Research on Parameter Optimization of Mixed Gas IR SVM Calibration Model

Jiang Wang; Peng Bai; Xiao Hu Duan; Yan Li

doi:10.4028/www.scientific.net/AMR.1083.97

Paper Titles

The Regular Pattern of Demagnetizing Factor Behaviour of Various ‘Cores’ of Granule-Ball Chains
p.75

Determination of Nitrophenol Isomers in Water
p.80

RP-HPLC-UV Method for Simultaneous Determination of Isoflavonoids in Huangqi Gegen and its Markted Formulations
p.84

GFRP Bar: Determining Tensile Strength with Bending Test
p.90

Research on Parameter Optimization of Mixed Gas IR SVM Calibration Model
p.97

Measurement of Thermo-Radiation Characteristics of IR Window Materials
p.104

Accurate Measurement on Cross Sectional Area of Single Filaments Using a Desktop SEM
p.111

A Research on High-Precision Strain Measurement Based on FBG with Temperature Compensation
p.121

Development of Temperature and Magnetic Field Monitoring System of ITER HTS Magnet
p.127

HomeAdvanced Materials ResearchAdvanced Materials Research Vol. 1083Research on Parameter Optimization of Mixed Gas IR...

Research on Parameter Optimization of Mixed Gas IR SVM Calibration Model

Abstract:

A SVM calibration model combined with new information processing method of support vector machine and infrared spectroscopy is established. For the problem of model parameters affecting the analysis results, the optimization of the model parameters is studied through the experiment. The mixed gas containing hydrocarbon is used as an example, spectra data preprocessing, spectra analysis band, spectrometer scanning interval, types of kernel function for SVM calibration model, penalty factor C, and other parameters that affect the measurement results are optimized. The experimental results show that the accuracy of the analysis results can be improved in the case of the SVM calibration model optimized and the model has a practical application value.

You might also be interested in these eBooks

View Preview

Info:

Periodical:

Advanced Materials Research (Volume 1083)

Pages:

97-103

DOI:

https://doi.org/10.4028/www.scientific.net/AMR.1083.97

Citation:

Cite this paper

Online since:

January 2015

Authors:

Jiang Wang*, Peng Bai, Xiao Hu Duan, Yan Li

Keywords:

Calibration Model, Mixed Gas, Optimization, Parameter, Support Vector Machine (SVM)

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

* - Corresponding Author

References

[1] LU Wan-Zhen, YUAN Hong-fu, XU Guang-tong, et al. Modern near Infrared Spectroscopy Analysis Technology. China Petro-chemistry Press, Beijing (2000).

Google Scholar

[2] YAN Yan-lu, ZHAO Long-lian, HAN Dong-hai. Near Infrared Spectroscopy and its Application. China Light Industry Press, Beijing (2005).

Google Scholar

[3] Pérez Marín D, Garrido Varo A, Guerrero J E. Talanta, 2007, 72(1): 28.

Google Scholar

[4] Roman M. Balabina, Ravilya Z. Safievaa, Ekaterina I. Lomakinab. Chemometrics and Intelligent Laboratory Systems, 2007, 93(1): 58.

Google Scholar

[5] TANG Shou-Peng, YAO Xin-Feng, YAO Xia, et al. Chinese Journal of Analytical Chemistry, 2009, 9(10): 1445.

Google Scholar

[6] V N. Vapnik. Statistical Learning Theory. New York: John Wiley & Sons Inc, (1998).

Google Scholar

[7] BAI Peng, XIE Wen-jun, LIU Jun-hua. Spectroscopy and Spectral Analysis, 2008, 28(2): 299.

Google Scholar

[8] CHEN Qiao, CAO Gen-niu, CHEN Liu. Computer Technology and Development, 2010, 20(1): 250.

Google Scholar

[9] ZHANG Lu-da, SU Shi-guang, WANG Lai-sheng, et al. Spectroscopy and Spectral Analysis, 2005, 25(1): 33.

Google Scholar

[10] V.N. Vapnik. IEEE Trans on Neural Network, 1999, 10(5): 988.

Google Scholar

[11] CHU Xiao-li, YUAN Hong-fu, LU Wan-zhen. Progress in Chemistry, 2004, 16(4): 528-542.

Google Scholar

[12] GAO Rong-qiang, FAN Shi-fu, YAN Yan-lu, et al. Spectroscopy and Spectral Analysis, 2004, 24(12): 1563.

Google Scholar

[13] DAN Tu-nan, DAI Lian-kui. Spectroscopy and Spectral Analysis, 2009, 29(2): 351.

Google Scholar