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

Electroencephalogram preprocessing method based on independent component analysis algorithm

An independent component analysis and EEG signal technology, which is applied in the direction of diagnostic signal processing, medical science, diagnosis, etc., can solve problems affecting the analysis of EEG signals

Inactive Publication Date: 2017-11-24
NANJING UNIV OF SCI & TECH
View PDF6 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, due to the interference of ECG signals, eye movement artifact signals, EMG signals and noise signals generated by other interference sources, EEG signals are doped with many invalid signals, which will affect the analysis of effective EEG signals, so it is necessary to preprocess it

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
  • Electroencephalogram preprocessing method based on independent component analysis algorithm
  • Electroencephalogram preprocessing method based on independent component analysis algorithm
  • Electroencephalogram preprocessing method based on independent component analysis algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0025] Such as figure 1 As shown, a method for preprocessing EEG signals based on independent component analysis of the present invention includes the following steps.

[0026] 1) Collect the user's multi-lead EEG signal;

[0027] 2) Independent component analysis is performed on the multi-lead signal to obtain the unmixing matrix and independent components;

[0028] 3) Remove the independent component of super-Gaussian noise by analyzing the kurtosis of the independent component;

[0029] 4) Analyze the unmixing matrix by the clustering method and the minimum variance method, and remove the independent components of the electrical reference;

[0030] 5) Signal restoration to obtain preprocessed EEG signals.

[0031] In an example of the present invention, Matlab is used to read the collected multi-lead EEG signals, which are sixteen-lead EEG signals with a sampling frequency of 500 Hz. The negative entropy decision criterion is adopted, the maximum negative entropy is tak...

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 provides an electroencephalogram preprocessing method based on an independent component analysis algorithm; the method comprises the steps of acquiring multi-lead electroencephalogram of a user; subjecting the multi-lead electroencephalogram to independent component analysis to obtain a demixing matrix and independent components; subjecting the independent components to kurtosis analysis to remove Super-Gaussian noise independent components; analyzing the demixing matrix through a clustering method and a minimum variance method to remove electrical reference independent components; restoring the electroencephalogram to obtain the preprocessed electroencephalogram. The method of the invention has the advantage that electroencephalogram preprocessing efficiency and accuracy are effectively improved.

Description

technical field [0001] The invention relates to an EEG signal preprocessing method, in particular to an EEG signal preprocessing method based on an independent component analysis algorithm. Background technique [0002] Modern medical research shows that when the human brain is working, a large number of neurons will synchronously generate post-synaptic potentials, thereby generating spontaneous electrophysiological activities. In modern medicine, a brain wave measuring instrument is usually used to measure the electrical signals of the electrophysiological activities of nerve cells in the cerebral cortex. Clinical practice has proved that EEG signals contain a large amount of physiological and disease information, which can effectively reveal the state of the human brain and mental activity. [0003] However, due to the interference of ECG signals, eye movement artifact signals, EMG signals and noise signals generated by other interference sources, EEG signals are doped wi...

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
IPC IPC(8): A61B5/0476
CPCA61B5/72A61B5/7203A61B5/369
Inventor 王子洵伏长虹
Owner NANJING UNIV OF SCI & TECH