Result Details
Multiobjective Selection of Input Sensors for Travel Times Forecasting Using Support Vector Regression
Fučík Otto, doc. Dr. Ing., DCSY (FIT)
Sekanina Lukáš, prof. Ing., Ph.D., DCSY (FIT)
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.
travel times forecasting, support vector regression, feature selection, multiobjective genetic algorithm
@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",
booktitle="2014 IEEE Symposium on Computational Intelligence in Vehicles and Transportation Systems Proceedings",
year="2014",
pages="14--21",
publisher="Institute of Electrical and Electronics Engineers",
address="Piscataway",
doi="10.1109/CIVTS.2014.7009472",
isbn="978-1-4799-4498-9"
}Centrum excelence IT4Innovations, MŠMT, Operační program Výzkum a vývoj pro inovace, ED1.1.00/02.0070, start: 2011-01-01, end: 2015-12-31, completed
Verification of the implementation of continuous traffic load map using modern classification and prediction methods, TAČR, Program aplikovaného výzkumu a experimentálního vývoje ALFA, TA02030915, start: 2012-01-01, end: 2014-12-31, completed