Electroencephalogram feature selecting and classifying method based on combined differential evaluation

A feature selection method, a technology of EEG signals, applied in the input/output of user/computer interaction, instrument, character and pattern recognition, etc., can solve the problems of inefficiency, tedious work of spatial filter coefficients and feature vectors, etc.

Inactive Publication Date: 2014-08-20
CENT SOUTH UNIV
View PDF2 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The present invention proposes a method for feature selection and classification of EEG signals based on combined differential evolution, using the outstanding performance of combined differential evolution algorithm in terms of global search ability and fast convergence, to quickly find the best spatial filter coefficients and feature vectors, and ov

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 feature selecting and classifying method based on combined differential evaluation
  • Electroencephalogram feature selecting and classifying method based on combined differential evaluation
  • Electroencephalogram feature selecting and classifying method based on combined differential evaluation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0041] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0042] A method for feature selection of EEG signals based on combined differential evolution, comprising the following steps:

[0043] Step 1: Select EEG signal sample data X t×c , and preprocess the EEG signal sample data to obtain training samples X is a t×c matrix, X FFT is a matrix of m×c, t is the number of data collected by each electrode, m is the number of eigenvalues ​​of each lead in a T time period, and c is the number of leads of the EEG signal;

[0044] Step 2: Set the coloring individual and fitness function, set the policy knowledge base, iteration stop condition and coloring individual population, and initialize the parameters of the coloring individual and the number of iterations;

[0045] spatial filter and feature selector As a chromatic individual [S, K], the encoding of S is a real number, and K is encoded by 0 and 1;

[...

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 an electroencephalogram feature selecting and classifying method based on combined differential evaluation. Due to the fact that a combined differential evaluation algorithm has the advantages in the global searching ability and the rapid convergence aspect, the combined differential evaluation algorithm is utilized to rapidly find out the optimal spatial filtering coefficients and feature vectors. Thus, the problem of complex and low-efficiency work of relying on manual work to decide spatial filtering coefficients and feature vectors in the prior art is solved, and a classifier is trained according to the searched optimal spatial filtering coefficients and feature vectors to classify electroencephalogram to improve the recognition rate of electroencephalogram. In addition, the purpose of recognizing electroencephalogram automatically is achieved, the labor intensity is reduced, and the processing efficiency of electroencephalogram is greatly improved.

Description

technical field [0001] The invention relates to a method for feature selection and classification of electroencephalogram signals based on combined differential evolution. Background technique [0002] The brain-computer interface system is a system that reads the brain's neural activity through sensors, uses computers to process and decode it online, and realizes the control of external devices. The brain-computer interface system mainly includes three main parts: data acquisition, signal processing, and application programs. Among them, the data acquisition module mainly obtains EEG signals from the head of the subject through electrodes and EEG amplifiers. The EEG amplifiers amplify the EEG signals obtained on the electrodes and convert analog-to-digital signals into digital signals, and then send them to Signal processing module processing. The signal processing module first needs to preprocess the signal, including denoising, data alignment, spatial filtering, etc. T...

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): G06K9/62G06F3/01
Inventor 谭平谭冠政王勇蔡自兴
Owner CENT SOUTH UNIV
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