Publication detail

Multiobjective Selection of Input Sensors for SVR Applied to Road Traffic Prediction

PETRLÍK, J. FUČÍK, O. SEKANINA, L.

Original Title

Multiobjective Selection of Input Sensors for SVR Applied to Road Traffic Prediction

Type

conference paper

Language

English

Original Abstract

Modern traffic sensors can measure various road traffic variables such as the traffic flow and average speed. However, some measurements can lead to incorrect data which cannot  further be used in subsequent processing tasks such as traffic prediction or intelligent control. In this paper, we propose a method selecting a subset of input sensors for a support vector regression (SVR) model which is used for traffic prediction. The method is based on a multimodal and multiobjective NSGA-II algorithm. The multiobjective approach allowed us to find a good trade off between the prediction error and the number of sensors in real-world situations when many traffic data measurements are unavailable.

Keywords

road traffic forecasting, multiobjective feature selection, multiobjective genetic algorithms

Authors

PETRLÍK, J.; FUČÍK, O.; SEKANINA, L.

RIV year

2014

Released

13. 9. 2014

Publisher

Springer Verlag

Location

Heidelberg

ISBN

978-3-319-10761-5

Book

Parallel Problem Solving from Nature - PPSN XIII

Edition

Lecture Notes in Computer Science

Pages from

802

Pages to

811

Pages count

10

BibTex

@inproceedings{BUT111559,
  author="Jiří {Petrlík} and Otto {Fučík} and Lukáš {Sekanina}",
  title="Multiobjective Selection of Input Sensors for SVR Applied to Road Traffic Prediction",
  booktitle="Parallel Problem Solving from Nature - PPSN XIII",
  year="2014",
  series="Lecture Notes in Computer Science",
  volume="8672",
  pages="802--811",
  publisher="Springer Verlag",
  address="Heidelberg",
  doi="10.1007/978-3-319-10762-2\{_}79",
  isbn="978-3-319-10761-5"
}