Aflatoxins and fumonisins, commonly found in maize and maize-derived products, frequently co-occur and can cause dangerous illness in humans and animals if ingested in large amounts. Efforts are being made to develop suitable analytical methods for screening that can rapidly detect mycotoxins in order to prevent illness through early detection. A method for classifying contaminated maize by applying hyperspectral imaging techniques including reflectance in the visible and near-infrared (VNIR) and short-wave infrared (SWIR) regions, and fluorescence was investigated. Machine learning classification models in combination with different preprocessing methods were applied to screen ground maize samples for naturally occurring aflatoxin and fumonisin as single contaminants and as co-contaminants. Partial least squares–discriminant analysis (PLS-DA) and support vector machine (SVM) with the radial basis function (RBF) kernel were employed as classification models using cut-off values of each mycotoxin. The classification performance of the SVM was better than that of PLS-DA, and the highest classification accuracies for fluorescence, VNIR, and SWIR were 89.1%, 71.7%, and 95.7%, respectively. SWIR imaging with the SVM model resulted in higher classification accuracies compared to the fluorescence and VNIR models, suggesting that as an alternative to conventional wet chemical methods, the hyperspectral SWIR imaging detection model may be the more effective and efficient analytical tool for mycotoxin analysis compared to fluorescence or VNIR imaging models. These methods represent a food safety screening tool capable of rapidly detecting mycotoxins in maize or other food ingredients consumed by animals or humans.

Consumption of aflatoxin-contaminated food can cause severe illness when consumed by humans or livestock. Because the mycotoxin frequently occurs in cereal grains and other agricultural crops, it is crucial to develop portable devices that can be used non-destructively and in real-time to identify aflatoxin-contaminated food materials during early stages of harvesting or processing. In this study, an aflatoxin detection method was developed using a compact Raman device that can be used in the field. Data were obtained using maize samples naturally contaminated with aflatoxin, and the data were analyzed using a machine learning method. Of the multiple classification models evaluated, such as linear discriminant analysis (LDA), linear support vector machines (LSVM), quadratic discriminant analysis (QDA), and quadratic support vector machines and spectral preprocessing methods, the best classification accuracy was achieved at 95.7% using LDA in combination with Savitzky-Golay 2nd derivative (SG2) preprocessing. Partial least squares regression (PLSR) models demonstrated a close-range accuracy within the scope of standard normal variate (SNV) and multiplicative scatter correction (MSC) preprocessing methods, with determination of coefficient values of R²_C and R²_V of 0.9998 and 0.8322 respectively for SNV, and 0.9916 and 0.8387 respectively for MSC. This study demonstrates the potential use of compact and automated Raman spectroscopy, coupled with chemometrics and machine learning methods, as a tool for rapidly screening food and feed for hazardous substances at on-site field processing locations.