Real-time freeway-experienced travel time prediction using N-curve and K nearest neighbor methods

Brenda I. Bustillos, Yi-Chang Chiu

Research output: Contribution to journalArticle

16 Citations (Scopus)

Abstract

This study presents a methodology for freeway travel time prediction that uses only count data. The proposed models include the generalized N-curve method in conjunction with the k nearest neighbor (kNN) method so that the travel time predicted for traversing a defined freeway segment at a certain departure time is similar to what a driver actually experiences. A real-world traffic network and demand are replicated in a traffic simulation model in which several scenarios are produced to serve as the test bed for evaluation and validation of the proposed algorithms. The proposed single-NN algorithm best predicts travel times for light, free-flow traffic conditions, and the multiple-NN algorithm best predicts travel times for congested traffic conditions. The hybrid-NN algorithm merges the single-NN and multiple-NN algorithms, exploiting each one where most suitable. A numerical analysis concludes the potential of the proposed models.

Original languageEnglish (US)
Pages (from-to)127-137
Number of pages11
JournalTransportation Research Record
Issue number2243
DOIs
StatePublished - Dec 1 2011

Fingerprint

Highway systems
Travel time
Telecommunication traffic
Numerical analysis

ASJC Scopus subject areas

  • Civil and Structural Engineering
  • Mechanical Engineering

Cite this

Real-time freeway-experienced travel time prediction using N-curve and K nearest neighbor methods. / Bustillos, Brenda I.; Chiu, Yi-Chang.

In: Transportation Research Record, No. 2243, 01.12.2011, p. 127-137.

Research output: Contribution to journalArticle

@article{23c2ce3d2f254701b0e11c39f3d37aa7,
title = "Real-time freeway-experienced travel time prediction using N-curve and K nearest neighbor methods",
abstract = "This study presents a methodology for freeway travel time prediction that uses only count data. The proposed models include the generalized N-curve method in conjunction with the k nearest neighbor (kNN) method so that the travel time predicted for traversing a defined freeway segment at a certain departure time is similar to what a driver actually experiences. A real-world traffic network and demand are replicated in a traffic simulation model in which several scenarios are produced to serve as the test bed for evaluation and validation of the proposed algorithms. The proposed single-NN algorithm best predicts travel times for light, free-flow traffic conditions, and the multiple-NN algorithm best predicts travel times for congested traffic conditions. The hybrid-NN algorithm merges the single-NN and multiple-NN algorithms, exploiting each one where most suitable. A numerical analysis concludes the potential of the proposed models.",
author = "Bustillos, {Brenda I.} and Yi-Chang Chiu",
year = "2011",
month = "12",
day = "1",
doi = "10.3141/2243-15",
language = "English (US)",
pages = "127--137",
journal = "Transportation Research Record",
issn = "0361-1981",
publisher = "US National Research Council",
number = "2243",

}

TY - JOUR

T1 - Real-time freeway-experienced travel time prediction using N-curve and K nearest neighbor methods

AU - Bustillos, Brenda I.

AU - Chiu, Yi-Chang

PY - 2011/12/1

Y1 - 2011/12/1

N2 - This study presents a methodology for freeway travel time prediction that uses only count data. The proposed models include the generalized N-curve method in conjunction with the k nearest neighbor (kNN) method so that the travel time predicted for traversing a defined freeway segment at a certain departure time is similar to what a driver actually experiences. A real-world traffic network and demand are replicated in a traffic simulation model in which several scenarios are produced to serve as the test bed for evaluation and validation of the proposed algorithms. The proposed single-NN algorithm best predicts travel times for light, free-flow traffic conditions, and the multiple-NN algorithm best predicts travel times for congested traffic conditions. The hybrid-NN algorithm merges the single-NN and multiple-NN algorithms, exploiting each one where most suitable. A numerical analysis concludes the potential of the proposed models.

AB - This study presents a methodology for freeway travel time prediction that uses only count data. The proposed models include the generalized N-curve method in conjunction with the k nearest neighbor (kNN) method so that the travel time predicted for traversing a defined freeway segment at a certain departure time is similar to what a driver actually experiences. A real-world traffic network and demand are replicated in a traffic simulation model in which several scenarios are produced to serve as the test bed for evaluation and validation of the proposed algorithms. The proposed single-NN algorithm best predicts travel times for light, free-flow traffic conditions, and the multiple-NN algorithm best predicts travel times for congested traffic conditions. The hybrid-NN algorithm merges the single-NN and multiple-NN algorithms, exploiting each one where most suitable. A numerical analysis concludes the potential of the proposed models.

UR - http://www.scopus.com/inward/record.url?scp=84855226756&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84855226756&partnerID=8YFLogxK

U2 - 10.3141/2243-15

DO - 10.3141/2243-15

M3 - Article

AN - SCOPUS:84855226756

SP - 127

EP - 137

JO - Transportation Research Record

JF - Transportation Research Record

SN - 0361-1981

IS - 2243

ER -