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

Convolutional neural network training method, electroencephalogram signal recognition method and device and medium

A convolutional neural network and electroencephalographic signal technology, applied in the field of convolutional neural network training method, electroencephalographic signal recognition method, device and medium, can solve the problem of unfavorable application of brain-computer interface, electroencephalographic signal noise interference, electroencephalic signal Identify problems such as unfavorableness, and achieve the effect of reducing over-fitting, improving the recognition effect, and increasing the amount of training data.

Pending Publication Date: 2020-11-03
GUANGZHOU UNIVERSITY
View PDF0 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The EEG signal also has the characteristics of non-stationary, nonlinear and random, that is, the characteristics of the EEG signal change with time, so the EEG signal is easily disturbed by noise, which is not good for the recognition of the EEG signal. application is also bad

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
  • Convolutional neural network training method, electroencephalogram signal recognition method and device and medium
  • Convolutional neural network training method, electroencephalogram signal recognition method and device and medium
  • Convolutional neural network training method, electroencephalogram signal recognition method and device and medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0046] In this example, refer to figure 1 , the convolutional neural network training method includes the following steps:

[0047] P1. Execute multiple acquisition processes; each acquisition process is used to acquire EEG signals;

[0048] P2. Perform time-domain data enhancement and frequency-domain data enhancement on EEG signals;

[0049] P3. Training a convolutional neural network using EEG signals augmented with time-domain data and frequency-domain data.

[0050] In this embodiment, when performing each acquisition process in step P1, the subject is required to imagine a certain type of action, so that the subject's brain generates EEG signals, which pass through the brain including C3, Cz and C4 channels. The electrical signal acquisition instrument acquires the electroencephalogram signal. In this embodiment, the subject may be required to imagine the same type of action in each acquisition process, which can reduce interference caused by different types of imagin...

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 convolutional neural network training method, an electroencephalogram signal recognition method and device and a medium, and the method comprises the steps: executing a plurality of obtaining processes, obtaining an electroencephalogram signal in each obtaining process, and executing the time domain data enhancement and frequency domain data enhancement of the electroencephalogram signal, and training a convolutional neural network by using the enhanced electroencephalogram signal, and the like. The convolutional neural network trained by the method is a multi-input,multi-convolution-scale and multi-convolution-type hybrid convolutional neural network, the sizes of a multi-input convolution layer and a convolution kernel are reasonably designed, and the method has high recognition accuracy; a training set used for training the convolutional neural network is obtained by performing time domain data enhancement and frequency domain data enhancement expansion based on the acquired electroencephalogram signals, so the training data volume of the convolutional neural network can be increased, the over-fitting phenomenon can be reduced, noise interference in the electroencephalogram signals can be effectively coped with, and the recognition effect can be improved. The method is widely applied to the technical field of signal processing.

Description

technical field [0001] The invention relates to the technical field of signal processing, in particular to a convolutional neural network training method, an EEG signal recognition method, a device and a medium. Background technique [0002] The brain-computer interface can convert brain activity into computer control instructions, thereby controlling external devices, and can be widely used in fields such as medicine and industrial control. EEG signals have the advantages of non-invasiveness and high temporal resolution, so they are used as signal sources for EEG interfaces. Applying EEG signals to brain-computer interfaces involves the process of identifying EEG signals, that is, identifying the type or characteristics of EEG signals, and then converting them into computer control instructions. The EEG signal also has the characteristics of non-stationary, nonlinear and random, that is, the characteristics of the EEG signal change with time, so the EEG signal is easily di...

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): G06N3/04G06N3/08G06K9/00G06F3/01
CPCG06N3/08G06F3/015G06N3/045G06F2218/12
Inventor 王力黄伟键刘彦俊颜振雄王友康
Owner GUANGZHOU UNIVERSITY
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