Detection and recognition of veterinary drug residues in beef using hyperspectral discrete wavelet transform and deep learning

Rongchang Jiang, Jingxin Shen, Xinran Li, Rui Gao, Qinghe Zhao, Zhongbin Su

Abstract


A fast, non-destructive recognition method for veterinary drug residues in beef was proposed to mitigate the laborious sample preparation and long detection times associated with conventional chemical detection techniques. Control beef samples free of veterinary drug residues and four groups of beef sprayed with relevant concentrations of metronidazole, ofloxacin, salbutamol, and dexamethasone under ambient conditions were analyzed by 400-1000 nm hyperspectral imaging followed by multiplicative scatter correction preprocessing. Data dimension reduction was performed using Competitive Adaptive Reweighted Sampling (CARS), Principal Component Analysis (PCA), and Discrete Wavelet Transform (DWT) based on Haar, db3, bior1.5, sym5, and rbio1.3 wavelet basis functions. Treated data were subjected to Convolutional Neural Network (CNN), Multilayer Perceptron (MLP), Random Forest (RF), and Support Vector Machine (SVM) modelling. CNN, MLP, SVM, and RF algorithms achieved overall accuracies of 91.6%, 88.6%, 87.6%, and 86.2%, respectively, when combined with DWT (wavelet basis functions and numbers of transform layers being Haar-4, db3-2, bior1.5-4, and sym5-3, respectively). The algorithm Kappa coefficients (0.89, 0.86, 0.85, and 0.83, respectively) and time consumption for prediction (140.60 ms, 57.85 ms, 70.67 ms, and 87.16 ms, respectively) were also superior to models based on CARS and PCA. DWT combined with deep learning can shorten prediction times, considerably improve the accuracy of classification and recognition, and alleviate the Hughes phenomenon, thus providing a new method for the fast, non-destructive detection and recognition of veterinary drug residues in beef.
Keywords: hyperspectral, beef, veterinary drug residues, discrete wavelet transform, convolutional neural network, deep learning
DOI: 10.25165/j.ijabe.20221501.6459

Citation: Jiang R C, Shen J X, Li X R, Gao R, Zhao Q H, Su Z B. Detection and recognition of veterinary drug residues in beef using hyperspectral discrete wavelet transform and deep learning. Int J Agric & Biol Eng, 2022; 15(1): 224–232.

Keywords


hyperspectral, beef, veterinary drug residues, discrete wavelet transform, convolutional neural network, deep learning

Full Text:

PDF

References


Liu Y F, Shen Q. Commonality and difference analysis of the effects of poultry and livestock products on human health. Journal of Shaanxi Normal University(Natural Science Edition), 2020; 48(1): 114–122. (in Chinese)

Hou M L. A brief analysis of the classification and detection techniques of veterinary drug residues in animal derived food. Modern Food, 2020; 3: 130–131, 134. (in Chinese)

Lozano A, Hernando M D, Uclés S, Hakme E, Fernandez-Alba A R. Identification and measurement of veterinary drug residues in beehive products. Food Chemistry, 2019; 274: 61–70. doi: 10.1016/j.foodchem. 2018.08.055.

Aman I M, Ahmed H F, Mostafa N Y, Kitada Y, Kar G. Detection of tetracycline veterinary drug residues in Egyptian poultry meat by high performance liquid chromatography. J Vet Med Allied Sci, 2017; 1(1): 52–58.

Masiá A, Suarez-Varela M M, Llopis-Gonzalez A, Pico Y. Determination of pesticides and veterinary drug residues in food by liquid chromatography-mass spectrometry: A review. Analytica Chimica Acta,

; 936: 40–61. doi: 10.1016/j.aca.2016.07.023.

Li N, Zhang Y T, Liu L, Shao H, Li H, Li J, Guo Y. Simultaneous determination of 4 kinds of 29 banned and restricted veterinary drugs in animal-derived foods by ultra performance liquid chromatography-tandem mass spectrometry and modified QUECHERS for sample preparation. Chinese Journal of Chromatography, 2014; 32(12): 1313–1319. (in Chinese)

Ji H X, Xia C X, Xu J J, Wu X X, Qiao L, Zhang C. A highly sensitive immunoassay of pesticide and veterinary drug residues in food by tandem conjugation of bi-functional mesoporous silica nanospheres. Analyst, 2020; 145: 2226–2232. doi: 10.1039/d1an00929j.

Zhao X L, Xie S Y, Chen Y, Wan K. Application of immunoanalyt analysis technology in the detection of agricultural and veterinary drug residues in agricultural products. China Inspection Body & Laboratory, 2020; 28(3): 18–20. (in Chinese)

Yu W, Li Y, Xie B, et al. An aggregation-induced emission-based indirect competitive immunoassay for fluorescence “turn-on” detection of drug residues in foodstuffs. Frontiers in Chemistry, 2019; 7: 228. doi: 10.3389/fchem.2019.00228.

