An Unsupervised Learning Approach for Analyzing Traffic Impacts under Arterial Road Closures: Case Study of East Liberty in Pittsburgh

AbstractThis paper adopts an unsupervised learning approach, k-means clustering, to analyze the arterial traffic flow data over a high-dimensional spatiotemporal feature space. As part of the adaptive traffic control system deployed around the East Liberty area in Pittsburgh, high-resolution traffic occupancies and counts are available at the lane level in virtually any time resolution. The k-means clustering method is used to analyze those data to understand the traffic patterns before and after the closure and reopening of an arterial bridge. The modeling framework also holds great potentials for predicting traffic flow and detect incidents. The main findings are that clustering on high-dimensional spatiotemporal features can effectively distinguish flow patterns before and after road closure and reopening and between weekends and weekdays. On arterial streets, clustering based on 5-min data is sufficient to eliminate potential distortion on measurements caused by signals. Either of the two, count or oc...

[1]  M. Karlaftis,et al.  Public Transportation during the Athens 2004 Olympics: From Planning to Performance Evaluation , 2006 .

[2]  R. Hall,et al.  Effects of the Los Angeles transit strike on highway congestion , 2006 .

[3]  A. R. Cook,et al.  ANALYSIS OF FREEWAY TRAFFIC TIME-SERIES DATA BY USING BOX-JENKINS TECHNIQUES , 1979 .

[4]  Henry X. Liu,et al.  Modeling the day-to-day traffic evolution process after an unexpected network disruption , 2012 .

[5]  J. Hunt,et al.  Responses to Centre Street Bridge Closure: Where the “Disappearing” Travelers Went , 2002 .

[6]  Joseph L. Schofer,et al.  Arterial incident detection using fixed detector and probe vehicle data , 1995 .

[7]  Fang Yuan,et al.  INCIDENT DETECTION USING SUPPORT VECTOR MACHINES , 2003 .

[8]  Carroll J Messer,et al.  Incident detection on urban freeways , 1974 .

[9]  E R Case,et al.  DEVELOPMENT OF FREEWAY INCIDENT-DETECTION ALGORITHMS BY USING PATTERN-RECOGNITION TECHNIQUES , 1979 .

[10]  Stephanie E. Chang,et al.  Measuring post-disaster transportation system performance: the 1995 Kobe earthquake in comparative perspective , 2001 .

[11]  T. Golob,et al.  Relationships Among Urban Freeway Accidents, Traffic Flow, Weather and Lighting Conditions , 2001 .

[12]  Baher Abdulhai,et al.  Enhancing the universality and transferability of freeway incident detection using a Bayesian-based neural network , 1999 .

[13]  Sergei Vassilvitskii,et al.  k-means++: the advantages of careful seeding , 2007, SODA '07.

[14]  P K Houpt,et al.  Dynamic model-based techniques for the detection of incidents on freeways , 1980 .

[15]  Hillel Bar-Gera,et al.  Evaluating the assumption of independent turning probabilities , 2006 .

[16]  Zhen Qian,et al.  What Happens When a Major Freeway is Closed for Repair? , 2012 .

[17]  Henry X. Liu,et al.  Bounded rationality and irreversible network change , 2011 .

[18]  Yi Qi,et al.  Application of wavelet technique to freeway incident detection , 2003 .

[19]  J A Martin,et al.  AUTOMATIC INCIDENT DETECTION - TRRL ALGORITHMS HIOCC AND PATREG , 1979 .

[20]  M. Brusco,et al.  A variable-selection heuristic for K-means clustering , 2001 .

[21]  Mgh Bell,et al.  AUTOMATIC DETECTION OF TRAFFIC INCIDENTS ON A SIGNAL-CONTROLLED ROAD NETWORK , 1988 .

[22]  David M Levinson,et al.  The Traffic and Behavioral Effects of the I-35W Mississippi River Bridge Collapse , 2010 .

[23]  J. MacQueen.  Some methods for classification and analysis of multivariate observations , 1967 .

[24]  Sally Cairns,et al.  TRAFFIC IMPACT OF HIGHWAY CAPACITY REDUCTIONS: ASSESSMENT OF THE EVIDENCE. , 1998 .

[25]  G. Giuliano,et al.  Impacts of the Northridge Earthquake on transit and highway use , 1998 .