Non-destructive evaluation of pork freshness using a portable electronic nose (E-nose) based on a colorimetric sensor array

Abstract

This paper investigated the feasibility of rapid non-destructive evaluation of pork freshness using a portable electronic nose (E-nose) based on a colorimetric sensor array. A novel and low-cost colorimetric sensor array was fabricated by printing 12 chemically responsive dyes on a silica-gel flat plate. The colorimetric sensor array had a specific colorific fingerprint for the volatile compounds released from pork samples, and could be successfully used to evaluate pork freshness with the help of multivariate calibration. Linear discriminant analysis (LDA) and back propagation artificial neural network (BP-ANN) were used for modeling. The experimental results showed that the performance of the BP-ANN model was superior to that of the LDA model. The optimum discrimination rates were 100% and 97.5% for the training and prediction sets respectively. The results demonstrated that this technology has high potential for real-time use in monitoring pork quality in meat processing industries.