|
|
|
|
|
|
Vis-NIR Spectra Discriminant of Pesticide Residues on the Hami Melon Surface by GADF and Multi-Scale CNN |
YU Guo-wei1, MA Ben-xue1,2*, CHEN Jin-cheng1,3, DANG Fu-min4,5, LI Xiao-zhan1, LI Cong1, WANG Gang1 |
1. College of Mechanical and Electrical Engineering, Shihezi University, Shihezi 832003, China
2. Key Laboratory of Northwest Agricultural Equipment, Ministry of Agriculture and Rural Affairs, Shihezi 832003, China
3. Mechanical Equipment Research Institute, Xinjiang Academy of Agricultural and Reclamation Science, Shihezi 832000, China
4. Food Quality Supervision and Testing Center (Shihezi), Ministry of Agriculture, Shihezi 832000, China
5. Analysis and Testing Center, Xinjiang Academy of Agricultural and Reclamation Science, Shihezi 832000, China |
|
|
Abstract Given the costly and destructive detection of pesticide residues on the Hami melon surface, the feasibility of visible/near-infrared (Vis/NIR) spectroscopy for the qualitative discriminant was assessed. In this study, Hami melon was taken as experimental samples. Two pesticides were taken as the research objects, including chlorothalonil and imidacloprid. Hami melon’s Vis/NIR spectra of Hami melon with no, chlorothalonil and imidacloprid residues were collected in the diffuse reflectance mode. Then the one-dimensional spectrum was transformed into a two-dimensional image by using gramian angular fields (GAF). The GAF image data set was constructed. A multi-scale convolutional neural network (CNN) architecture incorporatedan Inception module was developed, including aninput layer, three convolution layers, amerging layer, aflatten layer, two fully-connected layers, and an output layer. The confusion matrix result of the multi-scale CNN model suggested that the best method for expressing Vis/NIR spectral features was gramian angular difference fields (GADF) transformation. Moreover, two CNN models (AlexNet and VGG-16) and two machine learning models (support vector machine (SVM) and extreme learning machine (ELM)) were established toverify the proposed model performance. With higher average accuracy than SVM and ELM models, the CNN models had a better effect to identifying whether there were pesticide residues on the Hami melon surface. Compared with AlexNet and VGG-16 models, the proposed multi-scale CNN model had the best performance with the shortest training time of 14 s and the highest test accuracy of 98.33%.The multi-scale CNN structure can capture different level and scale features by using combinations of various small-size filters (1 1, 3 3 and 5 5) and stacking of parallel convolutions. The multi-scale deep feature fusion was carried out in the concatenation mode, which can improve the feature extraction ability of the CNN model. Compared with traditional CNN models with large depth, the model proposed in this study improved the discriminant accuracy while keeping the computational complexity constant. The overall research results reflected that GADF transformation combined with a multi-scale CNN model can effectively achieve the qualitative spectral data analysis. Vis/NIR spectroscopy can realize the qualitative discriminant of pesticide residues on the Hami melon surface. These findings can provide a reference for the rapid non-destructive detection of pesticide residues on the surface of other large melons and fruit.
|
Received: 2020-12-26
Accepted: 2021-04-06
|
|
Corresponding Authors:
MA Ben-xue
E-mail: mbx_shz@163.com
|
|
[1] WEI Kai-li, ZHOU Xiao-long, YAN Qiao-li, et al(韦凯丽, 周晓龙, 闫巧俐, 等). Food & Machinery(食品与机械),2019, 35(8): 90.
[2] JIANG Xue-song, WANG Wei-qin, XU Lin-yun, et al(蒋雪松, 王维琴, 许林云, 等). Transactions of the Chinese Society of Agricultural Engineering(农业工程学报),2016, 32(20): 267.
[3] Zhang X, Zhang N N. Agricultural Biotechnology,2018, 7(5): 222.
[4] Sun J, Ge X, Wu X H, et al. Journal of Food Process Engineering,2018, 41(6): e12816.
[5] Yazici A, Tiryaki G Y, Ayvaz H. Journal of the Science of Food and Agriculture,2020, 100(5): 1980.
[6] Yang J, Xu J F, Zhang X L, et al. Analytica Chimica Acta, 2019, 1081: 6.
[7] Zhang X L, Lin T, Xu J F, et al. Analytica Chimica Acta, 2019, 1058: 48.
[8] Zhang X L, Xu J F, Yang J, et al. Analytica Chimica Acta, 2020, 1119: 41.
[9] Wu M M, Sun J, Lu B, et al. Journal of Food Process Engineering,2019, 42(3): e13005.
[10] National Health Commission of the People’s Republic of China, Ministry of Agriculture and Rural Affairs of the People’s Republic of China, State Administration for Market Regulation(中华人民共和国国家卫生健康委员会, 中华人民共和国农业农村部, 国家市场监督管理总局). GB 2763—2021 National Food Safety Standard-Maximum Residue Limits for Pesticides in Food(GB 2763—2021食品安全国家标准 食品中农药残留最大限量),2021.
[11] Zhang G, Si Y J, Wang D, et al. IEEE Access,2019, 7: 171570.
