Chinese Optics Letters, 2006, 4 (4): 04243, Published Online: Jun. 6, 2006  

Mixture gas component concentration analysis based on support vector machine and infrared spectrum

Author Affiliations
1 School of Electrical Engineering, Xi'an Jiaotong University, Xi'an 710049
2 Institute of Science, Air Force Engineering University, Xi'an 710051
Abstract
A novel quantitative analysis method of multi-component mixture gas concentration based on support vector machine (SVM) and spectroscopy is proposed. Through transformation of the kernel function, the seriously overlapped and nonlinear spectrum data are transformed in high-dimensional space, but the high-dimensional data can be processed in the original space. Some factors, such as kernel function, range of the wavelength, and penalty coefficient, are discussed. This method is applied to the quantitative analysis of natural gas components concentration, and the component concentration maximal deviation is 2.28%.
References

[1] H. Yuan and W. Lu, Modern Scientific Instruments (in Chinese) (5) 6 (1998).

[2] K. Hidajat and S. M. Chong, J. Near Infrared Spectrosc. 8, 53 (2000).

[3] X. Wan, F. Yang, and H. Wang, China Environmental Science (in Chinese) 23, 110 (2003).

[4] X. Sun, Y. Li, and J. Wang, Spectroscopy and Spectral Analysis (in Chinese) 23, 739 (2003).

[5] Y. Shi, Y. Lu, G. Xu, Y. Xu, Z. Xu, D. Cai, W. Lu, and J. Ma, Chin. J. Analyt. Chem. (in Chinese) 29, 87 (2001).

[6] V. N. Vapnik, The Nature of Statistical Learning Theory (in Chinese) X. Zhang (trans.) (Tsinghua University Press, Beijing, 2000).

[7] V. N. Vapnik, IEEE Trans. Neural Networks 10, 988 (1999).

[8] N. Chen, W. Lu, C. Ye, and G. Li, Computers and Appl. Chem. (in Chinese) 19, 691 (2002).

[9] M. Ye, Chin. Opt. Lett. 3, 205 (2005).

[10] C.-C. Chang and C.-J. Lin, LIBSVM: a library for support vector machines, 2001. http://www.csie.ntu.edu.tw/~cjlin/libsvm.

Peng Bai, Junhua Liu. Mixture gas component concentration analysis based on support vector machine and infrared spectrum[J]. Chinese Optics Letters, 2006, 4(4): 04243.

关于本站 Cookie 的使用提示

中国光学期刊网使用基于 cookie 的技术来更好地为您提供各项服务,点击此处了解我们的隐私策略。 如您需继续使用本网站,请您授权我们使用本地 cookie 来保存部分信息。
全站搜索
您最值得信赖的光电行业旗舰网络服务平台!