Evaluation of Different Models for Non-Destructive Detection of Tomato Pesticide Residues Based on Near-Infrared Spectroscopy

Abstract

In this study, the possibility of non-destructive detection of tomato pesticide residues was investigated using Vis/NIRS and prediction models such as PLSR and ANN. First, Vis/NIR spectral data from 180 samples of non-pesticide tomatoes (used as a control treatment) and samples impregnated with pesticide with a concentration of 2 L per 1000 L between 350–1100 nm were recorded by a spectroradiometer. Then, they were divided into two parts: Calibration data (70%) and prediction data (30%). Next, the prediction performance of PLSR and ANN models after processing was compared with 10 spectral preprocessing methods. Spectral data obtained from spectroscopy were used as input and pesticide values obtained by gas chromatography method were used as output data. Data dimension reduction methods (principal component analysis (PCA), Random frog (RF), and Successive prediction algorithm (SPA)) were used to select the number of main variables. According to the values obtained for root-mean-square error (RMSE) and correlation coefficient (R) of the calibration and prediction data, it was found that the combined model SPA-ANN has the best performance (RC = 0.988, RP = 0.982, RMSEC = 0.141, RMSEP = 0.166). The investigational consequences obtained can be a reference for the development of internal content of agricultural products, based on NIR spectroscopy.

Non-Destructive Detection of Fruit Quality Parameters Using Hyperspectral Imaging, Multiple Regression Analysis and Artificial Intelligence

“…Measuring the quality of fruits, vegetables and food products is the focus of the food industry. Non-destructive measurements of quality parameters have been performed on many agricultural products, and are fast and accurate in estimating the quality factors involved [1][2][3][4][5].…”

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

“…These detection methods have high accuracy and sensitivity, but the detection steps are complex and costly [ 8 ]. As a rapid modern detection technique without sample pretreatment, visible/near-infrared (Vis/NIR) spectroscopy has been gradually applied in the quality and safety detection of fruits and vegetables [ 9 , 10 , 11 ], especially in qualitative discrimination, including type and level. Sun et al [ 12 ] established an optimized support vector machine (SVM) model using near-infrared transmission spectroscopy (950–1650 nm), which could identify two pesticide residue types (fenvalerate and chlorpyrifos) in lettuce leaves, and the prediction accuracy was 98.33%.…”

Monitoring Time-Non-Stable Surfaces Using Mobile NIR DLP Spectroscopy

“…The other type of NIR spectroscopy usage is connected with the need to detect undesired substances. One of the examples is non-destructive detection of tomato pesticide residues using VS/NIR spectroscopy and prediction models such as ANNs [5]. The authors used VS/NIR spectral data from 180 samples of non-pesticide tomatoes (used as a control treatment) and samples impregnated with a pesticide with a concentration of 2/1000 [L], recorded by a spectroradiometer working in the range 350-1100 [nm], to train and then verify ANNs.…”