Title :
The Application of Epsilon-SVR in Infrared Temperature Demarcating
Author :
Sun Jian ; Chen Liang ; Fu Yaqiong ; Wu Juan ; Chen Le
Author_Institution :
Coll. of Mechatron. Eng., China Jiliang Univ., Hangzhou, China
Abstract :
A epsiv-SVR (epsiv-Support Vector Regression) based modeling method is introduced to process data acquired from infrared temperature demarcating experiment. In the process of the temperature of black body ranging from 30degC to 72degC, 22 groups of samples are acquired, which include 17 groups of training samples and 5 groups of forecasting samples. The fitting curves are got through training samples and forecasting samples under MATLAB. Compared with traditional method of least square, the precision of this method is far higher. In conclusion, the method of epsiv-SVR can become a method of data processing to infrared temperature demarcating.
Keywords :
infrared imaging; regression analysis; support vector machines; temperature measurement; data processing; epsilon-SVR; infrared temperature demarcating; modeling; support vector regression; Curve fitting; Information processing; Infrared detectors; Infrared imaging; Least squares methods; Mathematical model; Power system reliability; Support vector machine classification; Support vector machines; Temperature measurement; ε -SVR; curve fitting; infrared temperature demarcating;
Conference_Titel :
Information Processing, 2009. APCIP 2009. Asia-Pacific Conference on
Conference_Location :
Shenzhen
Print_ISBN :
978-0-7695-3699-6
DOI :
10.1109/APCIP.2009.14
