Indoor Beef Quality Identification Using Gas Sensor Array and Probabilistic Neural Network Method

Beef is one of the foods most consumed by humans. However, rotten beef is often found in markets. This indicates the omission of the rotten beef, which is still stored in the warehouse. Rotten beef can release metabolic products such as ammonia (NH 3 ), hydrogen sulfide (H 2 S), and volatile organic compounds (VOC). This study has developed an electronic nose system that can identify the quality of beef indoors. This system uses the MQ-137, MQ-136, and TGS2602 gas sensors. However, the airflow in the room can cause a disturbance in the concentration of the gas, making the sensor's response unstable. Therefore, a probabilistic neural network (PNN) is employed to identify beef quality. The experimental results show that this method can identify the quality of fresh, spoiled, and rotten beef with a success rate of 94.9%.