Matrix concept decomposition method with local area limit

Abstract

The invention discloses a matrix concept decomposition method with a local area limit. The method includes: (1) constructing a sample characteristic matrix; (2) outputting a basis matrix and a coefficient matrix in iteration mode; and (3) calculating basis low dimension display of a sample characteristic matrix. The method adds regular terms of the local area limit into a target function to enable the base obtained by decomposition to approach more original data as much as possible. The obtain data display can simultaneously meet sparseness and local area limit. Redundancy information in the high dimension data is removed by reducing dimension. Low dimension display capable of accurately displaying data semantic structure is provided, so that clustering analysis of the high dimension data is simple and effective and has good interpretability.

Description

technical field [0001] The invention belongs to the technical field of data processing, and in particular relates to a matrix concept decomposition method with local limitations. Background technique [0002] Clustering is a common multivariate statistical analysis method in machine learning and data mining. It discusses a large number of samples and requires reasonable classification according to their respective characteristics. There is no model for reference or to follow, that is, in performed without prior knowledge. At present, as an effective means of data analysis, clustering methods are widely used in various fields: in business, cluster analysis is used to discover different customer groups, and characterize the characteristics of different customer groups through purchase patterns; In biology, cluster analysis is used to classify animals and plants and to classify genes to gain an understanding of the inherent structure of populations; in geography, clustering ca...

AI Technical Summary

Problems solved by technology

[0003] At present, most clustering methods can successfully solve the clustering problem of low-dimensional data, but due to the complexity of data in practical applications, they often fail when dealing with many high-dimensional data.

Because some clustering methods mainly encounter two problems when clustering high-dimensional data sets: (1) there are a large number of irrelevant attributes in high-dimensional data sets, making the possibility of clusters in all dimensions almost zero; (2) ) The curse of dimensionality brought by high dimensions makes the practicality of some clustering algorithms almost zero

Although both of the above methods can achieve the sparsity goal, they cannot guarantee the local limit

The bases obtained by these two decomposition methods may be far from the original data, and it is obviously not optimal to use such bases for data representation.

Images