A Classification Method of Elm Motor Imagery EEG Based on AR Coefficient Space
A technology of motion imagery and classification method, applied in the direction of instruments, character and pattern recognition, computer parts, etc., can solve the problem of taking up a lot of time, and achieve the effect of high stability, good generalization performance and fast learning speed
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0040] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.
[0041] like figure 1 As shown, the present embodiment provides an ELM motor imagery EEG classification method based on the AR coefficient space, which specifically includes the following steps:
[0042] Step S1: Use the p-order AR model to fit single-channel motor imagery EEG signals, using the formula Represents; where, x(n) represents the nth sampling value of the signal, p is the order of the AR model, a k is the AR coefficient of the AR model, k=1,2,...,p, s(n) is the mean value is zero, and the variance is σ 2 The white noise residual;
[0043] Step S2: Use the Burg algorithm to determine the undetermined coefficient a of the AR model described in step S1 1 ,a 2 ,...,a p , to solve;
[0044] Step S3: Connect the p-order AR coefficients of the motor imagery EEG signals of the m channels into a row vector, as follows: a i =[a i1 ,a i2 ,a i3...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
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