摘要
由一名新闻记者-机器人与机器学习每日新闻的工作人员新闻编辑-关于机器学习的最新研究结果已经发表。根据NewsRx Corres Pondents来自印度博帕尔的新闻报道，研究表明：“在无信号交叉口，特别是在城市地区，主要的安全危险是人车碰撞。由于其复杂性和注意力不集中，行人过街行为对他们的安全有重大影响。”我们的新闻记者从毛拉纳阿扎德国家技术研究所的研究中获得了一句话：“这项研究引入了一个新的框架，通过使用机器学习算法开发行人过街行为的预测模型来提高无信号交叉口的行人安全。同时，将过街行为作为因变量和其他自变量进行计算，模型结果表明:行人或车辆到达时间、行人延误、车辆速度、行人速度、年龄、性别、交通小时、交通时间、研究发现，基于随机森林法、极梯度Boosting法和二元Logit模型的行人行为预测分别达到81.72%、77.19%和74.95%，K近邻算法、人工神经网络RKS算法和支持向量机算法在前一步具有不同的分类性能。
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News-Current study results on Machine Learning have be en published. According to news originating from Bhopal, India, by NewsRx corres pondents, research stated, "The primary safety hazard at unsignalized intersecti ons, particularly in urban areas, is pedestrian-vehicle collisions. Due to its c omplexity and inattention, pedestrian crossing behaviour has a significant impac t on their safety." Our news journalists obtained a quote from the research from the Maulana Azad Na tional Institute of Technology, "This study introduces a novel framework to enha nce pedestrian safety at unsignalized intersections by developing a predictive m odel of pedestrian crossing behaviour using machine learning algorithms. While a ccounting for crossing behaviour as the dependent variable and other independent variables, the analysis prioritises accuracy and internal validity. Important f eature scores for the different algorithms were assessed. The model results reve aled that the arrival first of a pedestrian or vehicle, pedestrian delay, vehicl e speed, pedestrian speed, age, gender, traffic hour, and vehicle category are h ighly influencing variables for analysing pedestrian behaviour while crossing at unsignalized intersections. This study found that the prediction of pedestrian behaviour based on random forest, extreme gradient boosting and binary logit mod el achieved 81.72%, 77.19% and 74.95%, r espectively. Algorithms, including k-nearest neighbours, artificial neural netwo rks, and support vector machines, have varying classification performance at eve ry step."
NETL
NSTL