Abstract
The soft computing technique, such as an artificial neural network (ANN) is a modelling tool that is used to predict the pavement condition index value. ANN is used to model highly variable non-linear distress available in the pavement. In this paper, the ANN model is trained and tested using three different algorithm Levenberg–Marquardt (LM), Bayesian regularization (BR) and scaled conjugate gradient (SCG) algorithm available in the NN toolbox of MATLAB-2015 version. The flexible pavement distress data collected from the field surveying are used to train and test the ANN model. The algorithms are trained and tested using the 400 data points gathered after the rainy season from four different National Highways (NH) of Bihar, India. The performance of ANN algorithms are determined using the distress density and the calculated pavement condition index (PCI) value. The prediction accuracy of the LM, BR and SCG algorithm was compared using the minimum statistical errors (MSE) and the coefficient of correlation. The LM algorithm has performed better than BR and SCG algorithms. LM algorithm has shown the highest correlation value (89%) compared to BR (76%) and SCG (58%) during training, testing and validation of data points. The models predicted the PCI value with a high correlation coefficient and low MSE value. The five-fold cross-validation has been performed to explain the accuracy of the ANN model which is higher compare to random forest and support vector machine (SVM). The ANN model has shown the highest model accuracy (73%) compared to the SVM model (72%) and RF model (61%).
Similar content being viewed by others
References
Suman SK, Sinha S (2012) Pavement condition forecasting through artificial neural network modelling. Int J Emerg Technol Adv Eng 2:474–478
Attoh-Okine NO (1999) Analysis of learning rate and momentum term in backpropagation neural network algorithm trained to predict pavement performance. Adv Eng Softw 30:291–302. https://doi.org/10.1016/S0965-9978(98)00071-4
Attoh-Okine NO (2002) Combining use of rough set and artificial neural networks in doweled-pavement-performance modeling—a hybrid approach. J Transp Eng 128:270–275. https://doi.org/10.1061/(ASCE)0733-947X(2002)128:3(270)
Hossain MI, Gopisetti LSP, Miah MS (2019) International roughness index prediction of flexible pavements using neural networks. J Stomatol 145:1–10. https://doi.org/10.1061/JPEODX.0000088
Qiao Y (2015) Flexible pavements and climate change: impact of climate change on the performance, maintenance, and life-cycle costs of flexible pavements. Doctoral Dissertation, University of Nottingham
Lin JD, Yau JT, Hsiao LH (2003) Correlation analysis between international roughness index (IRI) and pavement distress by neural network. In: Proceedings of the 82nd annual meeting, transportation research board, Philadelphia, Pennsylvania, pp 12-16
Huang Y, Moore RK (2007) Roughness level probability prediction using artificial neural networks. Transp Res Rec J Transp Res Board 1592:89–97. https://doi.org/10.3141/1592-11
Ceylan H, Bayrak MB, Gopalakrishnan K (2014) Neural networks applications in pavement engineering: a recent survey. Int J Pavement Res Technol 7:434–444. https://doi.org/10.6135/ijprt.org.tw/2014
ASTM D6433-07 (2007) Standard Practice for Roads and Parking Lots Pavement Condition Index Surveys. Annual Book of ASTM Standards, ASTM International, West Conshohocken, PA
IRC:82 (2015) Code of practice for maintenance of bituminous surfaces of highways. New Delhi, India
Wu K (2015) Development of PCI Based Pavement Performance Model for Management of Road Infrastructure System. M.S. Dissertation, Arizona State University
Piryonesi SM, El-Diraby T (2018) Using Data Analytics for Cost-Effective Prediction of Road Conditions: Case of the Pavement Condition Index. Federal Highway Administration, Rep No FHWA-HRT-18-065
Piryonesi SM (2019) The Application of Data Analytics to Asset Management: Deterioration and Climate Change Adaptation in Ontario Roads. Doctoral Dissertation, University of Toronto
Piryonesi SM, El-Diraby TE (2020) Role of data analytics in infrastructure asset management: overcoming data size and quality problems. J Transp Eng Part B Pavements 146:04020022. https://doi.org/10.1061/jpeodx.0000175
Haykin S (2005) Neural networks—a comprehensive foundation, 9th edn. Pearson Education, Delhi
