Stuck Around the Stadium? An Approach to Identify Road Segments Affected by Planned Special Events

The recent availability of large amount of mobility data has fostered many research efforts to improve mobility prediction. Lots of these studies are focused on learning the impact of influencing factors on traffic, such as rush hour or accidents. Nevertheless, only very few have investigated the impact of Planned Special Events (PSEs), such as concerts, soccer games, etc., despite their well-known influence on traffic. In this paper we present an automatic solution to model the impact of PSEs on traffic around the venue of the events. In particular, we answer the question of "which road segments are affected by PSEs?" by identifying which roads show an event specific behavior that can identify the happening of a PSE reliably. For that, we propose a solution based on an Artificial Neural Network (ANN) classifier that is trained on traffic data on event and non-event days for each road. The proposed approach has been evaluated on two different venues in Germany with a leave-one-out cross-validation performed on all the soccer matches played in those locations during the season 2013/14 of the German First League. Results show that the approach can reliably identify road segments affected by PSEs, with an F-Measure up to 0.97.

[1]  Chetan Gupta,et al.  Forecasting Spatiotemporal Impact of Traffic Incidents on Road Networks , 2013, 2013 IEEE 13th International Conference on Data Mining.

[2]  Eric Horvitz,et al.  Prediction, Expectation, and Surprise: Methods, Designs, and Study of a Deployed Traffic Forecasting Service , 2005, UAI.

[3]  Emilia Mendes,et al.  Using tabu search to configure support vector regression for effort estimation , 2013, Empirical Software Engineering.

[4]  J. Manyika.  Big data: The next frontier for innovation, competition, and productivity , 2011 .

[5]  Wolfgang Nejdl,et al.  Predicting and visualizing traffic congestion in the presence of planned special events , 2014, J. Vis. Lang. Comput..

[6]  Jan-Ming Ho,et al.  Travel time prediction with support vector regression , 2003, Proceedings of the 2003 IEEE International Conference on Intelligent Transportation Systems.

[7]  Roland Chrobok,et al.  Different methods of traffic forecast based on real data , 2004, Eur. J. Oper. Res..

[8]  Robert J. Schalkoff,et al.  Artificial neural networks , 1997 .

[9]  Wolfgang Nejdl,et al.  Predicting Traffic Congestion in Presence of Planned Special Events , 2014, DMS.

[10]  Laurence R. Rilett,et al.  Spectral Basis Neural Networks for Real-Time Travel Time Forecasting , 1999 .

[11]  Eleni I. Vlahogianni,et al.  Short-term traffic forecasting: Where we are and where we’re going , 2014 .

[12]  Xiaoyan Zhang,et al.  Short-term travel time prediction , 2003 .

[13]  P. Varaiya,et al.  Components of Congestion: Delay from Incidents, Special Events, Lane Closures, Weather, Potential Ramp Metering Gain, and Excess Demand , 2006 .

[14]  Sherif Ishak,et al.  Performance evaluation of short-term time-series traffic prediction model , 2002 .

[15]  Qiu Hong-tong,et al.  Study on traffic organization and management strategies for large special events , 2012, 2012 International Conference on System Science and Engineering (ICSSE).

[16]  Eleni I. Vlahogianni,et al.  Statistical methods versus neural networks in transportation research: Differences, similarities and some insights , 2011 .

[17]  J. W. C. van Lint,et al.  Online Learning Solutions for Freeway Travel Time Prediction , 2008, IEEE Transactions on Intelligent Transportation Systems.

[18]  L. Vanajakshi,et al.  A comparison of the performance of artificial neural networks and support vector machines for the prediction of traffic speed , 2004, IEEE Intelligent Vehicles Symposium, 2004.