Abstract
Rapid discrimination of beer with different flavors was performed by ion-selective electrode array and chemometrics. Ion-selective electrode array consisted of twelve ion-selective electrodes. Six varieties of beer 10 types of each with different flavors from Tsingtao Brewery were investigated. Potentiometric measurements were conducted in presence of beer to obtain the output potential values. Principal component analysis (PCA) was applied as a data compaction technique to reduce complexity of the potential data. Linear discriminant analysis (LDA) and least-squares support vector machine (LS-SVM) methods were used to develop discriminant models. The LS-SVM model achieved a more satisfying performance with an identification rate of 95.0% than the LDA model. For validating reliability, the developed method and sensory evaluation method were used for discriminating the beer samples. The LS-SVM model with an identification rate of 98.3% was better than the sensory evaluation method with an identification rate of 89.2%. The prepared sensor array can rapidly and accurately discriminate beer samples with different flavors and quality.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have