Cross-domain migration electronic nose drift suppression method based on migration samples

Abstract

The invention discloses a cross-domain migration electronic nose drift suppression method based on migration samples. The method comprises steps of projecting the source domain data and the target data to a subspace, performing edge maximum mean difference minimization processing, condition maximum mean difference minimization processing and separability maximization processing on sets of different domain data, and performing maximization processing on discrimination information to obtain a conversion basis P, a corresponding projection source domain data set and a projection target domain data set; calculating an unknown output weight of the adaptive extreme learning machine according to the projection source domain data set and the projection target domain data set to obtain a final adaptive extreme learning machine; and performing a drift suppression test on the target domain data of the unknown label. The method has the beneficial effects that the discrimination information of thesource domain and the target domain is stored while drift is inhibited. The edge distribution difference and the condition distribution difference are minimized, and the robustness and the classification accuracy of the model are improved. Knowledge migration is realized in a feature layer and a decision layer, and migration samples are fully utilized.

Description

technical field [0001] The invention relates to the technical field of electronic nose signal processing, in particular to a cross-domain migration electronic nose drift suppression method based on migration samples. Background technique [0002] Time drift and board drift of metal-oxide-semiconductor sensors in electronic noses is an urgent problem in the current sensor and measurement field. The time-varying nature of the drift and the unpredictability of its direction make it difficult to measure the drift directly. Extreme learning machines with high efficiency and low computational complexity are often used to solve the temporal drift / inter-board drift phenomenon in electronic noses. [0003] There are two main methods to suppress sensor drift: [0004] 1. The suppression method at the feature level. It aims to suppress drift from the perspective of data distribution, so that the difference between the data distribution of the source domain and the target domain is r...

AI Technical Summary

Problems solved by technology

[0006] Disadvantages: 1. The suppression method based on the feature level does not consider the knowledge transfer ability of the classifier, and cannot be adjusted according to the target domain samples to obtain an adaptive classifier, and the classification effect is poor

2. The suppression method based on the decision-making level ignores the data distribution mismatch between the source domain and the target domain. The distribution of data in different domains before classification is very different, which reduces the classification performance.

Images