Development of Hybrid Optoacoustic Nanosensors for Simultaneous Detection and Quantification of Cross-Contaminant Mycotoxins (Aflatoxin, Zearalenone, and Fumonisin) in Imported and Domestic Grains and Determining the Source of Contamination Using Artificial Intelligence Algorithms

Mycotoxin cross-contamination in grains, involving aflatoxins (AFS), zearalenone (ZEN), and fumonisins (FUMs), threatens global food security, particularly in imported and domestic supplies. This study develops hybrid optoacoustic nanosensors integrating gold nanorods (AuNRs) with aptamer-functionalized quantum dots (QDs) for multiplexed, real-time detection. The sensors achieve limits of detection (LOD) of ۰.۰۵ μg/kg for AFs, ۰.۱ µg/kg for ZEN, and ۰.۲ μg/kg for FUMS, with photoacoustic signals amplified ۵۰-fold. Integrated AI algorithms, including convolutional neural networks (CNNs) and support vector machines (SVMs), trace contamination sources (e.g., storage vs. field) with ۹۴% accuracy based on spectral fingerprints and geospatial data. Tested on ۲۰۰ grain samples, the system enables rapid on-site screening, reducing economic losses from recalls.

کلیدواژه ها:

Optoacoustic nanosensors ، mycotoxins ، aflatoxin ، zearalenone ، fumonisin ، grains ، artificial intelligence ، contamination tracing ، photoacoustic detection ، hybrid nanomaterials