Pesticide residues in fruits and vegetables pose a serious threat to food safety. Traditional detection methods have defects such as complex operation, high cost, and long detection time. Therefore, it is of great significance to develop rapid, non-destructive, and efficient detection technologies and equipment. In recent years, the combination of spectroscopic techniques and imaging technologies with machine learning algorithms has developed rapidly, providing a new attempt to solve this problem. This review focuses on the research progress of the combination of spectroscopic techniques (near-infrared spectroscopy (NIRS), hyperspectral imaging technology (HSI), surface-enhanced Raman scattering (SERS), laser-induced breakdown spectroscopy (LIBS), and imaging techniques (visible light (VIS) imaging, NIRS imaging, HSI technology, terahertz imaging) with machine learning algorithms in the detection of pesticide residues in fruits and vegetables. It also explores the huge challenges faced by the application of spectroscopic and imaging technologies combined with machine learning algorithms in the intelligent perception of pesticide residues in fruits and vegetables: the performance of machine learning models requires further enhancement, the fusion of imaging and spectral data presents technical difficulties, and the commercialization of hardware devices remains underdeveloped. This review has proposed an innovative method that integrates spectral and image data, enhancing the accuracy of pesticide residue detection through the construction of interpretable machine learning algorithms, and providing support for the intelligent sensing and analysis of agricultural and food products.

Ochratoxin A (OTA) is the most common mycotoxin and can be found in wheat, corn and other grain products. As OTA pollution in these grain products is gaining prominence as a global issue, the demand to develop OTA detection technology has attracted increasing attention. Recently, a variety of label-free fluorescence biosensors based on aptamer have been established. However, the binding mechanisms of some aptasensors are still unclear. Herein, a label-free fluorescent aptasensor employing Thioflavin T (ThT) as donor for OTA detection was constructed based on the G-quadruplex aptamer of the OTA aptamer itself. The key binding region of aptamer was revealed by using molecular docking technology. In the absence of the OTA target, ThT fluorescent dye binds with the OTA aptamer to form an aptamer/ThT complex, and results in the fluorescence intensity being obviously enhanced. In the presence of OTA, the OTA aptamer binds to OTA because of its high affinity and specificity to form an aptamer/OTA complex, and the ThT fluorescent dye is released from the OTA aptamer into the solution. Therefore, the fluorescence intensity is significantly decreased. Molecular docking results revealed that OTA is binding to the pocket-like structure and surrounded by the A29-T3 base pair and C4, T30, G6 and G7 of the aptamer. Meanwhile, this aptasensor shows good selectivity, sensitivity and an excellent recovery rate of the wheat flour spiked experiment.