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

A convolutional neural network motor imagery electroencephalogram recognition method based on a time-frequency domain

A technology of convolutional neural network and EEG signal, which is applied in the field of motor imagery EEG signal recognition based on convolutional neural network based on time-frequency domain, can solve the problems that the recognition rate of EEG signal needs to be further improved

Active Publication Date: 2019-05-03
CHONGQING UNIV OF POSTS & TELECOMM
View PDF14 Cites 20 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Compared with the manual feature extraction method, CNN extracts abstract features in a data-driven manner, reducing the loss of information, but its recognition rate of EEG signals needs to be further improved

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
  • A convolutional neural network motor imagery electroencephalogram recognition method based on a time-frequency domain
  • A convolutional neural network motor imagery electroencephalogram recognition method based on a time-frequency domain
  • A convolutional neural network motor imagery electroencephalogram recognition method based on a time-frequency domain

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] The technical solutions in the embodiments of the present invention will be described clearly and in detail below with reference to the drawings in the embodiments of the present invention. The described embodiments are only some of the embodiments of the invention.

[0037] The technical scheme that the present invention solves the problems of the technologies described above is:

[0038] The present invention provides a method for recognizing motor imagery EEG signals based on a time-frequency domain-based convolutional neural network, which comprises the following steps:

[0039] S1, the motor imagery EEG signal is collected by three electrodes C3, CZ and C4), a two-dimensional time-frequency map is designed as the input of the CNN network. Perform short-time Fourier transform on the 2s long EEG signal collected by each electrode:

[0040]

[0041] Among them, X(w, t) represents the original EEG signal, w() represents the window function, and the Hamming window ...

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 requests to protect a convolutional neural network motor imagery EEG signal identification method based on a time-frequency domain. The method comprises the following steps: S1, converting original left and right hand motor imagery EEG signals into a two-dimensional time-frequency diagram by utilizing short-time Fourier transform; S2, designing a five-layer convolutional neural network structure for the obtained two-dimensional time-frequency diagram, and performing feature extraction in a one-dimensional convolution mode in order to avoid the mixing of time and frequency information; S3, training the whole CNN network by using a back propagation algorithm; and S4, taking the support vector machine as a classifier of the whole model, and replacing an output layer in the CNN with the support vector machine. The method can ensure that the extracted motor imagery electroencephalogram signal features of the left hand and the right hand have higher recognition rate and good robustness in the electroencephalogram data set.

Description

technical field [0001] The invention belongs to the field of electroencephalogram signal identification, in particular to an electroencephalogram signal identification method based on a convolutional neural network based on a time-frequency domain. Background technique [0002] The current research on Brain Computer Interface (BCI) based on Electroencephalogram (EEG) mainly focuses on motor imagery EEG signals, and how to extract features of signals in BCI is one of the most important issues. Motor imagery generates related signals by "thinking". Research on motor imagery shows that unilateral limb movement or imaginary movement can inhibit the rhythmic activity and power spectrum of wave (8-13Hz) and wave (14-30Hz) / enhanced effect, the event-related desynchronization / synchronization (ERD / ERS) phenomenon. According to this phenomenon, researchers have proposed many feature extraction methods so far, such as AR model (auto-regressive, autoregressive), Wavelet transform, Hil...

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): G06K9/00G06N3/04G06N3/08A61B5/0476
Inventor 胡章芳张力罗元
Owner CHONGQING UNIV OF POSTS & TELECOMM
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