Emotion trans-individual identification method based on tranquillization electroencephalography similarity

A recognition method and similarity technology, applied in medical science, psychological devices, sensors, etc., can solve problems such as the decline of recognition rate, and achieve the effect of solving the problem of low correct rate

Inactive Publication Date: 2017-12-01
TIANJIN UNIV
View PDF7 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Since the recognition model is only established by the EEG information from the subjects themselves, it is an individual-specific recognition model. When the model is used for the subjects themselves, it will achieve a good prediction effect. Once it is used to predict the emotions of other users, the recognition rate will increase. will drop significantly

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
  • Emotion trans-individual identification method based on tranquillization electroencephalography similarity
  • Emotion trans-individual identification method based on tranquillization electroencephalography similarity
  • Emotion trans-individual identification method based on tranquillization electroencephalography similarity

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0025] An embodiment of the present invention provides a method for recognizing EEG across time based on resting EEG similarity, see figure 1 , the method includes the following steps:

[0026] 101: Establish a multi-individual emotional database, including the resting EEG and emotional EEG of n subjects, and use autoregressive (autoregressive, AR) [1] The model extracts the power spectral density of four EEG frequency bands (theta, alpha, beta, gamma frequency bands) to form a resting EEG feature matrix and an emotional EEG feature matrix;

[0027] The steps of forming the resting EEG feature matrix and the emotional EEG feature matrix through the power spectral densities of the four frequency bands of the EEG are well known to those skilled in the art, and will not be described in detail in this embodiment of the present invention.

[0028] 102: Record the resting EEG of the subject to be detected, calculate the Euclidean distance between it and the resting EEG feature matr...

Embodiment 2

[0036] Combine below figure 2 , calculation formula, and example are further introduced to the scheme in embodiment 1, see the following description for details:

[0037] 201: Establish a multi-individual emotion database;

[0038] Firstly, the resting EEG and emotional EEG of n users are collected, and multiple individual emotion databases are established. The EEG acquisition device is Neuroscan’s 64-lead amplifier and Scan4.5 acquisition system. The electrodes are placed in accordance with the standard 10-20 system stipulated by the International Association of EEG. Such as figure 2 shown. The right mastoid was used as a reference electrode during collection, and the center of the top side of the forehead was grounded. The impedance of all electrodes was kept below 5k ohms, and the sampling frequency was 1 000 Hz. Before the start of the experiment, the subject’s resting EEG was collected for 2 minutes, and then the video was used to induce three emotional states of th...

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 an emotion trans-individual identification method based on tranquillization electroencephalography similarity. The emotion trans-individual identification method comprises the following steps that a multi-individual emotion database is established, each individual emotion database comprises n tested tranquillization electroencephalography and emotion electroencephalography, power spectral densities of the electroencephalography at four frequency bands are extracted through an AR model, and tranquillization electroencephalography characteristic matrixes and emotion electroencephalography characteristic matrixes are formed; the tested tranquillization electroencephalography needing to be detected is recorded, euclidean distances of the tested tranquillization electroencephalography needing to be detected and n tested tranquillization electroencephalography characteristic matrixes in the emotion database are correspondingly calculated, and smallest-distance 0.2*n subjects are selected to be used as user groups of emotion identification model training sets; and an emotion detecting model is established by using the emotion electroencephalography characteristic matrixes of the user groups, so that trans-individual emotion electroencephalography identification is accurately and objectively conducted. By means of the emotion trans-individual identification method based on the tranquillization electroencephalography similarity, the bottleneck problem that in current emotion identification, the accuracy of trans-individual identification is low can be effectively solved, the model is pushed into application, and considerable social and economic benefits are obtained.

Description

technical field [0001] The present invention relates to the field of emotion recognition based on EEG, in particular to a method for recognizing emotions across individuals based on resting EEG similarity, which can be used for auxiliary diagnosis and curative effect evaluation of emotional disorders, especially for special workers (such as astronauts, Driver) emotion recognition and feedback, entertainment games, human-computer interaction in distance learning. Background technique [0002] Emotion is a comprehensive state produced by people whether objective things meet their own needs. As a high-level function of the human brain, it ensures the survival and adaptation of organisms, and affects human learning, memory and decision-making to varying degrees. In people's daily work and life, the role of emotion is everywhere. Negative emotions can affect our physical and mental health, reduce work quality and efficiency, and in severe cases can cause mental illness (such as...

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): A61B5/0476A61B5/16A61B5/18
CPCA61B5/165A61B5/7203A61B5/7235A61B5/725A61B2503/22A61B5/316A61B5/369
Inventor 刘爽明东郭冬月柯余峰仝晶晶杨佳佳许敏鹏何峰
Owner TIANJIN UNIV
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap