Improvement of Search Strategy With K-Nearest Neighbors Approach for Traffic State Prediction

Oh, Simon; Byon, Young-Ji; Yeo, Hwasoo

doi:10.1109/tits.2015.2498408

Cited by 60 publications

(21 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As example it is possible to consider two interconnected tasks: search of digital educational resources [2][3][4] to texts of working programs and the automated formation of working programs of discipline on the basis of resources of network. In both cases on linguistic methods need of processing of partially structured text is imposed [5][6][7].…”

Section: Methodsmentioning

confidence: 99%

Intellectual Information System Of Subjects Methodological Support Based On The Web Search With Integrated Expert Evaluation

Grinchenkov¹,

Kushchiy²,

Kolomiets³

et al. 2019

Proceedings of the International Scientific-Practical Conference “Business Cooperation as a Resource of Sustainable Economic De

View full text Add to dashboard Cite

The relevance of the software product of electronic educational resources assessment for the purpose of their further integration into educational process is proved in the article. The basic principles of their search and examination procedure are determined. The general functional structure of intellectual system is considered, basic functions and components assignment of it are described. Architecture of developed information-retrieval system is determined. The basic principles of the procedure of their search are defined. The main screen forms showing work of system of thematic search are given.

show abstract

Section: Methodsmentioning

confidence: 99%

Intellectual Information System Of Subjects Methodological Support Based On The Web Search With Integrated Expert Evaluation

Grinchenkov¹,

Kushchiy²,

Kolomiets³

et al. 2019

Proceedings of the International Scientific-Practical Conference “Business Cooperation as a Resource of Sustainable Economic De

View full text Add to dashboard Cite

show abstract

“…Wilson et al [19] used the KNN approach to map the distribution and abundance of multiple tree species over large spatial domains. In the transportation field, researchers expanded the KNN method to develop searching algorithms to forecast traffic state (e.g., vehicle speed) based on previously observed traffic patterns [20,21]. Studying the proximity of point events can examine a typical spatial pattern-clustering, based on the assumption of spatial autocorrelation in which the attributes of one instance at a specific location are affected by the presence of other instances in geographic proximity.…”

Section: Spatial Analysis Of Crash Patternsmentioning

confidence: 99%

Evaluation of Spatial Resilience of Highway Networks in Response to Adverse Weather Conditions

Han

Zhang

2020

IJGI

View full text Add to dashboard Cite

Adverse weather poses a significant threat to the serviceability of highway infrastructure, as it causes more frequent and severe crash incidents. This study focuses on evaluating the resilience of highway networks by examining the crash-induced safety impact in response to extreme weather events. Unlike traditional service drop-based methods for resilience evaluation, this study endeavors to evaluate highway resilience in a spatial context. Three spatial metrics, including K-nearest neighbors, proximity to highways, and Kernel density hot spot, are introduced and employed to compare and analyze the spatial patterns (magnitude and distribution) of crashes in pre- and post-weather conditions. An illustrative example is also provided to showcase the applications of the proposed spatial resilience metrics for two study areas in the State of Illinois, U.S. The contribution of this study is to provide transportation practitioners with a tool to evaluate highway spatial resilience both visually and quantitatively, and ultimately improve highway safety and operation.

show abstract

“…In recent times, machine learning methods have gained significant popularity and are thus often used in this task as they can automatically learn the pattern of traffic dynamics. General practices include probabilistic graphical model (Antoniou, Koutsopoulos, & Yannis, ; Qi & Ishak, ; Zheng & Su, ) and k‐nearest neighbor method (Oh, Byon, & Yeo, ). To better capture the nonlinear relationship in the evolution of traffic (Smith & Demetsky, , ), the potential of neural networks was also investigated (e.g., Allström et al., ; Zhang, ).…”

Section: Literature Reviewmentioning

confidence: 99%

A spatio‐temporal ensemble method for large‐scale traffic state prediction

Liu

et al. 2019

Computer aided Civil Eng

View full text Add to dashboard Cite

How to effectively ensemble multiple models while leveraging the spatio‐temporal information is a challenging but practical problem. However, there is no existing ensemble method explicitly designed for spatio‐temporal data. In this paper, a fully convolutional model based on semantic segmentation technology is proposed, termed as spatio‐temporal ensemble net. The proposed method is suitable for grid‐based spatio‐temporal prediction in dense urban areas. Experiments demonstrate that through spatio‐temporal ensemble net, multiple traffic state prediction base models can be combined to improve the prediction accuracy.

show abstract

Improvement of Search Strategy With K-Nearest Neighbors Approach for Traffic State Prediction

Cited by 60 publications

References 53 publications

Intellectual Information System Of Subjects Methodological Support Based On The Web Search With Integrated Expert Evaluation

Intellectual Information System Of Subjects Methodological Support Based On The Web Search With Integrated Expert Evaluation

Evaluation of Spatial Resilience of Highway Networks in Response to Adverse Weather Conditions

A spatio‐temporal ensemble method for large‐scale traffic state prediction

Contact Info

Product

Resources

About