Formulae neighborhood based data dimensionality reduction method

Abstract

The invention discloses a data dimension reduction method based on neighborhood rule. The method includes the following steps: firstly, a spherical neighborhood of present sample points is established by using the geometric spherical-modelling theory and all the sample points contained in the spherical neighborhood are adopted as candidate neighbor points, thus not only preserving the effectivityof the dimension reduction capability when data sets are sparse but also getting the advantages of low-sensitivity to isolated points and good stability of the preserved topological structure; then adata relevance matrix more matching semantics can be obtained by relevance measurement based on route clusters to update the candidate neighbor points in the spherical neighborhood and optimize the regular neighborhood space of the present sample points, thus improving the phenomenon that the dimension reduction of sample sets provided with folded curved faces is apt to suffer the integrated-structure distortion in case of heterogeneous data distribution. The experiments on different sample sets demonstrate that the method provided by the invention is available and effective.

Description

Technical field [0001] The present invention relates to the field of information processing, in particular to a data dimensionality reduction method based on rule neighborhoods. Background technique [0002] Data dimensionality reduction refers to reducing the data in a high-dimensional space to a space with a lower dimensionality to eliminate the redundancy of the original data and improve the subsequent processing ability of the data. Traditional data dimensionality reduction is mainly based on linear. Principle Component Analysis (PCA) and Linear Discriminant Analysis (LDA) are currently the two most widely used linear dimensionality reduction methods. Although these two methods are mature in theory and fast in calculation, they can only reduce the dimensionality of data with linear structure, and it is difficult to directly process large-scale, high-dimensional and nonlinear data. [0003] Seung and Lee pointed out in the article "The Manifold Ways of Perception" in the inter...

AI Technical Summary

Problems solved by technology

However, this method also has some application limitations, such as: it is too sensitive to parameters and external noise, and the dimensionality reduction performance fails when dealing with sparsely distributed data sets.

Images