Laser-induced breakdown spectroscopy for the classification of wood materials using machine learning methods combined with feature selection

Xutai CUI (崔旭泰); Qianqian WANG (王茜蒨); Kai WEI (魏凯); Geer TENG (腾格尔); Xiangjun XU (徐向君)

doi:10.1088/2058-6272/abf1ac

Plasma Science and Technology > 2021 > 23(5): 55505-055505. > DOI: 10.1088/2058-6272/abf1ac

Xutai CUI (崔旭泰), Qianqian WANG (王茜蒨), Kai WEI (魏凯), Geer TENG (腾格尔), Xiangjun XU (徐向君). Laser-induced breakdown spectroscopy for the classification of wood materials using machine learning methods combined with feature selection[J]. Plasma Science and Technology, 2021, 23(5): 55505-055505. DOI: 10.1088/2058-6272/abf1ac

Citation:

PDF (4167 KB)

Laser-induced breakdown spectroscopy for the classification of wood materials using machine learning methods combined with feature selection

¹ School of Optics and Photonics, Beijing Institute of Technology, Beijing 100081, People's Republic of China
² Key Laboratory of Photonic Information Technology, Ministry of Industry and Information Technology, Beijing 100081, People's Republic of China

Funds: The authors gratefully acknowledge support from National Natural Science Foundation of China (No. 62075011) and Graduate Technological Innovation Project of Beijing Institute of Technology (No. 2019CX20026).

More Information

Received Date: December 25, 2020
Revised Date: March 21, 2021
Accepted Date: March 23, 2021

Graphical Abstract

Abstract

Abstract

In this paper, we explore whether a feature selection method can improve model performance by using some classical machine learning models, artificial neural network, k-nearest neighbor, partial least squares-discrimination analysis, random forest, and support vector machine (SVM), combined with the feature selection methods, distance correlation coefficient (DCC), important weight of linear discriminant analysis (IW-LDA), and Relief-F algorithms, to discriminate eight species of wood (African rosewood, Brazilian bubinga, elm, larch, Myanmar padauk, Pterocarpus erinaceus, poplar, and sycamore) based on the laser-induced breakdown spectroscopy (LIBS) technique. The spectral data are normalized by the maximum of line intensity and principal component analysis is applied to the exploratory data analysis. The feature spectral lines are selected out based on the important weight assessed by DCC, IW-LDA, and Relief-F. All models are built by using the different number of feature lines (sorted by their important weight) as input. The relationship between the number of feature lines and the correct classification rate (CCR) of the model is analyzed. The CCRs of all models are improved by using a suitable feature selection. The highest CCR achieves (98.55...0.39)% when the SVM model is established from 86 feature lines selected by the IW-LDA method. The result demonstrates that a suitable feature selection method can improve model recognition ability and reduce modeling time in the application of wood materials classification using LIBS.
- laser-induced breakdown spectroscopy (LIBS),
- feature selection,
- wood materials

FullText(HTML)

References (35)

References

[1]	Francisco-Fernández M et al 2012 Chemometr. Intell. Lab.Syst. 118 159
[2]	Liebmann M J et al 2016 Proc. Natl. Acad. Sci. USA 113 E696
[3]	Austerlitz F et al 2000 Genetics 154 1309
[4]	Han H et al 2017 Bot. Sci. 95 283
[5]	Khalid M et al 2008 Int. J. Simul. Syst. Sci. Technol. 9 9
[6]	Zhang M M et al 2019 IAWA J. 40 58
[7]	Cody R B et al 2012 J. Anal. Appl. Pyrol. 95 134
[8]	Kalaw J M and Sevilla F B III 2018 Holzforschung 72 215
[9]	Francisco-Fernández M et al 2015 J. Therm. Anal. Calorim.120 541
[10]	Piuri V and Scotti F 2010 IEEE Trans. Syst. Man Cybern. Part C (Appl. Rev.) 40 358
[11]	Shou G Z et al 2014 J. Near Infrared Spectrosc. 22 423
[12]	Park S Y et al 2017 J. Korean Wood Sci. Technol. 45 202
[13]	Kurata Y 2017 For. Prod. J. 67 63
[14]	Lavine B K et al 2001 Appl. Spectrosc. 55 960
[15]	Solo-Gabriele H M et al 2004 Waste Manag. 24 413
[16]	Blassino M, Solo-Gabriele H and Townsend T 2002 Waste Manag. Res. 20 290
[17]	Hahn D W and Omenetto N 2012 Appl. Spectrosc. 66 347
[18]	Singh J et al 2017 Food Chem. 221 1778
[19]	Unnikrishnan V K et al 2013 Anal. Methods 5 1294
[20]	Tognoni E et al 2002 Spectrochim. Acta Part B At. Spectrosc.57 1115
[21]	Lanza N L et al 2012 Appl. Opt. 51 B74
[22]	Leandro J G R, Gonzaga E B and de Figueiredo Latorraca J V 2019 Wood Sci. Technol. 53 1079
[23]	Cui X T et al 2019 Appl. Phys. B 125 56
[24]	Junjuri R et al 2019 Polym. Test. 76 101
[25]	Tang Y et al 2018 Optik 165 179
[26]	Duan F J et al 2018 Spectrochim. Acta Part B At. Spectrosc.143 12
[27]	Wang Y et al 2016 Spectrochim. Acta Part B 126 44
[28]	Fu X et al 2017 J. Anal. At. Spectrom. 32 1166
[29]	Myakalwar A K et al 2015 Sci. Rep. 5 13169
[30]	Wang Q Q et al 2018 Biomed. Opt. Express 9 5837
[31]	Song W R et al 2021 J. Anal. At. Spectrom. 36 111
[32]	Abdelli-Messaci S et al 2005 Spectrochim. Acta Part B At.Spectrosc. 60 955
[33]	Liu K et al 2019 Anal. Methods 11 4769
[34]	Wang Q Q et al 2020 Opt. Laser Technol. 125 106035
[35]	Vítková G et al 2012 Spectrochim. Acta Part B At. Spectrosc.73 1

