Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Unsupervised data dimension reduction method based on noise suppression

A technology for data dimensionality reduction and noise suppression, applied in instruments, character and pattern recognition, computer components, etc., can solve problems that affect data processing and cannot effectively remove noise data, so as to speed up computing time and reduce computational complexity Degree, the effect of effective dimensionality reduction

Pending Publication Date: 2021-10-01
NORTHWESTERN POLYTECHNICAL UNIV
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, since this method generalizes the local mapping relationship to the whole world in the process of building the model, this method may also learn the local structure of the noise into the projection matrix, resulting in the inability to effectively remove the noise data after the location, affecting subsequent data processing

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Unsupervised data dimension reduction method based on noise suppression
  • Unsupervised data dimension reduction method based on noise suppression
  • Unsupervised data dimension reduction method based on noise suppression

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment

[0117] like figure 2 As shown, the method proposed by the present invention and the comparative algorithm Principal Component Analysis (Principal Component Analysis, PCA), kernel principal component analysis (Kernel Principal Component Analysis, KPCA) results on the Wine data set. The Wine dataset has a total of 178 samples, a dimension of 13, and a total of 3 categories. The above three dimensionality reduction methods reduce the original data to the subspace and then cluster through K-means. The labels obtained after clustering are compared with the real labels of the samples to obtain the overall classification accuracy as the evaluation index. The overall classification accuracy The value is 0-1, and the larger the value, the better the dimensionality reduction method. As shown in the figure below, the overall classification accuracy of the proposed method in the subspace dimension is higher than that of the comparison algorithm, which also proves the effectiveness of th...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses an unsupervised data dimension reduction method based on noise suppression, which comprises the following steps of: firstly initializing a global divergence matrix, a graph matrix, a projection matrix, a Laplacian matrix and regularization parameters, then updating a matrix F, then updating a projection matrix P, and repeatedly iterating until an objective function is converged to realize unsupervised data dimension reduction. Calculation complexity is reduced, the operation time is shortened, and quick and effective dimension reduction of high-order data can be realized.

Description

technical field [0001] The invention belongs to the technical field of machine learning, and in particular relates to an unsupervised data dimensionality reduction method. Background technique [0002] With the continuous development of information acquisition technology, data has more samples and features. However, these large number of features are not completely independent, and there are a lot of noise and redundant information in them. In order to eliminate redundant and noise information, retain the most important data features, and alleviate the problem of "dimension disaster" brought about by high dimensions, researchers have proposed more and more data dimensionality reduction methods. As one of the research hotspots in the field of machine learning, these data dimensionality reduction methods have been widely applied to fields such as face recognition, image compression, hyperspectral band selection, and medical image processing. [0003] Zhou Zhihua (Zhou Zhihua...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/62
CPCG06F18/213G06F18/24
Inventor 王靖宇王林聂飞平李学龙
Owner NORTHWESTERN POLYTECHNICAL UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com