Method using electronic nose to identify vinegar varieties by extracting optimization fuzzy identification vector

Abstract

The invention discloses a method using an electronic nose to identify vinegar varieties by extracting an optimization fuzzy identification vector. Several sensors are randomly selected from the sensors of the electronic nose. Collected data corresponding to the sensors are extracted from training samples and are used as new training samples. The class mean value of new training samples, the grand mean of new training samples, the inter-class dispersion matrix and the intra-class dispersion matrix of new training samples, the trace of the inter-class dispersion matrix and the trace and the optimal value of the intra-class dispersion matrix are calculated. The new training sample corresponding to the selected sensor is used as the optimal training sample when the optimal value is the maximum. The identification information of the optimal training sample is extracted. The optimal identification vector set is acquired. The optimal identification vector set is linearly transformed to acquire a projection sample set. The projection sample set is classified to identify vinegar varieties. According to the invention, the data dimension can be reduced without the loss of main information; the influence of noise is reduced; and the classification accuracy of vinegar varieties is improved.

Description

technical field [0001] The invention relates to a method for identifying vinegar varieties, in particular to a method for identifying vinegar varieties by using an electronic nose. Background technique [0002] Vinegar is an essential condiment in family life. There are many types of vinegar on the market, and their flavors are different due to different places of origin, ingredients, and fermentation methods. Flavor is one of the important indicators of vinegar classification and one of the main factors of consumer acceptance. However, there are many vinegar products on the market. During the production process, the fermentation temperature, the depth of fermented grains, and the fermentation time are mostly controlled by the experience of the master workers, so it is easy to cause uneven quality of vinegar. Not one. For a long time, gas chromatography has been used to objectively measure odor, but gas chromatography has harsh requirements on the experimental environment ...

AI Technical Summary

Problems solved by technology

[0005] Aiming at the current problems that the cost of vinegar classification is too high, and the selection of different pattern recognition algorithms will affect the classification accuracy, the present invention proposes a method of optimizing the extraction of fuzzy identification vectors for electronic nose identification of vinegar varieties to improve the accuracy of vinegar category classification. Rate

Images