Tea grade discrimination method based on partial least square discriminant analysis model

Abstract

The invention discloses a tea grade discrimination method based on a partial least square discriminant analysis model. The method comprises the steps of directly constructing 20 PLS-DA models with potential variables from 1 to 20 between a response signal vector of a tea sample and a set label of the tea sample; predicting each tea sample by adopting the obtained 20 PLS-DA models and constructinga sorting difference sum matrix of the tea samples by using a prediction result; constructing a sorting difference sum standard reference sequence vector of each tea sample based on the sorting difference sum matrix of the tea samples, constructing a first index value matrix containing 20 rows and 1 column of index values, and then adjusting the row number of each row of data in the sorting difference sum matrix to construct a second index value matrix, and finally determining the grade of the tea samples by calculating the sum of the absolute difference values. The method has the advantages of simple discrimination process and higher discrimination precision.

Description

technical field [0001] The invention relates to a method for discriminating tea grades, in particular to a method for discriminating tea grades based on a partial least squares discriminant analysis model. Background technique [0002] As a beverage that is deeply loved by consumers, tea leaves are usually divided into multiple grades according to their color, aroma, maturity and various quality indicators. In order to regulate the tea sales market, protect the legitimate rights and interests of consumers, and prevent tea dealers from deceptively selling inferior tea as superior tea, it is often necessary to conduct quality testing and grade discrimination on tea. As a bionic sensor technology, electronic tongue technology combined with partial least squares-discriminant analysis (PLS-DA) model can quickly analyze and identify multi-grade tea samples, so as to realize the discriminant analysis of tea grades. [0003] In the existing tea grade discrimination method based on ...

AI Technical Summary

Problems solved by technology

[0003] In the existing tea grade discrimination method based on the partial least squares discriminant analysis model, in order to obtain the optimal classification effect, when using the PLS-DA model for discriminant analysis, it is usually necessary to use cross-validation calculations to determine the PLS-DA model. The optimal latent variable value, the cross-validation calculation not only increases the complexity of the discriminant process, but also usually needs to determine the sampling strategy and the cross-validation fold during the cross-validation calculation, which means that different sampling strategies and The cross-validation folds may get different optimal latent variable values, which eventually causes the PLS-DA model to fail to obtain the optimal discriminant effect, and ultimately leads to the low discriminative accuracy of the tea grade discriminant method, which is difficult to meet the accuracy requirements