Publication detail

Multiobjective Selection of Input Sensors for Travel Times Forecasting Using Support Vector Regression

PETRLÍK, J. FUČÍK, O. SEKANINA, L.

Original Title

Multiobjective Selection of Input Sensors for Travel Times Forecasting Using Support Vector Regression

English Title

Multiobjective Selection of Input Sensors for Travel Times Forecasting Using Support Vector Regression

Type

conference paper

Language

en

Original Abstract

In this paper we propose a new method for travel time prediction using a support vector regression model (SVR). The inputs of the method are data from license plate detection systems and traffic sensors such as induction loops or radars placed in the area. This method is mainly designed to be capable of dealing with missing values in traffic data. It is able to create many different SVR models with different input variables. These models are dynamicaly switched according to which traffic variables are currently available. The proposed method was compared with a license plate based prediction approach. The results showed that the proposed method provides a prediction of better quality. Moreover, it is available for a longer period of time.

English abstract

In this paper we propose a new method for travel time prediction using a support vector regression model (SVR). The inputs of the method are data from license plate detection systems and traffic sensors such as induction loops or radars placed in the area. This method is mainly designed to be capable of dealing with missing values in traffic data. It is able to create many different SVR models with different input variables. These models are dynamicaly switched according to which traffic variables are currently available. The proposed method was compared with a license plate based prediction approach. The results showed that the proposed method provides a prediction of better quality. Moreover, it is available for a longer period of time.

Keywords

travel times forecasting, support vector regression, feature selection, multiobjective genetic algorithm

RIV year

2014

Released

12.12.2014

Publisher

Institute of Electrical and Electronics Engineers

Location

Piscataway

ISBN

978-1-4799-4498-9

Book

2014 IEEE Symposium on Computational Intelligence in Vehicles and Transportation Systems Proceedings

Edition

NEUVEDEN

Edition number

NEUVEDEN

Pages from

14

Pages to

21

Pages count

8

BibTex


@inproceedings{BUT111629,
  author="Jiří {Petrlík} and Otto {Fučík} and Lukáš {Sekanina}",
  title="Multiobjective Selection of Input Sensors for Travel Times Forecasting Using Support Vector Regression",
  annote="
In this paper we propose a new method for travel time prediction using a support
vector regression model (SVR). The inputs of the method are data from license
plate detection systems and traffic sensors such as induction loops or radars
placed in the area. This method is mainly designed to be capable of dealing with
missing values in traffic data. It is able to create many different SVR models
with different input variables. These models are dynamicaly switched according to
which traffic variables are currently available. The proposed method was compared
with a license plate based prediction approach. The results showed that the
proposed method provides a prediction of better quality. Moreover, it is
available for a longer period of time.",
  address="Institute of Electrical and Electronics Engineers",
  booktitle="2014 IEEE Symposium on Computational Intelligence in Vehicles and Transportation Systems Proceedings",
  chapter="111629",
  doi="10.1109/CIVTS.2014.7009472",
  edition="NEUVEDEN",
  howpublished="electronic, physical medium",
  institution="Institute of Electrical and Electronics Engineers",
  year="2014",
  month="december",
  pages="14--21",
  publisher="Institute of Electrical and Electronics Engineers",
  type="conference paper"
}