Motion imagery electroencephalograph classification method based on multilayer extreme learning machine

An ultra-limited learning machine and EEG technology, which is applied in the field of motor imagery EEG signal classification to achieve the effect of low time consumption and improved classification accuracy.

Inactive Publication Date: 2017-03-08
BEIJING UNIV OF TECH
View PDF3 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, due to the limitation of its shallow structure,

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
  • Motion imagery electroencephalograph classification method based on multilayer extreme learning machine
  • Motion imagery electroencephalograph classification method based on multilayer extreme learning machine
  • Motion imagery electroencephalograph classification method based on multilayer extreme learning machine

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0017] The present invention will be further described below in conjunction with the drawings and specific embodiments.

[0018] Suppose there is a training data set TrainData and a set of test data set TestData. The sample size of TrainData is N and the dimension is D; the sample size of TestData is M and the dimension is also D. The samples in TrainData and TestData belong to K categories.

[0019] Classification method of motor imagery EEG signals based on multi-layer over-limit learning machine, the flowchart is as follows figure 1 Shown.

[0020] Step 1: Divide TrainData and TestData into S-segment brain electronic signals by means of fixed time window division. TrainData i Represents the i-th sub-signal in the training data set, and the dimension of each sub-signal is D i (i=1,2,...,S). TestData i Represents the i-th sub-signal in the test data set, and the dimension of each sub-signal is D i (i=1,2,...,S). Because of the fixed time window, the window size is fixed, so D 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 relates to a motion imagery electroencephalograph (EEG) classification method based on a multilayer extreme learning machine (ML-ELM), and the motion imagery EEG classification method belongs to the field of pattern identification and brain-computer interfaces (BCI). The classification and identification of EEG mainly comprise feature extraction and feature classification of the EEG. The motion imagery EEG classification method comprises the steps of: firstly, subjecting an original signal of each sample to windowing and segmentation to obtain S segments of sub-signals; secondly, performing principal component analysis and linear discriminant analysis on the S segments of sub-signals obtained through segmentation in the step 1 separately, and combining final S (K-1)-dimensional feature vectors to obtain features of S*(K-1) dimension; and finally, transmitting the features of the S* (K-1) dimension into an ML-ELM classifier, so as to obtain a final classification. Compared with the prior art, the motion imagery EEG classification method has the advantages that a traditional ELM algorithm is of a single-hidden layer structure and has great limitations in extracting features of complex signals, thus the motion imagery EEG classification method increases the number of hidden layers for extracting deep-layer information, thereby improving classification accuracy and maintaining the low time-consuming advantage of the ELM.

Description

technical field [0001] The invention belongs to the fields of pattern recognition and Brain-Computer Interface (Brain-Computer Interface, BCI), and relates to a method for classifying motor imagery EEG signals in a Brain-Computer Interface system device by using a multi-layer extreme learning machine. Background technique [0002] The human brain is a high-speed computing system that dominates and controls all human behaviors, thoughts, emotions and other high-level neural activities. How to effectively acquire and use brain information has always been a hot topic for researchers. Electroencephalogram (Electroencephalograph, EEG) is the discharge activity of brain neuron cells, which contains a large amount of information representing the physiological and psychological state of the human body, and is one of the important means to effectively obtain brain information. Brain-computer interface technology establishes a brand-new channel for transmitting information between th...

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): G06K9/00
CPCG06F2218/16
Inventor 段立娟鲍梦湖杨震苗军续艳慧郑黎玮
Owner BEIJING UNIV OF TECH
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