An Objective Method for Gravel Roads Riding Quality Utilizing Smartphones Data Collection and Artificial Neural Network Modelling — Oak Academic Publishing
Research ArticleOpen AccessGoogle Scholar indexed
An Objective Method for Gravel Roads Riding Quality Utilizing Smartphones Data Collection and Artificial Neural Network Modelling
Department of Civil and Architectural Engineering, University of Wyoming, Laramie, US
,
Department of Civil and Architectural Engineering, University of Wyoming, Laramie, US
,
Department of Civil and Architectural Engineering, University of Wyoming, Laramie, US
1 Department of Civil and Architectural Engineering, University of Wyoming, Laramie, US
2 Department of Civil and Architectural Engineering, University of Wyoming, Laramie, US
3 Department of Civil and Architectural Engineering, University of Wyoming, Laramie, US
The current limitation in maintenance budget and resources necessitates developing new cost-effective techniques for gravel roads management systems (GRMS). Thus, the Wyoming Technology Transfer Center (WYT2) has started developing a holistic automated GRMS. Utilizing smartphones in gravel roads data collection is one of the main features in the proposed system. In this study, smartphones were used to collect gravel roads condition data in terms of International Roughness Index (IRI) and corrugation to develop an objective computational method to estimate the riding quality on gravel roads. The developed method will help local agencies to reduce subjectivity in their data collection process and support them with a solid computational justification for their evaluation data and decisions. Two analyses have been carried out to achieve the purpose of this study. Artificial Neural Network ANN method and linear regression were used to develop the riding quality model. The linear regression resulted in a model that has a 0.8242 coefficient of determination (R 2 ) value which means that the developed riding quality model can represent 82.42% of the collected data. The achieved R 2 value is considered sufficient for GRMS purposes. In addition, the developed ANN model has a prediction accuracy of 92.5%. The achieved prediction accuracy shows that the ANN model can predict the riding quality significantly better than the linear regression, with 12.5% higher accuracy. Furthermore, thresholds for the gravel roads IRI were suggested and introduced in this study to be the first IRI thresholds for gravel roads in the literature. Based on the suggested threshold, the gravel roads IRI has three classes: smooth, acceptable and rough. The gravel road segment can be classified in terms of IRI to be smooth, acceptable, or rough if its IRI value is less than 284, between 284 and 496, or more than 496 inch/mile, respectively.
Aleadelat, W., Wright, C.H.G. and Ksaibati, K. (2018) Estimation of Gravel Roads Ride Quality through an Android-Based Smartphone. Transportation Research Record : Journal of the Transportation Research Board , 2672, 14-21. https://doi.org/10.1177/0361198118758693
Alhasan, A., White, D.J. and De Brabanter, K. (2015) Quantifying Roughness of Unpaved Roads by Terrestrial Laser Scanning. Transportation Research Record : Journal of the Transportation Research Board , 2523, 105-114. https://doi.org/10.3141/2523-12
Allouch, A., Koubaa, A., Abbes, T. and Ammar, A. (2017) RoadSense: Smartphone Application to Estimate Road Conditions Using Accelerometer and Gyroscope. IEEE Sensors Journal , 17, 4231-4238. https://doi.org/10.1109/jsen.2017.2702739
Astarita, V., Caruso, M.V., Danieli, G., Festa, D.C., Giofrè, V.P., Iuele, T., et al . (2012) A Mobile Application for Road Surface Quality Control: Uniqualroad. Procedia—Social and Behavioral Sciences , 54, 1135-1144. https://doi.org/10.1016/j.sbspro.2012.09.828
A World Bank Publication (1990) Road Deterioration and Maintenance Effects. The Highway Design and Maintenance Standards Series.
