The pavement performance model is a basic part of the pavement management system. The prediction accuracy of the model depends on the number of effective variables and the type of mathematical method that is used for modeling the pavement performance. In this paper, the capability of the support vector machine (SVM) method is analyzed for predicting the future of the pavement condition. Five kernel types of SVM algorithm are formed and nine input variables of the proposed models are extracted from the range of effective variables on the pavement condition. The international roughness index is used as the pavement performance index. The results show that the Pearson VII Universal kernel can accurately predict pavement performance in its life cycle.
Get full access to this article
View all access options for this article.
References
1.
TerziS.Modeling for Pavement Roughness Using the ANFIS Approach. Advances in Engineering Software, Vol. 57, 2013, pp. 59–64.
2.
KaranM., HaasR., and WalkerT.. Illustration of Pavement Management: From Data Inventory to Priority Analysis. In Transportation Research Record 814, TRB, National Research Council, Washington, D.C., 1981, pp. 22–28.
3.
WoltersA., ZimmermanK., SchattlerK., and RietgrafA.. Implementing Pavement Management Systems for Local Agencies. Report ICT-11-094. Illinois Center for Transportation, Rantoul, 2011.
4.
BianchiniA., and BandiniP.. Prediction of Pavement Performance Through Neuro-Fuzzy Reasoning. Computer-Aided Civil and Infrastructure Engineering, Vol. 25, No. 1, 2010, pp. 39–54.
5.
YangJ., LuJ. J., GunaratneM., and XiangQ.. Forecasting Overall Pavement Condition Forecasting Using Neural Networks: Application on Florida Highway Network. In Transportation Research Record: Journal of the Transportation Research Board, No. 1853, Transportation Research Board of the National Academies, Washington, D.C., 2003, pp. 3–12.
ShahinM. Y.Pavement Management for Airports, Roads, and Parking Lots. Springer, New York, 2005.
8.
IsmailN., IsmailA., and AtiqR.. An Overview of Expert Systems in Pavement Management. European Journal of Scientific Research, Vol. 30, No. 1, 2009, pp. 99–111.
9.
ProzziJ. A.Modeling Pavement Performance by Combining Field and Experimental Data. University of California Transportation Center, Berkeley, 2001.
10.
Attoh-OkineN. O.Predicting Roughness Progression in Flexible Pavements Using Artificial Neural Networks. In Proceedings of the Third International Conference on Managing Pavements, Vol. 1, TRB, National Research Council, Washington, D.C., 1994, pp. 55–62.
11.
HaasR., HudsonW. R., and ZaniewskiJ. P.. Modern Pavement Management. Krieger Publishing Company, Malabar, Fla., 1994.
12.
BrotenM.Local Agency Pavement Management Application Guide. Washington State Department of Transportation, Olympia, 1997.
13.
SabaR. G., HuvstigA., HildebrandG., SundE., EvensenR., SigursteinssonH., and ElsanderJ.. Performance Prediction Models for Flexible Pavements: A State-of-the-Art Report. Report 2477. Norwegian Public Roads Administration, Oslo, Norway, 2006.
14.
MolenaarA. A.Pavement Performance Evaluation and Rehabilitation Design. In Proceedings of the 3rd International Symposium on Maintenance and Rehabilitation of Pavements and Technological Control, University of Minho, Guimaraes, Portugal, 2003.
15.
PanN.-F., KoC.-H., YangM.-D., and HsuK.-C.. Pavement Performance Prediction Through Fuzzy Regression. Expert Systems with Applications, Vol. 38, No. 8, 2011, pp. 10010–10017.
16.
GeorgeK. P., RajagopalA. S., and LimL. K.. Models for Predicting Pavement Deterioration. In Transportation Research Record 1215, TRB, National Research Council, Washington, D.C., 1989, pp. 1–7.
17.
MadanatS., and IbrahimW. H. W.. Poisson Regression Models of Infrastructure Transition Probabilities. Journal of Transportation Engineering, Vol. 121, No. 3, 1995, pp. 267–272.
18.
ProzziJ. A., and HongF.. Transportation Infrastructure Performance Modeling Through Seemingly Unrelated Regression Systems. Journal of Infrastructure Systems, Vol. 14, No. 2, 2008, pp. 129–137.
19.
YuJ., ChouE. Y., and LuoZ.. Development of Linear Mixed Effects Models for Predicting Individual Pavement Conditions. Journal of Transportation Engineering, Vol. 133, No. 6, 2007, pp. 347–354.
20.
