Identification of Pesticide Residue Types in Chinese Cabbage Based on Hyperspectral and Convolutional Neural Network
JIANG Rong-chang1, 2, GU Ming-sheng2, ZHAO Qing-he1, LI Xin-ran1, SHEN Jing-xin1, 3, SU Zhong-bin1*
1. Institute of Electrical and Information, Northeast Agricultural University, Harbin 150030, China
2. Harbin City Data Center, Harbin 150030, China
3. Shandong Academy of Agricultural Machinery Sciences, Jinan 250100, China
Abstract:Traditional chemical detection methods for analyzing pesticide residues in chinese cabbage are slow and destructive. In this study, a rapid, non-destructive method for identifying the types of pesticide residues in chinese cabbage samples was developed. First, the hyperspectral imaging system was used to analyze chinese cabbage samples exposed to one of four pesticides chlorpyrifos, dimethoate, methomyl and cypermethrin. The pesticide concentration ratios were 0.10, 1.00, 0.20 and 2.00 mg·kg-1, respectively; and the data was compared to a pesticide-free sample. After 12 hours of natural degradation at room temperature, a hyperspectral imaging system corrected by a black and white plate was used to obtain 400~1 000 nm hyperspectral images of chinese cabbage samples, and the target area was selected by ENVI software. The specific regions of interest (ROI) in samples were further investigated, and the pre-processing by multiple scattering correction (MSC). Secondly, three algorithms such as competitive adaptive reweighting algorithm (CARS), principal component analysis (PCA), discrete wavelet transform (DWT) (based on db1, sym2, coif1, bior2.2, and rbio1.5 wave base functions) were then used to screen for dimensionality reduction from optimally pre-processed results. Finally, the screening results and the samples divided by the Kennard-Stone algorithm were adopted to construct three recognition models separately. Such as k-nearest-neighbor (KNN), support vector machine (SVM), multilayer perceptron (MLP) and convolutional neural network (CNN) were used to determine the best screening method for the dimension of pesticide residues and the optimal hyperspectral recognition model. Our results showed that the CNN, MLP, KNN, and SVM algorithms achieve the best overall accuracy (91.20%, 83.20%, 66.40%, and 90.40%, respectively), Kappa coefficient (0.89, 0.79, 0.58, and 0.88), and the prediction set time (86.01, 63.23, 20.02 and 14.03 ms) under the dimensionality reduction algorithm DWT, respectively; the wavelet basis function and the number of transform layers are coif1-2, coif1-4, bior2.2-2 and sym2-2. All three indicators are better than the modeling results based on CARS and PCA dimensionality reduction algorithms. It showed that the combination of discrete wavelet transform and convolutional neural network shortens the time of classification and identification and significantly improves the classification and identification accuracy, and improves the Hughes phenomenon, providing a new method for non-destructive and rapid detection and identification of chinese cabbage pesticide residues.
Key words:Hyperspectral; Chinese cabbage; Identification of pesticide residues; Discrete wavelet transform; Convolutional neural network(CNN)
姜荣昌,顾鸣声,赵庆贺,李欣然,沈景新,苏中滨. 高光谱和卷积神经网络的大白菜农残检测[J]. 光谱学与光谱分析, 2022, 42(05): 1385-1392.
JIANG Rong-chang, GU Ming-sheng, ZHAO Qing-he, LI Xin-ran, SHEN Jing-xin, SU Zhong-bin. Identification of Pesticide Residue Types in Chinese Cabbage Based on Hyperspectral and Convolutional Neural Network. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(05): 1385-1392.
[1] LIU Chun-long, WANG Cheng, GUO Yu(刘春龙,王 成,郭 禹). Agriculture and Technology(农业与技术), 2019, 39(15): 42.
[2] Zhu Xiaoyu, Li Wenjin, Wu Ruimei, et al. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2021, 250: 119366.
[3] LI Chun-yu, GE Xiao, JIN Yan-ting, et al(李春雨,葛 啸,金燕婷, 等). Agricultural Engineering(农业工程), 2019, 9(6): 33.
[4] Sun Jun, Cong Sunli, Mao Hanping, et al. Journal of Food Process Engineering, 2018, 41(2): e12654.
[5] JI Hai-yan, REN Zhan-qi, RAO Zhen-hong(吉海彦,任占奇,饶震红). Chinese Journal of Luminescence(发光学报), 2018, 39(12): 1778.
[6] XU Tong-yu, GUO Zhong-hui, YU Feng-hua, et al(许童羽,郭忠辉,于丰华, 等). Transactions of the Chinese Society of Agricultural Engineering(农业工程学报), 2020, 36(2): 209.
[7] DENG Lai-fei, ZHANG Fei, QI Ya-xiao, et al(邓来飞,张 飞,齐亚霄, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2020, 40(1): 247.
[8] SHI Yun, MA Dong-hui, LÜ Jie, et al(师 芸,马东晖,吕 杰, 等). Transactions of the Chinese Society of Agricultural Engineering(农业工程学报), 2020, 36(6): 151.
[9] SUN Jun, ZHANG Mei-xia, MAO Han-ping, et al(孙 俊,张梅霞,毛罕平, 等). Transactions of the Chinese Society for Agricultural Machinery(农业机械学报), 2015, 46(6): 251.