Performance of Automatic ANN-Based Incident Detection on Freeways
Publication: Journal of Transportation Engineering
Volume 125, Issue 4
Abstract
Automatic incident detection on freeways is an essential ingredient for the successful deployment of Intelligent Transportation Systems. Several incident detection algorithms have been developed in the past three decades; however, most of them have not shown the anticipated performance in terms of detection rate and false alarm rate. Recently, the artificial neural networks (ANN) have been introduced to incident detection and shown success over the traditional algorithms. This study explores the application of two neural network models, namely, the Multi-Layer Feed-Forward and the Fuzzy ART algorithm. This study was conducted on the central corridor of I-4 in Orlando using real-world data collected via the traffic surveillance system. Different scenarios were considered to improve the performance and to capture the sensitivity of the developed algorithms to some factors. The study results showed that the Fuzzy ART algorithm has generally outperformed the Multi-Layer Feed-Forward network and California algorithms #7 and #8.
Get full access to this article
View all available purchase options and get full access to this article.
References
1.
Ahmed, S. R., and Cook, A. R. (1982). “Application of time-series analysis techniques to freeway incident detection.” Transp. Res. Rec. 841, Transportation Research Board, Washington, D.C., 19–21.
2.
Al-Deek, H. M., Ishak, S. S., and Khan, A. A. (1996). “Impact of freeway geometric and incident characteristics on incident detection.”J. Transp. Engrg., ASCE, 122(6), 440–446.
3.
Camargo, F. A. ( 1990). “Learning algorithms in neural networks.” DCC Lab., Dept. of Comp. Sci., Columbia University, New York.
4.
Carpenter, G., Grossberg, S., and Rosen, D. (1991). “Fast stable learning and categorization of analog patterns by an adaptive resonance system.” Neural Networks, 4, 759–771.
5.
Cheu, R. L. ( 1994). “Neural network models for automated detection of lane-blocking incidents on freeways,” PhD dissertation, University of California at Irvine, Irvine, Calif.
6.
Collins, J. F. (1983). “Automatic incident detection—Experience with TRRL algorithm HIOCC.” Supplementary Rep. No. 775, Department of the Environment, U.S. Department of Transportation, Washington, D.C.
7.
Collins, J. F., Hopkins, C. M., and Martin, J. A. (1979). “Automatic incident detection—TRRL algorithms HIOCC and PATREG.” Supplementary Rep. No. 526, Department of the Environment, U.S. Department of Transportation, Washington, D.C.
8.
Dia, H., and Rose, G. (1995). “Development of artificial neural network models for automated detection of freeway incidents.” Proc., WCTR '95, 7th World Conf. on Transport Res.
9.
Dia, H., and Rose, G. (1997). “Development and evaluation of neural network freeway incident detection models using field data.” Transp. Res.-C, 5(5), 313–331.
10.
Dia, H., Rose, G., and Snell, A. (1996). “Comparative performance of freeway automated incident detection algorithms.” Proc., Joint 18th ARRB Transport Res. Conf. and Transit NZ Land Transport Symp.
11.
Forbes, J. F. (1992). “Identifying incident congestion.” ITE J., 17–22.
12.
Gall, A., and Hall, F. (1990). “Distinguishing between incident congestion and recurrent congestion: A proposed logic.” Transp. Res. Rec. 1232, Transportation Research Board, Washington, D.C., 1–8.
13.
Hall, F. Y., Shi, and Atala, G. (1993). On-line testing of the McMaster incident detection algorithm under recurrent congestion.” Proc., 72nd Annu. Meeting of the Transp. Res. Board, Washington, D.C.
14.
Hassoum, M. (1995). Fundamentals of artificial neural networks. MIT Press, Cambridge, Mass.
15.
Haykin, S. (1994). Neural networks a comprehensive foundation, McMillan College Publishing Co., New York.
16.
Hsiao, C. H., Lin, C. T., and Cassidy, M. (1993). “An application of fuzzy set theory to incident detection.” Proc., 72nd Annu. Meeting of the Transp. Res. Board, Washington, D.C.
17.
