Detection of infected kernels is important for Fusarium head blight (FHB) prevention and product quality assurance in wheat. In this study, Raman spectroscopy (RS) and deep learning networks were used for the determination of FHB-infected wheat kernels. First, the RS spectra of healthy, mild, and severe infection kernels were measured and spectral changes and band attribution were analyzed. Then, the Inception network was improved by residual and channel attention modules to develop the recognition models of FHB infection. The Inception–attention network produced the best determination with accuracies in training set, validation set, and prediction set of 97.13%, 91.49%, and 93.62%, among all models. The average feature map of the channel clarified the important information in feature extraction, itself required to clarify the decision-making strategy. Overall, RS and the Inception–attention network provide a noninvasive, rapid, and accurate determination of FHB-infected wheat kernels and are expected to be applied to other pathogens or diseases in various crops.

The detection of polycyclic aromatic hydrocarbons (PAHs) on fruit and vegetable surfaces is important for protecting human health and ensuring food safety. In this study, a method for the in situ detection and identification of PAH residues on fruit and vegetable surfaces was developed using surface-enhanced Raman spectroscopy (SERS) based on a flexible substrate and lightweight deep learning network. The flexible SERS substrate was fabricated by assembling β-cyclodextrin-modified gold nanoparticles (β-CD@AuNPs) on polytetrafluoroethylene (PTFE) film coated with perfluorinated liquid (β-CD@AuNP/PTFE). The concentrations of benzo(a)pyrene (BaP), naphthalene (Nap), and pyrene (Pyr) residues on fruit and vegetable surfaces could be detected at 0.25, 0.5, and 0.25 μg/cm², respectively, and all the relative standard deviations (RSD) were less than 10%, indicating that the β-CD@AuNP/PTFE exhibited high sensitivity and stability. The lightweight network was then used to construct a classification model for identifying various PAH residues. ShuffleNet obtained the best results with accuracies of 100%, 96.61%, and 97.63% for the training, validation, and prediction datasets, respectively. The proposed method realised the in situ detection and identification of various PAH residues on fruit and vegetables with simplicity, celerity, and sensitivity, demonstrating great potential for the rapid, nondestructive analysis of surface contaminant residues in the food-safety field.

A simple and sensitive method for detection of chlormequat chloride residue in wheat was developed using surface-enhanced Raman spectroscopy (SERS) coupled with chemometric methods on a portable Raman spectrometer. Pretreatment of wheat samples was performed using a two-step extraction procedure. Effective and uniform active substrate (gold nanorods) was prepared and mixed with the sample extraction solution for SERS measurement. The limit of detection for chlormequat chloride in wheat extracting solutions and wheat samples was 0.25 mg/L and 0.25 μg/g, which was far below the maximum residual value in wheat of China. Then, support vector regression (SVR) and kernel principal component analysis (KPCA), multiple linear regression, and partial least squares regression were employed to develop the regression models for quantitative analysis of chlormequat chloride residue with spectra around the characteristic peaks at 666, 713, and 853 cm⁻¹. As for the residue in wheat, the predicted recovery of established optimal model was in the range of 94.7% to 104.6%, and the standard deviation was about 0.007 mg/L to 0.066 mg/L. The results demonstrated that SERS, SVR, and KPCA can provide the accurate and quantitative determination for chlormequat chloride residue in wheat.