Smart System for Meat Quality Control

Consumers are increasingly questioning the quality of food products, especially meat, demanding reliable information about its freshness and safety. Traditional methods of assessing meat freshness, such as organoleptic and laboratory methods may be limited and time-consuming. This has led to the need for the development of effective and rapid methods for determining the freshness of meat. In this context, the relevance of using modern technologies, including neural networks, for meat freshness identification arises. Neural networks, which have become powerful tools in data processing and analysis, can provide precise and automated methods for determining the quality of food products. This research proposes combining a sensory network and a neural network to create a smart meat quality control system. This system integrates gas sensors and a color sensor, with the software using a neural network for analysis and decision-making. The authors have proposed the structure of the smart system, its principles of operation, features of the architecture, and the training of the neural network. The authors present the hardware and software components of the meat control and identification system. The project involves the integration of sensors, an Arduino microcontroller, and a Raspberry Pi single-board computer to implement a system capable of accurately and reliably identifying the freshness of meat.