Intelligent Road Inspection with Advanced Machine Learning; Hybrid Prediction Models for Smart Mobility and Transportation Maintenance Systems

Prediction models in mobility and transportation maintenance systems have been dramatically improved through using machine learning methods. This paper proposes novel machine learning models for intelligent road inspection. The traditional road inspection systems based on the pavement condition index (PCI) are often associated with the critical safety, energy and cost issues. Alternatively, the proposed models utilize surface deflection data from falling weight deflectometer (FWD) tests to predict the PCI. Machine learning methods are the single multi-layer perceptron (MLP) and radial basis function (RBF) neural networks as well as their hybrids, i.e., Levenberg-Marquardt (MLP-LM), scaled conjugate gradient (MLP-SCG), imperialist competitive (RBF-ICA), and genetic algorithms (RBF-GA). Furthermore, the committee machine intelligent systems (CMIS) method was adopted to combine the results and improve the accuracy of the modeling. The results of the analysis have been verified through using four criteria of average percent relative error (APRE), average absolute percent relative error (AAPRE), root mean square error (RMSE), and standard error (SD). The CMIS model outperforms other models with the promising results of APRE=2.3303, AAPRE=11.6768, RMSE=12.0056, and SD=0.0210.

[1]  Amir Mosavi,et al.  Prediction of remaining service life of pavement using an optimized support vector machine (case study of Semnan–Firuzkuh road) , 2019, Engineering Applications of Computational Fluid Mechanics.

[2]  Simon Haykin,et al.  Neural Networks and Learning Machines , 2010 .

[3]  Devesh Tiwari,et al.  Development of Overall Pavement Condition Index for Urban Road Network , 2013 .

[4]  Mehmet Saltan,et al.  Backcalculation of pavement layer thickness using data mining , 2012, Neural Computing and Applications.

[5]  N. Thomas,et al.  Applicability of the International Roughness Index as a Predictor of Asphalt Pavement Condition , 2007 .

[6]  Gerardo W Flintsch,et al.  Pavement Condition Data from Traffic Speed Deflectometer for Network Level Pavement Management , 2019 .

[7]  Ahmed Senouci,et al.  Condition rating of rigid pavements by neural networks , 1995 .

[8]  Michael A. Mooney,et al.  Development of Adaptive Performance Models for Oklahoma Airfield Pavement Management System , 2003 .

[9]  Giuseppe Loprencipe,et al.  Sustainable Pavement Management System in Urban Areas Considering the Vehicle Operating Costs , 2017 .

[10]  Sten Sundin,et al.  ARTIFICIAL INTELLIGENCE--BASED DECISION SUPPORT TECHNOLOGIES IN PAVEMENT MANAGEMENT , 2001 .

[11]  Eyal Levenberg,et al.  Comparing Traffic Speed Deflectometer and Falling Weight Deflectometer Data , 2018 .

[12]  Shameem A. Dewan,et al.  Estimating International Roughness Index from Pavement Distresses to Calculate Vehicle Operating Costs for the San Francisco Bay Area , 2002 .

[13]  Zeng Sheng.  Pavement Performance Evaluating Model by Using RBF , 2008 .

[14]  S. Esterby.  American Society for Testing and Materials , 2006 .

[15]  Mohamed Y Shahin,et al.  PREDICTION OF PAVEMENT PERFORMANCE BY USING NONDESTRUCTIVE TEST RESULTS , 1983 .

[16]  Melissa F. Anderson,et al.  Predicting Pavement Condition Index Using International Roughness Index in a Dense Urban Area , 2015 .

[17]  Chen-Ming Kuo,et al.  Significance of subgrade damping on structural evaluation of pavements , 2014 .

[18]  Mohamed Y Shahin,et al.  Pavement Maintenance Management for Roads and Parking Lots. , 1981 .

[19]  S. Travis Waller,et al.  Prediction of Pavement Performance: Application of Support Vector Regression with Different Kernels , 2016 .

[20]  Caro Lucas,et al.  Imperialist competitive algorithm: An algorithm for optimization inspired by imperialistic competition , 2007, 2007 IEEE Congress on Evolutionary Computation.

[21]  Adrienn Dineva,et al.  Comparative Analysis of Machine Learning Models for Prediction of Remaining Service Life of Flexible Pavement , 2019, Mathematics.

[22]  D. Broomhead,et al.  Radial Basis Functions, Multi-Variable Functional Interpolation and Adaptive Networks , 1988 .

[23]  Young-Chan Suh,et al.  Correlation Analysis between Pavement Condition Indices in Korean Roads , 2018 .

[24]  Siti Isnaini Kurniawati Djaha,et al.  Quality Assessment of Road Pavement using Lightweight Deflectometer , 2019 .

[25]  Martin Fodslette Meiller.  A Scaled Conjugate Gradient Algorithm for Fast Supervised Learning , 1993 .

[26]  Li Ningyuan,et al.  Integrating Dynamic Performance Prediction Models into Pavement ManagementMaintenance and Rehabilitation Programs , 2001 .