[1]	Jie LONG, Weiran SONG, Zongyu HOU, Zhe WANG. A data selection method for matrix effects and uncertainty reduction for laser-induced breakdown spectroscopy[J]. Plasma Science and Technology, 2023, 25(7): 075501. DOI: 10.1088/2058-6272/acb6dd
[2]	Guodong WANG (王国栋), Lanxiang SUN (孙兰香), Wei WANG (汪为), Tong CHEN (陈彤), Meiting GUO (郭美亭), Peng ZHANG (张鹏). A feature selection method combined with ridge regression and recursive feature elimination in quantitative analysis of laser induced breakdown spectroscopy[J]. Plasma Science and Technology, 2020, 22(7): 74002-074002. DOI: 10.1088/2058-6272/ab76b4
[3]	Yaguang MEI (梅亚光), Shusen CHENG (程树森), Zhongqi HAO (郝中骐), Lianbo GUO (郭连波), Xiangyou LI (李祥友), Xiaoyan ZENG (曾晓雁), Junliang GE (葛军亮). Quantitative analysis of steel and iron by laser-induced breakdown spectroscopy using GA-KELM[J]. Plasma Science and Technology, 2019, 21(3): 34020-034020. DOI: 10.1088/2058-6272/aaf6f3
[4]	Liuyang ZHAN (詹浏洋), Xiaohong MA (马晓红), Weiqi FANG (方玮骐), Rui WANG (王锐), Zesheng LIU (刘泽生), Yang SONG (宋阳), Huafeng ZHAO (赵华凤). A rapid classification method of aluminum alloy based on laser-induced breakdown spectroscopy and random forest algorithm[J]. Plasma Science and Technology, 2019, 21(3): 34018-034018. DOI: 10.1088/2058-6272/aaf7bf
[5]	Haobin PENG (彭浩斌), Guohua CHEN (陈国华), Xiaoxuan CHEN (陈小玄), Zhimin LU (卢志民), Shunchun YAO (姚顺春). Hybrid classification of coal and biomass by laser-induced breakdown spectroscopy combined with K-means and SVM[J]. Plasma Science and Technology, 2019, 21(3): 34008-034008. DOI: 10.1088/2058-6272/aaebc4
[6]	Dan LUO (罗丹), Ying LIU (刘英), Xiangyu LI (李香宇), Zhenyang ZHAO (赵珍阳), Shigong WANG (王世功), Yong ZHANG (张勇). Quantitative analysis of C, Si, Mn, Ni, Cr and Cu in low-alloy steel under ambient conditions via laser-induced breakdown spectroscopy[J]. Plasma Science and Technology, 2018, 20(7): 75504-075504. DOI: 10.1088/2058-6272/aabc5d
[7]	Ying LI (李颖), Yanhong GU (谷艳红), Ying ZHANG (张莹), Yuandong LI (李远东), Yuan LU (卢渊). Analytical study of seashell using laser-induced breakdown spectroscopy[J]. Plasma Science and Technology, 2017, 19(2): 25501-025501. DOI: 10.1088/2058-6272/19/2/025501
[8]	HE Li’ao (何力骜), WANG Qianqian (王茜蒨), ZHAO Yu (赵宇), LIU Li (刘莉), PENG Zhong (彭中). Study on Cluster Analysis Used with Laser-Induced Breakdown Spectroscopy[J]. Plasma Science and Technology, 2016, 18(6): 647-653. DOI: 10.1088/1009-0630/18/6/11
[9]	WEN Guanhong(温冠宏), SUN Duixiong(孙对兄), SU Maogen(苏茂根), DONG Chenzhong(董晨钟). LIBS Detection of Heavy Metal Elements in Liquid Solutions by Using Wood Pellet as Sample Matrix[J]. Plasma Science and Technology, 2014, 16(6): 598-601. DOI: 10.1088/1009-0630/16/6/11
[10]	ZHAO Dongye(赵栋烨), FARID Nazar(纳扎), HAI Ran(海然), WU Ding(吴鼎), DING Hongbin(丁洪斌). Diagnostics of First Wall Materials in a Magnetically Confined Fusion Device by Polarization-Resolved Laser-Induced Breakdown Spectroscopy[J]. Plasma Science and Technology, 2014, 16(2): 149-154. DOI: 10.1088/1009-0630/16/2/11

