TY - JOUR

T1 - Predicting and visualizing traffic congestion in the presence of planned special events

AU - Kwoczek, Simon

AU - Di Martino, Sergio

AU - Nejdl, Wolfgang

N1 - Funding information: The research leading to these results has been partly funded by the European Community?s Seventh Framework Programme (FP7/2007-2013) under grant agreement no. 610990 – Project COMPANION. The authors wish also to thank TomTom NV for providing the traffic data used in this research.

PY - 2014/11/7

Y1 - 2014/11/7

N2 - The recent availability of datasets on transportation networks with higher spatial and temporal resolution is enabling new research activities in the fields of Territorial Intelligence and Smart Cities. Among these, many research efforts are aimed at predicting traffic congestions to alleviate their negative effects on society, mainly by learning recurring mobility patterns. Within this field, in this paper we propose an integrated solution to predict and visualize non-recurring traffic congestion in urban environments caused by Planned Special Events (PSE), such as a soccer game or a concert. Predictions are done by means of two Machine Learning-based techniques. These have been proven to successfully outperform current state of the art predictions by 35% in an empirical assessment we conducted over a time frame of 7 months within the inner city of Cologne, Germany. The predicted congestions are fed into a specifically conceived visualization tool we designed to allow Decision Makers to evaluate the situation and take actions to improve mobility.

AB - The recent availability of datasets on transportation networks with higher spatial and temporal resolution is enabling new research activities in the fields of Territorial Intelligence and Smart Cities. Among these, many research efforts are aimed at predicting traffic congestions to alleviate their negative effects on society, mainly by learning recurring mobility patterns. Within this field, in this paper we propose an integrated solution to predict and visualize non-recurring traffic congestion in urban environments caused by Planned Special Events (PSE), such as a soccer game or a concert. Predictions are done by means of two Machine Learning-based techniques. These have been proven to successfully outperform current state of the art predictions by 35% in an empirical assessment we conducted over a time frame of 7 months within the inner city of Cologne, Germany. The predicted congestions are fed into a specifically conceived visualization tool we designed to allow Decision Makers to evaluate the situation and take actions to improve mobility.

KW - Geographic information systems

KW - Machine learning

KW - Mobility

KW - Traffic prediction

KW - Visualization

UR - http://www.scopus.com/inward/record.url?scp=85027939394&partnerID=8YFLogxK

U2 - 10.1016/j.jvlc.2014.10.028

DO - 10.1016/j.jvlc.2014.10.028

M3 - Article

AN - SCOPUS:85027939394

VL - 25

SP - 973

EP - 980

JO - Journal of Visual Languages and Computing

JF - Journal of Visual Languages and Computing

SN - 1045-926X

IS - 6

ER -