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

A Classification Method of ERP Signal Based on Sparse Discriminant of Optimal Score

A signal classification and sparse technology, applied in the field of biomedical signal processing, can solve the problem of low accuracy rate of EEG ERP signal classification, and achieve the effect of improving the classification accuracy rate

Active Publication Date: 2019-02-05
SHANDONG UNIV
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Aiming at the problem that the traditional method has a low accuracy rate of ERP signal classification in the case of a small sample training set, the present invention proposes a sparse discriminant classification method based on the optimal score

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
  • A Classification Method of ERP Signal Based on Sparse Discriminant of Optimal Score
  • A Classification Method of ERP Signal Based on Sparse Discriminant of Optimal Score

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0025] Such as figure 1 As shown, the EEG ERP signal recognition algorithm based on sparse discriminant analysis of the present invention specifically includes the following steps:

[0026] (1) Collect EEG signals, use BCI2000 to collect 64-lead signals, the sampling rate is 240Hz, and the cutoff frequency of the bandpass filter is 0.1Hz and 60Hz;

[0027] (2) Extract the EEG signal corresponding to the flicker, and select 16 leads, use a 0 phase shift filter for filtering, and downsample the filtered signal to 28 Hz to obtain a data matrix, reconstruct the obtained data matrix, The 12 flashes of the characters are rearranged in the order of 1-6 rows and 1-6 columns to obtain a new data matrix X, X is an N×d matrix, N represents the number of samples, and d represents the number of features;

[0028] (3) Divide the data matrix X into training data X train And test data X test Two sets, using training data X train Calculate the projection vector w c , The length is d, c=1, 2, 3...l ...

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 method for classifying ERP signals of brain electricity under a small sample data set by using sparse discriminant analysis based on the optimal score. This method uses the preprocessed data, obtains the objective function of sparse discriminant analysis through the optimal score and the l1 penalty term, solves the optimization problem through an alternate iterative algorithm, obtains the feature projection vector, and uses the projection vector to map the data to the sparse discriminant subspace Classify votes. The present invention uses the method of sparse discriminant analysis based on the optimal score to solve the feature projection vector through an alternate iterative algorithm, and finally improves the classification accuracy rate of ERP signals in a small-sample training set.

Description

Technical field [0001] The invention relates to an EEG ERP signal classification method under a small sample training set, and belongs to the field of biomedical signal processing. Background technique [0002] EEG signals are a reflection of the electrical activity of brain tissues and the functional state of the brain. Various forms of thinking and external stimuli will cause different EEG signals. As a way of expressing information, EEG signals have made more and more researchers actively explore how to use EEG signals as a tool for communication between humans and machines. [0003] The extraction and classification of EEG signals has important value in the field of brain-computer interface and medicine, and has many potential applications. In terms of brain-computer interface, the computer can recognize different EEG signals (event-related potential ERP, etc.) to control the machine and express information. For example, highly disabled people can control wheelchairs through E...

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 Patents(China)
IPC IPC(8): G06K9/00
CPCG06F2218/02G06F2218/12
Inventor 吴强辛雨航刘琚王朔
Owner SHANDONG UNIV