A comparison of the performance of artificial neural networks and support vector machines for the prediction of traffic speed

Lelitha Vanajakshi, Laurence R. Rilett

Research output: Contribution to conferencePaper

80 Citations (Scopus)

Abstract

The ability to predict traffic variables such as speed, travel time or flow, based on real time data and historic data, collected by various systems In transportation networks, Is vital to the Intelligent transportation systems (ITS) components such as in-vehicle route guidance systems (RGS), advanced traveler information systems (ATIS), and advanced traffic management systems (ATMS). In the context of prediction methodologies, different time series, and artificial neural networks (ANN) models have been developed in addition to the historic and real time approach. The present paper proposes the application of a recently developed pattern classification and regression technique called support vector machines (SVM) for the short-term prediction of traffic speed. An ANN model is also developed and a comparison of the performance of both these techniques is carried out, along with real time and historic approach results. Data from the freeways of San Antonio, Texas were used for the analysis.

Original languageEnglish (US)
Pages194-199
Number of pages6
StatePublished - Sep 27 2004
Event2004 IEEE Intelligent Vehicles Symposium - Parma, Italy
Duration: Jun 14 2004Jun 17 2004

Other

Other2004 IEEE Intelligent Vehicles Symposium
CountryItaly
CityParma
Period6/14/046/17/04

Fingerprint

Support vector machines
Artificial Neural Network
Support Vector Machine
Advanced traffic management systems
Advanced traveler information systems
Traffic
Neural networks
Neural Network Model
Prediction
Highway systems
Travel time
Real-time Data
Pattern recognition
Time series
Intelligent Transportation Systems
Traffic Management
Transportation Networks
Pattern Classification
Travel Time
Guidance

ASJC Scopus subject areas

  • Modeling and Simulation
  • Automotive Engineering
  • Computer Science Applications

Cite this

Vanajakshi, L., & Rilett, L. R. (2004). A comparison of the performance of artificial neural networks and support vector machines for the prediction of traffic speed. 194-199. Paper presented at 2004 IEEE Intelligent Vehicles Symposium, Parma, Italy.

A comparison of the performance of artificial neural networks and support vector machines for the prediction of traffic speed. / Vanajakshi, Lelitha; Rilett, Laurence R.

2004. 194-199 Paper presented at 2004 IEEE Intelligent Vehicles Symposium, Parma, Italy.

Research output: Contribution to conferencePaper

Vanajakshi, L & Rilett, LR 2004, 'A comparison of the performance of artificial neural networks and support vector machines for the prediction of traffic speed' Paper presented at 2004 IEEE Intelligent Vehicles Symposium, Parma, Italy, 6/14/04 - 6/17/04, pp. 194-199.
Vanajakshi L, Rilett LR. A comparison of the performance of artificial neural networks and support vector machines for the prediction of traffic speed. 2004. Paper presented at 2004 IEEE Intelligent Vehicles Symposium, Parma, Italy.
Vanajakshi, Lelitha ; Rilett, Laurence R. / A comparison of the performance of artificial neural networks and support vector machines for the prediction of traffic speed. Paper presented at 2004 IEEE Intelligent Vehicles Symposium, Parma, Italy.6 p.
@conference{6aaae07291f0401b826e0cdf8c108535,
title = "A comparison of the performance of artificial neural networks and support vector machines for the prediction of traffic speed",
abstract = "The ability to predict traffic variables such as speed, travel time or flow, based on real time data and historic data, collected by various systems In transportation networks, Is vital to the Intelligent transportation systems (ITS) components such as in-vehicle route guidance systems (RGS), advanced traveler information systems (ATIS), and advanced traffic management systems (ATMS). In the context of prediction methodologies, different time series, and artificial neural networks (ANN) models have been developed in addition to the historic and real time approach. The present paper proposes the application of a recently developed pattern classification and regression technique called support vector machines (SVM) for the short-term prediction of traffic speed. An ANN model is also developed and a comparison of the performance of both these techniques is carried out, along with real time and historic approach results. Data from the freeways of San Antonio, Texas were used for the analysis.",
author = "Lelitha Vanajakshi and Rilett, {Laurence R.}",
year = "2004",
month = "9",
day = "27",
language = "English (US)",
pages = "194--199",
note = "2004 IEEE Intelligent Vehicles Symposium ; Conference date: 14-06-2004 Through 17-06-2004",

}

TY - CONF

T1 - A comparison of the performance of artificial neural networks and support vector machines for the prediction of traffic speed

AU - Vanajakshi, Lelitha

AU - Rilett, Laurence R.

PY - 2004/9/27

Y1 - 2004/9/27

N2 - The ability to predict traffic variables such as speed, travel time or flow, based on real time data and historic data, collected by various systems In transportation networks, Is vital to the Intelligent transportation systems (ITS) components such as in-vehicle route guidance systems (RGS), advanced traveler information systems (ATIS), and advanced traffic management systems (ATMS). In the context of prediction methodologies, different time series, and artificial neural networks (ANN) models have been developed in addition to the historic and real time approach. The present paper proposes the application of a recently developed pattern classification and regression technique called support vector machines (SVM) for the short-term prediction of traffic speed. An ANN model is also developed and a comparison of the performance of both these techniques is carried out, along with real time and historic approach results. Data from the freeways of San Antonio, Texas were used for the analysis.

AB - The ability to predict traffic variables such as speed, travel time or flow, based on real time data and historic data, collected by various systems In transportation networks, Is vital to the Intelligent transportation systems (ITS) components such as in-vehicle route guidance systems (RGS), advanced traveler information systems (ATIS), and advanced traffic management systems (ATMS). In the context of prediction methodologies, different time series, and artificial neural networks (ANN) models have been developed in addition to the historic and real time approach. The present paper proposes the application of a recently developed pattern classification and regression technique called support vector machines (SVM) for the short-term prediction of traffic speed. An ANN model is also developed and a comparison of the performance of both these techniques is carried out, along with real time and historic approach results. Data from the freeways of San Antonio, Texas were used for the analysis.

UR - http://www.scopus.com/inward/record.url?scp=4544262864&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=4544262864&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:4544262864

SP - 194

EP - 199

ER -