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

Electroencephalogram signal recognition model construction method and device and electroencephalogram signal recognition method and device

A technology for EEG signal and model recognition, applied in signal pattern recognition, character and pattern recognition, instruments, etc., can solve problems such as weak EEG features, achieve effective operation effect, improve real-time performance, and meet the needs of daily actions Effect

Active Publication Date: 2019-11-19
ZHENGZHOU UNIV
View PDF12 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the EEG features in the exercise preparation stage are weak, how to accurately identify the exercise idle state and the exercise readiness state is still a difficult problem

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 recognition model construction method and device and electroencephalogram signal recognition method and device
  • Electroencephalogram signal recognition model construction method and device and electroencephalogram signal recognition method and device
  • Electroencephalogram signal recognition model construction method and device and electroencephalogram signal recognition method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0043] Such as figure 1 As shown, this embodiment provides a method for building a recognition model of EEG signals. First, the EEG signals and EMG signals during the movement are collected, and the EEG signals are filtered; the start time of the EEG signals is determined. The movement start moment of the EEG signal is determined according to the movement start moment of the EMG signal, and in this embodiment, the movement start moment of the EEG signal is the same as the movement start moment of the EMG signal.

[0044] Select the EEG signal corresponding to the first set time period before the start of the movement of the EEG signal as the exercise idle state data, and select the EEG signal corresponding to the second set time period before the start of the movement of the EEG signal as exercise readiness data.

[0045] Sampling the motion idle state data and the motion readiness state data respectively to obtain the eigenvalues ​​of the motion idle state data and the motio...

Embodiment 2

[0062] This embodiment provides a device for constructing an EEG signal recognition model in Embodiment 1, including an EEG collector for collecting EEG signals, an EMG collector for collecting EMG signals, a memory, a processor, and The computer program is stored in the memory and can run on the processor, and the processor is connected with the EEG collector, the myoelectric collector and the memory. The method for constructing the EEG signal recognition model described in Embodiment 1 is implemented when the processor executes the computer program.

Embodiment 3

[0064] This embodiment provides an EEG signal recognition method based on the recognition model in Embodiment 1. After the recognition model is obtained, the real-time EEG signal is collected, and then the real-time EEG signal is processed, and the motion idle state of the real-time EEG signal The eigenvalues ​​of the data and the eigenvalues ​​of the exercise readiness data are input into the recognition model, and the real-time EEG signal is judged according to the output of the recognition model whether it is in the exercise idle state or in the exercise readiness state.

[0065] In this embodiment, the recognition model is y=w T x, 10 subjects were tested according to the above method, and the eigenvalue matrix x of the 10 subjects was obtained first, which were respectively substituted into the recognition model, and the exercise preparation of each subject was carried out according to the obtained output value y. Recognition, for example, if the output value y is -1, it ...

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 provides an electroencephalogram signal recognition model construction method and device and an electroencephalogram signal recognition method and device. The method comprises the following steps: firstly, determining the movement starting moment of an electroencephalogram signal through an electromyogram signal; determining a motion idle state and a motion preparation state in a time period before a starting moment, performing feature extraction on the motion idle state and the motion preparation state respectively, acquiring an identification model by adopting a linear discriminant mode, and inputting the electroencephalogram signals acquired in real time into the identification model so as to judge the current motion state. The movement intention of a person with mobilitydifficulties can be detected in time; compared with a brain-computer interface system based on motor imagery, the brain-computer interface system based on motor imagery has the advantages that the action intention can be acquired in advance, the real-time performance of the system is improved, and a better experience effect is provided for people with mobility difficulties.

Description

technical field [0001] The invention relates to the field of electroencephalogram signal processing, in particular to a method and device for constructing a recognition model of electroencephalogram signals, and a recognition method and device. Background technique [0002] The Brain-Computer Interface (BCI) system is a direct communication path between the brain and external devices that does not rely on peripheral neural circuits. Currently, the commonly used BCI system is mainly based on three types of EEG signals, namely Steady-State Visual Evoked Potential (SSVEP), P300 potential and motor imagery. Steady-state visual evoked potentials and P300 potentials belong to visual evoked potentials, which have high recognition rate and information transmission rate, so they are often used in brain-computer interface systems for character input. Motor imagery belongs to spontaneous EEG and does not depend on the stimulation of peripheral devices. It is often used to control peri...

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
CPCG06F2218/02G06F2218/08
Inventor 胡玉霞张利朋张锐申通达苏筱雅师丽高金峰
Owner ZHENGZHOU UNIV