Discrimination of chicken freshness using electronic nose combined with PCA and ANN

Abstract

We have developed a portable electronic nose (E-nose) based on eight metal oxide gas sensors for classification and prediction of meat freshness. In this study, the E-nose was applied to predict chicken freshness during different storage days. Principal component analysis (PCA) and artificial neural network (ANN) were used to analyze the experiment data. The PCA method can classify the chicken freshness related to storage days. The ANN result shows good agreement with the PCA result. The correct rate in classification of ANN is 97.92%. From PCA and ANN results, it indicates that the E-nose can well classify and predict the freshness of chicken and owns many advantages over other methods including easy operation, rapid detection, high accuracy, and safety for meat.