Human body emotion recognizing method based on real-time electroencephalography

An emotion recognition and EEG technology, applied in medical science, psychological devices, sensors, etc., can solve the problems of inability to comprehensively, effectively and accurately identify EEG signals, unable to meet the needs of work and life, and complex EEG signals. The method is simple, improve work efficiency, and identify comprehensive and accurate effects

Inactive Publication Date: 2019-02-15
蓝色传感(北京)科技有限公司
View PDF10 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The above-mentioned patent documents disclose a system and method for identifying EEG features, but the method for this system is complex in collecting EEG signals, the cost is high, and it cannot comprehensively, effectively and accurately identify EEG signals, and cannot meet the needs of modern work and life.

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
  • Human body emotion recognizing method based on real-time electroencephalography
  • Human body emotion recognizing method based on real-time electroencephalography
  • Human body emotion recognizing method based on real-time electroencephalography

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0043] see figure 1 , the human emotion recognition method based on real-time EEG, comprising the following steps:

[0044] Step 1) EEG signal acquisition S1: including collecting the subject's EEG signal by using a multi-channel EEG acquisition device;

[0045] Step 2) EEG signal preprocessing S2: Preprocessing the EEG signal obtained in step 1 to reduce trail interference and improve the final classification recognition rate;

[0046] Step 3) extracting S3 features of the EEG signal sample;

[0047] Step 4) classification S4 of EEG signals;

[0048] Step 5) Carry out emotion recognition S5.

[0049] Said step 3) extracting the features of the EEG samples includes extracting the features of the EEG samples through the sample entropy algorithm; said sample entropy algorithm is specifically obtained by the following algorithm formula:

[0050] Let the original data be a time series of length N, expressed as: {u(i):1≤i≤N};

[0051] 3) Construct a set of vectors X(1), X(2),......

Embodiment 2

[0067] The difference with the foregoing embodiment is that in this embodiment, the step 3) extracting the feature of the EEG signal sample also includes extracting the feature of the EEG signal sample through the binary distance matrix sample entropy algorithm; The distance matrix sample entropy algorithm is specifically obtained through the following algorithm formula:

[0068] Step 1: For the N-point sequence, first calculate the N×N binary distance matrix D=[d ij ] N×N .

[0069]

[0070] In the second step, using the elements in the matrix D, according to the increasing order of rows, the matrix elements of every two rows (when m=2) or every three rows (when m=3) are combined according to the direction of the oblique line "and " operation, add up the result of the slash "AND" of each line and divide it by N-(m+1), you can get and

[0071] Such as figure 2 Shown:

[0072]

[0073]

[0074] For example, when m=2, we need to judge whether d[X(2), X(4)24 *d...

Embodiment 3

[0078] see figure 1 , the difference from the above-mentioned embodiment is that in this embodiment, the step 4) classifying the EEG signals includes a support vector machine classification method and a genetic algorithm classification method.

[0079] The support vector machine is a new machine learning method developed by Vapnik on the basis of statistical learning theory. It is based on the principle of structural risk minimization, which ensures that the learning machine has good generalization ability. , high-dimensional, nonlinear, local minimum and other problems are better. The least squares support vector machine is a new type of support vector machine proposed by Suykens et al. It incorporates the least squares linear method into the support vector machine, and transforms the quadratic programming problem in the standard support vector machine into Linear equations are solved, thus simplifying the computational complexity.

[0080] The genetic algorithm classifies ...

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 human body emotion recognizing method based on real-time electroencephalography. The method comprises the following steps of 1, collecting electroencephalogram signals, wherein multi-channel electroencephalogram collecting equipment is adopted for collecting tested electroencephalogram signals; 2, preprocessing the electroencephalogram signals, wherein the electroencephalogram signals obtained in step 1 are compared to be preprocessed so that wake interference can be reduced, and the final classification recognition rate is increased; 3, extracting electroencephalogram signal sample characteristics; 4, classifying the electroencephalogram signals; 5 performing emotion recognition. The human body emotion recognizing method based on real-time electroencephalographyis simple in electroencephalogram signal collection, high in intelligent degree and capable of comprehensively, accurately and effectively recognizing the electroencephalogram signals.

Description

technical field [0001] The invention relates to the technical field of EEG signal feature classification in the field of biological feature recognition, in particular to a real-time EEG-based human emotion recognition method. Background technique [0002] Emotions can reflect a person's cognition and attitude, can affect people's psychology and behavior, and are an important part of people's daily life. With the rapid development of human-computer interaction applications, people hope to have more humanized computers to assist people in completing work tasks, which requires computers to have certain emotion recognition capabilities. In the process of human-computer interaction, if the computer can quickly and accurately identify the emotional state of the person, it can adjust its work content and methods according to the emotional state of the person, improve the experience of human-computer interaction, and make the process of human-computer interaction more efficient. Fr...

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): A61B5/16A61B5/0476
CPCA61B5/165A61B5/7203A61B5/7267A61B5/369
Inventor 黄涌李妮蔚陈衍行
Owner 蓝色传感(北京)科技有限公司
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