Liu C L, Wang C, Guo Y. Detection of veterinary drug residues in animal derived food. Agriculture and Technology, 2019; 39(15): 42–43. (in Chinese)

Tao J J, Liu M H, Yuan H C, Zhao J Y. Surface-enhanced raman spectroscopy for rapid detection of testosterone propionate residues in duck meat. Chinese Journal of Analysis Laboratory, 2019; 38(2): 152–156. (in Chinese)

Guo L. Preparation and application of surface molecular imprinted polymer of sulfadimethoxine. Master dissertation. Shenyang Agricultural University, 2019; 54p. (in Chinese)

Sun J, Cong S, Mao H, Wu X, Yang N. Quantitative detection of mixed pesticide residue of lettuce leaves based on hyperspectral technique. Journal of Food Process Engineering, 2018; 41(2): e12654. doi: 10.1111/jfpe.12654.

Ji H, Ren Z, Rao Z. Identification of pesticide residue types in spinach leaves based on hyperspectral imaging. Chinese Journal of Luminescence, 2018; 39(12): 1778–1784. (in Chinese)

Gao Z M, Shao Y Y, Xuan G T, Wang Y X, Liu Y, Han X. Real-time hyperspectral imaging for the in-field estimation of strawberry ripeness with deep learning. Artificial Intelligence in Agriculture, 2020; 4(1): 31–38. doi: 10.1016/j.aiia.2020.04.003.

Sifuzzaman M, Islam M R, Ali M Z. Application of wavelet transform and its advantages compared to Fourier transform. Journal of hsical Sciences, 2009; 13: 121–134.

Xu T Y, Guo Z H, Yu F H, Xu B, Feng S. Genetic algorithm combined with extreme learning machine to diagnose nitrogen deficiency in rice in cold region. Transactions of the CSAE, 2020; 36(2): 209–218. (in Chinese)

Gao Z M, Zhao Y R, Khot L R, Hoheisel G, Zhang Q. Optical sensing for early spring freeze related blueberry bud damage detection: Hyperspectral imaging for salient spectral wavelengths identification. Computers and Electronics in Agriculture, 2019; 167: 105025. doi: 10.1016/j.compag. 2019.105025.

Yuan Z R, Wei L F, Zhang Y X, Yu M, Yan X. Hyperspectral inversion and analysis of heavy metal arsenic content in farmland soil based on optimizing CARS combined with PSO-SVM algorithm. Spectroscopy and Spectral Analysis, 2020; 40(2): 567–573. doi: 10.3964/ j.issn.1000-0593(2020)02-0567-07. (in Chinese)

Peng H G, Jin Y, Zhan Y G, Chen Y, Feng X, Qian F, et al. Quantitative determination of hydrolytic nitrogen content in soil by near infrared spectroscopy combined with competitive adaptive reweighted sampling variable selection algorithm. Journal of Instrumental Analysis, 2020; 39(10): 1305–1310. (in Chinese)

Okayama T, Shintaku Y, Katsuura E. New conformal map for the Sinc approximation for exponentially decaying functions over the semi-infinite interval. Journal of Computational and Applied Mathematics, 2020; 373: 112358. doi: 10.1016/j.cam.2019.112358.

Wang G F, Zhang Y X, Xu W L, Zhou W, Wu H, Xu Z, et al. Estimation of phytoplankton pigment concentration in South China sea from hyperspectral absorption data. Acta Optica Sinica, 2021; 41(6): 14–28. (in Chinese)

Chen M, Hu X Q, Lu W K. Application of artificial neural network in agricultural disease prediction. Modern Agricultural Science and Technology, 2020; 11(21): 136–140. (in Chinese)

Deng L F, Zhang F, Qi Y X, Yuan J. Identification of sodium ion spectral characteristics of halophytes based on parameter optimized SVM method. Spectroscopy and Spectral Analysis, 2020; 40(1): 247–254. (in Chinese)

Li G, Gao X, Xiao N, Xiao Y. Estimation soil organic matter contents with hyperspectra based on SCARS and RF algorithms. Chinese Journal of Luminescence, 2019; 40: 1030–1039. (in Chinese)

Krizhevsky A, Sutskever I, Hinton G E. ImageNet classification with deep convolutional neural networks. Advances in neural information processing systems, 2012; 25: 1097–1105.

Wu H M, Xu J Q, Liu H L, Liu C, Zhang D, Chen K. Identification of water injection meat based on hyperspectral technique and spectrum characteristics. Transactions of the Chinese Society for Agricultural Machinery, 2019; 50(11): 367–372. (in Chinese)

Shi Y, Ma D H, Lu J, Li J, Shi J. Hyperspectral image classification based on manifold spectral dimensionality reduction and deep learning method. Transactions of the CSAE, 2020; 36(6): 151–160. (in Chinese)




Copyright (c) 2022 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