation Research Record: Journal of the Transportation Research Board No. 1935
Corp. Authors / Publisher	Transportation Research Board
Publication Date	20050000
Description	pp 28-36; Figures(6); References(38); Tables(3)
Media Type	Print
Languages	English
Abstract	Providing reliable predictive traffic information is a crucial element for successful operation of intelligent transportation systems. However, there are difficulties in providing accurate predictions mainly because of limitations in processing data associated with existing traffic surveillance systems and the lack of suitable prediction techniques. This study examines different aggregation intervals to characterize various levels of traffic dynamic representations and to investigate their effects on prediction accuracy. The relationship between data aggregation and predictability is explored by predicting travel times obtained from the inductive signature–based vehicle reidentification system on the I-405 freeway detector test bed in Irvine, California. For travel time prediction, this study employs three techniques: adaptive exponential smoothing, adaptive autoregressive model using Kalman filtering, and recurrent neural network with genetically optimized parameters. Finally, findings are discussed on suggestions for applying prediction techniques effectively.
TRT Terms	Accuracy ; Kalman filtering ; Mathematical prediction ; Neural networks ; Test beds ; Travel time
Geographical Terms	Irvine (California)
Other Terms	Adaptive autoregressive models; Adaptive exponential smoothing; Data aggregation
Subject Areas	H12 PLANNING; I72 Traffic and Transport Planning
ISBN	0309094097
Availability	Transportation Research Board Business Office Order Document: http://trb.org/news/blurb_detail.asp?id=6233 Find a library where document is available Order Document: http://worldcat.org/isbn/0309094097
TRIS Files	HRIS
Database	TRIS Online

TRIS is a bibliographic database funded by sponsors of the Transportation Research Board (TRB), primarily the state departments of transportation and selected federal transportation agencies. TRIS Online is hosted by the National Transportation Library under a cooperative agreement between the Bureau of Transportation Statistics and TRB.