Multiscale Deepspectra Network: Detection of Pyrethroid Pesticide Residues on the Hami Melon
文献类型： 外文期刊
作者： Yu, Guowei 1 ; Li, Huihui 2 ; Li, Yujie 1 ; Hu, Yating 1 ; Wang, Gang 1 ; Ma, Benxue 1 ; Wang, Huting 1 ;
作者机构： 1.Shihezi Univ, Coll Mech & Elect Engn, Shihezi 832003, Peoples R China
2.Xinjiang Acad Agr & Reclamat Sci, Anal & Testing Ctr, Shihezi 832000, Peoples R China
3.Minist Agr & Rural Affairs, Food Qual Supervis & Testing Ctr Shihezi, Shihezi 832000, Peoples R China
4.Minist Agr & Rural Affairs, Key Lab Northwest Agr Equipment, Shihezi 832003, Peoples R China
5.Minist Educ, Engn Res Ctr Prod Mechanizat Oasis Characterist Ca, Shihezi 832003, Peoples R China
关键词： visible; near-infrared spectroscopy; deep learning; pesticide residues; spectral analysis; Hami melon
期刊名称：FOODS （ 影响因子：5.2； 五年影响因子：5.5 ）
ISSN：
年卷期： 2023 年 12 卷 9 期
页码：
收录情况： SCI
摘要： The problem of pyrethroid residues has become a topical issue, posing a potential food safety concern. Pyrethroid pesticides are widely used to prevent and combat pests in Hami melon cultivation. Due to its high sensitivity and accuracy, gas chromatography (GC) is used most frequently for detecting pyrethroid pesticide residues. However, GC has a high cost and complex operation. This study proposed a deep-learning approach based on the one-dimensional convolutional neural network (1D-CNN), named Deepspectra network, to detect pesticide residues on the Hami melon based on visible/near-infrared (380-1140 nm) spectroscopy. Three combinations of convolution kernels were compared in the single-scale Deepspectra network. The convolution group of "5 x 1" and "3 x 1" kernels obtained a better overall performance. The multiscale Deepspectra network was compared to three single-scale Deepspectra networks on the preprocessing spectral data and obtained better results. The coefficient of determination (R2) for lambda-cyhalothrin and beta-cypermethrin was 0.758 and 0.835, respectively. The residual predictive deviation (RPD) for lambda-cyhalothrin and beta-cypermethrin was 2.033 and 2.460, respectively. The Deepspectra networks were compared with two conventional regression models: partial least square regression (PLSR) and support vector regression (SVR). The results showed that the multiscale Deepspectra network outperformed the other models. It was found that the multiscale Deepspectra network could be a novel approach for the quantitative estimation of pyrethroid pesticide residues on the Hami melon. These findings can also provide an effective strategy for spectral analysis.
- 相关文献
作者其他论文 更多>>
-
An innovative variant based on generative adversarial network (GAN): Regression GAN combined with hyperspectral imaging to predict pesticide residue content of Hami melon
作者：Tan, Haibo;Ma, Benxue;Xu, Ying;Yu, Guowei;Bian, Huitao;Ma, Benxue;Dang, Fumin
关键词：Hyperspectral imaging; Pesticide residue content; Generative adversarial network; Data augmentation; Hami melon
-
Impact of irrigation water volume and deep vertical rotating tillage depth on the development and feeding quality of Suaeda salsa under drip irrigation
作者：Xu, Yibin;Xu, Qiang;Zhang, Qian;Liu, Hongguang;Gong, Ping;Li, Pengfei;Dang, Yingsheng;Li, Yufang;Wang, Jingrun;Guo, Yong;Xu, Yibin;Xu, Qiang;Zhang, Qian;Liu, Hongguang;Gong, Ping;Li, Pengfei;Dang, Yingsheng;Li, Yufang;Wang, Jingrun;Guo, Yong;Wang, Gang;Wang, Tangang
关键词：Suaeda salsa; Deep vertical rotary tillage; Irrigation volume; Forage quality
-
Silencing of GhSHP1 hindered flowering and boll cracking in upland cotton
作者：Xu, Wenjuan;Ju, Jisheng;Zhang, Xueli;Yuan, Wenmin;Hai, Han;Wang, Caixiang;Su, Junji;Ma, Qi;Wang, Gang;Ma, Qi;Wang, Gang
关键词：
Gossypium hirsutum ; cotton boll cracking; GhSHP1; virus-induced gene silencing (VIGS); paraffin section -
Low-cost detection method for early-stage mildew in Hami melons based on hyperspectral image reconstruction using Sim-MST
作者：Dong, Fujia;Xu, Ying;Ma, Benxue;Zhang, Minghui;Wu, Fan;Yu, Guowei;Dang, Fumin;Li, Yujie;Ma, Benxue;Ma, Benxue
关键词：Hyperspectral imaging; RGB images; Spectral reconstruction; Hami melon; Sim-MST plus plus; 3D-Dilated attention convolutional neural; network
-
A method for multi-target segmentation of bud-stage apple trees based on improved YOLOv8
作者：Chen, Jincheng;Li, Yujie;Ma, Benxue;Chen, Jincheng;Ji, Chao;Zhang, Jing;Chen, Jincheng;Ji, Chao;Zhang, Jing;Li, Yujie;Ma, Benxue;Feng, Qingchun;Li, Yujie;Ma, Benxue
关键词：YOLOv8; Bud stage; Apple tree; Multi-target segmentation; Complex background
-
Apple inflorescence recognition of phenology stage in complex background based on improved YOLOv7
作者：Chen, Jincheng;Ma, Benxue;Liu, Xin;Li, Yujie;Chen, Jincheng;Ji, Chao;Zhang, Jing;Ma, Benxue;Feng, Qingchun;Ma, Benxue
关键词：Phenology; Apple inflorescence; Deep learning; YOLOv7; Target recognition
-
RAD gene family analysis in cotton provides some key genes for flowering and stress tolerance in upland cotton G. hirsutum
作者：Kabir, Nosheen;Qanmber, Ghulam;Wang, Yu Xuan;Zhang, Xin;Zhang, Lian;Wang, Gang;Liu, Le;Zhao, Na;Sun, Zhuojing
关键词：RAD; G; hirsutum; Phylogenetic tree; Phytohormones; Sequence logs; Cis-acting elements
