A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Surface Temperature Prediction of Asphalt Pavement Based on APRIORI-GBDT
Distribution characteristics and vary rules of asphalt pavement temperature have an important impact on the bearing capacity and performance of pavement. The objective of this study was to explore the correlation between temperature of asphalt pavements and meteorological factors and implement an accurate trend prediction of the asphalt pavement temperature. First, Apriori was applied to identify the key factors affecting the asphalt pavement temperature. Then, based on the relevant factors mined by Apriori, the three kinds of temperature prediction models were established by gradient boosting decision tree (GBDT), random forest (RF), and linear regression (LR). The results indicate that Apriori would perform an excellent ability to analyze the correlation rules and the relevant factors which affect the asphalt pavement temperature is excavated including air temperature, air pressure, dew point temperature, and relative humidity. The mean-square-error of the GBDT predicting results has a lower value of 1.5 when compared with the Random Forest and Linear Regression owing to the high robustness and the good generalization ability, which reflects the GBDT has a good applicability in the field of prediction. The research would serve as a technical support for the machine learning applied in the field of the association rule analysis and the application of prediction problems.
Surface Temperature Prediction of Asphalt Pavement Based on APRIORI-GBDT
Distribution characteristics and vary rules of asphalt pavement temperature have an important impact on the bearing capacity and performance of pavement. The objective of this study was to explore the correlation between temperature of asphalt pavements and meteorological factors and implement an accurate trend prediction of the asphalt pavement temperature. First, Apriori was applied to identify the key factors affecting the asphalt pavement temperature. Then, based on the relevant factors mined by Apriori, the three kinds of temperature prediction models were established by gradient boosting decision tree (GBDT), random forest (RF), and linear regression (LR). The results indicate that Apriori would perform an excellent ability to analyze the correlation rules and the relevant factors which affect the asphalt pavement temperature is excavated including air temperature, air pressure, dew point temperature, and relative humidity. The mean-square-error of the GBDT predicting results has a lower value of 1.5 when compared with the Random Forest and Linear Regression owing to the high robustness and the good generalization ability, which reflects the GBDT has a good applicability in the field of prediction. The research would serve as a technical support for the machine learning applied in the field of the association rule analysis and the application of prediction problems.
Surface Temperature Prediction of Asphalt Pavement Based on APRIORI-GBDT
Qiu, Xin (author) / Hong, Haojue (author) / Xu, Wenyi (author) / Yang, Qing (author) / Xiao, Shanglin (author)
International Conference on Transportation and Development 2020 ; 2020 ; Seattle, Washington (Conference Cancelled)
2020-08-31
Conference paper
Electronic Resource
English
Prediction of Asphalt Pavement Temperature
| ASCE | 2013
ASPHALT PAVEMENT, ASPHALT PAVEMENT ROAD SURFACE STRUCTURE, AND ASPHALT PAVEMENT FORMING METHOD
| European Patent Office | 2016
Flame detection based on GBDT feature for building
| IEEE | 2017