首页|New Machine Learning Data Have Been Reported by Researchers at Louisiana State U niversity (Machine Learning-based Technology for Asphalt Concrete Pavement Perfo rmance Decision-making In Hot and Humid Climates)
New Machine Learning Data Have Been Reported by Researchers at Louisiana State U niversity (Machine Learning-based Technology for Asphalt Concrete Pavement Perfo rmance Decision-making In Hot and Humid Climates)
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-A new study on Machine Learning is now available. According to news reporting originating from Baton Rouge, Louisiana, by NewsRx correspondents, research stated, "Highway state agencies incur signif icant budget savings through optimal allocation of pavement Maintenance, Rehabil itation, and Reconstruction (MR&R) &R) activities. The se activities require robust prediction models that can handle large-scale, real -world data and can forecast pavement performance in the long run." Our news editors obtained a quote from the research from Louisiana State Univers ity, "Unfortunately, the traditional performance prediction models have been que stionable in terms of efficiency and accuracy, are based on a limited number of explanatory variables, and are designated to predict short-term (up to five year s) pavement conditions. Therefore, the goal of this study was to propose a machi ne learningbased technology that can predict the field performance by up to 11 years of Asphalt Concrete (AC) overlays placed on asphalt pavements in Southern states in the US based on key project conditions. The proposed technology result ed from assessing the prediction accuracy of machine learning algorithms, includ ing Decision-Tree (DT), eXtreme Gradient Boosting (XGBoost), Artificial Neural N etwork (ANN), and ensemble-learning method, in forecasting the Pavement Conditio n Index (PCI) as the pavement performance indicator. For each algorithm, six mod els were developed sequentially based on historical pavement condition data coll ected from the Louisiana Department of Transportation and Development (LaDOTD) P avement Management System (PMS) database. The six models learned from 892 log mi les of randomly placed AC overlay sections in Louisiana. The output of these mod els was the future PCI of AC overlays at a biannual rate from one to 11 years. T he findings showed that XGBoost and ensemble learning showed similar performance during model training and were further evaluated using the testing dataset. Dur ing model testing, the ensemble learning method yielded higher prediction accura cy than other algorithms, with R2 2 values decreasing from 0.77 at age 1 to 0.67 at age 11, Root Mean Square Error (RMSE) values increasing from +1.65 to +4.74, and Mean Absolute Error (MAE) increasing from 1.24 to 4.59."
Baton RougeLouisianaUnited StatesNorth and Central AmericaCyborgsEmerging TechnologiesMachine LearningTech nologyLouisiana State University
NETL
NSTL
