NEW INDUCED MUTATION GENETIC ALGORITHM FOR SPECTRAL VARIABLES SELECTION IN NEAR INFRARED SPECTROSCOPY
Abstract
In this paper, a new spectral variables selection method, induced mutation genetic algorithm (IMGA), is proposed for near-infrared (NIR) spectroscopy. Based on the idea of genetic algorithm (GA), the IMGA greatly simplifies the process of biological evolution, which not only inherits the advantages of global optimization of the GA, but also effectively improves the convergence speed. In this study, the IMGA is applied to the selection of characteristic spectral variables for green tea origin identification. After five times of genetic evolutions, 11 characteristic spectral variables are selected from 156 spectral variables. Based on the 11 characteristic spectral variables, the classification model is built by partial least squares (PLS), and both the sensitivity and specificity of classification model are raised to 1 for prediction set. The overall results indicate that the IMGA can be well applied to the selection of characteristic spectral variables and effectively improve the prediction accuracy and calculation speed of the near-infrared model.
Supporting agencies: This work has been financially supported by the Key Research and Development Program of Anhui Province (No. 201904a07020073), Foundation of Science and Technology on Electronic Test & Measurement Laboratory (No. 6142001180307), and National Defense Basic Technology of China (No. JSJL2018210C003).
About the Authors
X. G. Zhuang
The 41st Research Institute of CETC; Science and Technology on Electronic Test & Measurement Laboratory
China
Qingdao
China
Qingdao
X. S. Shi
The 41st Research Institute of CETC; Science and Technology on Electronic Test & Measurement Laboratory
China
Qingdao
China
Qingdao
P. J. Zhang
The 41st Research Institute of CETC
China
Qingdao
China
Qingdao
H. B. Liu
The 41st Research Institute of CETC
China
Qingdao
China
Qingdao
C. M. Liu
The 41st Research Institute of CETC
China
Qingdao
China
Qingdao
H. F. Wang
The 41st Research Institute of CETC
China
Qingdao
China
Qingdao
References
1. V. R. Sinija, H. N. Mishra, Food Bioproc. Technol., 4, 136–141 (2011).
2. X. G. Zhuang, L. L. Wang, Q. Chen, X. Y. Wu, J. X. Fang, Sci. China Technol., 60, 84–90 (2017).
3. Q. S. Chen, J. W. Zhao, H. Lin, Spectrochim. Acta, A, 72, 845–850 (2009).
4. D. Ono, T. Bamba, Y. Oku, T. Yonetani, E. Fukusaki, J. Biosci. Bioeng., 112, 247–251 (2011).
5. Z. M. Guo, Q. S. Chen, L. P. Chen, W. Q. Huang, C. Zhang, C. J. Zhao, Appl. Spectrosc., 65, 1062–1067 (2011).
6. Q. O. Yang, J. W. Zhao, Q. S. Chen, H. Lin, Z. B. Sun, Anal. Methods, 4, 940–946 (2012).
7. M. Vohland, M. Ludwig, S. Thiele-Bruhn, B. Ludwig, Geoderma, 223-225, 88–96 (2014).
8. H. Jiang, G. H. Liu, C. L. Mei, S. Yu, X. H. Xiao, Y. H. Ding, Anal. Bioanal. Chem., 404, 603–611 (2012).
9. B. M. Smith, P. J. Gemperline, Anal. Chim. Acta, 423, 167–177 (2000).
10. J. Y. Shi, X. P. Yin, X. B. Zou, J. W. Zhao, S. G. Ju, Chin. Soc. Agric. Mach., 41, 99–103 (2010).
11. M. Ghasemi-Varnamkhasti, S. S. Mohtasebi, M. L. Rodriguez-Mendez, A. A. Gomes, M. C. U. Araújo, R. K. H. Galvão, Talanta, 89, 286–291 (2012).
12. X. G. Zhuang, L. L. Wang, X. Y. Wu, J. X. Fang, J. Infrared Millimeter Waves, 35, 200–205 (2016).
13. J. Jiang, R. J. Berry, H. W. Siesler, Y. Ozaki, Anal. Chem., 74, 3555–3565 (2002).
14. R. Leardi, A. L. Gonzalez, Chemometr. Intell. Lab., 41, 195–207 (1998).
15. Q. S. Chen, P. Jiang, J. W. Zhao, Spectrochim. Acta, A, 76, 50–55 (2010).
16. J. H. Holland, Adaptation in Natural and Artificial Systems, MIT Press, 126–137 (1975).
17. L. Cséfalvayová, M. Pelikan, I. Kralj Cigić, J. Kolar, M. Strlič, Talanta, 82, 1784–1790 (2010).
18. Y. F. Zhai, L. J. Cui, X. Zhou, Y. Gao, T. Fei, W. X. Gao, Int. J. Remote Sens., 34, 2502–2518 (2013).
Review
For citations:
Zhuang X.G., Shi X.S., Zhang P.J., Liu H.B., Liu C.M., Wang H.F. NEW INDUCED MUTATION GENETIC ALGORITHM FOR SPECTRAL VARIABLES SELECTION IN NEAR INFRARED SPECTROSCOPY. Zhurnal Prikladnoii Spektroskopii. 2020;87(2):245-251.
Views: 290
Email this article 