Semi-supervised LIBS quantitative analysis method based on co-training regression model with selection of effective unlabeled samples

Xiaomeng LI (李晓萌); Huili LU (陆慧丽); Jianhong YANG (阳建宏); Fu CHANG (常福)

doi:10.1088/2058-6272/aaee14

Plasma Science and Technology > 2019 > 21(3): 34015-034015. > DOI: 10.1088/2058-6272/aaee14

Xiaomeng LI (李晓萌), Huili LU (陆慧丽), Jianhong YANG (阳建宏), Fu CHANG (常福). Semi-supervised LIBS quantitative analysis method based on co-training regression model with selection of effective unlabeled samples[J]. Plasma Science and Technology, 2019, 21(3): 34015-034015. DOI: 10.1088/2058-6272/aaee14

Citation:

PDF (1366 KB)

Semi-supervised LIBS quantitative analysis method based on co-training regression model with selection of effective unlabeled samples

¹ School of Mechanical Engineering, University of Science and Technology Beijing, Beijing 100083, People’s Republic of China
² Basic Experimental Center of Natural Science, University of Science and Technology Beijing, Beijing 100083, People’s Republic of China

Funds: This work was supported by National Natural Science Foundation of China (No. 51674032).

More Information

Received Date: July 27, 2018

Graphical Abstract

Abstract

Abstract

The accuracy of laser-induced breakdown spectroscopy (LIBS) quantitative method is greatly dependent on the amount of certified standard samples used for training. However, in practical applications, only limited standard samples with labeled certified concentrations are available. A novel semi-supervised LIBS quantitative analysis method is proposed, based on co-training regression model with selection of effective unlabeled samples. The main idea of the proposed method is to obtain better regression performance by adding effective unlabeled samples in semi- supervised learning. First, effective unlabeled samples are selected according to the testing samples by Euclidean metric. Two original regression models based on least squares support vector machine with different parameters are trained by the labeled samples separately, and then the effective unlabeled samples predicted by the two models are used to enlarge the training dataset based on labeling confidence estimation. The final predictions of the proposed method on the testing samples will be determined by weighted combinations of the predictions of two updated regression models. Chromium concentration analysis experiments of 23 certified standard high-alloy steel samples were carried out, in which 5 samples with labeled concentrations and 11 unlabeled samples were used to train the regression models and the remaining 7 samples were used for testing. With the numbers of effective unlabeled samples increasing, the root mean square error of the proposed method went down from 1.80% to 0.84% and the relative prediction error was reduced from 9.15% to 4.04%.
- LIBS, effective unlabeled samples,
- co-training,
- semi-supervised,
- labeling confidence estimation

FullText(HTML)

References (26)

References

[1]	Li X W et al 2015 Plasma Sci. Technol. 17 621
[2]	Guo Y M et al 2018 Plasma Sci. Technol. 20 065505
[3]	Yu J L et al 2018 Anal. Methods 10 281
[4]	Xie S C et al 2018 J. Anal. At. Spectrom. 33 975
[5]	Tognoni E et al 2002 Spectrochim. Acta B 57 1115
[6]	Labutin T A et al 2013 Spectrochim. Acta B 87 57
[7]	Li L Z et al 2011 J. Anal. At. Spectrom. 26 2274
[8]	Wang Z et al 2012 Spectrochim. Acta B 68 58
[9]	Zaytsev S M et al 2018 Spectrochim. Acta B 140 65
[10]	Zhang T L et al 2014 J. Anal. At. Spectrom. 29 2323
[11]	Dingari N C et al 2012 Anal. Chem. 84 2686
[12]	Wang Z et al 2011 J. Anal. At. Spectrom. 26 2175
[13]	Tsuda K and R?tsch G 2005 IEEE Trans. Image Process. 14 737
[14]	Feng W et al 2009 J. Vis. Lang. Comput. 20 188
[15]	Yu Z T et al 2010 Pattern Recognit. Lett. 31 1975
[16]	Yuan H J, Wang C R and Liu J 2011 Adv. Mater. Res. 267 1065
[17]	Zhou Z H and Li M 2005 Semi-supervised regression with co- training Proc. 19th Int. Joint Conf. on Artificial Intelligence (Edinburgh) (ACM) p 908
[18]	Shahshahani B M and Landgrebe D A 1994 IEEE Trans. Geosci. Remote Sens. 32 1087
[19]	Baluja S 1998 Probabilistic modeling for face orientation discrimination: learning from labeled and unlabeled data Proc. 11th Int. Conf. on Neural Information Processing Systems 11 (Denver) (ACM) p 854
[20]	Belkin M and Niyogi P 2004 Mach. Learn. 56 209
[21]	Niyogi P 2013 J. Mach. Learn. Res. 14 1229
[22]	Zhou Z H and Li M 2005 IEEE Trans. Knowl. Data Eng. 17 1529
[23]	Blum A and Mitchell T 1998 Combining labeled and unlabeled data with co-training Proc. 11th Annual Conf. on Computational Learning Theory (Madison, WI) (ACM) p 92
[24]	Suykens J A K and Vandewalle J 1999 Neural Process. Lett. 9 293
[25]	Pontes M J C et al 2005 Chemometr. Intell. Lab. Syst. 78 11
[26]	Poli R, Kennedy J and Blackwell T 2007 Swarm Intell. 1 33

