The Research on Freshness Change Monitoring of Animal Products Based on SqueezeNet

This study investigates the subtle changes in the appearance and temperature of freshness products over time, and analyzes early signs of data degradation using the SqueezeNet model. The lightweight nature of SqueezeNet allows for the exploration of using a lightweight convolutional neural network (CNN) to monitor animal products with the highest computational efficiency. The results of this study indicate that reducing waste and improving sources for real-time processing are of great significance for the processing, storage, and distribution of animal products. The use of visual and thermal sensors to capture motion is essential for achieving high supply chain management efficiency. This study developed a deep learning based system that has the potential to detect spoilage and monitor the freshness of quality. SqueezeNet was used to modify it for practical applications in the food industry.