Support vector machine technique for the short term prediction of travel time

Lelitha Vanajakshi, Laurence R. Rilett

Research output: Chapter in Book/Report/Conference proceedingConference contribution

65 Citations (Scopus)

Abstract

A vast majority of urban transportation systems in North America are equipped with traffic surveillance systems that provide real time traffic information to traffic management centers. The information from these are processed and provided back to the travelers in real time. However, the travelers are interested to know not only the current traffic information, but also the future traffic conditions predicted based on the real time data. These predicted values inform the drivers on what they can expect when they make the trip. Travel time is one of the most popular variables which the users are interested to know. Travelers make decisions to bypass congested segments of the network, to change departure time or destination etc., based on this information. Hence it is important that the predicted values be as accurate as possible. A number of different forecasting methods have been proposed for travel time forecasting including historic method, real-time method, time series analysis, and artificial neural networks (ANN). This paper examines the use of a machine learning technique, namely support vector machines (SVM), for the short-term prediction of travel time. While other machine learning techniques, such as ANN, have been extensively studied, the reported applications of SVM in the field of transportation engineering are very few. A comparison of the performance of SVM with ANN, real time, and historic approach is carried out. Data from the TransGuide Traffic Management center in San Antonio, Texas, USA is used for the analysis. From the results it was found that SVM is a viable alternative for short-term prediction problems when the amount of data is less or noisy in nature.

Original languageEnglish (US)
Title of host publicationProceedings of the 2007 IEEE Intelligent Vehicles Symposium, IV 2007
Pages600-605
Number of pages6
StatePublished - Dec 1 2007
Event2007 IEEE Intelligent Vehicles Symposium, IV 2007 - Istanbul, Turkey
Duration: Jun 13 2007Jun 15 2007

Publication series

NameIEEE Intelligent Vehicles Symposium, Proceedings

Other

Other2007 IEEE Intelligent Vehicles Symposium, IV 2007
CountryTurkey
CityIstanbul
Period6/13/076/15/07

Fingerprint

Travel Time
Travel time
Support vector machines
Support Vector Machine
Traffic
Artificial Neural Network
Traffic Management
Prediction
Term
Neural networks
Learning systems
Forecasting
Machine Learning
Real-time Data
Urban transportation
Time series analysis
Time Series Analysis
Surveillance
Driver
Engineering

Keywords

  • Inductive loop detectors
  • Machine learning techniques
  • Support vector machines
  • Travel time prediction

ASJC Scopus subject areas

  • Modeling and Simulation
  • Automotive Engineering
  • Computer Science Applications

Cite this

Vanajakshi, L., & Rilett, L. R. (2007). Support vector machine technique for the short term prediction of travel time. In Proceedings of the 2007 IEEE Intelligent Vehicles Symposium, IV 2007 (pp. 600-605). [4290181] (IEEE Intelligent Vehicles Symposium, Proceedings).

Support vector machine technique for the short term prediction of travel time. / Vanajakshi, Lelitha; Rilett, Laurence R.

Proceedings of the 2007 IEEE Intelligent Vehicles Symposium, IV 2007. 2007. p. 600-605 4290181 (IEEE Intelligent Vehicles Symposium, Proceedings).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Vanajakshi, L & Rilett, LR 2007, Support vector machine technique for the short term prediction of travel time. in Proceedings of the 2007 IEEE Intelligent Vehicles Symposium, IV 2007., 4290181, IEEE Intelligent Vehicles Symposium, Proceedings, pp. 600-605, 2007 IEEE Intelligent Vehicles Symposium, IV 2007, Istanbul, Turkey, 6/13/07.
Vanajakshi L, Rilett LR. Support vector machine technique for the short term prediction of travel time. In Proceedings of the 2007 IEEE Intelligent Vehicles Symposium, IV 2007. 2007. p. 600-605. 4290181. (IEEE Intelligent Vehicles Symposium, Proceedings).
Vanajakshi, Lelitha ; Rilett, Laurence R. / Support vector machine technique for the short term prediction of travel time. Proceedings of the 2007 IEEE Intelligent Vehicles Symposium, IV 2007. 2007. pp. 600-605 (IEEE Intelligent Vehicles Symposium, Proceedings).
@inproceedings{f0814813807c4d10a395b5eeb8bc586f,
title = "Support vector machine technique for the short term prediction of travel time",
abstract = "A vast majority of urban transportation systems in North America are equipped with traffic surveillance systems that provide real time traffic information to traffic management centers. The information from these are processed and provided back to the travelers in real time. However, the travelers are interested to know not only the current traffic information, but also the future traffic conditions predicted based on the real time data. These predicted values inform the drivers on what they can expect when they make the trip. Travel time is one of the most popular variables which the users are interested to know. Travelers make decisions to bypass congested segments of the network, to change departure time or destination etc., based on this information. Hence it is important that the predicted values be as accurate as possible. A number of different forecasting methods have been proposed for travel time forecasting including historic method, real-time method, time series analysis, and artificial neural networks (ANN). This paper examines the use of a machine learning technique, namely support vector machines (SVM), for the short-term prediction of travel time. While other machine learning techniques, such as ANN, have been extensively studied, the reported applications of SVM in the field of transportation engineering are very few. A comparison of the performance of SVM with ANN, real time, and historic approach is carried out. Data from the TransGuide Traffic Management center in San Antonio, Texas, USA is used for the analysis. From the results it was found that SVM is a viable alternative for short-term prediction problems when the amount of data is less or noisy in nature.",
keywords = "Inductive loop detectors, Machine learning techniques, Support vector machines, Travel time prediction",
author = "Lelitha Vanajakshi and Rilett, {Laurence R.}",
year = "2007",
month = "12",
day = "1",
language = "English (US)",
isbn = "1424410681",
series = "IEEE Intelligent Vehicles Symposium, Proceedings",
pages = "600--605",
booktitle = "Proceedings of the 2007 IEEE Intelligent Vehicles Symposium, IV 2007",