[1]	Lunjiang CHEN (陈伦江), Wenbo CHEN (陈文波), Chuandong LIU (刘川东), Honghui TONG (童洪辉), Qing ZHAO (赵青). Estimation of plasma parameters in the process of micro-scale powder plastic and characteristics of its products[J]. Plasma Science and Technology, 2019, 21(7): 74006-074006. DOI: 10.1088/2058-6272/ab00ac
[2]	Bowen RUAN (阮博文), Zhoujun YANG (杨州军), Xiaoming PAN (潘晓明), Hao ZHOU (周豪), Fengqi CHANG (常风岐), Jing ZHOU (周静). Estimation of magnetic island width by the fluctuations of electron cyclotron emission radiometer on J-TEXT[J]. Plasma Science and Technology, 2019, 21(1): 15102-015102. DOI: 10.1088/2058-6272/aae382
[3]	Lei YE (叶磊), Xiaotao XIAO (肖小涛), Yingfeng XU (徐颖峰), Zongliang DAI (戴宗良), Shaojie WANG (王少杰). Implementation of field-aligned coordinates in a semi-Lagrangian gyrokinetic code for tokamak turbulence simulation[J]. Plasma Science and Technology, 2018, 20(7): 74008-074008. DOI: 10.1088/2058-6272/aac013
[4]	Carlo POGGI, Théo GUILLAUME, Fabrice DOVEIL, Laurence CHÉRIGIER-KOVACIC. Estimation of the Lyman-α signal of the EFILE diagnostic under static or radiofrequency electric field in vacuum[J]. Plasma Science and Technology, 2018, 20(7): 74001-074001. DOI: 10.1088/2058-6272/aabde3
[5]	M SHAHMANSOURI, A P MISRA. Surface plasmon oscillations in a semi-bounded semiconductor plasma[J]. Plasma Science and Technology, 2018, 20(2): 25001-025001. DOI: 10.1088/2058-6272/aa9213
[6]	K. HANADA, H. ZUSHI, H. IDEI, K. NAKAMURA, M. ISHIGURO, S. TASHIMA, E. I. KALINNIKOVA, Y. NAGASHIMA, M. HASEGAWA, A. FUJISAWA, A. HIGASHIJIMA, S. KAWASAKI, H. NAKASHIMA, O. MITARAI, A. FUKUYAMA, Y. TAKASE, X. GAO, H. LIU, J. QIAN, M. ONO, R. RAMAN. Power Balance Estimation in Long Duration Discharges on QUEST[J]. Plasma Science and Technology, 2016, 18(11): 1069-1075. DOI: 10.1088/1009-0630/18/11/03
[7]	Djilali BENYOUCEF, Mohammed YOUSFI. Ar ⁺ /Ar, O₂ ⁺ /O₂ and N₂ ⁺ /N ₂ Elastic Momentum Collision Cross Sections: Calculation and Validation Using the Semi-Classical Model[J]. Plasma Science and Technology, 2014, 16(6): 588-592. DOI: 10.1088/1009-0630/16/6/09
[8]	LIU Xuandong (刘轩东), WANG Hu (王虎), LI Xiaoang (李晓昂), ZHANG Qiaogen (张乔根), et al.. Estimation of Surface Roughness due to Electrode Erosion in Field-Distortion Gas Switch[J]. Plasma Science and Technology, 2013, 15(8): 812-816. DOI: 10.1088/1009-0630/15/8/18
[9]	Youji SOMEYA, Kenji TOBITA. Estimation of TBR on the Gap Between Neighboring Blanket Modules in the DEMO Reactor[J]. Plasma Science and Technology, 2013, 15(2): 171-174. DOI: 10.1088/1009-0630/15/2/19
[10]	ZHANG Ling, XU Guosheng, DING Siye, GAO Wei, WU Zhenwei, CHEN Yingjie, HUANG Juan. Estimation of Neutral Density in Edge Plasma with Double Null Configuration in EAST[J]. Plasma Science and Technology, 2011, 13(4): 431-434.

