Unlock instant, AI-driven research and patent intelligence for your innovation.

LSTM and BP-based motor imagery electroencephalogram signal classification method

A technology of EEG signal and classification method, applied in the field of BCI research, can solve the problem of low classification accuracy, and achieve the effect of improving classification accuracy, extraction accuracy and high accuracy.

Pending Publication Date: 2022-03-04
JIANGSU UNIV OF SCI & TECH
View PDF10 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, the classification accuracy of motor imagery EEG signals is low. Therefore, it is particularly important to study how to accurately classify EEG signals through algorithms.

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
  • LSTM and BP-based motor imagery electroencephalogram signal classification method
  • LSTM and BP-based motor imagery electroencephalogram signal classification method
  • LSTM and BP-based motor imagery electroencephalogram signal classification method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] Embodiments of the present invention will be disclosed in the drawings below, and for the sake of clarity, many practical details will be described together in the following description. It should be understood, however, that these practical details should not be used to limit the invention. That is, in some embodiments of the invention, these practical details are unnecessary.

[0039] like Figure 1-2 As shown, the present invention is a classification method of motor imagery EEG signals based on LSTM and BP, including the following steps:

[0040] Step 1: Data preprocessing: Data preprocessing is performed on the original EEG signal to reduce interference and improve the signal-to-noise ratio, thereby improving the accuracy of feature extraction.

[0041] The data preprocessing is as follows: use FIR band-pass filter to perform band-pass filtering of 4-30 Hz on the initial data, select 4-30 Hz for the pass-band cut-off frequency, and select 3 Hz and 31 Hz for the s...

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 relates to a motor imagery electroencephalogram signal classification method based on LSTM and BP. The method comprises the following steps of 1, preprocessing data; 2, performing normalization processing on the data obtained in the step 1; step 3, feature extraction is automatically carried out by using the improved LSTM module; 4, the features extracted in the LSTM module in the step 3 are transmitted to a BP neural network classifier, and a classification result is obtained; and 5, performing parameter optimization by adopting a gradient descent method. According to the method, firstly, the improved LSTM module is used for carrying out feature extraction on the preprocessed data, then the BP neural network classifier is used for classifying the extracted features, finally, parameter optimization is carried out to reach the highest accurate value, and the accuracy of feature classification of the electroencephalogram signals is improved.

Description

technical field [0001] The invention relates to feature extraction and classification of electroencephalographic signals of motor imagery, belongs to the field of BCI research, and in particular relates to a method based on a long short-term memory (LSTM) model combined with a BP neural network. Background technique [0002] The brain is the central nervous system that controls human activities. However, in modern society, more and more diseases are threatening the health of the brain and the neurospinal cord, making the human brain unable to interact with the outside world normally. For example, cerebral palsy, brain stem stroke, amyotrophy, amyotrophic lateral sclerosis (ALS), epilepsy, etc., these diseases are collectively referred to as "locked in syndrome". [0003] With the continuous deepening of human research on the brain and the rapid development of computer science and information processing technology, with the original intention of enhancing the ability of patie...

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): A61B5/372A61B5/00
CPCA61B5/372A61B5/7264A61B5/7267A61B5/725
Inventor 郑威程怡
Owner JIANGSU UNIV OF SCI & TECH