Predicting pavement marking retroreflectivity using artificial neural networks: Exploratory analysis

Journal of Transportation Engineering

Volumn 137, Issue 2, 2010, Pages 91-103

  Karwa, Vishesh ^a   Donnell, Eric T ^b  

^a PENNSYLVANIA STATE UNIVERSITY   (United States)

^b The Pennsylvania State University   (United States)

Author keywords

Degradation; Neural networks; North Carolina; Pavement markings; Service life

Indexed keywords

ARTIFICIAL NEURAL NETWORK; DEGRADATION PATTERNS; EXPLORATORY ANALYSIS; INPUT AND OUTPUTS; INPUT VARIABLES; LOCATION INFORMATION; NORTH CAROLINA; PAVEMENT MARKINGS; SURFACE PLOTS; THRESHOLD LEVELS; TRAFFIC FLOW; TRANSPORTATION AGENCIES;

DEGRADATION; HIGHWAY MARKINGS; NEURAL NETWORKS; PAVEMENTS; SERVICE LIFE; TRAFFIC SURVEYS; TRANSPORTATION; VISIBILITY;

ROAD AND STREET MARKINGS;

ARTIFICIAL NEURAL NETWORK; DATA PROCESSING; DEGRADATION; MARKING METHOD; NONLINEARITY; PAVEMENT; PREDICTION; REFLECTIVITY;

NORTH CAROLINA; UNITED STATES;

EID: 78651509637     PISSN: 0733947X     EISSN: None     Source Type: Journal    
DOI: 10.1061/(ASCE)TE.1943-5436.0000194     Document Type: Article

References (46)

