| Abstrak/Abstract |
An electronic nose (E-nose), comprising eight metal oxide semiconductor (MOS) gas
sensors, was used in situ for real-time classification of black tea according to its quality level.
Principal component analysis (PCA) coupled with signal preprocessing techniques (i.e., time set
value preprocessing, F1; area under curve preprocessing, F2; and maximum value preprocessing,
F3), allowed grouping the samples from seven brands according to the quality level. The E-nose
performance was further checked using multivariate supervised statistical methods, namely, the
linear and quadratic discriminant analysis, support vector machine together with linear or radial
kernels (SVM-linear and SVM-radial, respectively). For this purpose, the experimental dataset
was split into two subsets, one used for model training and internal validation using a repeated
K-fold cross-validation procedure (containing the samples collected during the first three days of tea
production); and the other, for external validation purpose (i.e., test dataset, containing the samples
collected during the 4th and 5th production days). The results pointed out that the E-nose-SVM-linear
model together with the F3 signal preprocessing method was the most accurate, allowing 100%
of correct predictive classifications (external-validation data subset) of the samples according to
their quality levels. So, the E-nose-chemometric approach could be foreseen has a practical and
feasible classification tool for assessing the black tea quality level, even when applied in-situ, at the
harsh industrial environment, requiring a minimum and simple sample preparation. The proposed
approach is a cost-eective and fast, green procedure that could be implemented in the near future by
the tea industry.
Keywords: electronic |
