Discrimination of Pesticide Residue Levels on the Hami Melon Surface Using Multiscale Convolution

Abstract

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.

Multiscale Deepspectra Network: Detection of Pyrethroid Pesticide Residues on the Hami Melon

“…The reference measurement was performed after spectral data acquisi ence values of the pesticide residue contents were measured in the Food Q sion and Testing Center (Shihezi), Ministry of Agriculture and Rural Affa urement procedure was consistent with Yu et al [15]. (1) Standard preparat ard mixture intermediate and working solutions were prepared in n-hexa tration of 20.0 mg/mL and 1.0 mg/mL, respectively.…”

“…A single-scale, one-dimensional convolutional neural network (1D-CNN) was proposed to recognize pesticide residues (lambda-cyhalothrin, trichlorfon, phoxim, and mixtures of trichlorfon and phoxim) on garlic chive leaves, achieving a better accuracy of 97.9% [13]. 1D-CNN models using multiscale convolution were proposed to identify the types and levels of pesticide residues on the Hami melon [14,15]. The test results showed that the multiscale convolution networks provided a better model performance than the single-scale networks.…”