首页|Reports on Machine Learning Findings from Universidad Panamericana Provide New I nsights (Damage Importance Analysis for Pavement Condition Index Using Machine-L earning Sensitivity Analysis)
Reports on Machine Learning Findings from Universidad Panamericana Provide New I nsights (Damage Importance Analysis for Pavement Condition Index Using Machine-L earning Sensitivity Analysis)
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-Research findings on artificial intell igence are discussed in a new report. According to news reporting originating fr om Aguascalientes, Mexico, by NewsRx correspondents, research stated, "The Pavem ent Condition Index (PCI) is a prevalent metric for assessing the condition of r igid pavements. The PCI calculation involves evaluating 19 types of damage." Funders for this research include Chairs Program of The National Council of Huma nities, Science And Technology (Conahcyt) Project. The news journalists obtained a quote from the research from Universidad Panamer icana: "This study aims to analyze how different types of damage impact the PCI calculation and the impact of the performance of prediction models of PCI by red ucing the number of evaluated damages. The Municipality of Leon, Gto., Mexico, p rovided a dataset of 5271 records. We evaluated five different decision-tree mod els to predict the PCI value. The Extra Trees model, which exhibited the best pe rformance, was used to assess the feature importance of each type of damage, rev ealing their relative impacts on PCI predictions. To explore the potential for r educing the complexity of the PCI evaluation, we applied Sequential Forward Sear ch and Brute Force Search techniques to analyze the performance of models with v arious feature combinations. Our findings indicate no significant statistical di fference in terms of Mean Absolute Error (MAE) and the coefficient of determinat ion (R2) between models trained with 13 features compared to those trained with All 17 features."
Universidad PanamericanaAguascalientesMexicoNorth and Central AmericaCyborgsEmerging TechnologiesMachine Lea rning
NETL
NSTL
