2016
DOI: 10.1016/j.trc.2015.11.002
|View full text |Cite
|
Sign up to set email alerts
|

A spatiotemporal correlative k-nearest neighbor model for short-term traffic multistep forecasting

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
4
1

Citation Types

2
181
0
1

Year Published

2016
2016
2022
2022

Publication Types

Select...
6
4

Relationship

0
10

Authors

Journals

citations
Cited by 350 publications
(185 citation statements)
references
References 24 publications
2
181
0
1
Order By: Relevance
“…Main drawback can be assumption of an underlying DGP distribution, higher computational time in case of high dimensional state transition, and need of retraining to update estimated state distributions. Location depended k-NN method is presented by (Cai et al (2016)) in an attempt to address similarity in historical data and spatial correlations. The method uses large datasets for up to an hour-step speed predictions.…”
Section: Introductionmentioning
confidence: 99%
“…Main drawback can be assumption of an underlying DGP distribution, higher computational time in case of high dimensional state transition, and need of retraining to update estimated state distributions. Location depended k-NN method is presented by (Cai et al (2016)) in an attempt to address similarity in historical data and spatial correlations. The method uses large datasets for up to an hour-step speed predictions.…”
Section: Introductionmentioning
confidence: 99%
“…Different terms, such as spatial dependency/relationship in traffic [1,2] and spatial correlation [3][4][5][6], are used in the literature to express such relationship between neighboring roads. In this paper, we use the term traffic interaction to describe the traffic influence between neighboring roads, which is fundamentally caused by the dynamic vehicle movements from one road to another.…”
Section: Introductionmentioning
confidence: 99%
“…In recent years, the applications of computational intelligence-based models were the focal point in literature including Neural and Bayesian Networks [18,19], Support Vector Regression (SVR) [20], k-nearest neighbours [21,22], regression trees [23,24], etc. This type of models was considered as inevitable, particularly as most classical approaches have been shown inadequate under unstable traffic conditions and complex road settings when and where it is needed [25].…”
Section: General Description Of Srmentioning
confidence: 99%