Application of Neural Networks to Estimate AADT on Low-Volume Roads
Publication: Journal of Transportation Engineering
Volume 127, Issue 5
Abstract
Artificial neural networks are applied as a means of estimating the average annual daily traffic (AADT) volume from short-period traffic counts. Fifty-five automatic traffic recorder sites located on low-volume rural roads in Alberta, Canada are studied. The neural network models used in this study are based on a multilayered, feedforward, and back-propagation design for supervised learning. The AADT estimation errors resulting from various durations and frequencies of counts are analyzed by computing average and percentile errors. The results of this study indicate a clear preference for two 48-h counts as compared to other frequencies (one or three) or durations (24- or 72-h) of counts. In fact, the 95th percentile error values of about 25% for the neural network models compare favorably with the values reported in the literature for low-volume roads using the traditional factor approach. A number of advantages of the neural network approach over the traditional factor approach of AADT estimation are also included in the paper.
Get full access to this article
View all available purchase options and get full access to this article.
References
1.
Albright, D. ( 1991). “An imperative for, and current progress toward national traffic monitoring standards.” Inst. of Transp. Engrs., 61(6), 22–26.
2.
Bodle, R. ( 1967). “Evaluation of rural coverage count duration for estimating annual average daily traffic.” Transp. Res. Rec. 199, Transportation Research Board, Washington, D.C., 67–77.
3.
Davis, G. A. ( 1996). “Estimation theory approaches to monitoring and updating average daily traffic.” Rep. No. 97-05. Center of Transportation Studies, University of Minnesota, Minneapolis.
4.
Davis, G. A. ( 1997). “Accuracy of estimates of mean daily traffic: A review.” Transp. Res. Rec. 1593. Transportation Research Board, Washington, D.C., 12–16.
5.
Dougherty, M. S. ( 1995). “A review of neural networks applied to transportation.” Transp. Res., Part C, 3(4), 247–260.
6.
Garber, N. J., and Hoel, L. A. ( 1999). Traffic and highway engineering, Revised 2nd Ed., West Publishing Co., New York.
7.
Guidelines for traffic monitoring programs. (1992). American Association of State Highway and Transportation Officials, Washington, D.C.
8.
Gulati, B. M. ( 1995). “Precision of AADT estimates from short-period traffic counts.” MASc thesis, University of Regina, Regina, Sask., Canada.
9.
Hecht-Nielsen, R. ( 1990). Neurocomputing, Addison-Wesley, Don Mills, Ont., Canada.
10.
Lawrence, J. ( 1993). Introduction to neural networks: Design, theory and applications, California Scientific Software Press, Nevada City, Calif.
11.
Lingras, P. (1995). “Classifying highways: Hierarchical grouping versus Kohonen neural networks.”J. Transp. Engrg., ASCE, 121(4), 364–368.
12.
Lingras, P., and Sharma, S. C. ( 1997). “Determination of traffic volume parameters using neural networks.” Proc., 5th Int. Conf. on Comp. in Urban Plng. and Mgmt., 16–19.
13.
Oglesby, C. H. ( 1976). “Dilemmas in the administration, planning, design, construction, and maintenance of low-volume roads.” Low-Vol. Roads: Spec. Rep. 160, Transportation Research Board, Washington, D.C.
14.
Petroff, B. ( 1946). “Some criteria for scheduling mechanical traffic counts.” Proc., 26th Annu. Meeting. Highway Research Board, Washington, D.C., 389–396.
15.
Planning manual procedure. (1982). Wisconsin State Department of Transportation, Madison, Wis.
16.
Sharma, S. C., Gulati, B. M., and Rizak, S. N. (1996). “Statewide traffic volume studies and precision of AADT estimates.”J. Transp. Engrg., ASCE, 122(6), 430–439.
17.
Sharma, S. C., Lingras, P., Xu, F., and Liu, G. X. ( 1999). “Neural networks as an alternative to the traditional factor approach of AADT estimation from traffic counts.” Transp. Res. Rec. 1660, Transportation Research Board, Washington, D.C., 24–31.
18.
Swanson, A. H. ( 1994). “Survey of low-volume urban and rural roads.” Inst. of Transp. Engrs., 64(3), 20–22.
19.
Traffic monitoring guide, 3rd Ed. (1995). U.S. Department of Transportation, Federal Highway Administration, Washington, D.C.
20.
Xu, F. ( 1998). “Estimation of annual average daily traffic using the traditional and neural network methods.” MASc thesis, University of Regina, Regina, Sask., Canada.
21.
Zegeer, C. V., Stewart, R., Council, F., and Neuman, T. R. ( 1994). “Chapter 1: Introduction and research approach.” Roadway Widths for Low-Traffic-Vol. Roads: Rep. 362, National Cooperative Highway Research Program, Transportation Research Board, Washington, D.C.
22.
Zell, A., Mamier, G., and Vogt, M. ( 1995). Stuttgart neural network simulator—Version 4.0, Institute for Parallel and Distributed High Performance Systems, University of Stuttgart, Germany.
Information & Authors
Information
Published In
History
Received: Apr 14, 1999
Published online: Oct 1, 2001
Published in print: Oct 2001
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.