摘要
由一名新闻记者兼机器人与机器学习每日新闻编辑-研究人员详细介绍了机器学习的新数据。根据NewsRx记者在路易斯安那州巴吞鲁日的新闻报道，研究表明，“路面标记是提高夜间驾驶安全的必要交通控制装置。在先前的研究中，已经开发了许多统计学习模型来预测标记的反射率，但这些模型的适用性在准确性方面是值得怀疑的。”本研究的资金支持包括国家合作公路研究项目(NCHRP)，NCHRP IDEA项目。新闻记者从路易斯安那州州立大学获得了这项研究的引用，“这项研究的关键目标是开发一个基于机器学习的框架，美国运输机构可以使用该框架，利用最初测量的反射系数和其他关键项目条件，可靠地预测其路面标线在3年内的反射系数。本研究使用随机森林(RF)算法来开发拟议的框架网络，其中考虑了3种不同类型的标记材料。”在美国不同气候区，从国家交通产品评价项目(NTPEP)中测试了49632个横向跳跃反射系数测量值，建立了11个RF模型，对不同预测层位的反射系数进行了预测，并随机选取80%的数据点对模型进行了训练。利用剩余20%的数据点对所建立模型的预测性能进行了测试，RF模型预测的后向反射率具有较高的精度（±2在0.88～0.99之间）。
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Researchers detail new data in Machine Learning. According to news reporting originating in Baton Rouge, Louisiana, by NewsRx journalists, research stated, “Pavement markings are essential traffic c ontrol devices that enhance safety for motorists during nighttime. Numerous stat istical learning models have been developed in prior studies to predict the retr oreflectivity of the markings, but the applicability of these models is question able in terms of accuracy.” Financial supporters for this research include National Cooperative Highway Rese arch Program (NCHRP), NCHRP IDEA project. The news reporters obtained a quote from the research from Louisiana State Unive rsity, “The key objective of this study was to develop a machine learning-based framework that can be used by US transportation agencies to reliably predict the retroreflectivity of their pavement markings over a period of 3 years utilizing the initially measured retroreflectivity and other key project conditions. The random forest (RF) algorithm was used in this study to develop the proposed fram ework considering seven types of marking materials in three different US climate zones. A total of 49,632 transverse skip retroreflectivity measurements were re trieved from the National Transportation Product Evaluation Program (NTPEP) and 11 RF models were developed to sequentially predict retroreflectivity at differe nt prediction horizons. The models were trained with randomly selected 80% of the total data points, and the remaining 20% data points were u tilized for testing the predictive performance of the developed models. The RF m odels predicted the retroreflectivity with a superior level of accuracy (R2 rang ing between 0.88 and 0.99) than the models proposed in prior studies.”
NETL
NSTL