Yang J, Lu JJ, Gunaratne M, Xiang Q (2003) Forecasting overall pavement condition with neural networks: application on florida highway network. Transp Res Rec. https://doi.org/10.3141/1853-01
Shekharan AR (1998) Assessment of relative contribution of input variables to pavement performance prediction by artificial neural networks. Transp Res Rec. https://doi.org/10.3141/1655-06
Raab C, Grenfell J, Abd El Halim AO, Partl MN (2015) The influence of age on interlayer shear properties. Int J Pavement Eng 16:559–569. https://doi.org/10.1080/10298436.2014.943212
Shahnazari H, Tutunchian MA, Mashayekhi M, Amini AA (2012) Application of soft computing for prediction of pavement condition index. J Transp Eng 138:1495–1506. https://doi.org/10.1061/(ASCE)TE.1943-5436.0000454
Kirbaş U, Karaşahin M (2016) Performance models for hot mix asphalt pavements in urban roads. Constr Build Mater 116:281–288. https://doi.org/10.1016/j.conbuildmat.2016.04.118
Fakhri M, Shahni Dezfoulian R (2019) Pavement structural evaluation based on roughness and surface distress survey using neural network model. Constr Build Mater 204:768–780. https://doi.org/10.1016/j.conbuildmat.2019.01.142
Piryonesi SM, El-Diraby TE (2020) Data analytics in asset management: cost-effective prediction of the pavement condition index. J Infrastruct Syst. https://doi.org/10.1061/(ASCE)IS.1943-555X.0000512
Yan K, Yin H, Liao H, Huang L (2011) Prediction of resilient modulus of asphalt pavement material using support vector machine. Geotech Spec Publ. https://doi.org/10.1061/47624(403)3
Gong H, Sun Y, Shu X, Huang B (2018) Use of random forests regression for predicting IRI of asphalt pavements. Constr Build Mater 189:890–897. https://doi.org/10.1016/j.conbuildmat.2018.09.017
Bahrami M, Akbari M, Bagherzadeh SA et al (2019) Develop 24 dissimilar ANNs by suitable architectures & training algorithms via sensitivity analysis to better statistical presentation: measure MSEs between targets & ANN for Fe–CuO/Eg–Water nanofluid. Phys A Stat Mech its Appl 519:159–168. https://doi.org/10.1016/j.physa.2018.12.031
de Moura GA, de Bezerra STM, Gomes HP, da Silva SA (2018) Neural network using the Levenberg–Marquardt algorithm for optimal real-time operation of water distribution systems. Urban Water J 15:692–699. https://doi.org/10.1080/1573062X.2018.1539503
Gan L, Narisetty NN, Liang F (2019) Bayesian regularization for graphical models with unequal shrinkage. J Am Stat Assoc 114:1218–1231. https://doi.org/10.1080/01621459.2018.1482755
Chel H, Majumder A, Nandi D (2011) Scaled Conjugate Gradient Algorithm in Neural Network Based Approach for Handwritten Text Recognition. In: Proceedings, First International Conference on Computational Science, Engineering and Information Technology, Tamil Nadu, India, pp 196–210
Fakhri M, Dezfoulian RS, Golroo A, Makkiabadi B (2019) Developing an approach for measuring the intensity of cracking based on geospatial analysis using GIS and automated data collection system. Int J Pavement Eng. https://doi.org/10.1080/10298436.2019.1628961
Parsons TA, Pullen BA (2017) Characterization of Pavement Condition Index Deterioration Curve Shape for USAF Airfield Pavements. In: Proceedings of the International Conference on Highway Pavements and Airfield Technology, pp 230–240
Amin MSR, Amador-Jiménez LE (2015) Pavement management with dynamic traffic and artificial neural network: a case study of Montreal. Can J Civ Eng 43:241–251. https://doi.org/10.1139/cjce-2015-0299
Parsons TA, Pullen BA (2016) Relationship between climate type and observed pavement distresses. Int Conf Transp Dev. https://doi.org/10.1061/9780784479926.009
Jack Feng CX, Yu ZGS, Kingi U, Pervaiz Baig M (2005) Threefold vs. fivefold cross validation in one-hidden-layer and two-hidden-layer predictive neural network modeling of machining surface roughness data. J Manuf Syst 24:93–107. https://doi.org/10.1016/S0278-6125(05)80010-X
Acknowledgements
The authors acknowledge the opportunity to submit the research work at the 5th Conference of the Transportation Research Group of India held at Bhopal (India) from 18 to 21 December 2019, which forms the basis of this article.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Kumar, R., Suman, S.K. & Prakash, G. Evaluation of Pavement Condition Index Using Artificial Neural Network Approach. Transp. in Dev. Econ. 7, 20 (2021). https://doi.org/10.1007/s40890-021-00130-7
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s40890-021-00130-7