AUTOMATIC PREDICTION OF ICY CONDITIONS ON ROADS USING A LS-SVM CLASSIFIER

Autor:	Georges Bastin, Vincent Wertz, S. Beguin
Rok vydání:	2005
Předmět:	Engineering Horizon (archaeology) business.industry General Medicine computer.software_genre Machine learning Svm classifier Air temperature Prediction methods Least squares support vector machine Center (algebra and category theory) Data mining Artificial intelligence business computer
Zdroj:	IFAC Proceedings Volumes. 38:37-42
ISSN:	1474-6670
DOI:	10.3182/20050703-6-cz-1902.02029
Popis:	This paper describes a method for predicting the presence or absence of ice on the road. The method is based on a Least Squares Support Vector Machine applied to data from the road in Wallonia (Belgium). It is shown that including a prediction of the air temperature given by a meteorological center in the model helps having better accuracy. In this application, 95% accuracy have been achieved for a 3 hours prediction horizon, and 92% for 6, 12 and 24 hours horizon.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::765a1b5ed9f5c72540dce3ebb0589fa8 https://doi.org/10.3182/20050703-6-cz-1902.02029 Zobrazit plný text záznamu