ButtA. A., ShahinM. Y., FeighanK. J., and CarpenterS. H.. Pavement Performance Prediction Model Using the Markov Process. In Transportation Research Record 1123, TRB, National Research Council, Washington, D.C., 1987, pp. 12–19.
21.
JiangY., SaitoM., and SinhaK. C.. Bridge Performance Prediction Model Using the Markov Chain. In Transportation Research Record 1180, TRB, National Research Council, Washington, D.C., 1988, pp. 25–32.
22.
YangJ., GunaratneM., LuJ. J., and DietrichB.. Use of Recurrent Markov Chains for Modeling the Crack Performance of Flexible Pavements. Journal of Transportation Engineering, Vol. 131, No. 11, 2005, pp. 861–872.
23.
ZiariH., SobhaniJ., AyoubinejadJ., and HartmannT.. Prediction of IRI in Short and Long Terms for Flexible Pavements: ANN and GMDH Methods. International Journal of Pavement Engineering, Vol. 17, No. 9, 2016, pp. 776–788.
24.
FwaT. F., and ChanW. T.. Priority Rating of Highway Maintenance Needs by Neural Networks. Journal of Transportation Engineering, Vol. 119, No. 3, 1993, pp. 419–432.
25.
AlsugairA., and Al-QudrahA.. Artificial Neural Network Approach for Pavement Maintenance. Journal of Computing in Civil Engineering, Vol. 12, No. 4, 1998, pp. 249–255.
26.
QianW.-D.Road Pavement Performance Evaluation Model Based on Hybrid Genetic Algorithm Neural Network. In Proceedings of the Second International Conference on Computational Intelligence and Natural Computing, IEEE, Piscataway, N.J., 2010, pp. 209–212.
27.
Attoh-OkineN. O.Analysis of Learning Rate and Momentum Term in Back Propagation Neural Network Algorithm Trained to Predict Pavement Performance. Journal of Advances in Engineering Software, Vol. 30, 1999, pp. 291–302.
28.
ChouE., PulugurtaH., and DattaD.. Pavement Forecasting Models. Ohio Department of Transportation, Columbus, 2008.
29.
MaghrebiM., SammutC., and WallerS. T.. Predicting the Duration of Concrete Operations via Artificial Neural Network and by Focusing on Supply Chain Parameters. Building Research Journal, Vol. 61, No. 1, 2014, pp. 1–14.
30.
MaghrebiM., SammutC., and WallerT.. Reconstruction of an Expert’s Decision Making Expertise in Concrete Dispatching by Machine Learning. Journal of Civil Engineering and Architecture, Vol. 7, No. 12, 2013, pp. 1540–1547.
31.
MaghrebiM., and WallerS. T.. Exploring Experts Decisions in Concrete Delivery Dispatching Systems Using Bayesian Network Learning Techniques. In Proceedings of the 2nd International Conference on Artificial Intelligence, Modelling and Simulation, IEEE, Piscataway, N.J., 2014. pp. 103–108.
32.
MaghrebiM., WallerS. T., and SammutC.. Feasibility Study of Automatically Performing the Concrete Delivery Dispatching by Implementing Machine Learning Techniques. Engineering, Construction and Architectural Management, Vol. 22, No. 5, 2015, pp. 573–590.
33.
MaghrebiM., WallerS. T., and SammutC.. Reconstruction of an Expert’s Decision Making Expertise in Concrete Dispatching by Machine Learning. Journal of Civil Engineering and Architecture, Vol. 7, No. 12, 2013, pp. 1540–1547.
34.
GhasriM., RashidiT. H., and WallerS. T.. A Novel System of Disaggregate Models for Travel Demand Modelling, Using Decision Tree and Random Forest Concepts. Presented at 94th Annual Meeting of the Transportation Research Board, Washington, D.C., 2015.
35.
MaghrebiM., ShamsoddiniA., and WallerS. T.. Machine Learning Fusion Based Technique for Predicting the Concrete Pouring Production Rate Based on Traffic and Supply Chain Parameters. Presented at 94th Annual Meeting of the Transportation Research Board, Washington, D.C., 2015.
36.
MaghrebiM., WallerS. T., and SammutC.. Text Mining Approach for Reviewing the Ready Mixed Concrete Literature. Presented at 2nd International Conference on Civil and Building Engineering Informatics, Tokyo, 2015.
37.
YanK.-Z., and ZhangZ.. Research in Analysis of Asphalt Pavement Performance Evaluation Based on PSO-SVM. Applied Mechanics and Materials, Vol. 97–98, 2011, pp. 203–207.
