Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Brain structure feature selection method, mobile terminal and computer readable storage medium

A feature selection method and feature selection technology, applied in computer parts, computing, instruments, etc., can solve the problem of loss of brain feature information, and achieve the effect of reducing dimensions and effectively classifying features

Pending Publication Date: 2020-04-24
SHENZHEN UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The main purpose of the present invention is to provide a method for selecting brain structural features, a mobile terminal and a computer-readable storage medium, aiming to solve the technical problem of brain feature information loss when extracting and classifying brain features at the present stage

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
  • Brain structure feature selection method, mobile terminal and computer readable storage medium
  • Brain structure feature selection method, mobile terminal and computer readable storage medium
  • Brain structure feature selection method, mobile terminal and computer readable storage medium

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0088] Based on the first embodiment, a second embodiment of the brain structure feature selection method of the present invention is proposed. In this embodiment, step S21 includes:

[0089] Step S211, using target software to reconstruct the target data to obtain an initial brain model;

[0090] Step S212, if the initial brain model is an abnormal brain model, then adjust the initial brain model to obtain a target brain model.

[0091] In this embodiment, after the target software is used to reconstruct the target data to obtain the initial brain model, the constructed initial brain model can be viewed in the target software, and if abnormal defects in the initial brain model are detected, then The initial brain model is an abnormal brain model, and then the initial brain model is adjusted to obtain a target brain model.

[0092] Specifically, step S212 includes,

[0093] Step S213, if it is detected that the fulcrum coordinate deviation of the initial brain model exceeds ...

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 brain structure feature selection method, a mobile terminal and a computer readable storage medium. The brain structure feature selection method comprises the following steps: selecting brain structure features; acquiring original data of a brain nuclear magnetic resonance structural image; performing format conversion on the original data; obtaining target data, preprocessing the target data by adopting target software; obtaining feature data of the target data, constructing a feature data matrix by using the feature data; inputting the characteristic data matrix into a support matrix machine, acquiring feature data with category labels, performing visualization processing on the feature data with the category labels based on a target encoder so as to acquire a visualization feature image. The method can reduce the dimension of the feature data, can store brain feature information, and can extract more effective classification features.

Description

technical field [0001] The invention relates to the field of brain features, in particular to a brain structure feature selection method, a mobile terminal and a computer-readable storage medium. Background technique [0002] In the neuroimaging research of brain science in recent years, whether it is possible to extract brain features with strong expressive ability is the cornerstone of neuroimaging research in brain science. With a large enough discriminative difference, the feature classification methods at this stage generally use the difference test between groups driven by specific assumptions or models. Before classification, the feature matrix needs to be converted into the form of feature vectors. However, In this way, the feature matrix information will be lost, which will further affect the accuracy of feature classification. [0003] The above content is only used to assist in understanding the technical solution of the present invention, and does not mean that ...

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
CPCG06V2201/03G06F18/2133
Inventor 刘维湘陈柏宏
Owner SHENZHEN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
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