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

A feature extraction method of motor imagery EEG signals

A technology of EEG signal and motor imagery, which is applied in the extraction of motor imagery EEG signal features, and in the field of feature extraction of motor imagery EEG signals, can solve the problem of low classification accuracy, limited application, and no consideration of individual differences in subjects Frequency characteristics of sexual EEG signals and other issues, to achieve the effect of improving classification accuracy and classification accuracy

Active Publication Date: 2018-03-16
BEIJING UNIV OF TECH
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the CSP algorithm has two shortcomings: first, the CSP algorithm has a significant effect on the EEG signals of a large number of electrodes, which limits its application in portable BCI systems; second, when performing motor imagery tasks, each subject The frequency bands in which ERS / ERD occurs have individual differences, and the CSP algorithm does not consider the individual differences of subjects and the frequency characteristics of EEG signals when extracting EEG features, which will result in low classification accuracy

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 feature extraction method of motor imagery EEG signals
  • A feature extraction method of motor imagery EEG signals
  • A feature extraction method of motor imagery EEG signals

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0065] This embodiment is carried out under the simulation environment of Matlab2014a.

[0066] The examples use Data Set I data from BCI Competition III. Such as image 3 As shown, the Data Set I data of BCICompetition III was collected by an 8×8 (total 64 leads) electrode array implanted in the right motor cortex of the brain. The experiment performed two motor imagery tasks of imagining the left little finger and imagining the tongue. The sampling frequency of the signal is 1000Hz, and it is band-pass filtered from 0.016-300Hz.

[0067] The experimental timing diagram is as follows Figure 4 As shown, each experiment lasted 7 s. At 0-1s, a cross cursor appears on the screen; at 1-5s, a prompt picture appears on the screen to remind the tester to imagine the movement of the left little finger or tongue; 5-7s the screen is in a blank state, and the subject rests; then proceed to the next experiment . The Data Set I data set has a total of 3000 sampling points between 1.5...

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 characteristic extraction method of motor imagery electroencephalogram signals. According to the method, firstly, the collected electroencephalogram signals are preprocessed, then EMD is performed on all leads of signals to obtain multi-order IMF signals, then the IMF signals which are identical in number of orders are selected as new signals, a spatial filter is obtained through a CSP algorithm, characteristics of the electroencephalogram signals are extracted and input into a classifier for classification, the optimal value of parameters in the EMD and CSP is selected according to the classification accuracy rate, and finally the electroencephalogram characteristics under the optimal parameter are obtained. Based on the EMD and CSP, characteristic extraction is performed on the motor imagery electroencephalogram signals, the signals can be decomposed into the multiple IMF signals in a self-adaptation mode according to characteristics of the electroencephalogram signals of different persons, characteristic extraction can be performed on the electroencephalogram signals only by few electrodes, and the classification accuracy rate of the electroencephalogram signals is increased to a greater degree.

Description

technical field [0001] The invention belongs to the technical field of EEG signal processing, in particular to a method for extracting features of motor imagery EEG signals in a Brain-Computer Interface (Brain-Computer Interface, BCI) system. Feature extraction of motor imagery EEG signals. Background technique [0002] Aging of the population and traffic accidents have caused a large number of patients with spinal cord lesions or injuries. The action commands of their brains cannot be transmitted to the muscles through normal internal pathways, thus losing the ability to move their limbs. Due to the advancement of modern medicine, these patients can continue to live in wheelchairs and beds for a long time, but they lose the ability to work and find it difficult to take care of themselves. This not only causes great pain for the patients, but also brings burdens to their families and society. [0003] BCI establishes a communication and control channel between human and com...

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): G06K9/62G06F3/01
Inventor 李明爱郭硕达田晓霞杨金福罗新勇张梦徐金凤
Owner BEIJING UNIV OF TECH