American Society of Civil Engineers


Applying Locally Linear Embedding on Feature Extraction of Traffic Flow Data


by Yenan Chen, (Department of Automation, Tsinghua University, Haidian District, Beijing 100084, China E-mail: chenyn06@mails.tsinghua.edu.cn), Jianming Hu, (Associate Professor, Tsinghua University, Haidian District, Beijing 100084, China E-mail: hujm@mail.tsinghua.edu.cn), Yi Zhang, (No affiliation information available.), and Di Li, (No affiliation information available.)

pp. 891-902, (doi:  http://dx.doi.org/10.1061/41123(383)84)

     Access full text
     Purchase Subscription
     Permissions for Reuse  

Document type: Conference Proceeding Paper
Part of: Traffic and Transportation Studies 2010
Abstract: We encounter high dimensional data when using time series vector to describe the traffic flow of a certain link during some time period, or using flow data from different links to describe the traffic status of a region at a certain time point. This paper applies a dimensionality reduction method, named Locally Linear Embedding (LLE) to extract temporal and spatial features out of these high dimensional traffic flow data. LLE can visualize our data in a low dimension space, thus giving a vivid perspective on the emerging features. According to these features, we can put links into different clusters and better interpret the evolution of traffic patterns. Furthermore, comparison between linear dimensionality reduction method, PCA and LLE is carried out. The result shows that LLE has better performance.


ASCE Subject Headings:
Traffic flow
Data analysis