Přístupnostní navigace
E-application
Search Search Close
Publication detail
PETRLÍK, J. SEKANINA, L.
Original Title
Towards Robust and Accurate Traffic Prediction Using Parallel Multiobjective Genetic Algorithms and Support Vector Regression
Type
conference paper
Language
English
Original Abstract
The support vector regression (SVR) is a very successful method in solving many difficult tasks in the area of traffic prediction. However, the performance of SVR is very sensitive to the parameters setting and the selection of input variables such as sensors providing the input data. In this paper, we describe a new method, which simultaneously optimizes the meta-parameters of SVR model and the subset of its input variables. The method is based on a multiobjective genetic algorithm. The proposed implementation is intended for a parallel environment supporting OpenMP. We evaluated the method in the tasks of data imputation, short term prediction of traffic variables and travel times prediction using real world open data. It was confirmed that the simultaneous optimization of SVR parameters and input variables provides better quality of prediction than previous methods.
Keywords
road traffic forecasting, travel times, support vector regression, multiobjective genetic algorithm
Authors
PETRLÍK, J.; SEKANINA, L.
RIV year
2015
Released
15. 9. 2015
Publisher
IEEE Computer Society
Location
Los Alamitos
ISBN
978-1-4673-6596-3
Book
2015 IEEE 18th International Conference on Intelligent Transportation Systems
Pages from
2231
Pages to
2236
Pages count
6
URL
https://www.fit.vut.cz/research/publication/10886/
BibTex
@inproceedings{BUT119857, author="Jiří {Petrlík} and Lukáš {Sekanina}", title="Towards Robust and Accurate Traffic Prediction Using Parallel Multiobjective Genetic Algorithms and Support Vector Regression", booktitle="2015 IEEE 18th International Conference on Intelligent Transportation Systems", year="2015", pages="2231--2236", publisher="IEEE Computer Society", address="Los Alamitos", doi="10.1109/ITSC.2015.360", isbn="978-1-4673-6596-3", url="https://www.fit.vut.cz/research/publication/10886/" }