Analyzing spatiotemporal congestion pattern on urban roads based on taxi GPS data

With the development of in-vehicle data collection devices, GPS trajectory has become a priority source to identify traffic congestion and understand the operational states of road network in recent years. This study aims to investigate the relationship between traffic congestion and built environm...

Full description

Saved in:
Bibliographic Details
Main Authors: Kaisheng Zhang, Daniel (Jian) Sun, Suwan Shen, Yi Zhu
Format: Article
Language:English
Published: University of Minnesota Libraries Publishing 2017-06-01
Series:Journal of Transport and Land Use
Subjects:
Online Access:https://www.jtlu.org/index.php/jtlu/article/view/954
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849695417132908544
author Kaisheng Zhang
Daniel (Jian) Sun
Suwan Shen
Yi Zhu
author_facet Kaisheng Zhang
Daniel (Jian) Sun
Suwan Shen
Yi Zhu
author_sort Kaisheng Zhang
collection DOAJ
description With the development of in-vehicle data collection devices, GPS trajectory has become a priority source to identify traffic congestion and understand the operational states of road network in recent years. This study aims to investigate the relationship between traffic congestion and built environment, including traffic related factors and land use. Fuzzy C-means clustering was used to conduct an exhaustive study on 24-hour congestion pattern of road segments in urban area, so that the spatial autoregressive moving average model (SARMA) was introduced to analyze the output from the clustering analysis to establish the relationship between built environment and the 24-hour congestion pattern. The clustering result classified the road segments into four congestion levels, while the regression explained 12 traffic-related factors and land use factors’ impact on road congestion pattern. The continuous congestion was found to mainly occur in the city center, and the factors, such as road type, bus station in the vicinity, ramp nearby, commercial land use and so on have large impact on congestion formation. The Fuzzy C-means clustering was proposed to be combined with quantitative spatial regression, and the overall evaluation process will assist to assess the spatial-temporal levels of service of traffic from the congestion perspective.
format Article
id doaj-art-94a84955a3f04579b19ebeafce619cd9
institution DOAJ
issn 1938-7849
language English
publishDate 2017-06-01
publisher University of Minnesota Libraries Publishing
record_format Article
series Journal of Transport and Land Use
spelling doaj-art-94a84955a3f04579b19ebeafce619cd92025-08-20T03:19:47ZengUniversity of Minnesota Libraries PublishingJournal of Transport and Land Use1938-78492017-06-0110110.5198/jtlu.2017.954267Analyzing spatiotemporal congestion pattern on urban roads based on taxi GPS dataKaisheng Zhang0Daniel (Jian) Sun1Suwan Shen2Yi Zhu3Shanghai Jiao Tong UniversityShanghai Jiao Tong UniversityUniversity of Hawaii, ManoaShanghai Jiao Tong UniversityWith the development of in-vehicle data collection devices, GPS trajectory has become a priority source to identify traffic congestion and understand the operational states of road network in recent years. This study aims to investigate the relationship between traffic congestion and built environment, including traffic related factors and land use. Fuzzy C-means clustering was used to conduct an exhaustive study on 24-hour congestion pattern of road segments in urban area, so that the spatial autoregressive moving average model (SARMA) was introduced to analyze the output from the clustering analysis to establish the relationship between built environment and the 24-hour congestion pattern. The clustering result classified the road segments into four congestion levels, while the regression explained 12 traffic-related factors and land use factors’ impact on road congestion pattern. The continuous congestion was found to mainly occur in the city center, and the factors, such as road type, bus station in the vicinity, ramp nearby, commercial land use and so on have large impact on congestion formation. The Fuzzy C-means clustering was proposed to be combined with quantitative spatial regression, and the overall evaluation process will assist to assess the spatial-temporal levels of service of traffic from the congestion perspective.https://www.jtlu.org/index.php/jtlu/article/view/954Congestion PatternTaxi GPS DataFuzzy C-means ClusterSpatiotemporal RegressionBuilt Environment Factor
spellingShingle Kaisheng Zhang
Daniel (Jian) Sun
Suwan Shen
Yi Zhu
Analyzing spatiotemporal congestion pattern on urban roads based on taxi GPS data
Journal of Transport and Land Use
Congestion Pattern
Taxi GPS Data
Fuzzy C-means Cluster
Spatiotemporal Regression
Built Environment Factor
title Analyzing spatiotemporal congestion pattern on urban roads based on taxi GPS data
title_full Analyzing spatiotemporal congestion pattern on urban roads based on taxi GPS data
title_fullStr Analyzing spatiotemporal congestion pattern on urban roads based on taxi GPS data
title_full_unstemmed Analyzing spatiotemporal congestion pattern on urban roads based on taxi GPS data
title_short Analyzing spatiotemporal congestion pattern on urban roads based on taxi GPS data
title_sort analyzing spatiotemporal congestion pattern on urban roads based on taxi gps data
topic Congestion Pattern
Taxi GPS Data
Fuzzy C-means Cluster
Spatiotemporal Regression
Built Environment Factor
url https://www.jtlu.org/index.php/jtlu/article/view/954
work_keys_str_mv AT kaishengzhang analyzingspatiotemporalcongestionpatternonurbanroadsbasedontaxigpsdata
AT danieljiansun analyzingspatiotemporalcongestionpatternonurbanroadsbasedontaxigpsdata
AT suwanshen analyzingspatiotemporalcongestionpatternonurbanroadsbasedontaxigpsdata
AT yizhu analyzingspatiotemporalcongestionpatternonurbanroadsbasedontaxigpsdata