文献类型： 外文期刊

作者： Yu, Guowei ¹ ; Ma, Benxue ¹ ; Li, Huihui ³ ; Hu, Yating ¹ ; Li, Yujie ¹ ;

作者机构： 1.Shihezi Univ, Coll Mech & Elect Engn, Shihezi 832003, Peoples R China

2.Minist Agr & Rural Affairs, Key Lab Northwest Agr Equipment, Shihezi 832003, Peoples R China

3.Xinjiang Acad Agr & Reclamat Sci, Analysis & Testing Ctr, Shihezi 832000, Peoples R China

4.Minist Agr & Rural Affairs, Food Qual Supervis & Testing Ctr Shihezi, Shihezi 832000, Peoples R China

关键词： safety detection; pesticide residues; convolutional neural network; visible; near-infrared spectroscopy; Hami melon

期刊名称：FOODS （ 影响因子：5.561； 五年影响因子：5.94 ）

ISSN：

年卷期： 2022 年 11 卷 23 期

页码：

收录情况： SCI

摘要： Pesticide residues directly or indirectly threaten the health of humans and animals. We need a rapid and nondestructive method for the safety evaluation of fruits. In this study, the feasibility of visible/near-infrared (Vis/NIR) spectroscopy technology was explored for the discrimination of pesticide residue levels on the Hami melon surface. The one-dimensional convolutional neural network (1D-CNN) model was proposed for spectral data discrimination. We compared the effect of different convolutional architectures on the model performance, including single-depth, symmetric, and asymmetric multiscale convolution. The results showed that the 1D-CNN model could discriminate the presence or absence of pesticide residues with a high accuracy above 99.00%. The multiscale convolution could significantly improve the model accuracy while reducing the modeling time. In particular, the asymmetric convolution had a better comprehensive performance. For two-level discrimination, the accuracy of lambda-cyhalothrin and beta-cypermethrin was 93.68% and 95.79%, respectively. For three-level discrimination, the accuracy of lambda-cyhalothrin and beta-cypermethrin was 86.32% and 89.47%, respectively. For four-level discrimination, the accuracy of lambda-cyhalothrin and beta-cypermethrin was 87.37% and 93.68%, respectively, and the average modeling time was 3.5 s. This finding will encourage more relevant research to use multiscale 1D-CNN as a spectral analysis strategy for the detection of pesticide residues in fruits.