SMART SHELF - LIFE PREDICITION SYSTEM FOR PACKAGED FOODS

The smart shelf-life prediction system for packaged foods is designed to make it easier to keep track of how long food stays fresh. It does this by using sensors that measure the temperature and humidity around the food. An ESP32 microcontroller takes the data from these sensors. Sends it over Wi-Fi to a cloud platform where it can be monitored. The system uses the information about the food. How it is stored to figure out how much time is left before the food might go bad. Users can scan a QR code to see details about the product and the estimated shelf life. The system can also send a warning if the shelf life is about to end or if the storage conditions are not good. This way people can manage their food better. Avoid throwing away food that is still safe to eat.. The system needs to be accurate and work well. That depends on how the sensors are set up the details about each type of food and the model used for predictions. More tests with food, in different storage situations are needed to check if the system works as it should.

[1] “An RFID-Powered Multisensing Fusion Industrial IoT System for Food Quality Assessment and Sensing,” IEEE Transactions on Industrial Informatics, vol. 20, no. 1, pp. 337–348, 2024. doi: 10.1109/TII.2023.3262197.   [2] “Artificial Intelligence and Digital Twins in Postharvest Food Systems: Transforming Quality Prediction, Shelf-Life Management, and Food Loss Reduction,” Frontiers in Sustainable Food Systems, vol. 10, 2026. doi: 10.3389/fsufs.2026.1932749.   M. G. Corradini, “Shelf Life of Food Products: From Open Labeling to Real-Time Measurements,” Annual Review of Food Science and Technology, vol. 9, pp. 251–269, 2018. doi: 10.1146/annurev-food-030117-012433.   F. Cui, S. Zheng, D. Wang, X. Tan, Q. Li, J. Li, and T. Li, “Recent Advances in Shelf- Life Prediction Models for Monitoring Food Quality,” Comprehensive Reviews in Food Science and Food Safety, vol. 22, no. 2, pp. 1257–1284, 2023. doi: 10.1111/1541-4337.13110.   [5] A. Gupta and V. Jain, “Blockchain-Assisted IoT Framework for Reliable Monitoring and Predictive Analytics in Perishable Food Supply Chains,” Journal of Food Process Engineering, vol. 49, no. 1, Art. no. e70333, 2026. doi: 10.1111/jfpe.70333.   [6] A. Lamberty and J. Kreyenschmidt, “Technical, Process-Related and Sustainability Requirements for IoT-Based Temperature Monitoring in Fruit and Vegetable Supply Chains,” Discover Food, vol. 5, Art. no. 151, 2025. doi: 10.1007/s44187-025-00427-1.   [7] P. Li, J. Yang, A. M. Jiménez-Carvelo, and S. W. Erasmus, “Applications of Food Packaging Quick Response Codes in Information Transmission Toward Food Supply Chain Integrity,” Trends in Food Science & Technology, vol. 146, Art. no. 104384, 2024. doi: 10.1016/j.tifs.2024.104384.   [8] M. Liang et al., “Deep Learning Models for Shelf- Life Prediction and Regulation of Various Foods: A Systematic Review,” Journal of Food Science, vol. 91, no. 3, Art. no. e70945, 2026. doi: 10.1111/1750-3841.70945.   9 M. Masuduzzaman, E. Hassini, M. F. Rahaman, et al., “FreshTrack: An Innovative IoT-Sensor-Driven Food Freshness Estimation Framework Integrating Blockchain,” Scientific Reports, vol. 16, Art. no. 13847, 2026. doi: 10.1038/s41598-026-44579-1.   [10] J. Qiao, M. Zhang, L. Qiu, A. S. Mujumdar, and Y. Ma, “Visual Early Warning and Prediction of Fresh Food Quality Deterioration: Research Progress and Application in Supply Chain,” Food Bioscience, vol. 59, Art. no. 103671, 2024. doi: 10.1016/j.fbio.2024.103671.