• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>Coat international conference of transportation professionals >Feature Extraction of Urban Traffic Network Data Based on Locally Sensitive Discriminant Analysis Algorithm
【24h】

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

机译：基于局部敏感判别分析算法的城市交通网络数据特征提取

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

摘要

The urban road network state can be characterized by diversiform parameters of all links; however, it is difficult to directly express the road network's state by these parameters. Thus, a synthetic evaluation index should be extracted from various parameters to express the road network's state comprehensively and intuitively. This paper proposes a novel model for extracting temporal and spatial features in a networked traffic system, Locality Sensitive Discriminant Analysis (LSDA) is used to reduce data dimensionality and extract features from traffic data analysis. Selected link and parameter data points are compressed and the output matrix has fewer dimensions than the original data. The corresponding relationship between the synthetic evaluation index and various parameters is analyzed. Simulation results prove that this method is effective in revealing hidden patterns in traffic data and the synthetic evaluation index can express the evolution of road network state comprehensively and accurately.
机译：城市道路网络状态可以通过所有链路的各种参数来表征。但是，通过这些参数难以直接表示道路网的状态。因此，应该从各种参数中提取综合评价指标，以全面，直观地表达路网的状态。本文提出了一种新型的网络交通系统中时空特征提取模型，采用局部敏感判别分析（LSDA）来减少数据维数，并从交通数据分析中提取特征。选定的链接和参数数据点被压缩，并且输出矩阵的维数少于原始数据的维数。分析了综合评价指标与各种参数之间的对应关系。仿真结果表明，该方法能有效地揭示交通数据中的隐患，综合评价指标能够全面，准确地表达路网状态的演变。

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