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

An EEG Signal Classification Method Based on Improved Deep Residual Group Convolutional Network

An EEG signal and convolutional network technology, applied in the field of pattern recognition, can solve problems such as inability to utilize EEG signals, optimize the amount of calculation and feature transfer, and achieve the effect of improving the gradient explosion problem, easy optimization, and speeding up the convergence speed.

Active Publication Date: 2022-05-31
JILIN UNIV
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The technical problem solved by the present invention is to overcome the problem that the existing technology cannot fully utilize the features extracted from the EEG signal and optimize the amount of calculation and feature transfer. On the basis of ResNeXt, a layer of convolutional layer is directly Lian, provided an improved ResNeXt-based EEG signal classification method

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
  • An EEG Signal Classification Method Based on Improved Deep Residual Group Convolutional Network
  • An EEG Signal Classification Method Based on Improved Deep Residual Group Convolutional Network
  • An EEG Signal Classification Method Based on Improved Deep Residual Group Convolutional Network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0052] The present invention is described in detail below in conjunction with the accompanying drawings.

[0056] 2) The brain electrical signals of the experimenter are collected, and the collection frequency is set to 250Hz.

[0064] Using the wavelet transform to extract the EEG signal in the frequency range of 0.5Hz to 30Hz, the 1.5-dimensional EEG signal of the collected EEG

[0068] 3) Configure the improved ResNeXt.

[0079] 1) Use wavelet transform to extract the EEG signal in the frequency range of 0.5Hz to 30Hz.

[0081]

[0084] (4) Establish an EEG signal classification network based on improved ResNeXt.

[0088] The number of channels for each path of each cardinality is set to 4. ResNeXt structure parameter column

[0089]

[0090]

[0091] The activation function of the present invention selects the ReLU activation function, which can effectively improve the gradient

[0094] where x represents the output signal of a node in the ResNeXt classification network.

[00...

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 belongs to the field of pattern recognition and EEG signal processing, and relates to an EEG signal classification method based on an improved ResNeXt network; it includes four parts: EEG signal acquisition, preprocessing, feature extraction, and training ResNeXt classification network; training ResNeXt classification network is Refers to: dividing the training set and test set; building an improved ResNeXt EEG signal classification network; training the improved ResNeXt EEG signal classification network; building an improved ResNeXt EEG signal classification network refers to: improving on the basis of ResNeXt, and convolving the groups The middle layer of the convolutional layer of each block module increases the direct connection operation, speeds up the speed of model convergence, reduces the test error of the model, and improves the generalization ability; the invention speeds up the convergence speed of the classification model, compared with the convolutional neural network brain The electrical classification model, the improved ResNeXt classification model is easier to optimize, effectively improves the gradient explosion problem in the deep training model, and can greatly deepen the number of layers of the network while avoiding the degradation of the classification model.

Description

An EEG Signal Classification Method Based on Improved Deep Residual Grouping Convolutional Networks technical field The invention belongs to the field of pattern recognition, relate to EEG pattern classification in brain-computer interface, particularly a kind of basic To improve the classification of EEG signals with deep residual grouped convolutional networks. Background technique In recent years, with the rapid development of neuroscience, information science, computer science and other fields, a kind of New high-tech technology - brain-computer interface technology. Brain-Computer Interface (BCI), yes Also known as "brain port" or "brain-machine fusion perception", it is the use of EEG between human or animal brains and external devices Or other physiological measures of brain activity that establish communication conduits that do not rely on traditional neuromuscular output. brain-computer interface Representing the potential next hardware interface, the fu...

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 Patents(China)
IPC IPC(8): G06K9/00G06K9/62G06N3/04
CPCG06N3/045G06F2218/12G06F18/214
Inventor 陈万忠于子航
Owner JILIN 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