Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/10788
Title: Analysis of urban freeway traffic flow characteristics based on frequent pattern tree
Authors: Lin, L
Yuan, K
Ren, S
Issue Date: 2014
Publisher: Institute of Electrical and Electronics Engineers Inc.
Source: 2014 17th IEEE International Conference on Intelligent Transportation Systems, ITSC 2014, 2014, 6957941, p. 1719-1725 How to cite?
Abstract: Understanding the characteristics of urban freeway traffic flow plays an important role in traffic management. This paper was based on a detailed traffic dataset including traffic flow rate, density and speed with a resolution of fifteen minutes of the whole year 2005 from detector W64-07 at highway I-64 West, Virginia. These three variables, plus another three corresponding ones: season, day of the week and hour of the day, form the records of the new dataset I. Then for each variable of dataset I, fuzzy c-means method was applied, and the continuous values of each variable were replaced with the discrete cluster values, which produced the second new dataset II. At last, based on dataset II, frequent pattern tree was taken to find the most frequent patterns under certain combinations of season, day of the week and hour of the day. For these patterns, the statistical features of volume, velocity and density distributions were investigated and compared with each other. The results show season, day of the week and hour of the day all have impacts on the traffic characteristics. Besides that, the frequent patterns under congestion conditions were also analyzed. These frequent patterns can provide useful information for traffic control and guidance.
Description: 2014 17th IEEE International Conference on Intelligent Transportation Systems, ITSC 2014, 8-11 October 2014
URI: http://hdl.handle.net/10397/10788
ISBN: 9781479960781
DOI: 10.1109/ITSC.2014.6957941
Appears in Collections:Conference Paper

Access
View full-text via PolyU eLinks SFX Query
Show full item record

Page view(s)

33
Last Week
1
Last month
Checked on Aug 14, 2017

Google ScholarTM

Check

Altmetric



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.