[27]  Mahamad Nabab Alam,et al.  A comparative study of metaheuristic optimization approaches for directional overcurrent relays coordination , 2015 .

[28]  Gerardo W Flintsch,et al.  An adaptive hybrid genetic algorithm for pavement management , 2019 .

[29]  A. Suraji,et al.  Analysis of Road Surface Defects Using Road Condition Index Method on the Caruban-Ngawi Road Segment , 2018, JOURNAL OF SCIENCE AND APPLIED ENGINEERING.

[30]  Kasthurirangan Gopalakrishnan,et al.  Neural Network–Swarm Intelligence Hybrid Nonlinear Optimization Algorithm for Pavement Moduli Back-Calculation , 2010 .

[31]  M. Y. Shahin,et al.  Pavement Management for Airports, Roads, and Parking Lots , 2006 .

[32]  L. Cooper,et al.  When Networks Disagree: Ensemble Methods for Hybrid Neural Networks , 1992 .

[33]  Saurav Kumar,et al.  Parametric Study of Pavement Deterioration Using Machine Learning Algorithms , 2019 .

[34]  Simona Fontul,et al.  Track Substructure Assessment using Non-Destructive Load Tests. A Portuguese Case Study , 2012 .

[35]  Lawrence. Davis,et al.  Handbook Of Genetic Algorithms , 1990 .

[36]  Hao Yu,et al.  Levenberg—Marquardt Training , 2011 .

[37]  J. Antonio Ramos García,et al.  Analysis of the temperature influence on flexible pavement deflection , 2011 .

[38]  Ananth Ranganathan,et al.  The Levenberg-Marquardt Algorithm , 2004 .

[39]  Sahin Yildirim,et al.  Statistical analysis of vehicles' vibration due to road roughness using radial basis artificial neural network , 2001, Appl. Artif. Intell..

[40]  William J. O'Brien,et al.  Developing a Sustainable Pavement Management Plan: Tradeoffs in Road Condition, User Costs, and Greenhouse Gas Emissions , 2019, Journal of Management in Engineering.

[41]  JaChing Chou,et al.  Pavement distress classification using neural networks , 1994, Proceedings of IEEE International Conference on Systems, Man and Cybernetics.

[42]  Nima Kargah-Ostadi,et al.  Comparison of Machine Learning Techniques for Developing Performance Prediction Models , 2014 .

[43]  Daniel Gillblad,et al.  Learning Machines , 2020, AAAI Spring Symposia.

[44]  Dominic J. Michels.  Pavement Condition Index and Cost of Ownership Analysis on Preventative Maintenance Projects in Kentucky , 2017 .

[45]  Sherif Hashem Bruce Schmeiser.  Approximating a Function and its Derivatives Using MSE-Optimal Linear Combinations of Trained Feedfo , 1993 .

[46]  Jian-Shiuh Chen,et al.  Proposal of a New Road Surface Management System(RSMS) for Developing Countries. , 1999 .

[47]  Seyedmohsen Hosseini,et al.  A survey on the Imperialist Competitive Algorithm metaheuristic: Implementation in engineering domain and directions for future research , 2014, Appl. Soft Comput..

[48]  O. Kisi,et al.  Comparison of three back-propagation training algorithms for two case studies , 2005 .

[49]  Amir Amini,et al.  Application of Soft Computing for Prediction of Pavement Condition Index , 2012 .

[50]  Mohammad Bagher Menhaj,et al.  Training feedforward networks with the Marquardt algorithm , 1994, IEEE Trans. Neural Networks.

[51]  Christina Plati,et al.  Soft Computing Models to Predict Pavement Roughness: A Comparative Study , 2018, Advances in Civil Engineering.

[52]  Amir Varamesh,et al.  On the evaluation of the viscosity of nanofluid systems: Modeling and data assessment , 2018 .

[53]  Brian K Diefenderfer,et al.  Enhancing Network-Level Decision Making through the use of a Structural Capacity Index , 2013 .

[54]  Karim Chatti,et al.  Backcalculation of Dynamic Modulus Mastercurve from Falling Weight Deflectometer Surface Deflections , 2011 .

[55]  Xiaoduan Sun,et al.  Development of Uniform Sections for PMS Inventory and Application , 2007 .

[56]  James W Mack,et al.  Using Remaining Service Life as the National Performance Measure of Pavement Assets , 2014 .

[57]  Jidong Yang,et al.  Forecasting Overall Pavement Condition with Neural Networks: Application on Florida Highway Network , 2003 .

[58]  Zhongjie Zhang,et al.  Prediction of In-Service Pavement Structural Capacity Based on Traffic-Speed Deflection Measurements , 2016 .

[59]  Hojjat Adeli,et al.  RADIAL BASIS FUNCTION NEURAL NETWORK FOR WORK ZONE CAPACITY AND QUEUE ESTIMATION , 2003 .

[60]  Shakir Shatnawi,et al.  Structural evaluation of rigid pavement sections , 2000 .