This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
2009 Fifth International Conference on Natural Computation
On Modeling of Atmospheric Visibility Classification Forecast with Nonlinear Support Vector Machine
Tianjian, China
August 14-August 16
ISBN: 978-0-7695-3736-8
ASCII Text
x 
 
Zai-Wen Wang, Chao-Lin Zhang, Chen Su, Cong-Lan Cheng, "On Modeling of Atmospheric Visibility Classification Forecast with Nonlinear Support Vector Machine," 2013 International Conference on Computing, Networking and Communications (ICNC), vol. 2, pp. 240-244, 2009 Fifth International Conference on Natural Computation, 2009.
 
 
BibTex
x
 
@article{ 10.1109/ICNC.2009.418,
author = {Zai-Wen Wang and Chao-Lin Zhang and Chen Su and Cong-Lan Cheng},
title = {On Modeling of Atmospheric Visibility Classification Forecast with Nonlinear Support Vector Machine},
journal ={2013 International Conference on Computing, Networking and Communications (ICNC)},
volume = {2},
year = {2009},
isbn = {978-0-7695-3736-8},
pages = {240-244},
doi = {http://doi.ieeecomputersociety.org/10.1109/ICNC.2009.418},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},
}
 
 
RefWorks Procite/RefMan/Endnote
x 
 
TY - CONF
JO - 2013 International Conference on Computing, Networking and Communications (ICNC)
TI - On Modeling of Atmospheric Visibility Classification Forecast with Nonlinear Support Vector Machine
SN - 978-0-7695-3736-8
SP240
EP244
A1 - Zai-Wen Wang,
A1 - Chao-Lin Zhang,
A1 - Chen Su,
A1 - Cong-Lan Cheng,
PY - 2009
KW - Support Vector Machine
KW - atmospheric visibility
KW - nonlinear
KW - road weather information
VL - 2
JA - 2013 International Conference on Computing, Networking and Communications (ICNC)
ER -
 
Based on the consecutive high temporal resolution data observed at the special automatic weather stations ROSA on Beijing airport highway during 2006-2007, the modeling of atmospheric visibility classification forecast model with the nonlinear Support Vector Machine method was discussed and evaluated in this paper. The evaluation result shows that the performance of the forecast model by the Support Vector Machine method was good. 40% of atmospheric visibility classification forecast is consistent with the observed data; more than 90% of the forecast classification errors is within one level (including equality). Moreover, in the future 3–48 h forecast the atmospheric visibility performed stably. The perfect forecast results verify that the Support Vector Machine method has strong capability of processing the nonlinear relationship between atmospheric visibility and meteorological factors.
Index Terms:
Support Vector Machine, atmospheric visibility, nonlinear, road weather information
Citation:
Zai-Wen Wang, Chao-Lin Zhang, Chen Su, Cong-Lan Cheng, "On Modeling of Atmospheric Visibility Classification Forecast with Nonlinear Support Vector Machine," icnc, vol. 2, pp.240-244, 2009 Fifth International Conference on Natural Computation, 2009
Usage of this product signifies your acceptance of the Terms of Use.