Cited By

Cited by

Periodical cited type(16)

1.	Shentu, L., Peng, D., Xi, J. A novel neural network architecture dedicated for LIBS spectrum analysis with its application to steel pipe classification. Measurement Science and Technology, 2025, 36(1): 015215. DOI:10.1088/1361-6501/ad9166
2.	Hao, Z., Liu, K., Lian, Q. et al. Machine learning in laser-induced breakdown spectroscopy: A review. Frontiers of Physics, 2024, 19(6): 62501. DOI:10.1007/s11467-024-1427-2
3.	Wang, A., Cui, J.-C., Song, W.-R. et al. Quantitative Analysis of Coal Properties Using Laser-Induced Breakdown Spectroscopy and Semi-Supervised Learning \| [基于激光诱导击穿光谱与半监督学习的煤质定量分析研究]. Guang Pu Xue Yu Guang Pu Fen Xi/Spectroscopy and Spectral Analysis, 2024, 44(7): 1940-1945. DOI:10.3964/j.issn.1000-0593(2024)07-1940-06
4.	Wang, D., Xu, L., Gao, W. et al. Application of Semi-Supervised Learning Model to Coal Sample Classification. Applied Sciences (Switzerland), 2024, 14(4): 1606. DOI:10.3390/app14041606
5.	Képeš, E., Vrábel, J., Siozos, P. et al. Quantification of alloying elements in steel targets: The LIBS 2022 regression contest. Spectrochimica Acta - Part B Atomic Spectroscopy, 2023. DOI:10.1016/j.sab.2023.106710
6.	Van den Eynde, S., Díaz-Romero, D.J., Zaplana, I. et al. Deep learning regression for quantitative LIBS analysis. Spectrochimica Acta - Part B Atomic Spectroscopy, 2023. DOI:10.1016/j.sab.2023.106634
7.	Zhu, Q.-X., Zhang, H.-T., Tian, Y. et al. Co-training based virtual sample generation for solving the small sample size problem in process industry. ISA Transactions, 2023. DOI:10.1016/j.isatra.2022.08.021
8.	Zhang, D., Zhang, H., Zhao, Y. et al. A brief review of new data analysis methods of laser-induced breakdown spectroscopy: machine learning. Applied Spectroscopy Reviews, 2022, 57(2): 89-111. DOI:10.1080/05704928.2020.1843175
9.	Wang, Z., Afgan, M.S., Gu, W. et al. Recent advances in laser-induced breakdown spectroscopy quantification: From fundamental understanding to data processing. TrAC - Trends in Analytical Chemistry, 2021. DOI:10.1016/j.trac.2021.116385
10.	Chang, F., Yang, J., Lu, H. et al. Repeatability enhancing method for one-shot LIBS analysis: Via spectral intensity correction based on probability distribution. Journal of Analytical Atomic Spectrometry, 2021, 36(8): 1712-1723. DOI:10.1039/d1ja00040c
11.	Xu, W., Tang, J., Xia, H. A review of semi-supervised learning for industrial process regression modeling. 2021. DOI:10.23919/CCC52363.2021.9550262
12.	Li, D., Huang, D., Liu, Y. Research on semi-supervised heterogeneous adaptive co-training soft-sensor model \| [基于协同训练的半监督异构自适应软测量建模方法的研究]. Huagong Xuebao/CIESC Journal, 2020, 71(5): 2128-2138. DOI:10.11949/0438-1157.20191378
13.	Gao, J., Tian, Y., Chen, X. Antenna Optimization Based on Co-Training Algorithm of Gaussian Process and Support Vector Machine. IEEE Access, 2020. DOI:10.1109/ACCESS.2020.3039269
14.	Carter, S., Clough, R., Fisher, A. et al. Atomic spectrometry update: Review of advances in the analysis of metals, chemicals and materials. Journal of Analytical Atomic Spectrometry, 2019, 34(11): 2159-2216. DOI:10.1039/c9ja90058f
15.	Bai, X., Zhang, L., Yang, T. et al. Semi-supervised learning based acoustic NLOS identification for smartphone indoor positioning. 2019. DOI:10.1109/ICSPCC46631.2019.8960779
16.	Fu, Y., Hou, Z., Deguchi, Y. et al. From big to strong: Growth of the Asian laser-induced breakdown spectroscopy community. Plasma Science and Technology, 2019, 21(3): 030101. DOI:10.1088/2058-6272/aaf873

Other cited types(0)

Get Citation

PDF

XML

Article views (162) PDF downloads (260) Cited by(16)

Turn off MathJax

Article Contents

Abstract

References

Semi-supervised LIBS quantitative analysis method based on co-training regression model with selection of effective unlabeled samples