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

Data dimensionality reduction method for two-dimensional time-frequency data

A data dimensionality reduction, time-frequency technology, used in instruments, character and pattern recognition, computer parts, etc., can solve the problems of unable to use the nonlinear characteristics of data, and the recognition rate cannot reach the ideal.

Active Publication Date: 2018-10-09
UNIV OF ELECTRONIC SCI & TECH OF CHINA
View PDF5 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The present invention aims at the situation that when the two-dimensional two-dimensional principal component analysis algorithm reduces the dimensionality of two-dimensional data, the non-linear features contained in the data cannot be used, and the recognition rate cannot reach the ideal situation.

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
  • Data dimensionality reduction method for two-dimensional time-frequency data
  • Data dimensionality reduction method for two-dimensional time-frequency data
  • Data dimensionality reduction method for two-dimensional time-frequency data

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] In the following, the algorithm of the present invention is used to reduce the dimensionality of the wavelet transform two-dimensional time-frequency representation data of the radar high-resolution range image, and obtain its projection transformation matrix. This example is used to describe the implementation of the present invention in detail, so as to have a deeper understanding of how to apply the technical means of the present invention to solve technical problems, in order to achieve the purpose of solving practical problems well, and implement accordingly. The present invention kernel two-dimensional two-dimensional principal component analysis algorithm, the implementation steps of the present invention are as follows figure 1 As shown, each step is specifically implemented in the following manner:

[0031] Step 1: Centralize each range image time-frequency representation sample A i ∈R m × R n (i=1,2,...,M, M is the number of time-frequency sample matrix): ...

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 a data dimensionality reduction method for two-dimensional time-frequency data. The method is applied to the dimensionality reduction and the compression of two-dimensional data. The method mainly comprises the following steps: firstly, carrying out centralization on sample data; secondly, mapping the centralized data to a high-dimensional space, and constructing the covariance of mapping data by using a kernel function in the high-dimensional space; finally, carrying out dimensionality reduction on the covariance by utilizing a bilateral two-dimensional principal component analysis algorithm, and obtaining a feature projection transformation matrix. According to the invention, by adopting the algorithm, nonlinear features in original data are fully utilized, and the number of obtained feature projection matrix systems is small. Therefore, the recognition rate and the data compression rate are improved, and the calculation amount is reduced.

Description

technical field [0001] The invention relates to the linearization of nonlinear features of two-dimensional data, and extracts the principal element of the linearized feature, and realizes dimensionality reduction and reconstruction of data through the principal element. It is mainly used in target recognition and classification based on two-dimensional image features such as radar time-frequency distribution and face features. Background technique [0002] Principal Component Analysis (PCA) converts high-dimensional data containing redundant information into a small number of low-dimensional data, namely principal components, where each principal component contains almost all valid information of the original data. In this way, the intricate data analysis problem is transformed into a problem that only needs to study a few principal components, not only can the problem be analyzed more deeply, but also the analysis process becomes very easy. The basic idea is to find a proj...

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
IPC IPC(8): G06K9/62
CPCG06F18/2135
Inventor 于雪莲曲学超徐丽唐永昊赵林森
Owner UNIV OF ELECTRONIC SCI & TECH OF CHINA
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