As a guest user you are not logged in or recognized by your IP address. You have
access to the Front Matter, Abstracts, Author Index, Subject Index and the full
text of Open Access publications.
In order to explore the correlation among various influence factors on pavement skid resistance performance and improve the performance prediction accuracy, this research has established a pavement skid resistance performance prediction model based on XGBoost algorithm, with the analysis and pre-process of related big data from LTPP database. The research then uses this prediction model to analyze the influence of basic features and time sequence features on pavement’s skid resistance performance, and compares the prediction results with other commonly used prediction models to evaluate the prediction accuracy and effectiveness. Results have shown that in terms of model evaluation index R2 and RMSE values, the XGBoost model has much better prediction performance than the linear regression model LR, the gray model GM, and the BPNN model. According to the output of XGBoost model, the initial side-way force coefficient is the most important indicator for predicting SFC, while rainfall and snowfall are also strongly correlated with skid resistance performance prediction. Meanwhile, if target characteristics and prediction features modified to different occasions, this XGBoost prediction model has great potential for even wider application.
This website uses cookies
We use cookies to provide you with the best possible experience. They also allow us to analyze user behavior in order to constantly improve the website for you. Info about the privacy policy of IOS Press.
This website uses cookies
We use cookies to provide you with the best possible experience. They also allow us to analyze user behavior in order to constantly improve the website for you. Info about the privacy policy of IOS Press.