A Review of High-Throughput Optical Sensors for Food Detection Based on Machine Learning

As the global food industry expands and consumers demand higher food safety and quality standards, high-throughput detection technology utilizing digital intelligent optical sensors has emerged as a research hotspot in food testing due to its advantages of speed, precision, and non-destructive operation. Integrating cutting-edge achievements in optics, electronics, and computer science with machine learning algorithms, this technology efficiently processes massive datasets. This paper systematically summarizes the construction principles of intelligent optical sensors and their applications in food inspection. Sensors convert light signals into electrical signals using nanomaterials such as quantum dots, metal nanoparticles, and upconversion nanoparticles, and then employ machine learning algorithms including support vector machines, random forests, and convolutional neural networks for data analysis and model optimization. This enables efficient detection of target substances like pesticide residues, heavy metals, microorganisms, and food freshness. Furthermore, the integration of multiple detection mechanisms-including spectral analysis, fluorescence imaging, and hyperspectral imaging-has significantly broadened the sensors' application scenarios. Looking ahead, optical sensors will evolve toward multifunctional integration, miniaturization, and intelligent operation. By leveraging cloud computing and IoT technologies, they will deliver innovative solutions for comprehensive monitoring of food quality and safety across the entire supply chain.