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

Safe semi-supervised learning electroencephalogram signal identification method based on self-adaptive risk degree

A semi-supervised learning and EEG signal technology, applied in the fields of application, medical science, electrical digital data processing, etc., can solve the problem of lack of safe semi-supervised signal recognition methods, achieve enhanced robustness and practicability, and improve recognition rate , the effect of reducing risk

Pending Publication Date: 2020-05-19
HANGZHOU DIANZI UNIV
View PDF1 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, there is currently a lack of self-adaptive-based secure semi-supervised signal recognition methods for multi-class problems.

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
  • Safe semi-supervised learning electroencephalogram signal identification method based on self-adaptive risk degree
  • Safe semi-supervised learning electroencephalogram signal identification method based on self-adaptive risk degree
  • Safe semi-supervised learning electroencephalogram signal identification method based on self-adaptive risk degree

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0014] The present invention is further illustrated in conjunction with the accompanying drawings. It should be understood that these embodiments are only used to illustrate the present invention and are not intended to limit the scope of the present invention. After reading the present invention, those skilled in the art will modify various equivalent forms of the present invention All fall within the scope defined by the appended claims of this application.

[0015] Such as figure 1 As shown, the implementation of the present invention mainly includes four steps: (1) input and preprocessing of EEG signals to form a database; (2) construct a neighbor graph W, and train a multi-class supervised classifier to obtain predictions of unlabeled samples label; (3) using l 2，1 The norm constructs the optimization problem, obtains the objective function, and trains the safe semi-supervised classifier through iterative optimization; (4) Input the signal to be identified, and use the s...

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 safe semi-supervised learning electroencephalogram signal identification method based on self-adaptive risk degree. Firstly, an electroencephalogram signal database is constructed; preprocessing and feature extraction are carried out; a neighbor graph W is calculated; a plurality of types of supervised classifiers are trained and an unmarked sample prediction label is obtained; an objective function is constructed by utilizing an l<2,1> norm; an optimal safe semi-supervised classifier is searched through an alternative iterative optimization method; and samples to beidentified are identified by utilizing the safe semi-supervised classifier. According to the invention, identification performance and robustness of a BCI system are enhanced by improving the semi-supervised classifier.

Description

technical field [0001] The invention belongs to the field of brain-computer interface, and relates to an EEG signal identification method based on self-adaptive risk degree-based safe semi-supervised learning. [0002] technical background [0003] The BCI system based on motor imagery collects and models the cerebral cortex signals of the subjects, and then interprets the subjects' brain intentions or instructions to realize the brain's control of external devices such as wheelchairs and intelligent prostheses. For patients with severe damage to the central nervous system, the BCI system based on motor imagery provides a way to communicate and control with the outside world, which helps to improve their quality of life and self-care ability, and has great practical significance in rehabilitation medicine, military and other fields . [0004] Improving the recognition rate of motor imagery patterns is the core of the BCI system. To obtain a high-performance recognition algor...

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): A61B5/0476G06F3/01
CPCG06F3/015A61B5/7267A61B5/7235G06F2203/011A61B5/369
Inventor 杨策丞甘海涛张肖辉庄栋
Owner HANGZHOU DIANZI 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