Predicting the Spatial Impact of Planned Special Events
| Autor: | Simon Kwoczek, Sergio Di Martino, Silvia Rossi |
|---|---|
| Přispěvatelé: | Kawai Y.,Storandt S.,Sumiya K., Di Martino, Sergio, Kwoczek, Simon, Rossi, Silvia |
| Jazyk: | angličtina |
| Rok vydání: | 2019 |
| Předmět: |
050101 languages & linguistics
Computer science Event (computing) 05 social sciences 02 engineering and technology Special events League Pipeline (software) Intelligent Transportation Systems Routing Machine Learning Transport engineering 0202 electrical engineering electronic engineering information engineering Neighbor classifier 020201 artificial intelligence & image processing 0501 psychology and cognitive sciences Road traffic |
| Zdroj: | Web and Wireless Geographical Information Systems ISBN: 9783030172459 W2GIS |
| Popis: | 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|