Automatic determination of optimal spectral peaks for classification of Chinese tea varieties using laser-induced breakdown spectroscopy

Hongyang Zhang, Qibing Zhu, Min Huang, Ya Guo

Abstract


The accurate identification of tea varieties is of great significance to ensure the interests of tea producers and consumers. As a non-destructive or micro damage detection method, laser-induced breakdown spectroscopy (LIBS) has been widely used in the quality detection or classification of agricultural products and food. The objective of this research was to automatically select optimal spectral peaks from the full LIBS spectra, and develop effective classification model for identifying tea varieties. The LIBS spectra covering the region 200-500 nm were measured for 600 Chinese tea leaves including six varieties (i.e. Longjing green tea, Jinhao black tea, Tie Guanyin, Huang Jinya, White peony tea, and Anhua dark tea). A total of 50 optimal spectral peaks were automatically selected from full LIBS spectra (6102) by using the uninformative variable elimination (UVE) and partial least squares projection analysis, and the selected spectral peaks mainly represent the elemental difference in C, Fe, Mg, Mn, Al and Ca. Partial Least Squares Discriminant Analysis (PLS-DA) was used for developing classification model using selected optimal spectral peaks, and yielded the 99.77% classification accuracy for 300 test samples was reached. The results indicate that the proposed method can be used to identify leaf varieties in various tea products.
Keywords: LIBS, tea varieties classification, feature selection, PLS projection algorithm, UVE, PLSDA
DOI: 10.25165/j.ijabe.20181103.3482

Citation: Zhang H Y, Zhu Q B, Huang M, Guo Y. Automatic determination of optimal spectral peaks for classification of Chinese tea varieties using laser-induced breakdown spectroscopy. Int J Agric & Biol Eng, 2018; 11(3): 154–158.

Keywords


LIBS, tea species classification, feature selection, PLS projection algorithm, UVE, PLSDALIBS, tea varieties classification, feature selection, PLS projection algorithm, UVE, PLSDA

Full Text:

PDF

References


Higdon J V, Frei B. Tea catechins and polyphenols: health effects, metabolism, and antioxidant functions. Critical Reviews in Food Science and Nutrition, 2003; 43(1): 89–143.

Liao S, Kao Y H, Hiipakka R A. Green tea: biochemical and biological basis for health benefits. Vitamins & Hormones, 2001; 62(1): 1–94.

Han L, Li R. Determination of minerals and trace elements in various tea by ICP-AES. Spectroscopy & Spectral Analysis, 2002; 22(2): 304–306.

Wang X P, Ma Y J, Itoh M. Analysis of 23 mineral elements in tea samples collected from China and Japan by using ICP-AES and ICP-MS combined with a closed decomposition. Spectroscopy and Spectral Analysis, 2005; 25(10): 1703–1707.

Cai L C. Arsenic speciation in drinking tea samples by hydride generation atomic fluorescence spectrometry. Asian Journal of Chemistry, 2013; 25(14): 8169–8172.

Pongsuwan W, Bamba T, Yonetani T, Kobayashi A, Fukusaki E. Quality prediction of Japanese green tea using pyrolyzer coupled GC/MS based metabolic fingerprinting. Journal of Agricultural & Food Chemistry, 2008; 56(3): 744–750.

Lee M S, Hwang Y S, Lee J, Choung M G. The characterization of caffeine and nine individual catechins in the leaves of green tea (camellia sinensis L.) by near–infrared reflectance spectroscopy. Food Chemistry,

; 158(11): 351–357.

He Q, Yao K, Jia D Y, Fan H J, Liao X P, Shi B. Determination of total catechins in tea extracts by HPLC and spectrophotometry. Natural Product Research, 2009; 23(1): 93–100.

Zhang T, Wu S, Dong J, Li H. Quantitative and classification analysis of slag samples by laser-induced breakdown spectroscopy (LIBS) coupled with support vector machine (SVM) and partial least square (PLS) methods. J. of Analytical Atomic Spectrometry, 2015; 30(2): 368–374.

Pandhija S, Rai A K. Screening of brick-kiln area soil for determination of heavy metal Pb using LIBS. Environmental Monitoring & Assessment, 2008; 148(1-4): 437–447.

Multari R A, Cremers D A, Dupre J A, Gustafson J E. Detection of biological contaminants on foods and food surfaces using laser-induced breakdown spectroscopy (LIBS). Journal of Agricultural & Food Chemistry, 2013; 61(36): 8687–8694.

Gottfried J L, Harmon R S, Jr F C D L, Miziolek A W. Multivariate analysis of laser-induced breakdown spectroscopy chemical signatures for geomaterial classification. Spectrochimica Acta Part B Atomic Spectroscopy, 2009; 64(10): 1009–1019.

Jr L F C D, Gottfried J L. Influence of variable selection on partial least squares discriminant analysis models for explosive residue classification. Spectrochimica Acta Part B Atomic Spectroscopy, 2011; 66(2): 122–128.

Yueh F Y, Zheng H, Singh J P, Burgess S. Preliminary evaluation of laser-induced breakdown spectroscopy for tissue classification. Spectrochimica Acta Part B Atomic Spectroscopy, 2009; 64(10): 1059–1067.

Wang J M, Zheng P C, Liu H D, Fang L. Classification of Chinese tea leaves using laser-induced breakdown spectroscopy combined with the discriminant analysis method. Analytical Methods, 2016; 8(15): 3204–3209.

Zheng P C, Shi M J, Wang J M, Liu H D. The spectral emission characteristics of laser induced plasma on tea samples. Plasma Science and Technology, 2015; 17(8): 664–670.

Centner V, Massart D L, de Noord O E, De J S, Vandeginste B M, Sterna C. Elimination of uninformative variables for multivariate calibration. Analytical Chemistry, 1996; 68(21): 3851–3858.

Dan, T N, Dai L K. Spectral wavelength selection based on PLS projection analysis. Spectroscopy and Spectral Analysis, 2009; 29(2): 351–354. (in Chinese)

Barker M, Rayens W. Partial least squares for discrimination. Journal of Chemometrics, 2003; 17(3): 166–173.

http://www.physics.nist.gov/PhysRefData/ASD/lines-form.html.

Morel S, Leone N, Adam P, Amouroux J. Detection of bacteria by time-resolved laser-induced breakdown spectroscopy. Applied Optics, 2003; 42(30): 6184–6191.




Copyright (c) 2018



2023-2026 Copyright IJABE Editing and Publishing Office