交通运输系统工程与信息

交通运输系统工程与信息 ›› 2016, Vol. 16 ›› Issue (3): 95-100.

• 智能交通系统与信息技术 • 上一篇    下一篇

基于局部敏感判别分析的路网状态特征 提取模型研究

徐丽香1，2，王云鹏1，2，于海洋*1   

  1. 1. 北京航空航天大学交通科学与工程学院，北京100191； 2. 城市交通管理集成与优化技术公安部重点实验室，合肥230088
  • 收稿日期:2015-11-09 修回日期:2016-01-06 出版日期:2016-06-25 发布日期:2016-06-27
  • 作者简介:徐丽香（1990-），女，山东日照人，硕士生.
  • 基金资助:

    国家自然科学基金/National Natural Science Foundation of China（51308021）

Feature Extraction Model of Urban Traffic Network Data Based on Locality Sensitive Discriminant Analysis Algorithm

XU Li-xiang1,2，WANG Yun-peng1,2，YU Hai-yang1,2   

  1. 1. School of Transportation Science and Engineering, Beihang University, Beijing 100191, China; 2. Key Laboratory of Urban ITS Technology Optimization and Integration Ministry of Public Security, People’s Republic of China, Hefei 230088, China
  • Received:2015-11-09 Revised:2016-01-06 Online:2016-06-25 Published:2016-06-27

PDF

被引次数

1

摘要：

为简化路网状态表达，最大限度地实现路网信息增值，本文构建了从海量历史 交通数据中提取特征参量来表达路网运行状态的模型.模型选取城市区域路网的流量、车 速和密度数据，综合考虑交通数据的非线性和相关性，基于自适应邻域选择的局部敏感 判别分析算法，实现城市路网数据特征提取.通过实例验证了模型的有效性.结果表明：本 文得到的特征参量能有效地描述路网状态变化的24 h 周期性，可直观反映早晚高峰现象 及工作日与周末的区别性；与核主成分分析算法比较，模型得到的特征参量具有可分性 更好的特点，可以表达宏观路网运行状态，为交通管理者提供决策依据.

关键词: 城市交通, 特征提取, 局部敏感判别分析, 路网状态, 自适应邻域选择

Abstract:

To simplify the way of expressing road network state and maximize the value of network information, this paper constructs a model of extracting feature parameter from massive historical traffic data to express road network running state. In this model, the flow, speed and density data of road network in urban areas are selected, considering the nonlinearity and correlation of traffic data, the feature of urban road network data is extracted based on adaptive neighborhood selection of local sensitive discriminant analysis algorithm (ANS-LSDA). Examples demonstrate the effectiveness of the model, results show that feature parameter obtained in this paper can effectively describe the road network 24 h periodicity, directly reflect the phenomenon of morning and evening peak as well as the difference between weekday and weekend. Compared to kernel principal component analysis (KPCA), the feature parameter of ANS-LSDA model has better divisibility, which can express macro road network running state and provide basis for traffic managers in decision making

Key words: urban traffic, feature extraction, locality sensitive discriminant analysis, state road network, adaptive neighborhood selection

中图分类号: