Version 1
: Received: 10 October 2019 / Approved: 12 October 2019 / Online: 12 October 2019 (06:08:32 CEST)
How to cite:
Karballaeezadeh, N.; Zaremotekhases, F.; Nabipour, N.; Shamshirband, S.; Mosavi, A. Usage Surface Deflection Data for Performance Prediction in Flexible Pavement. Preprints2019, 2019100141. https://doi.org/10.20944/preprints201910.0141.v1
Karballaeezadeh, N.; Zaremotekhases, F.; Nabipour, N.; Shamshirband, S.; Mosavi, A. Usage Surface Deflection Data for Performance Prediction in Flexible Pavement. Preprints 2019, 2019100141. https://doi.org/10.20944/preprints201910.0141.v1
Karballaeezadeh, N.; Zaremotekhases, F.; Nabipour, N.; Shamshirband, S.; Mosavi, A. Usage Surface Deflection Data for Performance Prediction in Flexible Pavement. Preprints2019, 2019100141. https://doi.org/10.20944/preprints201910.0141.v1
APA Style
Karballaeezadeh, N., Zaremotekhases, F., Nabipour, N., Shamshirband, S., & Mosavi, A. (2019). Usage Surface Deflection Data for Performance Prediction in Flexible Pavement. Preprints. https://doi.org/10.20944/preprints201910.0141.v1
Chicago/Turabian Style
Karballaeezadeh, N., Shahaboddin Shamshirband and Amir Mosavi. 2019 "Usage Surface Deflection Data for Performance Prediction in Flexible Pavement" Preprints. https://doi.org/10.20944/preprints201910.0141.v1
Abstract
The conventional method used for calculating pavement condition index (PCI) has two major drawbacks: safety problems during pavement inspection, and human error. This paper proposes a method for removing these problems. The proposed method uses surface deflection data in falling weight Deflectometer test to estimate PCI. The data used in this study were derived from 236 pavement segments taken from Tehran-Qom freeway in Iran. The data set was analyzed using multi layers perceptron (MLP) and radial basis function (RBF) neural networks. These neural networks were optimized by levenberg-marquardt (MLP-LM), scaled conjugate gradient (MLP-SCG), imperialist competitive (RBF-ICA), and genetic (RBF-GA) algorithms. After initial modeling with four neural networks mentioned, the committee machine intelligent systems (CMIS) method was adopted to combine the results and improve the accuracy of the modeling. The results of analysis have been verified by the four criteria of average percent relative error (APRE), average absolute percent relative error (AAPRE), root mean square error (RMSE) and standard error (SD). The best reported results belonged to CMIS, including APRE=2.3303, AAPRE=11.6768, RMSE=12.0056, and SD=0.0210.
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
,
,
,
*
