Faculty of Information Technology, BUT

Publication Details

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

PETRLÍK Jiří, FUČÍK Otto and SEKANINA Lukáš. Multiobjective Selection of Input Sensors for SVR Applied to Road Traffic Prediction. In: Parallel Problem Solving from Nature - PPSN XIII. Lecture Notes in Computer Science, vol. 8672. Heidelberg: Springer Verlag, 2014, pp. 802-811. ISBN 978-3-319-10761-5.
Czech title
Multikriteriální výběr vstupních senzorů pro SVR pro účely predikce dopravy
Type
conference paper
Language
english
Authors
Keywords
road traffic forecasting, multiobjective feature selection, multiobjective genetic algorithms
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.
Published
2014
Pages
802-811
Proceedings
Parallel Problem Solving from Nature - PPSN XIII
Series
Lecture Notes in Computer Science
Volume
8672
Conference
Parallel Problem Solving from Nature 2014, Ljubljana Exhibition and Convention Centre, SI
ISBN
978-3-319-10761-5
Publisher
Springer Verlag
Place
Heidelberg, DE
DOI
BibTeX
@INPROCEEDINGS{FITPUB10582,
   author = "Ji\v{r}\'{i} Petrl\'{i}k and Otto Fu\v{c}\'{i}k and Luk\'{a}\v{s} Sekanina",
   title = "Multiobjective Selection of Input Sensors for SVR Applied to Road Traffic Prediction",
   pages = "802--811",
   booktitle = "Parallel Problem Solving from Nature - PPSN XIII",
   series = "Lecture Notes in Computer Science",
   volume = 8672,
   year = 2014,
   location = "Heidelberg, DE",
   publisher = "Springer Verlag",
   ISBN = "978-3-319-10761-5",
   doi = "10.1007/978-3-319-10762-2\_79",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/10582"
}
Back to top