|
|
|
|
|
|
| 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.
|
|
Received: 2021-08-03
Accepted: 2021-10-31
|
|
|
|
Corresponding Authors:
SU Zhong-bin
E-mail: suzb001@163.com
|
|
[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.
|
| [1] |
JIN Cheng-qian1, 2, GUO Zhen1, ZHANG Jing1, MA Cheng-ye1, TANG Xiao-han1, ZHAO Nan1, YIN Xiang1. Non-Destructive Detection and Visualization of Soybean Moisture Content Using Hyperspectral Technique[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(10): 3052-3057. |
| [2] |
GAO Rong-hua1, 2, FENG Lu1, 2*, ZHANG Yue3, YUAN Ji-dong3, WU Hua-rui1, 2, GU Jing-qiu1, 2. Early Detection of Tomato Gray Mold Disease With Multi-Dimensional Random Forest Based on Hyperspectral Image[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(10): 3226-3234. |
| [3] |
WANG Fan1, 2, CHEN Long-yue2, 3, DUAN Dan-dan1, 2, 4*, CAO Qiong1, 4, ZHAO Yu1, LAN Wan-rong5. Estimation of Total Nitrogen Content in Fresh Tea Leaves Based on
Wavelet Analysis[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(10): 3235-3242. |
| [4] |
YANG Xin1, 2, YUAN Zi-ran1, 2, YE Yin1, 2*, WANG Dao-zhong1, 2, HUA Ke-ke1, 2, GUO Zhi-bin1, 2. Winter Wheat Total Nitrogen Content Estimation Based on UAV
Hyperspectral Remote Sensing[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(10): 3269-3274. |
| [5] |
XIANG Song-yang1, 3, XU Zhang-hua1, 2, 4, 5, 6*, ZHANG Yi-wei1, 2, ZHANG Qi1, 3, ZHOU Xin1, 2, YU Hui1, 3, LI Bin1, 2, LI Yi-fan1, 2. Construction and Application of ReliefF-RFE Feature Selection Algorithm for Hyperspectral Image Classification[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(10): 3283-3290. |
| [6] |
ZHANG Yang1, 2, YUE Jun1*, JIA Shi-xiang1, LI Zhen-bo2, SHENG Guo-rui1. Recognition of Shellfish Based on Visible Spectrum and Convolutional Neural Network[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(10): 3298-3306. |
| [7] |
DAI Qiu-fang1, 2, 3, LIAO Chen-long1, 2, LI Zhen1, 2, 3*，SONG Shu-ran1, 2, 3，XUE Xiu-yun1, 2, 3，XIONG Shi-lu1, 2. Hyperspectral Visualization of Citrus Leaf Moisture Content Based on CARS-CNN[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(09): 2848-2854. |
| [8] |
ZHANG Zhen-qing1, 2, 3, DONG Li-juan2*, HUANG Yu4, CHEN Xing-hai4, HUANG Wei5, SUN Yong6. Identification of True and Counterfeit Banknotes Based on Hyperspectral Imaging[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(09): 2903-2912. |
| [9] |
WANG Xi1, CHEN Gui-fen1,2*, CAO Li-ying1, MA Li1. Study on Maize Leaf Nitrogen Inversion Model Based on Equivalent Water Thickness Gradient[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(09): 2913-2918. |
| [10] |
GUI Jiang-sheng1, HE Jie1, FU Xia-ping2. Hyperspectral Detection of Soybean Heart-Eating Insect Pests Based on Image Retrieval[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(09): 2931-2934. |
| [11] |
PIAO Zhao-jia, YU Hai-ye, ZHANG Jun-he, ZHOU Hai-gen, LIU Shuang, KONG Li-juan, DANG Jing-min*. Hyperspectral Inversion Model of Pectin Content in Wheat Under Salt and Physical Damage Stresses[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(09): 2935-2940. |
| [12] |
ZHANG Yan1, 2, 3，WU Hua-rui1, 2, 3，ZHU Hua-ji1, 2, 3*. Hyperspectral Latent Period Diagnosis of Tomato Gray Mold Based on TLBO-ELM Model[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(09): 2969-2975. |
| [13] |
WANG Chun-ling1, 2, SHI Kai-yuan1, 2, MING Xing3*, CONG Mao-qin3, LIU Xin-yue3, GUO Wen-ji3. A Comparative Study of the COD Hyperspectral Inversion Models in
Water Based on the Maching Learning[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(08): 2353-2358. |
| [14] |
LI Bin, YIN Hai, ZHANG Feng, CUI Hui-zhen, OUYANG Ai-guo*. Research on Protein Powder Adulteration Detection Based on
Hyperspectral Technology[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(08): 2380-2386. |
| [15] |
WU Ye-lan1, GUAN Hui-ning1, LIAN Xiao-qin1, YU Chong-chong1, LIAO Yu2, GAO Chao1. Study on Detection Method of Leaves With Various Citrus Pests and
Diseases by Hyperspectral Imaging[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(08): 2397-2402. |
|
|
|
|