Ram, B.M., Sindu, C.L. and Srinivasa, K.R. (2018) Roughness Evaluation of Flexible Pavements Using Merlin and Total Station Equipment. I-Manager ’ s Journal on Civil Engineering , 8, 41-46. https://doi.org/10.26634/jce.8.1.14012
Bhoraskar, R., Vankadhara, N., Raman, B. and Kulkarni, P. (2012) Wolverine: Traffic and Road Condition Estimation Using Smartphone Sensors. 2012 Fourth International Conference on Communication Systems and Networks ( COMSNETS 2012), Bangalore, 3-7 January 2012, 1-6. https://doi.org/10.1109/comsnets.2012.6151382
Burger, A.F., Henderson, M. and Van Rooyen, G.C. (2007) Development of Scheduling Algorithms for Routine Maintenance of Unsealed Roads in Western Cape Province, South Africa. Transportation Research Record : Journal of the Transportation Research Board , 1989, 240-249. https://doi.org/10.3141/1989-28
Ceylan, H., Gopalakrishnan, K. and Guclu, A. (2007) Advanced Approaches to Characterizing Nonlinear Pavement System Responses. Transportation Research Record : Journal of the Transportation Research Board , 2005, 86-94. https://doi.org/10.3141/2005-10
Chamorro, A., de Solminihac, H., Salgado, M. and Barrera, E. (2009) Development and Validation of a Method to Evaluate Unpaved Road Condition with Objective Distress Measures. Transportation Research Record : Journal of the Transportation Research Board , 2101, 3-9. https://doi.org/10.3141/2101-01
Chen, R. and Guinness, R. (2014) Geospatial Computing in Mobile Devices. Artech House, 1-8.
Das, T., Mohan, P., Padmanabhan, V.N., Ramjee, R. and Sharma, A. (2010) PRISM: Platform for Remote Sensing Using Smartphones. Proceedings of the 8 th International Conference on Mobile Systems , Applications , and Services , San Francisco, 15-18 June 2010, 63-76. https://doi.org/10.1145/1814433.1814442
Douangphachanh, V. and Oneyama, H. (2013) A Study on the Use of Smartphones for Road Roughness Condition Estimation. Journal of the Eastern Asia Society for Transportation Studies , 10, 1551-1564.
Eaton, R.A. and Beaucham, R.E. (1992) Unsurfaced Road Maintenance Management. CRREL Special Report 92-26. Cold Regions Research and Engineering Laboratory, U.S. Army Corps of Engineers.
Federal Highway Administration (FHWA) (2004) Transportation Applications of Recycled Concrete Aggregate.
Harikrishnan, P.M. and Gopi, V.P. (2017) Vehicle Vibration Signal Processing for Road Surface Monitoring. IEEE Sensors Journal , 17, 5192-5197. https://doi.org/10.1109/jsen.2017.2719865
Hossain, M.I. and Tutumluer, E. (2019) Methodology for Evaluation of Seal-Coated, Gravel and Dirt Roads. Research Report No. FHWA-ICT-19-008. A Report of the Findings of ICT PROJECT R27-174 Methodology for Evaluation of Seal-Coated, Gravel, and Dirt Roads. Civil Engineering Studies Illinois Center for Transportation Series No. 19-009.
Huntington, G. and Ksaibati, K. (2011) Management of Unsealed Gravel Roads. Transportation Research Record : Journal of the Transportation Research Board , 2232, 1-9. https://doi.org/10.3141/2232-01
Huntington, G. and Ksaibati, K. (2015) Visual Assessment System for Rating Unsealed Roads. Transportation Research Record : Journal of the Transportation Research Board , 2474, 116-122. https://doi.org/10.3141/2474-14
Goodspeed, C.H., Schmeckpeper, E.R. and Lemieux, R.L. (1994) Road Surface Management System. 3 rd International Conference on Managing Pavements , Washington DC, 8 January 2010, 101.
Huntington, G. and Ksaibati, K. (2011) Gravel Roads Management. Report prepared for the Wyoming Department of Transportation and the Mountain-Plains Consorti-um, Wyoming Technology Transfer Center (T2/LTAP).
Jones, D, and Paige-Green, P. (2000) DRAFT TMH12 Pavement Management Systems: Standard Visual Assessment Manual for Unsealed Roads Version 1. Contract Report CR2000/66.
