While it is widely acknowledged that Planned Special Events (PSEs), such as concerts, soccer games, etc., have a strong impact on road traffic, very few studies have quantitatively investigated this phenomenon. In this paper we present the preliminary results of a technique to quantify the impact of PSEs on traffic around the venue of the events. In particular, our goal was to automatically identify all those road segments around a venue that show a different traffic behavior on event days than on non-event days. To this aim, we defined a specific pipeline, including a K-Nearest Neighbor classifier, trained on traffic data of event and non-event days for each road, using the Dynamic Time Warp (DTW) as distance metric. The proposed solutions has been empirically evaluated on four PSE venues in Germany. Two of them hosted only soccer matches of the German First League, while the other two had mixed types of PSEs, including sport, concerts and other categories of events. Results are very positive for the soccer stadiums, while more research is needed for the venues hosting mixed types of PSEs.

Predicting the Spatial Impact of Planned Special Events / Di Martino, Sergio; Kwoczek, Simon; Rossi, Silvia. - 11474:(2019), pp. 102-117. (Intervento presentato al convegno 17th International Symposium on Web and Wireless Geographical Information Systems, W2GIS 2019 tenutosi a Giappone nel 2019) [10.1007/978-3-030-17246-6_9].

Predicting the Spatial Impact of Planned Special Events

Di Martino, Sergio
;
Rossi, Silvia
2019

Abstract

While it is widely acknowledged that Planned Special Events (PSEs), such as concerts, soccer games, etc., have a strong impact on road traffic, very few studies have quantitatively investigated this phenomenon. In this paper we present the preliminary results of a technique to quantify the impact of PSEs on traffic around the venue of the events. In particular, our goal was to automatically identify all those road segments around a venue that show a different traffic behavior on event days than on non-event days. To this aim, we defined a specific pipeline, including a K-Nearest Neighbor classifier, trained on traffic data of event and non-event days for each road, using the Dynamic Time Warp (DTW) as distance metric. The proposed solutions has been empirically evaluated on four PSE venues in Germany. Two of them hosted only soccer matches of the German First League, while the other two had mixed types of PSEs, including sport, concerts and other categories of events. Results are very positive for the soccer stadiums, while more research is needed for the venues hosting mixed types of PSEs.
2019
9783030172459
Predicting the Spatial Impact of Planned Special Events / Di Martino, Sergio; Kwoczek, Simon; Rossi, Silvia. - 11474:(2019), pp. 102-117. (Intervento presentato al convegno 17th International Symposium on Web and Wireless Geographical Information Systems, W2GIS 2019 tenutosi a Giappone nel 2019) [10.1007/978-3-030-17246-6_9].
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11588/753396
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 3
  • ???jsp.display-item.citation.isi??? 2
social impact