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

Electroencephalogram signal classification method and system

A technology of EEG signal and classification method, which is applied in pattern recognition in signal, instrument, character and pattern recognition, etc. It can solve the problems of wavelet transform resolution reduction, poor variance performance, and low resolution, so as to improve accuracy , the effect of improving classification efficiency

Inactive Publication Date: 2020-04-10
SICHUAN UNIV
View PDF3 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The frequency domain method is to convert the brain wave that changes with time into a spectrogram of brain power that changes with frequency. The traditional frequency domain method calculates the power spectrum in the form of a window function. Although it has certain calculation advantages, its variance performance Poor and low resolution
The wavelet transform in the time-frequency domain can decompose the signal locally, which has good locality, but the resolution of the wavelet transform decreases as the frequency increases, and it also has certain defects.

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 signal classification method and system
  • Electroencephalogram signal classification method and system
  • Electroencephalogram signal classification method and system

Examples

Experimental program
Comparison scheme
Effect test

experiment example

[0082] In this method, the fuzzy entropy (FE) is used as the eigenvalue, and the Laplacian eigenmap is used to reduce the dimensionality (LE). Finally, the support vector machine based on genetic algorithm (GA-SVM) is used to classify EEG signals. A total of 36 sets of experiments were performed by comparing with other features and classification methods.

[0083] The extracted features include wavelet packet entropy (WPE), permutation entropy (PE), and fuzzy entropy (FE).

[0084] Dimensionality reduction methods used include principal component analysis (PCA), Laplacian eigenmap dimensionality reduction (LE), and local tangent space alignment (LTSA).

[0085] The classifiers used include Random Forest (RF), Naive Bayes (NB), K-Nearest Neighbors (KNN) and Support Vector Machines (SVM).

[0086] The effects of different combinations of the above features, dimensionality reduction methods, and classifiers on data classification are as follows: figure 2 and shown in Table 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 an electroencephalogram signal classification method and system. The method comprises the following steps: preprocessing an obtained electroencephalogram signal; extracting anonlinear fuzzy entropy from the preprocessed electroencephalogram signal as a feature of the electroencephalogram signal; performing dimension reduction processing on the extracted nonlinear fuzzy entropy; and inputting the nonlinear fuzzy entropy subjected to dimension reduction processing into a pre-trained classification model, and outputting to obtain a classification result. Electroencephalogram signals are classified through the method or system, the classification efficiency can be improved, and the accuracy of the classification result can also be improved.

Description

technical field [0001] The invention relates to the technical field of physiological information detection, in particular to a method and system for classifying electroencephalogram signals. Background technique [0002] EEG signals can be used to reflect certain physiological and psychological states, so analyzing EEG signals is an important means for early detection of brain diseases. However, due to its complexity as a neurophysiological signal, and the EEG signal is a random non-stationary signal, it is difficult to obtain the characteristics related to physiological and psychological states by conventional signal analysis methods. For example, in the detection of cover-up behavior in the process of psychological problems, since the testee’s cover-up behavior and normal cognitive activities occur simultaneously during the entire test process, it is a complicated process, so the conventional time domain, Frequency domain, time-frequency domain methods cannot classify EEG...

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
CPCG06F2218/02G06F2218/08G06F2218/12
Inventor 郑秀娟瞿智豪赵童杨晓梅刘凯
Owner SICHUAN UNIV