Machine Learning Algorithm Based Meat Spoilage Detection: To Avoid Foodborne Infection

Abstract

People are becoming more health conscious and paying more attention to food safety in recent years. Instead of the fresh meat that is needed, spoiled meat are increasingly being sold in marketplaces. Meat spoilage is a major issue that affects everyone in the globe. Million instances of food-borne disease are recorded globally each year. This is a result of eating rotten meat. Meat that has been spoiled includes a number of toxic volatile organic chemicals. Thus, it is imperative to have a system that can identify food deterioration before any symptoms appear. Using the proper sensors and keeping track of gases produced from meat, the system seeks to identify freshness of meat. This study suggests utilising gas sensors to measure the level of gases released by raw meat, temperature and humidity in order to determine how fresh it is. It makes use of machine learning algorithms to distinguish between fresh and spoiled meat. Various sensors are used to detect various food properties, such as temperature, moisture, ammonia gas, H2S gas, or methane. The sensors provide readings to the microcontroller. These readings serve as the input for the machine learning algorithm that decides whether the meat has spoiled or not. The findings highlight potential benefits of predicting meat rotting level. The sensor data was clearly gathered, delivered to an IoT module for monitoring via the Cayenne app. Consuming fresh meat and avoiding food-borne diseases would be made easier as a result. Human errors that happen during the inspection can also be prevented with the aid of this device. There is no possibility of human mistake with our suggested system because it is based on real-time sensing and machine learning. Because of this, its accuracy has improved. When the meat is spoiled, the system detects it accurately. Due to the system’s great efficiency, less time and money would be spent, which will benefit big businesses and small businesses.