Details
| Originalsprache | Englisch |
|---|---|
| Aufsatznummer | 248 |
| Fachzeitschrift | ISPRS International Journal of Geo-Information |
| Jahrgang | 10 |
| Ausgabenummer | 4 |
| Publikationsstatus | Veröffentlicht - 8 Apr. 2021 |
Abstract
The discovery of spatio-temporal dependencies within urban road networks that cause Recurrent Congestion (RC) patterns is crucial for numerous real-world applications, including urban planning and the scheduling of public transportation services. While most existing studies investigate temporal patterns of RC phenomena, the influence of the road network topology on RC is often over-looked. This article proposes the ST-DISCOVERY algorithm, a novel unsupervised spatio-temporal data mining algorithm that facilitates effective data-driven discovery of RC dependencies induced by the road network topology using real-world traffic data. We factor out regularly reoccurring traffic phenomena, such as rush hours, mainly induced by the daytime, by modelling and systematically exploiting temporal traffic load outliers. We present an algorithm that first constructs connected subgraphs of the road network based on the traffic speed outliers. Second, the algorithm identifies pairs of subgraphs that indicate spatio-temporal correlations in their traffic load behaviour to identify topological dependencies within the road network. Finally, we rank the identified subgraph pairs based on the dependency score determined by our algorithm. Our experimental results demonstrate that ST-DISCOVERY can effectively reveal topological dependencies in urban road networks.
ASJC Scopus Sachgebiete
- Sozialwissenschaften (insg.)
- Geografie, Planung und Entwicklung
- Erdkunde und Planetologie (insg.)
- Computer in den Geowissenschaften
- Erdkunde und Planetologie (insg.)
- Erdkunde und Planetologie (sonstige)
Ziele für nachhaltige Entwicklung
Zitieren
- Standard
- Harvard
- Apa
- Vancouver
- BibTex
- RIS
in: ISPRS International Journal of Geo-Information, Jahrgang 10, Nr. 4, 248, 08.04.2021.
Publikation: Beitrag in Fachzeitschrift › Artikel › Forschung › Peer-Review
}
TY - JOUR
T1 - Mining topological dependencies of recurrent congestion in road networks
AU - Tempelmeier, Nicolas
AU - Feuerhake, Udo
AU - Wage, Oskar
AU - Demidova, Elena
N1 - Funding Information: Funding: This work is partially funded by the BMBF and the BMWi, Germany under the projects “Data4UrbanMobility” (grant ID 02K15A040), “USEfUL” (grant ID 03SF0547), “CampaNeo” (grant ID 01MD19007B), “d-E-mand” (grant ID 01ME19009B), the European Commission (EU H2020, “smashHit”, grant-ID 871477) as well as by the research initiatives “Mobiler Mensch” and “Urbane Logistik Hannover”.
PY - 2021/4/8
Y1 - 2021/4/8
N2 - The discovery of spatio-temporal dependencies within urban road networks that cause Recurrent Congestion (RC) patterns is crucial for numerous real-world applications, including urban planning and the scheduling of public transportation services. While most existing studies investigate temporal patterns of RC phenomena, the influence of the road network topology on RC is often over-looked. This article proposes the ST-DISCOVERY algorithm, a novel unsupervised spatio-temporal data mining algorithm that facilitates effective data-driven discovery of RC dependencies induced by the road network topology using real-world traffic data. We factor out regularly reoccurring traffic phenomena, such as rush hours, mainly induced by the daytime, by modelling and systematically exploiting temporal traffic load outliers. We present an algorithm that first constructs connected subgraphs of the road network based on the traffic speed outliers. Second, the algorithm identifies pairs of subgraphs that indicate spatio-temporal correlations in their traffic load behaviour to identify topological dependencies within the road network. Finally, we rank the identified subgraph pairs based on the dependency score determined by our algorithm. Our experimental results demonstrate that ST-DISCOVERY can effectively reveal topological dependencies in urban road networks.
AB - The discovery of spatio-temporal dependencies within urban road networks that cause Recurrent Congestion (RC) patterns is crucial for numerous real-world applications, including urban planning and the scheduling of public transportation services. While most existing studies investigate temporal patterns of RC phenomena, the influence of the road network topology on RC is often over-looked. This article proposes the ST-DISCOVERY algorithm, a novel unsupervised spatio-temporal data mining algorithm that facilitates effective data-driven discovery of RC dependencies induced by the road network topology using real-world traffic data. We factor out regularly reoccurring traffic phenomena, such as rush hours, mainly induced by the daytime, by modelling and systematically exploiting temporal traffic load outliers. We present an algorithm that first constructs connected subgraphs of the road network based on the traffic speed outliers. Second, the algorithm identifies pairs of subgraphs that indicate spatio-temporal correlations in their traffic load behaviour to identify topological dependencies within the road network. Finally, we rank the identified subgraph pairs based on the dependency score determined by our algorithm. Our experimental results demonstrate that ST-DISCOVERY can effectively reveal topological dependencies in urban road networks.
KW - Recurrent congestion
KW - Road network analysis
KW - Spatio-temporal data mining
UR - http://www.scopus.com/inward/record.url?scp=85106489117&partnerID=8YFLogxK
U2 - 10.3390/ijgi10040248
DO - 10.3390/ijgi10040248
M3 - Article
AN - SCOPUS:85106489117
VL - 10
JO - ISPRS International Journal of Geo-Information
JF - ISPRS International Journal of Geo-Information
SN - 2220-9964
IS - 4
M1 - 248
ER -