Target domain migration extreme learning-based electronic nose heterogeneous data identification method

Abstract

The invention provides a target domain migration extreme learning-based electronic nose heterogeneous data identification method. A domain migration extreme learning machine framework is put forward from an angle of machine learning and is used for solving a problem of sensor drift. Via gas sensor array sensing data matrixes which are collected via an electronic nose before drift and labeled and non-labeled gas sensor array sensing data matrixes which are collected via the electronic nose after drift, a source domain data set, a target domain data set and a data set for a domain to be tested are respectively established and are respectively used as input for an extreme learning machine, an electronic nose identification and classification machine can be learned, gas identification tolerance performance of the identification and classification machine can be improved after the electronic nose is drifted, an aim of drift compensation and improvement of heterogeneous data sample identification precision in gas identification is attained, technical advantages of the extreme learning machine are kept, good generalization and migration performance of the method are realized, and the method can be widely applied to different electronic nose products for identifying different gases.

Description

technical field [0001] The invention relates to the technical field of electronic nose detection, in particular to an electronic nose heterogeneous data identification method based on target domain migration limit learning. Background technique [0002] An electronic nose is an intelligent electronic device or artificial olfactory system that uses the response map of a gas sensor array to identify gases. Due to the crossover characteristics and broad spectrum of gas sensor arrays in electronic noses, the gas recognition capabilities of electronic noses are widely used in medical diagnosis, tea quality assessment, environmental detection, and gas concentration prediction. [0003] However, the gas sensor of the electronic nose is aging continuously with the increase of usage time, which greatly shortens the service life of the gas sensor array of the electronic nose. Poisoning, aging or environmental variables can cause the gas sensor drift of the electronic nose, and the ga...

AI Technical Summary

Problems solved by technology

[0006] A typical multivariate component correction method is the component correction principal component analysis method, which uses principal component analysis to find the drift direction, thereby removing the drift component; however, the compensation idea of ​​the component correction principal component analysis method needs to be based on the drift of all categories of data However, the actual drift of the electronic nose is not the case, so it is difficult to effectively apply this method to the drift compensation of the electronic nose; and if a multiplier correction is added on the basis of the component correction principal component analysis method Variables are used to improve the consistency limitation of the data drift direction, and the generalization of its drift compensation will be restricted by the nonlinear dynamic characteristics of the gas sensor in online applications, making it difficult for its drift compensation effect to be specific to different Suitable for a wide range of gas identification applications

[0007] The adjustment compensation method is to adjust the difference in the distribution of the sensing features by adjusting the response changes of the gas sensor array of the electronic nose during gas recognition and detection at different stages, thereby realizing drift compensation; When the gas sensor array of the electronic nose has a transient response, it is misjudged that the gas sensor array is undergoing drastic changes in drift, and then frequently adjusted and compensated, it is easy to disrupt the original eigenvalue distribution of the gas sensor array of the electronic nose. As a result, the original relatively accurate identification neural network cannot correctly identify its matching gas after drift compensation, which affects the gas identification accuracy of the electronic nose

[0008] Previously, researchers have also carried out some research on the drift compensation of electronic noses through machine learning methods, but the machine learning methods currently used are mainly based on support vector machines, which often require a large number of training samples for learning. In the case of limited training samples, the compensation effect is not good, and it is still not possible to improve the recognition accuracy of the electronic nose for heterogeneous data samples in gas recognition through drift compensation. In addition, this type of machine learning method usually needs to train many base classifiers. Therefore, its domain transfer ability and generalization are limited

[0009] To sum up, in the existing technology, the compensation method for the drift of the electronic nose gas sensor generally has the problems of low gas recognition accuracy, poor migration ability and generalization of the electronic nose after compensation.

Images