Development of one-class classification method for identifying healthy T. granosa from those contaminated with uncertain heavy metals by LIBS

Zhonghao Xie, Xi'an Feng, Xiao Chen, Guangzao Huang, Xiaojing Chen, Limin Li, Wen Shi, Chengxi Jiang, Shuwen Yu

Abstract


Laser-induced breakdown spectroscopy (LIBS) can be used for the rapid detection of heavy metal contamination of Tegillarca granosa (T. granosa), but an appropriate classification model needs to be constructed. In the one-class classification method, only target samples are needed in training process to achieve the recognition of abnormal samples, which is suitable for rapid identification of healthy T. granosa from those contaminated with uncertain heavy metals. The construction of a one-class classification model for heavy metal detection in T. granosa by LIBS has faced the problem of high-dimension and small samples. To solve this problem, a novel one-class classification method was proposed in this study. Here, the principal component scores and the intensity of the residual spectrum were combined as extracted features. Then, a one-class classifier based on Mahalanobis distance using the extracted features was constructed and its threshold was set by leave-one-out cross-validation. The sensitivity, specificity and accuracy of the proposed method were reached to 1, 0.9333 and 0.9667 respectively, which are superior to the previously reported methods.
Keywords: laser-induced breakdown spectroscopy, Heavy metal contamination, Tegillarca granosa, one-class classification
DOI: 10.25165/j.ijabe.20231604.7666

Citation: Xie Z H, Feng X A, Chen X, Huang G Z, Chen X J, Li L M, et al. Development of one-class classification method for identifying healthy T. granosa from those contaminated with uncertain heavy metals by LIBS. Int J Agric & Biol Eng, 2023; 16(4): 201－206.

Keywords


laser-induced breakdown spectroscopy, Heavy metal contamination, Tegillarca granosa, one-class classification

Full Text:

PDF

References


Zhang M, Sun X, Xu J L. Heavy metal pollution in the East China Sea: A review. Marine Pollution Bulletin 2020; 159: 111473. doi: 10.1016/j.marpolbul.2020.111473.

Briffa J, Sinagra E, Blundell R. Heavy metal pollution in the environment and their toxicological effects on humans. Heliyon 2020; 6(9): e04691. doi: 10.1016/j.heliyon.2020.e04691.

Riza S, Gevisioner G, Suprijanto J, Widowati I, Putra I, Effendi I. Farming and food safety analysis of blood cockles (Anadara granosa) from Rokan Hilir, Riau, Indonesia. Aquaculture, Aquarium, Conservation & Legislation 2021; 14: 814–812.

Chen X J, Liu K, Cai J B, Zhu D H, Chen H L. Identification of heavy metal-contaminated Tegillarca granosa using infrared spectroscopy. Journal of Chinese Institute of Food Science & Technology 2015; 7(5): 2172–2181.

Yuan L M, Chen X J, Lai Y J, Chen X, Shi Y J, Zhu D H, et al. A Novel strategy of clustering informative variables for quantitative analysis of potential toxics element in Tegillarca granosa using laser-induced breakdown spectroscopy. Food Analytical Methods, 2018; 11(5): 1405-1416.

Ipeaiyeda A, Ayoade A. Flame atomic absorption spectrometric determination of heavy metals in aqueous solution and surface water preceded by co-precipitation procedure with copper (II) 8-hydroxyquinoline. Applied Water Science 2017; 7: 4449–4459.

Suo L Z, Dong X Y, Gao X, Xu J F, Huang Z, Ye J, et al. Silica-coated magnetic graphene oxide nanocomposite based magnetic solid phase extraction of trace amounts of heavy metals in water samples prior to determination by inductively coupled plasma mass spectrometry. Microchemical Journal, 2019; 149: 104039. doi: 10.1016/j.microc.2019.104039.

Vinhal J O, Cassella R J. Novel extraction induced by microemulsion breaking for Cu, Ni, Pb and V determination in ethanol-containing gasoline by graphite furnace atomic absorption spectrometry. Spectrochimica Acta Part B: Atomic Spectroscopy, 2019; 151: 33–40.

Fu Y T, Gu W L, Hou Z Y, Muhammed S A, Li T Q, Wang Y, et al. Mechanism of signal uncertainty generation for laser-induced breakdown spectroscopy. Frontiers of Physics, 2021; 16(2): 1–10.

