Title :
A Method of Mixed Gas Infrared Spectrum Analysis Based on SVM Data Fusion Model
Author :
Peng, Bai ; Aifan, Ling ; Daguang, Yu ; Yan, Li
Author_Institution :
Sci. Inst., Air Force Eng. Univ., Xi´´an, China
Abstract :
In order to solve the problem of non-linear in mixed gas infrared spectra analysis, the data fusion method based on support vector machine is used. Data fusion is a new information processing method, and it may use superfluous and complementary information to improve the performance of output, and the data fusion model is established. The non-linear processing function of support vector machine is used in model. The experimental result shows that, the maximum absolute error is 0.91%, the maximum mean absolute error is 0.39%, and the model has the certain project application value.
Keywords :
infrared spectra; sensor fusion; spectral analysis; support vector machines; SVM data fusion model; information processing method; mixed gas infrared spectrum analysis; nonlinear processing function; support vector machine; Cities and towns; Data analysis; Data engineering; Educational institutions; Gas detectors; Information analysis; Information processing; Infrared sensors; Infrared spectra; Support vector machines; data fusion; infrared spectra analysis; support vector machine;
Conference_Titel :
Intelligent Computation Technology and Automation, 2009. ICICTA '09. Second International Conference on
Conference_Location :
Changsha, Hunan
Print_ISBN :
978-0-7695-3804-4
DOI :
10.1109/ICICTA.2009.126