Lima, L.C., Amorim, V.J.P., Pereira, I.M., Ribeiro, F.N. and Oliveira, R.A.R. (2016) Using Crowdsourcing Techniques and Mobile Devices for Asphaltic Pavement Quality Recognition. 2016 VI Brazilian Symposium on Computing Systems Engineering ( SBESC ), João Pessoa, 1-4 November 2016, 144-149. https://doi.org/10.1109/sbesc.2016.029
Li, M. and Wang, H. (2017) Development of ANN-GA Program for Back Calculation of Pavement Moduli under FWD Testing with Viscoelastic and Nonlinear Parameters. International Journal of Pavement Engineering , 20, 490-498. https://doi.org/10.1080/10298436.2017.1309197
Singh, G., Bansal, D., Sofat, S. and Aggarwal, N. (2017) Smart Patrolling: An Efficient Road Surface Monitoring Using Smartphone Sensors and Crowdsourcing. Pervasive and Mobile Computing , 40, 71-88. https://doi.org/10.1016/j.pmcj.2017.06.002
Strazdins, G., Mednis, A., Kanonirs, G., Zviedris, R. and Selavo, L. (2011) Towards Vehicular Sensor Networks with Android Smartphones for Road Surface Monitoring. Proc eeding of 2 nd International Workshop on Networks of Cooperating Objects , Washington DC, 8 January 2010, 120.
Surdahl, R.W., Woll, J.H. and Marquez, R. (2005) Report: Road Stablizer Product Performance: Buenos Aires National Wildlife Refuge. United States. Federal Highway Administration. Central Federal Lands Highway Division.
Steyn, W.J., Bean, W.L. and Monismith, C.L. (2008) The Potential Costs of Bad Roads in South Africa. In: Ittmann, H., Havenga, J. and de Swart, A., Eds., Fifth Annual State of Logistics Survey for South Africa , CSIR, 49-52.
Transportation Information Center, University of Wisconsin-Madison (2002) Pavement Surface Evaluation and Rating (PASER) Manual-Gravel Roads.
Varma, S. and Emin Kutay, M. (2015) Backcalculation of Viscoelastic and Nonlinear Flexible Pavement Layer Properties from Falling Weight Deflections. International Journal of Pavement Engineering , 17, 388-402. https://doi.org/10.1080/10298436.2014.993196
Walker, D. (1989) Gravel PASER Manual: Pavement Surface Evaluation and Rating. Wisconsin Transportation Information Center.
Steyn, W.J.V., Bean, W., King, D. and Komba, J. (2011) Evaluation of Selected Effects of Pavement Riding Quality on Logistics Costs in South Africa. Transportation Research Record : Journal of the Transportation Research Board , 2227, 138-145. https://doi.org/10.3141/2227-15
Wyoming Technology Transfer Center/Local Technical Assistance Program (WYT2/ LTAP) (2014) Riding Quality Rating Guide.
Li, X. and Goldberg, D.W. (2018) Toward a Mobile Crowdsensing System for Road Surface Assessment. Computers , Environment and Urban Systems , 69, 51-62. https://doi.org/10.1016/j.compenvurbsys.2017.12.005
Zhang, C. and Elaksher, A. (2011) An Unmanned Aerial Vehicle-Based Imaging System for 3D Measurement of Unpaved Road Surface Distresses. Computer - Aided Civil and Infrastructure Engineering , 27, 118-129. https://doi.org/10.1111/j.1467-8667.2011.00727.x
Zhang, Z.L. (2014) Investigation of an Alternative Gravel Roads Rejuvenation Method. Ph.D. Thesis, Iowa State University.
Abu Daoud, O., Albatayneh, O., Forslof, L. and Ksaibati, K. (2021) Validating the Practicality of Utilising an Image Classifier Developed Using Tensorflow Framework in Collecting Corrugation Data from Gravel Roads. International Journal of Pavement Engineering , 23, 3797-3808. https://doi.org/10.1080/10298436.2021.1921773
Daoud, O.A. and Ksaibati, K. (2022) Artificial Neural Network-Based Roughness Prediction Models for Gravel Roads Considering Land Use. Innovative Infrastructure Solutions , 7, Article No. 231. https://doi.org/10.1007/s41062-022-00793-0
Abu Daoud, O. and Ksaibati, K. (2021) Studying the Effect of Gravel Roads Geometric Features on Corrugation Behavior. International Journal of Pavement Research and Technology , 16, 44-52. https://doi.org/10.1007/s42947-021-00110-5
Al-Suleiman, T.I. and Daoud, O.A. (2021) Evaluation of Pavement Condition of the Primary Roads in Jordan Using SHRP Procedure. Jordan Journal of Civil Engineering , 15, 305-317.