2017
DOI: 10.1016/j.trpro.2017.03.063
|View full text |Cite
|
Sign up to set email alerts
|

Identifying patterns under both normal and abnormal traffic conditions for short-term traffic prediction

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
19
0

Year Published

2018
2018
2024
2024

Publication Types

Select...
5
3

Relationship

0
8

Authors

Journals

citations
Cited by 28 publications
(19 citation statements)
references
References 24 publications
0
19
0
Order By: Relevance
“…Next, the ST-DBSCAN clustering algorithm was used to cluster the Waze user reports. DBSCAN (density-based spatial clustering of applications with noise), introduced by Westerman et al ( 21 ) in 1996, is one of the most widely used density-based clustering algorithms and has been extensively applied in the transportation field, such as traffic congestion detection ( 22 , 23 ) and traffic incident detection ( 24 ). The main reason for using DBSCAN is that it is suitable for spatial clustering and can identify clusters with any shape.…”
Section: Network-based Spatial-temporal Clusteringmentioning
confidence: 99%
“…Next, the ST-DBSCAN clustering algorithm was used to cluster the Waze user reports. DBSCAN (density-based spatial clustering of applications with noise), introduced by Westerman et al ( 21 ) in 1996, is one of the most widely used density-based clustering algorithms and has been extensively applied in the transportation field, such as traffic congestion detection ( 22 , 23 ) and traffic incident detection ( 24 ). The main reason for using DBSCAN is that it is suitable for spatial clustering and can identify clusters with any shape.…”
Section: Network-based Spatial-temporal Clusteringmentioning
confidence: 99%
“…Allström et al [35] suggested using non‐parametric models for traffic prediction under recurrent traffic conditions and using parametric models under non‐recurring traffic conditions. Salamanis et al [36] clustered traffic flow and incident data into different categories and built different models using the data in different clusters. The authors reported improved results by using different models per class.…”
Section: Related Workmentioning
confidence: 99%
“…The clustering methods group road links according to their similarity in terms of traffic properties. The clustering methods have wide applications in traffic pattern extraction as they can consider various traffic features [14][15][16]. To obtain more accurate results, several NN methods are applied in traffic data analysis, such as local artificial neural networks [20], fuzzy neural networks [8], and sequence graph neural networks [21].…”
Section: Data-driven Traffic Monitoringmentioning
confidence: 99%
“…Several transport attributes have been recognized from various data sources, for example, road network [6], travel speed [7], travel volume [8], and traffic congestion [9]. A set of effective approaches has been developed for analyzing road traffic, which includes statistics-based methods [10][11][12][13] and clustering-based methods [14][15][16]. For example, Zou et al [17] examined road traffic using long-term vehicle trajectories and identified the spatial dependency of the traffic state via spatial autocorrelation.…”
Section: Introductionmentioning
confidence: 99%