• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>Transportation Research Board Annual meeting >THE GROUP LEAST ABSOLUTE SHRINKAGE AND SELECTION OPERAT OR “GLASSO” TECHNIQUE: APPLICATION IN VARIABLE SELECTION AND CRASH PREDICTION AT UNSIGNALIZED INTERSECTIONS
【24h】

THE GROUP LEAST ABSOLUTE SHRINKAGE AND SELECTION OPERAT OR “GLASSO” TECHNIQUE: APPLICATION IN VARIABLE SELECTION AND CRASH PREDICTION AT UNSIGNALIZED INTERSECTIONS

机译：小组绝对收缩和选择操作符或“玻璃”技术：在无信号交叉口的可变选择和碰撞预测中的应用

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

In this paper, we propose a new promising machine learning technique to select importantexplanatory covariates, as well as to improve crash prediction; the group least absolute shrinkageand selection operator (GLASSO) technique. GLASSO’s main strength lies in its ability to dealwith datasets having relatively large number of categorical variables, which is the case in thisstudy. Identifying the significant factors affecting safety of unsignalized intersections was alsoan essential objective. Two applications of GLASSO were investigated; application for variablescreening before fitting the traditional negative binomial (NB) model, as well as before fittinganother promising data mining technique (the multivariate adaptive regression splines “MARS”).Extensive data collected at 2475 unsignalized intersections were used. For fitting the NB models,the backward deletion and the random forest techniques were separately used as variablesscreening, and their prediction performance was compared to that from GLASSO. All the threemethods resulted in almost similar predictions. For GLASSO’s second application with MARS,the model fitting relatively outperformed that from the random forest technique with MARS,with similar prediction performance. Due to its outstanding performance with categoricalvariables, as well as its simplicity, GLASSO is recommended as a promising variable selectiontechnique. Significant predictors affecting total crashes at unsignalized intersections were trafficvolume on the major road, the upstream and downstream distances to the nearest signalizedintersection, median type on major and minor approaches, and type of land use. Resemblingprevious studies, the volume of traffic was the most important predictor.
机译：在本文中，我们提出了一种新的有前途的机器学习技术来选择重要的 解释性协变量，以及改善碰撞预测;组中最小绝对收缩 和选择运算符（GLASSO）技术。 GLASSO的主要优势在于其处理能力 具有相对大量分类变量的数据集，在这种情况下就是这种情况 学习。确定影响无信号交叉口安全性的重要因素也是 一个基本目标。研究了GLASSO的两种应用;申请变量 在拟合传统负二项式（NB）模型之前以及在拟合之前进行筛查 另一种有前途的数据挖掘技术（多元自适应回归样条“ MARS”）。 使用了在2475个无信号交叉口收集的大量数据。为了安装NB型号， 向后删除和随机森林技术分别用作变量 筛选，并将其预测性能与GLASSO的预测性能进行比较。全部三个 方法得出的预测几乎相似。对于GLASSO在MARS上的第二次申请， 该模型的拟合相对优于采用MARS的随机森林技术的模型， 具有相似的预测性能由于其出色的分类性能 变量及其简单性，建议使用GLASSO作为有前途的变量选择 技术。影响无信号交叉口总事故的重要预测因素是交通 主要道路上的交通量，到最近信号通知的上游和下游距离 交叉点，主要和次要途径的中位数类型以及土地使用类型。相似 在以前的研究中，流量是最重要的预测指标。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号