1. Alsugair A.M. Sharaf E. A decision support system for pavement maintenance using artificial neural networks technology. Proc., 4th Saudi Engineering Conf. 1995, 2:425-435. and Vol. King Abdulaziz Univ., Jeddah, Saudi Arabia.
2. Amari S. Theory of adaptive pattern classifiers. IEEE Transactions in EC 1967, 16(3):299-307.
3. Amari S. Murata N. Asymptotic statistical theory of overtraining and cross-validation. IEEE Trans. Neural Netw. 1997, 8(5):985-996. ITNNEP, 1045-9227, 10.1109/72.623200, and.
4. Anders U. Korn O. Model selection in neural networks. Neural Networks 1999, 12(2):309-323. NNETEB, 0893-6080, 10.1016/S0893-6080(98)00117-8, and.
5. Andrews R. Diederich J. Tickle A.B. A survey and critique of techniques for extracting rules from trained artificial neural networks. Knowl. Base. Syst. 1995, 8(6):373-389. 10.1016/0950-7051(96)81920-4, 0950-7051, and.
6. Standard test method for measurement of retroreflective pavement marking materials with CEN-prescribed geometry using portable retroreflectometers. 2005, ASTM, E1710-05, West Conshohocken, Pa.
7. Bahar G. Masliah M. Erwin T. Tan E. Hauer E. Pavement marking materials and markers: Real-world relationship between retroreflectivity and safety over time. NCHRP web-only document 92 2006, and Transportation Research Board, Washington, D.C.
8. Bishop C.M. Neural networks for pattern recognition 1995, Oxford University Press, New York.
9. Buntine W.L. Weigend A.S. Computing second derivatives in feed-forward networks: A review. IEEE Trans. Neural Netw. 1994, 5(3):480-488. ITNNEP, 1045-9227, 10.1109/72.286919, and.
10. Carlson P.J. Park E.S. Andersen C.K. The benefits of pavement markings: A renewed perspective based on recent and ongoing research. 2009, 59-68. and Transportation Research Record.2107, Transportation Research Board of the National Academies, Washington, D.C.
11. Caruana R. Lawrence S. Giles L. Overfitting in neutral nets: Back-propagation, conjugate gradient and early stopping. Advances in Neural Information Processing Systems 2001, 13:402-408. and.
12. Cheng B. Titterington D.M. Neural networks: A review from a statistical perspective. Stat. Sci. 1994, 9(1):2-30. STSCEP, 0883-4237, 10.1214/ss/1177010638, and.
13. Council F.M. Patel R. Mohamedshah Y. Highway Safety Information System guidebook for the North Carolina state data files 2006, and Federal Highway Administration, Washington, D.C.
14. Craven M. Extracting comprehensible models from trained neural networks. 1996, Ph.D. thesis, Univ. of Wisconsin, Madison, Wis.
15. Cybenko G. Approximation by superpositions of a sigmoid function. Math. Control, Signals, Syst. 1989, 2(4):303-314. ZZZZZZ, 0932-4194, 10.1007/BF02551274.
16. Deballion C. Carlson P. He Y. Schnell T. Aktan F. Updates to research on recommended minimum levels for pavement marking retroreflectivity to meet driver night visibility needs. 2007, and Rep. No.FHWA-HRT-07-059, Federal Highway Administration, McLean, Va.
17. Efron B. Tibshirani R. An introduction to the bootstrap 1997, and Chapman and Hall/CRC Press, Boca Raton, Fla.
18. Faghri A. Hua J. Evaluation of artificial neural network applications in transportation engineering. 1991, 71-80. and Transportation Research Record.1358, Transportation Research Board, Washington, D.C.
19. Flood I. Kartam N. Neural networks in civil engineering. I: Principles and understanding. J. Comput. Civ. Eng. 1994, 8(2):131-148. JCCEE5, 0887-3801, 10.1061/(ASCE)0887-3801(1994)8:2(131), and.
20. Fogel D.B. An information criterion for optimal neural network selection. IEEE Trans. Neural Netw. 1991, 2(5):490-497. ITNNEP, 1045-9227, 10.1109/72.134286.
21. Funahashi K. On the approximate realization of continuous mappings by neural networks. Neural Networks 1989, 2(3):183-192. NNETEB, 0893-6080, 10.1016/0893-6080(89)90003-8.
22. Guha R. Stanton D.T. Jurs C.P. Interpreting computational neural network quantitative structure-activity relationship models: A detailed interpretation of the weights and biases. J. Chem. Inf. Model. 2005, 45(4):1109-1121. ZZZZZZ, 1549-9596, 10.1021/ci050110v, and.
23. Hawkins H.G. Parham A. Womack K.N. Feasibility study for an all-white pavement marking system. 2002, and NCHRP Rep. No.484, Transportation Research Board, Washington, D.C.
24. Hecht-Neilson R. Theory of the back-propagation neural networks. Proc., Int. Joint Conf. on Neural Networks 1989, 593-606. IEEE, New York.
25. Ishak S. Al-Deek H. Performance of automatic ANN-based incident detection on freeways. J. Transp. Eng. 1999, 125(4):281-290. JTPEDI, 0733-947X, 10.1061/(ASCE)0733-947X(1999)125:4(281), and.
26. Kennedy P. guide to econometrics 2003, 5th Ed., MIT Press, Cambridge, Mass.
27. Kopf J. Reflectivity of pavement markings: Analysis of retroreflectivity degradation curves. 2004, Rep. No.WA-RD 592.1, Univ. of Washington, Seattle.
28. Kůrková V. Kolmogorov's theorem and multilayer neural networks. Neural Networks 1992, 5(3):501-506. NNETEB, 0893-6080, 10.1016/0893-6080(92)90012-8.
29. Lapedes A. Farber R. How neural nets work. Neural information processing systems 1988, 442-456. D. Z. Anderson, and ed., American Institute of Physics, New York.
30. Lindly J.K. Wijesundera R.K. Evaluation of profiled pavement markings. 2003, and Rep. No.UTCA 01465, Univ. Transportation Center for Alabama, Tuscaloosa, Ala.
31. Maren A.J. Jones D. Franklin S. Configuring and optimizing the back-propagation network. Handbook of neural computing applications 1990, and Academic, San Diego.
32. Migletz J. Graham J.L. Harwood D.W. Bauer K.M. Service life of durable pavement markings. 2001, 13-21. and Transportation Research Record.1749, Transportation Research Board, Washington, D.C.
33. Morgan N. Bourlard H. Generalization and parameter estimation in feedforward nets: Some experiments. Advances in neural information processing systems 2 1990, 630-637. D. S. Touretzky, and ed., San Mateo, Calif.
34. Murata N. Yoshizawa S. Amari S. Network information criterion-determining the number of hidden units for an artificial neural network model. IEEE Trans. Neural Netw. 1994, 5(6):865-872. ITNNEP, 1045-9227, 10.1109/72.329683, and.
35. Specifications and special provisions. Pavement marking general requirements 2006, North Carolina DOT, Raleigh, N.C.
36. Rumelhart D.E. Hinton G.E. Williams R.J. Learning internal representations by error propagation. Parallel distributed processing: Explorations of microstructure 1986, 1:318-362. and Vol.
37. Saad E.W. Wunsch D.C. Neural network explanation using inversion. Neural Networks 2007, 20(1):78-93. NNETEB, 0893-6080, 10.1016/j.neunet.2006.07.005, and.
38. Sarasua W.A. Clarke D.B. Davis W.J. Evaluation of interstate pavement marking retroreflectivity. 2003, and Rep. No.FHWA-SC-03-01, Clemson Univ., Clemson, S.C.
39. Sarle W.S. Neural networks and statistical models. Proc., 19th Annual SAS Users Group Int. Conf. 1994, 1538-1550. SAS Institute, Cary, N.C.
40. Sarle W.S. Stopped training and other remedies for overfitting. Proc., 27th Symp. on Interface of Computing Science and Statistics 1995, 352-360. Interface Foundation of North America, Pittsburgh, P.A.
41. Sathyanarayanan S. Shankar V.N. Donnell E.T. Pavement marking retroreflectivity inspection data: A Weibull analysis. 2008, 63-70. and Transportation Research Record.2055, Transportation Research Board, Washington, D.C.
42. Sayed T. Tavakolie A. Razavi A. Comparison of adaptive network based fuzzy inference systems and B-spline neuro-fuzzy mode choice models. J. Comput. Civ. Eng. 2003, 17(2):123-130. JCCEE5, 0887-3801, 10.1061/(ASCE)0887-3801(2003)17:2(123), and.
43. Smith M. Neural networks for statistical modeling 1993, Van Nostrand Reinhold, New York.
44. Taylor D.R. Muthiah S. Kulakowski B.T. Mahoney K.M. Porter R.J. Artificial neural network speed profile model for construction work zones on high-speed highways. J. Transp. Eng. 2007, 133(3):198-204. JTPEDI, 0733-947X, 10.1061/(ASCE)0733-947X(2007)133:3(198), and.
45. Veaux R.D. Schumi J. Schweinsberg J. Shellington D. Ungar L.H. Prediction intervals for neural networks via nonlinear regression. J. Am. Stat. Assoc. 1998, 40(4):273-282. JSTNAL, 0003-1291, and.
46. Zhang Y. Wu D. Development of methodologies to predict service lives of pavement marking materials. J. of the Trans. Res. Forum 2006, 45(3):5-18. and.