Nondestructively sensing of total viable count (TVC) in chicken using an artificial olfaction system based colorimetric sensor array

Total viable count (TVC) is one of the most important indexes in evaluation of chicken's freshness. This paper attempted to quantify the TVC in chicken using a novel nondestructive sensing tool based on colorimetric sensor array. First, we fabricated a novel and low-cost colorimetric sensors array, with a specific colorific fingerprint to volatile compounds from chicken, using printing chemically responsive dyes on a C2 reverse silica-gel flat plate. And an artificial olfactory system based on colorimetric sensor array was developed for data acquisition. In addition, we proposed a novel efficient back propagation adaptive boosting (BP-AdaBoost) algorithm for data modeling, and we compared it with the classic modeling algorithms. The optimum results were achieved using BP-AdaBoost modeling algorithm as follows: the root mean square error of prediction (RMSEP) = 0.5430 lg CFU/g and the determination coefficient (Rp) = 0.8119 in the prediction set. This work demonstrates that the artificial olfactory technique based on colorimetric sensor array, as a nondestructive sensing tool, has a high potential to quantify TVC in chicken.