Evaluation of chicken freshness using a low-cost colorimetric sensor array with AdaBoost–OLDA classification algorithm

This paper attempted to evaluate chicken freshness using a low-cost colorimetric sensor array with the help of a classification algorithm. We fabricated a novel and low-cost colorimetric sensors array, with a specific colorific fingerprint to volatile compounds, using printing chemically responsive dyes on a C2 reverse silica-gel flat plate. In addition, we proposed a novel classification algorithm for sensors data classification – orthogonal linear discriminant analysis (OLDA) and adaptive boosting (AdaBoost) algorithm, namely AdaBoost–OLDA. And we compared it with two classical classification algorithms – linear discriminant analysis (LDA) and back propagation artificial neural network (BP-ANN). Experimental results showed classification results by AdaBoost–OLDA algorithm is superior to BP-ANN and LDA algorithms, the classification results by which are both 100% in the calibration and prediction sets. This study sufficiently demonstrated that the colorimetric sensors array with a classification algorithm has a high potential in evaluating chicken freshness, and AdaBoost–OLDA algorithm has a strong performance in solution to a complex data classification.