首页|Researcher from University of Sharjah Publishes Findings in Machine Learning (A Comparative Study of Pavement Roughness Prediction Models under Different Climat ic Conditions)
Researcher from University of Sharjah Publishes Findings in Machine Learning (A Comparative Study of Pavement Roughness Prediction Models under Different Climat ic Conditions)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Data detailed on artificial intelligen ce have been presented. According to news reporting from the University of Sharj ah by NewsRx journalists, research stated, “Predicting the International Roughne ss Index (IRI) is crucial for maintaining road quality and ensuring the safety a nd comfort of road users. Accurate IRI predictions help in the timely identifica tion of road sections that require maintenance, thus preventing further deterior ation and reducing overall maintenance costs.” The news reporters obtained a quote from the research from University of Sharjah : “This study aims to develop robust predictive models for the IRI using advance d machine learning techniques across different climatic conditions. Data were so urced from the Ministry of Energy and Infrastructure in the UAE for localized co nditions coupled with the Long-Term Pavement Performance (LTPP) database for com parison and validation purposes. This study evaluates several machine learning m odels, including regression trees, support vector machines (SVMs), ensemble tree s, Gaussian process regression (GPR),artificial neural networks (ANNs), and ker nel-based methods. Among the models tested, GPR, particularly with rational quad ratic specifications, consistently demonstrated superior performance with the lo west Root Mean Square Error (RMSE) and highest R-squared values across all datas ets. Sensitivity analysis identified age, total pavement thickness, precipitatio n, temperature, and Annual Average Daily Truck Traffic (AADTT) as key factors in fluencing the IRI. The results indicate that pavement age and higher traffic loa ds significantly increase roughness, while thicker pavements contribute to smoot her surfaces. Climatic factors such as temperature and precipitation showed vary ing impacts depending on the regional conditions.”
University of SharjahCyborgsEmerging TechnologiesMachine Learning
NETL
NSTL
