Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Common-spatial-pattern (CSP) spatial-domain feature extraction method based on quantized minimum error entropy (QMEE)

A technology of spatial patterns and extraction methods, applied in the field of signal processing, can solve problems such as weak robustness, reduced classification accuracy, and amplified negative effects of outliers

Active Publication Date: 2018-05-01
XI AN JIAOTONG UNIV
View PDF4 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The CSP algorithm can effectively obtain spatial filters, but because its cost function is based on L 2 Norm, which will amplify the negative impact of outliers, resulting in weak robustness and reduced 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
  • Common-spatial-pattern (CSP) spatial-domain feature extraction method based on quantized minimum error entropy (QMEE)
  • Common-spatial-pattern (CSP) spatial-domain feature extraction method based on quantized minimum error entropy (QMEE)
  • Common-spatial-pattern (CSP) spatial-domain feature extraction method based on quantized minimum error entropy (QMEE)

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0056] The present invention will be further described below in conjunction with the accompanying drawings.

[0057] The robust common spatial patterns (CSP) algorithm (CSP-QMEE) based on quantized minimum error entropy criterion (quantized minimum error entropycriterion, QMEE) of the present invention is divided into three parts, data preprocessing, feature extraction and classification , the specific introduction is as follows:

[0058] Suppose there are two types of EEG motor imagery data, represent a class, represents another class, c is the number of data channels, and l is the number of sampling points for each experiment. Assume that the two types of data have N y and N x trials, all EEG data can be expressed as and where n=l×N y , m=l×N x , is the total number of sample points of the two types of data. These motor imagery data need to be preprocessed, which is divided into three steps. Suppose an EEG data segment is First use a bandpass filter to filter...

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 a common-spatial-pattern (CSP) spatial-domain feature extraction method based on quantized minimum error entropy (QMEE). The QMEE is applied to improve a cost function of a traditional algorithm to enable the same to be robust for outliers, a better spatial-domain filter and better features can be obtained when the outliers occur, and then a good classification effect is obtained. The QMEE is an improvement on MEE, and can effectively solve the problem of a too high calculation cost of the MEE. Calculation of the MEE requires double summation, and time complexity is O(N2), and N is the number of samples, but complexity of the QMEE is O(MN), and M<<N. At the same time, the QMEE retains the advantages of the MEE, and has good robustness for nonlinear and non-Gaussiansignal processing and machine learning problems.

Description

technical field [0001] The invention belongs to the field of signal processing, and relates to a method for extracting common spatial pattern airspace features based on quantized minimum error entropy. Background technique [0002] Brain-computer interfaces have become an effective way to convert brain signals into specific instructions, helping severely paralyzed patients communicate with the outside world. EEG is a widely used brain signal with high temporal resolution, easy to use, and inexpensive equipment. An important issue for EEG-based BCI is how to accurately and robustly classify brain signals. [0003] In order to be able to extract effective separable features from EEG, many algorithms have been developed so far, among which the common spatial patterns algorithm (common spatial patterns, CSP) is a very effective method for processing two types of multi-channel data. . This method obtains multiple spatial domain filters to maximize the variance of the filtered ...

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): G06K9/00
CPCG06F2218/08G06F2218/12
Inventor 陈霸东董继尧李元昊郑南宁
Owner XI AN JIAOTONG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com