}

TY - GEN

T1 - Support vector machine technique for the short term prediction of travel time

AU - Vanajakshi, Lelitha

AU - Rilett, Laurence R.

PY - 2007/12/1

Y1 - 2007/12/1

N2 - A vast majority of urban transportation systems in North America are equipped with traffic surveillance systems that provide real time traffic information to traffic management centers. The information from these are processed and provided back to the travelers in real time. However, the travelers are interested to know not only the current traffic information, but also the future traffic conditions predicted based on the real time data. These predicted values inform the drivers on what they can expect when they make the trip. Travel time is one of the most popular variables which the users are interested to know. Travelers make decisions to bypass congested segments of the network, to change departure time or destination etc., based on this information. Hence it is important that the predicted values be as accurate as possible. A number of different forecasting methods have been proposed for travel time forecasting including historic method, real-time method, time series analysis, and artificial neural networks (ANN). This paper examines the use of a machine learning technique, namely support vector machines (SVM), for the short-term prediction of travel time. While other machine learning techniques, such as ANN, have been extensively studied, the reported applications of SVM in the field of transportation engineering are very few. A comparison of the performance of SVM with ANN, real time, and historic approach is carried out. Data from the TransGuide Traffic Management center in San Antonio, Texas, USA is used for the analysis. From the results it was found that SVM is a viable alternative for short-term prediction problems when the amount of data is less or noisy in nature.

AB - A vast majority of urban transportation systems in North America are equipped with traffic surveillance systems that provide real time traffic information to traffic management centers. The information from these are processed and provided back to the travelers in real time. However, the travelers are interested to know not only the current traffic information, but also the future traffic conditions predicted based on the real time data. These predicted values inform the drivers on what they can expect when they make the trip. Travel time is one of the most popular variables which the users are interested to know. Travelers make decisions to bypass congested segments of the network, to change departure time or destination etc., based on this information. Hence it is important that the predicted values be as accurate as possible. A number of different forecasting methods have been proposed for travel time forecasting including historic method, real-time method, time series analysis, and artificial neural networks (ANN). This paper examines the use of a machine learning technique, namely support vector machines (SVM), for the short-term prediction of travel time. While other machine learning techniques, such as ANN, have been extensively studied, the reported applications of SVM in the field of transportation engineering are very few. A comparison of the performance of SVM with ANN, real time, and historic approach is carried out. Data from the TransGuide Traffic Management center in San Antonio, Texas, USA is used for the analysis. From the results it was found that SVM is a viable alternative for short-term prediction problems when the amount of data is less or noisy in nature.

KW - Inductive loop detectors

KW - Machine learning techniques

KW - Support vector machines

KW - Travel time prediction

UR - http://www.scopus.com/inward/record.url?scp=47849099540&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=47849099540&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:47849099540

SN - 1424410681

SN - 9781424410682

T3 - IEEE Intelligent Vehicles Symposium, Proceedings

SP - 600

EP - 605

BT - Proceedings of the 2007 IEEE Intelligent Vehicles Symposium, IV 2007

ER -