RESUMO
Mee tea, one of the major types of green tea in China, is often used for export because of its elegant appearance, high fragrance and strong taste. However, the quality of tea differs greatly due to the difference in raw material selection and production technology level. In order to accurately and quickly differentiate different grades of Mee tea, fuzzy fast pseudoinverse linear discriminant analysis (FFPLDA) was proposed based on fast pseudoinverse linear discriminant analysis (FPLDA) for extracting discriminant information from near-infrared (NIR) spectra. Firstly, NIR spectra of Mee tea samples were acquired, and then they were preprocessed by multiplicative scatter correlation (MSC). Secondly, the compression of data was achieved by principal component analysis (PCA). Thirdly, linear discriminant analysis (LDA), FPLDA, FFPLDA and fuzzy Foley-Sammon transformation (FFST) were respectively performed to retrieve discriminant information from NIR data. Finally, the K-nearest neighbor (KNN) was utilized to classify Mee tea grades. In this study, experimental results showed that the accuracy of FFPLDA was higher than that of LDA, FFST and FPLDA. Therefore, NIR spectroscopy coupled with FFPLDA and KNN has a good effect in discrimination of Mee tea grades and also a great application potential.
RESUMO
In order to quickly, nondestructively, and effectively distinguish red jujube varieties, based on the combination of fuzzy theory and improved LDA (iLDA), fuzzy improved linear discriminant analysis (FiLDA) algorithm was proposed to classify near-infrared reflectance (NIR) spectra of red jujube samples. FiLDA shows performs better than iLDA in dealing with NIR spectra containing noise. Firstly, the portable NIR spectrometer was employed to gather the NIR spectra of five kinds of red jujube, and the initial NIR spectra were pretreated by standard normal variate transformation (SNV), multiplicative scatter correction (MSC), Savitzky-Golay smoothing (S-G smoothing), mean centering (MC) and Savitzky-Golay filter (S-G filter). Secondly, the high-dimensional spectra were processed for dimension reduction by principal component analysis (PCA). Then, linear discriminant analysis (LDA), iLDA and FiLDA were applied to extract features from the NIR spectra, respectively. Finally, K nearest neighbor (KNN) served as a classifier for the classification of red jujube samples. The highest classification accuracy of this identification system for red jujube, by using FiLDA and KNN, was 94.4%. These results indicated that FiLDA combined with NIR spectroscopy was an available method for identifying the red jujube varieties and this method has wide application prospects.
