Feature selection method based on optimal reconstruction

Abstract

The present invention provides a feature selection method based on optimal reconstruction, the steps of which are: 1) represent each original feature in the data set as d-dimensional data as a data matrix X, where d>1; 2) for the above data matrix X establishes an optimal linear reconstruction model, and the optimization target of the model is the representation matrix B; 3) Transpose the above data matrix X to obtain the feature matrix F, and clear the representation matrix B; 4) Use iterative alternate optimization Solve the above-mentioned optimized linear reconstruction model after step 3) in a way to obtain the optimal representation matrix B*; 5) select the optimal k-dimensional feature subset that can represent all d-dimensional features according to the optimal representation matrix B* , where k

Description

Technical field [0001] The present invention relates to the technical field of data mining, in particular to a feature selection method based on optimal reconstruction. Background technique [0002] In machine learning, high-dimensional data is often difficult to process efficiently in mathematics and operations. Feature learning aims to find the low-dimensional representation of the original high-dimensional data. Feature learning methods are divided into two types: feature extraction and feature selection. Feature extraction maps the original high-dimensional feature space to a low-dimensional subspace. After obtaining the optimal mapping function, all features need to participate in feature transformation to obtain low-dimensional feature expression; while feature selection is directly selected from the original high-dimensional features Low-dimensional subsets and removal of other features do not involve feature calculation. After obtaining the optimal feature position, low...

AI Technical Summary

Problems solved by technology

In practical applications, data labeling is time-consuming, laborious, and expensive, so the number of labeled data is difficult to guarantee; on the other hand, compared to the full amount of data, labeled data only accounts for a small proportion, and the data distribution that labeled data obeys is not comprehensive. Reflect the distribution of the full amount of data

Therefore, the above factors restrict the effect of feature selection

Images