A method for EEG classification based on frequency-band attention residual network

A classification method and attention technology, applied in biological neural network models, medical science, diagnosis, etc., can solve problems such as lack of flexibility, and achieve the effect of obtaining flexibility

Active Publication Date: 2021-08-06
BEIJING UNIV OF TECH
View PDF21 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the feature combination patterns obtained by these methods are mostly fixed and lack flexibility.

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 method for EEG classification based on frequency-band attention residual network
  • A method for EEG classification based on frequency-band attention residual network
  • A method for EEG classification based on frequency-band attention residual network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0016] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments.

[0017] The flow process of the method involved in the present invention comprises the following steps:

[0018] (1) EEG signal preprocessing.

[0019] Use EEGLab to perform baseline removal, band-pass filtering, independent component analysis and artifact removal operations on the original N-lead EEG signals with a total duration of T seconds and a sampling frequency of M. The range of band-pass filtering is between 0.5 Hz and 47 Hz. between.

[0020] (2) EEG signal segmentation.

[0021] Use a sliding window with a segment length of W seconds to segment the N-lead EEG signals processed in (1), there is no overlap between segments, and a total of S data segments are obtained, and each data segment has a dimension of A two-dimensional matrix of N*(W*M), where S is the result of dividing the original data duration T by the sliding window segme...

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

An EEG classification method based on frequency-band attention residual network belongs to the field of pattern recognition and bioinformatics. First, preprocess the original EEG signal to remove noise and artifacts in the signal; then, use a fixed-length sliding window to segment the preprocessed N-lead EEG signal to obtain a total of S-segment N-lead sub-signals ; Then use the wavelet packet decomposition to decompose and reconstruct the S segment N derivation sub-signals, each sub-band signal of each data segment is decomposed into F sub-band signals; after that, the multi-conductor decomposition results of each frequency band are converted into electrode correlation matrix; and then use the electrode correlation matrix of F frequency bands as the input of the frequency band attention residual network to complete the classification of EEG signals. Compared with the existing technology, the present invention has the advantages that the frequency band attention module is used to obtain frequency band importance weights, and a personalized frequency band attention distribution is given to each sample.

Description

technical field [0001] The invention relates to EEG signal processing technology, the field of deep learning and the field of bioinformatics. Background technique [0002] With the vigorous development of the field of machine learning, a large number of classification models have been proposed and optimized. Traditional classification models include methods such as Random Forest (RF), K-Nearest Neighbors (KNN), Logistic Regression (LR), and Linear Discriminant Analysis (LDA). In recent years, due to the significant improvement in the computing power of devices, more and more deep learning methods have also been applied to EEG classification problems. In the EEG classification problem, the change of category prediction accuracy is inseparable from the selection of classification model, and the decrease of false detection rate depends on the optimization of the model. At present, a large number of EEG classification algorithms have been proposed. These methods start from dif...

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): A61B5/369A61B5/00G06N3/04
Inventor 段立娟肖莹徐凡乔元华陈军成苗军
Owner BEIJING UNIV OF TECH
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