[12] Szegedy C, Liu W, Jia Y Q, et al. IEEE Computer Society,2015, 1.
[13] Sun J T, Ma B X, Dong J, et al. Journal of Food Process Engineering,2017, 40: e12496.
[14] Hu R, Zhang L X, Yu Z Y, et al. Infrared Physics and Technology,2019, 102: 102999. |
[1] |
LI Xue-ying1, 2, LI Zong-min3*, CHEN Guang-yuan4, QIU Hui-min2, HOU Guang-li2, FAN Ping-ping2*. Prediction of Tidal Flat Sediment Moisture Content Based on Wavelet Transform[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(04): 1156-1161. |
[2] |
LÜ Xue-gang1, 2,LI Xiu-hua1, 2*,ZHANG Shi-min2,ZHANG Mu-qing1, JIANG Hong-tao1. A Method for Detecting Sucrose in Living Sugarcane With Visible-NIR Transmittance Spectroscopy[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2021, 41(12): 3747-3752. |
[3] |
HAO Yong1,DU Jiao-jun1, ZHANG Shu-min2, WANG Qi-ming1. Research on Construction of Visible-Near Infrared Spectroscopy Analysis Model for Soluble Solid Content in Different Colors of Jujube[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2021, 41(11): 3385-3391. |
[4] |
FAN Shu-xiang1, WANG Qing-yan1, YANG Yu-sen2, LI Jiang-bo1, ZHANG Chi1, TIAN Xi1, HUANG Wen-qian1*. Development and Experiment of a Handheld Visible/Near Infrared Device for Nondestructive Determination of Fruit Sugar Content[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2021, 41(10): 3058-3063. |
[5] |
LIU Chen-yang1,2, XU Huang-rong2,3, DUAN Feng4, WANG Tai-sheng1, LU Zhen-wu1, YU Wei-xing3*. Spectral Discrimination of Rabbit Liver VX2 Tumor and Normal Tissue Based on Genetic Algorithm-Support Vector Machine[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2021, 41(10): 3123-3128. |
[6] |
HAO Yong1, WANG Qi-ming1, ZHANG Shu-min2. Study on Online Detection Method of “Yali” Pear Black Heart Disease Based on Vis-Near Infrared Spectroscopy and AdaBoost Integrated Model[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2021, 41(09): 2764-2769. |
[7] |
BAI Xue-bing1, LI Xin-xing1, ZHANG Xiao-shuan2, LUO Hai-ling3, FU Ze-tian2*. Quantitative Detection of Mutton Hardness Based on Twice Iterative Monte Carlo Method[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2021, 41(07): 2057-2063. |
[8] |
KU Ya-lun1, YANG Ming-xing1, 2*. Study on Spectral Characteristics of Turquoise With Blue “Water Ripple” From Shiyan, Hubei Province[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2021, 41(02): 636-642. |
[9] |
LI Qing-xu1, WANG Qiao-hua1, 2*, GU Wei1, GAO Sheng1, MA Mei-hu3. Non-Destructive Testing of Fertilization Information of Pre-Incubation Duck Eggs Based on Convolutional Neural Network and Spectral Features[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2020, 40(12): 3847-3853. |
[10] |
YAN Chen1, JIANG Xue-song1*, SHEN Fei2*, HE Xue-ming2, FANG Yong2, LIU Qin2, ZHOU Hong-ping1, LIU Xing-quan3. Visible/Near-Infrared Spectroscopy Combined With Machine Vision for Dynamic Detection of Aflatoxin B1 Contamination in Peanut[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2020, 40(12): 3865-3870. |
[11] |
ZHANG Hao-dan1,SUN Xiao-lin1, 2*,WANG Xiao-qing1,WANG Hui-li3. Analyzing Errors due to Measurement Positions and Sampling Locations for In Situ Measurements of Soil Organic Matter Using Vis-NIR Spectroscopy[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2020, 40(11): 3499-3507. |
[12] |
KU Ya-lun1, YANG Ming-xing1, 2*, LIU Jia1. Spectroscopic Characteristics of Turquoise With Reddish-Brown Stripes From Shiyan, Hubei Province[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2020, 40(11): 3639-3643. |
[13] |
YUAN Li, SHI Bin, YU Jian-cheng, TANG Tian-yu, YUAN Yuan, TANG Yan-lin*. Application of Different Smoothing Ensemble CARS Algorithm in Spectral Discrimination of Black Tea Grade[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2020, 40(10): 3254-3259. |
[14] |
LIU Hui-jun, WEI Chao-yu, HAN Wen, YAO Yan. Determination of Huanghua Pear’s Harvest Time Based on Convolutional Neural Networks by Visible-Near Infrared Spectroscopy[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2020, 40(09): 2932-2936. |
[15] |
LI Bin1, 2, 3, GAO Pan1, 2, 3, FENG Pan1, 2, 3, CHEN Dan-yan1, 2, 3, ZHANG Hai-hui1, 2, 3, HU Jin1, 2, 3*. Prediction of Eggplant Leaf Fv/Fm Based on Vis-NIR Spectroscopy[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2020, 40(09): 2834-2839. |
|
|
|
|