Cited By

Cited by

Periodical cited type(15)

1.	Betlej, I., Skrzeczanowski, W., Nasiłowska, B. et al. Application of Laser-Induced Breakdown Spectroscopy (LIBS) as an Attempt to Determine Graphene Oxide Incorporation on Wood Surfaces. Coatings, 2025, 15(1): 34. DOI:10.3390/coatings15010034
2.	Lyu, Y., Song, W., Hou, Z. et al. Incorporating empirical knowledge into data-driven variable selection for quantitative analysis of coal ash content by laser-induced breakdown spectroscopy. Plasma Science and Technology, 2024, 26(7): 075509. DOI:10.1088/2058-6272/ad370c
3.	Xu, X., Teng, G., Wang, Q. et al. Accuracy Enhancement of Glioma Boundary Tissue Identification by Polarization-resolved LIBS Spectral Fusion. Atomic Spectroscopy, 2024, 45(3): 216-225. DOI:10.46770/AS.2024.101
4.	Ali, Z., Jamil, Y., Anwar, H. et al. Classification of e-waste using machine learning-assisted laser-induced breakdown spectroscopy. Waste Management and Research, 2024. DOI:10.1177/0734242X241248730
5.	Sarafis, A., Gerodimos, T., Kechaoglou, E. et al. Identification of wood specimens utilizing fs-LIBS and machine learning techniques. EPJ Applied Physics, 2024. DOI:10.1051/epjap/2024230215
6.	Huang, Y., Bais, A., Hussein, A.E. Domain Adaptation Using Class-Balanced Self-Paced Learning for Soil Classification with LIBS. IEEE Transactions on Plasma Science, 2023, 51(9): 2742-2755. DOI:10.1109/TPS.2023.3305559
7.	Wei, K., Teng, G., Wang, Q. et al. Rapid Test for Adulteration of Fritillaria Thunbergii in Fritillaria Cirrhosa by Laser-Induced Breakdown Spectroscopy. Foods, 2023, 12(8): 1710. DOI:10.3390/foods12081710
8.	Jiang, H., Ji, X., Yang, Y. et al. Vibration Signal Analysis of Roadheader Based on Referential Manifold Learning. Shock and Vibration, 2023. DOI:10.1155/2023/8818380
9.	He, Y., Zhang, Y., Ke, C. et al. Optical Scanning Analysis of Static Samples by Compact Laser Induced Breakdown Spectroscopy. IEEE Transactions on Instrumentation and Measurement, 2023. DOI:10.1109/TIM.2023.3300425
10.	Xu, X., Teng, G., Wang, Q. et al. Spectral preprocessing combined with feature selection improve model robustness for plastics samples classification by LIBS. Frontiers in Environmental Science, 2023. DOI:10.3389/fenvs.2023.1175392
11.	He, J., Sun, Y., Yu, C. et al. An Improved Wood Recognition Method Based on the One-Class Algorithm. Forests, 2022, 13(9): 1350. DOI:10.3390/f13091350
12.	He, Y., Xu, T., Zhang, Y. et al. Quantitative analysis and time-resolved characterization of simulated tokamak exhaust gas by laser-induced breakdown spectroscopy. Plasma Science and Technology, 2022, 24(4): 045506. DOI:10.1088/2058-6272/ac45e4
13.	Pratondo, A., Novianty, A. Comparison of Wood Classification using Machine Learning. 2022. DOI:10.1109/ICSPC55597.2022.10001776
14.	Liu, Z., Hao, J., Yang, D. et al. A Novel Reformed Reduced Kernel Extreme Learning Machine with RELIEF-F for Classification. Computational Intelligence and Neuroscience, 2022. DOI:10.1155/2022/4795535
15.	Ji, X., Yang, Y., Qu, Y. et al. Health Diagnosis of Roadheader Based on Reference Manifold Learning and Improved K -Means. Shock and Vibration, 2021. DOI:10.1155/2021/6311795

Other cited types(0)

Get Citation

PDF

XML

Article views (142) PDF downloads (188) Cited by(15)

Turn off MathJax

Article Contents

Abstract

References

Laser-induced breakdown spectroscopy for the classification of wood materials using machine learning methods combined with feature selection