Modeling of pavement roughness utilizing artificial neural network approach for Laos national road network
The International Roughness Index (IRI) has become the reference scale for assessing pavement roughness in many highway agencies worldwide. This research aims to develop two Artificial Neural Network (ANN) models for Double Bituminous Surface Treatment (DBST) and Asphalt Concrete (AC) pavement secti...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Vilnius Gediminas Technical University
2022-03-01
|
| Series: | Journal of Civil Engineering and Management |
| Subjects: | |
| Online Access: | https://journals.vgtu.lt/index.php/JCEM/article/view/15851 |
| _version_ | 1818335223361830912 |
|---|---|
| author | Mohamed Gharieb Takafumi Nishikawa Shozo Nakamura Khampaseuth Thepvongsa |
| author_facet | Mohamed Gharieb Takafumi Nishikawa Shozo Nakamura Khampaseuth Thepvongsa |
| author_sort | Mohamed Gharieb |
| collection | DOAJ |
| description | The International Roughness Index (IRI) has become the reference scale for assessing pavement roughness in many highway agencies worldwide. This research aims to develop two Artificial Neural Network (ANN) models for Double Bituminous Surface Treatment (DBST) and Asphalt Concrete (AC) pavement sections using Laos Pavement Management System (PMS) database for National Road Network (NRN). The final database consisted of 269 and 122 observations covering 1850 km of DBST NRN and 718 km of AC NRN, respectively. The proposed models predict IRI as a function of pavement age and Cumulative Equivalent Single-Axle Load (CESAL). The obtained data were randomly divided into training (70%), validation (15%), and testing (15%) datasets. The statistical evaluation results of the training dataset reveal that both ANN models (DBST and AC) have good prediction ability with high values of coefficient of determination (R2 = 0.96 and 0.94) and low values of Mean Absolute Error (MAE = 0.23 and 0.19) and Mean Squared Percentage Error (RMSPE = 7.03 and 9.98). Eventually, the goodness of fit of the proposed ANN models was compared with the Multiple Linear Regression (MLR) models previously developed under the same conditions. The results show that ANN models yielded higher prediction accuracy than MLR models. |
| first_indexed | 2024-12-13T14:20:01Z |
| format | Article |
| id | doaj.art-a9535851dd984b2287c58784ab1a7a83 |
| institution | Directory Open Access Journal |
| issn | 1392-3730 1822-3605 |
| language | English |
| last_indexed | 2024-12-13T14:20:01Z |
| publishDate | 2022-03-01 |
| publisher | Vilnius Gediminas Technical University |
| record_format | Article |
| series | Journal of Civil Engineering and Management |
| spelling | doaj.art-a9535851dd984b2287c58784ab1a7a832022-12-21T23:42:07ZengVilnius Gediminas Technical UniversityJournal of Civil Engineering and Management1392-37301822-36052022-03-01284261–277261–27710.3846/jcem.2022.1585115851Modeling of pavement roughness utilizing artificial neural network approach for Laos national road networkMohamed Gharieb0Takafumi Nishikawa1Shozo Nakamura2Khampaseuth Thepvongsa3Graduate School of Engineering, Nagasaki University, 1-14 Bunkyo-machi, Nagasaki 852-8521, JapanGraduate School of Engineering, Nagasaki University, 1-14 Bunkyo-machi, Nagasaki 852-8521, Graduate School of Engineering, Nagasaki University, 1-14 Bunkyo-machi, Nagasaki 852-8521, JapanFaculty of Engineering, National University of Laos, Lao-Thai Road, Sokpaluang Village, Sisatanak District, Vientiane Capital, LaosThe International Roughness Index (IRI) has become the reference scale for assessing pavement roughness in many highway agencies worldwide. This research aims to develop two Artificial Neural Network (ANN) models for Double Bituminous Surface Treatment (DBST) and Asphalt Concrete (AC) pavement sections using Laos Pavement Management System (PMS) database for National Road Network (NRN). The final database consisted of 269 and 122 observations covering 1850 km of DBST NRN and 718 km of AC NRN, respectively. The proposed models predict IRI as a function of pavement age and Cumulative Equivalent Single-Axle Load (CESAL). The obtained data were randomly divided into training (70%), validation (15%), and testing (15%) datasets. The statistical evaluation results of the training dataset reveal that both ANN models (DBST and AC) have good prediction ability with high values of coefficient of determination (R2 = 0.96 and 0.94) and low values of Mean Absolute Error (MAE = 0.23 and 0.19) and Mean Squared Percentage Error (RMSPE = 7.03 and 9.98). Eventually, the goodness of fit of the proposed ANN models was compared with the Multiple Linear Regression (MLR) models previously developed under the same conditions. The results show that ANN models yielded higher prediction accuracy than MLR models.https://journals.vgtu.lt/index.php/JCEM/article/view/15851international roughness index (iri)laos pavement management system (pms)artificial neural network (ann)backpropagation algorithmdouble bituminous surface treatment (dbst)asphalt concrete (ac)pavement agecumulative equivalent single-axle load (cesal)pavement performance model |
| spellingShingle | Mohamed Gharieb Takafumi Nishikawa Shozo Nakamura Khampaseuth Thepvongsa Modeling of pavement roughness utilizing artificial neural network approach for Laos national road network Journal of Civil Engineering and Management international roughness index (iri) laos pavement management system (pms) artificial neural network (ann) backpropagation algorithm double bituminous surface treatment (dbst) asphalt concrete (ac) pavement age cumulative equivalent single-axle load (cesal) pavement performance model |
| title | Modeling of pavement roughness utilizing artificial neural network approach for Laos national road network |
| title_full | Modeling of pavement roughness utilizing artificial neural network approach for Laos national road network |
| title_fullStr | Modeling of pavement roughness utilizing artificial neural network approach for Laos national road network |
| title_full_unstemmed | Modeling of pavement roughness utilizing artificial neural network approach for Laos national road network |
| title_short | Modeling of pavement roughness utilizing artificial neural network approach for Laos national road network |
| title_sort | modeling of pavement roughness utilizing artificial neural network approach for laos national road network |
| topic | international roughness index (iri) laos pavement management system (pms) artificial neural network (ann) backpropagation algorithm double bituminous surface treatment (dbst) asphalt concrete (ac) pavement age cumulative equivalent single-axle load (cesal) pavement performance model |
| url | https://journals.vgtu.lt/index.php/JCEM/article/view/15851 |
| work_keys_str_mv | AT mohamedgharieb modelingofpavementroughnessutilizingartificialneuralnetworkapproachforlaosnationalroadnetwork AT takafuminishikawa modelingofpavementroughnessutilizingartificialneuralnetworkapproachforlaosnationalroadnetwork AT shozonakamura modelingofpavementroughnessutilizingartificialneuralnetworkapproachforlaosnationalroadnetwork AT khampaseuththepvongsa modelingofpavementroughnessutilizingartificialneuralnetworkapproachforlaosnationalroadnetwork |