CNN classification model and generative adversarial network-based motor imagery classification method and system

A technology of motion imagery and classification models, applied in neural learning methods, biological neural network models, character and pattern recognition, etc., can solve problems such as incomplete solutions, and achieve the effect of improving quality

Pending Publication Date: 2021-06-01
四川省博瑞恩科技有限公司
View PDF0 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although solutions to different problems are proposed in the above documents, these solutions are not comprehensive

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
  • CNN classification model and generative adversarial network-based motor imagery classification method and system
  • CNN classification model and generative adversarial network-based motor imagery classification method and system
  • CNN classification model and generative adversarial network-based motor imagery classification method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0061] Such as figure 1 , this embodiment proposes a motion imagery classification method based on a CNN classification model and a generative confrontation network, including steps S1 to S3:

[0062] S1. Data preprocessing: Eliminate part of the noise through ICA on the collected MI raw data, eliminate unimportant or interfering signals through a band-pass filter, and perform feature extraction through wavelet transform and fast Fourier transform;

[0063] S2. Data expansion: Generate high-quality MI data through long-term short-term memory network and generative confrontation network;

[0064] S3. Data classification: improve classification performance and obtain classification results through multi-output convolutional neural network;

[0065] Wherein, the long-short-term memory-based network and the generated confrontation network include a generator and a discriminator, the generator includes a first fully connected layer, multiple convolutional layers, and multiple atte...

Embodiment 2

[0106] On the basis of embodiment 1, this embodiment proposes a kind of motor imagery classification system based on CNN classification model and generation confrontation network, including:

[0107] The preprocessing module is used to eliminate part of the noise through ICA for the collected MI raw data, eliminate unimportant or interfering signals through a band-pass filter, and perform feature extraction through wavelet transform and fast Fourier transform;

[0108] The data expansion module is used to generate high-quality MI data based on long-term short-term memory network and generative confrontation network;

[0109] Data classification is used to improve classification performance and obtain classification results through multi-output convolutional neural networks.

[0110] Further, the data expansion module includes:

[0111] A generator unit for generating realistic MI data and establishing a mapping relationship between categories and data;

[0112] The filter un...

Embodiment 3

[0115] Such as Figure 4 , on the basis of embodiment 1, this embodiment proposes a terminal device based on CNN classification model and generative confrontation network motor imagery classification, terminal device 200 includes at least one memory 210, at least one processor 220 and a system connected to different platforms bus 230 .

[0116] Memory 210 may include readable media in the form of volatile memory, such as random access memory (RAM) 211 and / or cache memory 212 , and may further include read only memory (ROM) 213 .

[0117] Wherein, the memory 210 also stores a computer program, and the computer program can be executed by the processor 220, so that the processor 220 executes any one of the above-mentioned motor imagery classification methods based on the CNN classification model and the generation confrontation network in the embodiment of the present application, wherein The specific implementation manner is consistent with the implementation manners and achiev...

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 CNN classification model and generative adversarial network-based motor imagery classification method and system, and the method comprises the steps: data preprocessing: eliminating part of noise of collected MI original data through ICA, eliminating unimportant or interfering signals through a band-pass filter, and carrying out the feature extraction through wavelet transform and fast Fourier transform; data expansion: generating high-quality MI data based on a long short-term memory network and a generative adversarial network; and data classification: through a multi-output convolutional neural network, improving the classification performance, and obtaining a classification result. The long short-term memory-based network and generative adversarial network comprises a generator and a discriminator, the generator comprises a first fully connected layer, a plurality of convolutional layers and a plurality of attention networks, and the discriminator comprises a plurality of convolutional LSTMs and a second fully connected layer. According to the method, the LSTM and the GAN are used for constructing the LGAN, space-time dimension modeling of the MI data is completed, high-quality new data are generated through the generator, and the influence of insufficient data on a classification result is reduced.

Description

technical field [0001] The invention relates to the field of motion image classification, in particular to a motion imagery classification method and system based on a CNN classification model and a generative confrontation network. Background technique [0002] A brain-computer interface (BCI) establishes a connection path between the brain and the computer, allowing the conversion of electroencephalogram (EEG) signals into peripheral control signals. BCIs record electrical brain activity through electrodes placed on the surface of the scalp or inside the skull. The signal exhibits high temporal and spatial resolution. In recent years, moving images (MI) as important EEG signals have been extensively studied. A typical MI task is to record and analyze EEG signals. These signals come from the hypothetical movement of specific body parts of the participants. MI has been widely used in various fields such as entertainment, medical, military and autonomous driving. [0003...

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): G06K9/62G06N3/04G06N3/08
CPCG06N3/084G06N3/047G06N3/048G06N3/045G06N3/044G06F18/2134G06F18/214G06F18/2415
Inventor 谢佳欣郜东瑞张家璇张倩倩
Owner 四川省博瑞恩科技有限公司
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
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap