Electronic nose vinegar variety identification method through fuzzy covariance learning network

Abstract

The invention discloses an electronic nose vinegar variety identification method through a fuzzy covariance learning network. The method concretely comprises the following steps that firstly the electronic nose is applied to acquire different varieties of vinegar data, then the acquired vinegar data are preprocessed through a standard normal variable transformation (SNV), then data compression isperformed by using principal component analysis (PCA) and the identification information of training samples is extracted by using linear discriminant analysis (LDA), and finally the vinegar variety is identified according to the fuzzy covariance learning network method. The electronic nose vinegar variety identification method through the fuzzy covariance learning network is high in classification accuracy, simple and convenient, lossless, low in cost and easy to implement and popularize and use.

Description

technical field [0001] The invention relates to the field of vinegar variety identification, in particular to a method for identifying vinegar varieties using an electronic nose using a fuzzy covariance learning network. Background technique [0002] Vinegar is one of the seasonings in many families. There are various kinds of vinegar on the market. Different brands of vinegar, different brewing methods and different brewing raw materials have different quality and flavor of vinegar. As the majority of consumers have more requirements for the quality of vinegar, it is of great significance and value to study the distinction between the quality and variety of vinegar. [0003] Generally speaking, the method of odor identification is carried out by some trained people with many years of work experience, and the objective determination method of odor is generally using gas chromatography. However, these two methods have disadvantages: the subjectivity of professionals is highe...

AI Technical Summary

Problems solved by technology

However, these two methods have disadvantages: the subjectivity of professionals is higher, and it is expensive to train professionals who specialize in identification; the experiment using gas chromatography is not only complicated, but also has very harsh requirements for the experimental environment. On-site detection by chromatography has certain limitations

Although the neural network (BP) can achieve nonlinear classification by learning sample data, the neural network has problems such as local minimum points and over-learning.

Images