Electronic nose-based monitoring of vacuum-packaged chicken meat freshness in room and refrigerated storage
摘要
Monitoring chicken meat is a crucial process for food safety and consumer health, as it helps prevent the growth of harmful bacteria, minimizing the risk of foodborne illnesses. Currently, electronic nose (E-nose) technology plays a significant role in food quality assessment as it can detect changes in volatile compounds associated with food freshness. In this study, a self-designed, cost-efficient E-nose system was introduced to evaluate the freshness and bacterial growth of vacuum-packaged chicken meat stored at room temperature and refrigerator at 4 °C. Polynomial feature extraction with varying degrees was employed to extract important information from the sensor responses. Principal component analysis (PCA) and linear discriminant analysis (LDA) were implemented for data dimensionality reduction and classification. A support vector regression (SVR) model was built and employed to evaluate the bacteria population based on response patterns from the E-nose device. The LDA results clearly showed the classification of chicken meat freshness corresponding to different storage days and temperatures. The E-nose device with the SVR model combined with extracted parameters using a 2-degree polynomial provided good prediction results for the bacteria population with high