38.
GopalakrishnanK., and KimS.. Support Vector Machines for Nonlinear Pavement Backanalysis. Journal of Civil Engineering, Vol. 38, No. 2, 2010, pp. 173–190.
39.
TabatabaeeN., ZiyadiM., and ShafahiY.. Two-Stage Support Vector Classifier and Recurrent Neural Network Predictor for Pavement Performance Modeling. Journal of Infrastructure Systems, Vol. 19, No. 3, 2013, pp. 266–274.
40.
NegaA., NikrazH., HerathS., and GhadimiB.. Distress Identification, Cost Analysis and Pavement Temperature Prediction for the Long-Term Pavement Performance for Western Australia. International Journal of Engineering and Technology, Vol. 7, No. 4, 2015, pp. 267–275.
41.
GopalakrishnanK., and KimS.. Support Vector Machines Approach to HMA Stiffness Prediction. Journal of Engineering Mechanics, Vol. 137, No. 2, 2011, pp. 138–146.
42.
BoserB. E., GuyonI. M., and VapnikV. N.. A Training Algorithm for Optimal Margin Classifiers. In Proceedings of the Fifth Annual Workshop on Computational Learning Theory, ACM, New York, 1992, pp. 144–152.
43.
LuenbergerD. G.Linear and Nonlinear Programming. Springer, New York, 1984.
44.
KarushW.Minima of Functions of Several Variables with Inequalities as Side Constraints. MS thesis. University of Chicago, Ill., 1939.
45.
GönenM., and AlpaydınE.. Multiple Kernel Learning Algorithms. Journal of Machine Learning Research, Vol. 12, 2011, pp. 2211–2268.
46.
CortesC., and VapnikV.. Support-Vector Networks. Machine Learning, Vol. 20, No. 3, 1995, pp. 273–297.
47.
PlattJ. C.Fast Training of Support Vector Machines Using Sequential Minimal Optimization. In Advances in Kernel Methods, MIT Press, Cambridge, Mass., 1999, pp. 185–208.
48.
TsochantaridisI., HofmannT., JoachimsT., and AltunY.. Support Vector Machine Learning for Interdependent and Structured Output Spaces. Presented at 21st International Conference on Machine Learning, Banff, Alberta, Canada, 2004.
49.
SteinwartI., and ChristmannA.. Support Vector Machines. Springer Science & Business Media, New York, 2008.
50.
ÜstünB., MelssenW. J., and BuydensL. M.. Facilitating the Application of Support Vector Regression by Using a Universal Pearson VII Function Based Kernel. Chemometrics and Intelligent Laboratory Systems, Vol. 81, No. 1, 2006, pp. 29–40.
51.
PearsonK.Contributions to the Mathematical Theory of Evolution. II. Skew Variation in Homogeneous Material. Philosophical Transactions of the Royal Society of London A, Vol. 186, 1895, pp. 343–414.
52.
ProzziJ., and MadanatS.. Development of Pavement Performance Models by Combining Experimental and Field Data. Journal of Infrastructure Systems, Vol. 10, No. 1, 2004, pp. 9–22.
53.
HuangY. H.Pavement Analysis and Design. Pearson Education, Upper Saddle River, N.J., 1993.
54.
ChurillaC.The Long-Term Pavement Performance Program Roadmap: A Strategy Plan. FHWA, U.S. Department of Transportation, 1995.
55.
ChapelleO., VapnikV., BousquetO., and MukherjeeS.. Choosing Multiple Parameters for Support Vector Machines. Machine Learning, Vol. 46, No. 1–3, 2002, pp. 131–159.
56.
FrohlichH., and ZellA.. Efficient Parameter Selection for Support Vector Machines in Classification and Regression via Model-Based Global Optimization. In Proceedings of the IEEE International Joint Conference on Neural Networks, IEEE, Piscataway, N.J., 2005, pp. 1431–1436.
57.
LinS.-L., and LiuZ.. Parameter Selection in SVM with RBF Kernel Function. Journal of Zhejiang University of Technology, Vol. 35, No. 2, 2007, p. 163.
58.
CherkasskyV., and MaY.. Practical Selection of SVM Parameters and Noise Estimation for SVM regression. Neural Networks, Vol. 17, No. 1, 2004, pp. 113–126.
59.
WittenI. H., and FrankE.. Data Mining: Practical Machine Learning Tools and Techniques. Morgan Kaufmann Publishers, Burlington, Mass., 2005.