Hsiao, C. H., Lin, C. T., and Cassidy, M. (1994). “Application of fuzzy logic and neural networks to automatically detect freeway traffic incidents.”J. Transp. Engrg., ASCE, 120(5).
18.
Huang, J., Georgiopoulos, M., and Heileman, G. L. (1995). “Fuzzy ART properties.” Neural Networks, 8(2), 203–213.
19.
Ishak, S. S. ( 1998). “Application of artificial neural networks to automatic freeway incident detection,” PhD dissertation, University of Central Florida, Orlando, Fla.
20.
Ishak, S., and Al-Deek, H. (1998). “Applying fuzzy ART to freeway incident detection.” Transp. Res. Rec., Transportation Research Board, Washington, D.C., in press.
21.
Kasabov, N. K. (1996). Foundations of neural networks, fuzzy systems, and knowledge engineering. MIT Press, Cambridge, Mass.
22.
Khan, R. (1972). “Interim report on incident detection logics for the Los Angeles Freeway surveillance and control project.” Rep. for California Department of Transportation, Sacramento, Calif.
23.
Levin, M., and Krause, G. (1979a). “Incident-detection algorithms, Part 1. Off-line evaluation.” Transp. Res. Rec. 722, Transportation Research Board, Washington, D.C., 49–58.
24.
Levin, M., and Krause, G. (1979b). “Incident-detection algorithms, Part 2. On-line evaluation.” Transp. Res. Rec. 722, Transportation Research Board, Washington, D.C., 58–64.
25.
Payne, H. (1976). “Development and testing of incident-detection algorithms: Vol. 1, Summary of results.” Rep. No. FHWA-RD-76-19, Fed. Hwy. Admin., U.S. Department of Transportation, Washington, D.C.
26.
Payne, H., Helfenbein, E., and Knobel, H. (1976). “Development and testing of incident-detection algorithms: Vol. 2, Research methodology and detailed results.” Rep. No. FHWA-RD-76-20, Fed. Hwy. Admin., U.S. Department of Transportation, Washington, D.C.
27.
Payne, H., and Tignor, S. (1978). “Freeway incident detection algorithms based on decision trees with states.” Transp. Res. Rec. 682, Transportation Research Board, Washington, D.C., 30–37.
28.
Persaud, B., and Hall, F. ( 1988). “The McMaster single station algorithm for detection of freeway incidents,” Working paper, Dept. of Civil Engineering, McMaster University.
29.
Persaud, B., and Hall, F. (1989). “Catastrophe theory and patterns in 30-second freeway traffic data—Implications for incident detection.” Transp. Res.-A, 23A(2), 103–113.
30.
Ritchie, S., and Ruey, L. C. (1993). “Simulation of freeway incident detection using artificial neural networks.” Transp. Res.-C, 1(3), 203–217.
31.
Rose, G., and Dia, H. (1995). “Freeway automatic incident detection using artificial neural networks.” Proc., Application of New Technol. to Transport Sys. Int. Conf.
32.
Ruey, C., and Ritchie, S. (1995). “Automated detection of lane-blocking freeway incidents using artificial neural networks.” Transp. Res.-C, 3(6), 371–388.
33.
Stephanedes, Y. J., and Athanassios, P. C. (1993). “Freeway incident detection through filtering.” Transp. Res.-C, 1(3), 219–233.
34.
Stephanedes, Y. J., and Chassiakos, A. P. (1993). “Applications of filtering techniques for incident detection.”J. Transp. Engrg., ASCE, 119(1).
35.
Tignor, S., and Payne, H. (1977). “Improved freeway incident-detection algorithms.” Public Roads, 32–40.
36.
Willsky, A. S., Chow, E. Y., Gershwin, S. B., Greene, C. S., Houpt, P. T., and Kurkjian, A. L. (1980). “Dynamic model-based techniques for the detection of incidents on freeways.” IEEE Trans. Autom. Control, 25, 347–360.
Information & Authors
Information
Published In
Journal of Transportation Engineering
Volume 125 • Issue 4 • July 1999
Pages: 281 - 290
History
Received: Aug 17, 1998
Published online: Jul 1, 1999
Published in print: Jul 1999
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.