Ji G L, Ye P C, Shi Y J, Yuan L M, Chen X J, Yuan M S, et al. Laser-induced breakdown spectroscopy for rapid discrimination of heavy-metal-contaminated seafood Tegillarca granosa. Sensors, 2017; 17(11): 2655. doi: 10.3390/s17112655.

Xie Z H, Meng L W, Chen X J, Chen X, Yuan L M, Shi W, et al . Identification of heavy metal-contaminated Tegillarca granosa using laser-induced breakdown spectroscopy and linear regression for classification. Plasma Science and Technology, 2020; 22(8): 085503. doi: 10.1088/2058-6272/ab8c31.

Chen H, Tan C, Li H J. Untargeted identification of adulterated Sanqi powder by near-infrared spectroscopy and one-class model. Journal of Food Composition and Analysis, 2020; 88: 103450.

Santana F B, Neto W B, Poppi R J. Random forest as one-class classifier and infrared spectroscopy for food adulteration detection. Food chemistry, 2019; 293: 323–332.

Esteki M, Simal-Gandara J, Shahsavari Z, Zandbaaf S, Dashtaki E, Vander Heyden Y. A review on the application of chromatographic methods, coupled to chemometrics, for food authentication. Food Control, 2018; 93: 165–182.

Oliveri P. Class-modelling in food analytical chemistry: Development, sampling, optimisation and validation issues–A tutorial. Analytica chimica acta, 2017; 982: 9–19.

Huang G Z, Yang Z J, Chen X J, Ji G L. An innovative one-class least squares support vector machine model based on continuous cognition. Knowledge-Based Systems, 2017; 123: 217–228.

Tax D M J. One-class classification. Applied Sciences, 2001; 212p.

Oza P, Patel V M. One-class convolutional neural network. IEEE Signal Processing Letters, 2018; 26(2): 277–281.

Wetzel S J. Unsupervised learning of phase transitions: From principal component analysis to variational autoencoders. Physical Review E, 2017; 96(2): 022140. doi: 10.1103/PhysRevE.96.022140.

Ghorbani H. Mahalanobis distance and its application for detecting multivariate outliers. Facta Universitatis-Series Mathematics and Informatics, 2019; 34: 583–595.

Zontov Y, Rodionova O Y, Pomerantsev A, Kucheryavskiy S. DD-SIMCA–a Matlab GUI tool for data driven SIMCA approach. Chemometrics and Intelligent Laboratory Systems, 2017; 167: 23–28.

Xu L, Yan S M, Cai C B, Yu X P. One-class partial least squares (OCPLS) classifier. Chemometrics & Intelligent Laboratory Systems, 2013; 126: 1–5.

Xu L, Goodarzi M, Shi W, Cai C B, Jiang J H. A Matlab toolbox for class modeling using one-class partial least squares (OCPLS) classifiers. Chemometrics and Intelligent Laboratory Systems, 2014; 139: 58–63.

Xie Z H, Feng X A, Chen X J. Partial least trimmed squares regression. Chemometrics and Intelligent Laboratory Systems, 2022; 221: 104486. doi: 10.1016/j.chemolab.2021.104486.

Xie Z H, Feng X A, Chen X J. Subsampling for partial least-squares regression via an influence function. Knowledge-Based Systems, 2022; 245: 108661. doi: 10.1016/j.knosys.2022.108661.

Tax D. DDtools, the Data Description Toolbox for Matlab, 2014. Software available at http://prlab tudelft nl/david-tax/dd_tools html, 2015

Tao X M, Chen W, Li X K, Zhang X H, Li Y T, et al. The ensemble of density-sensitive SVDD classifier based on maximum soft margin for imbalanced datasets. Knowledge-Based Systems, 2021; 219: 106897. doi: 10.1016/j.knosys.2021.106897.

Chen W H, Chen H Z, Feng Q X, Mo L N, Hong S Y. A hybrid optimization method for sample partitioning in near-infrared analysis. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2021; 248: 119182. doi: 10.1016/j.saa.2020.119182.




Copyright (c) 2023 International Journal of Agricultural and Biological Engineering

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.

2023-2026 Copyright IJABE Editing and Publishing Office