Emotion recognition method based on brain-computer cross-modal migration

An emotion recognition, cross-modal technology, applied in character and pattern recognition, neural learning methods, computer parts, etc. Costs, Effects of Enhanced Emotional Learning

Pending Publication Date: 2022-01-28
HANGZHOU DIANZI UNIV
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Using the powerful intelligent form of brain-computer collaboration can not only retain the advantages of the human brain and machines, but also solve the problems of the former’s inconvenient data collection and the latter’s large data volume requirements, and realize brain-computer collaborative work

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 recognition method based on brain-computer cross-modal migration
  • Emotion recognition method based on brain-computer cross-modal migration
  • Emotion recognition method based on brain-computer cross-modal migration

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] like figure 1 , 2 As shown in and 3, an emotion recognition method based on brain-computer cross-modal transfer, the specific process is as follows:

[0039] Step 1. Get data

[0040]All the facial emotion images involved in this experiment come from the Chinese Facial Affective Picture System (CFAPS). The emotion images in the system mainly include 7 types of basic expressions, and a total of 870 emotional face images were collected. Among them, 74 were angry, 47 were disgusted, 64 were fearful, 95 were sad, 120 were surprised, 222 were neutral, and 248 were happy.

[0041] In order to introduce human cognitive ability, image-induced EEG features are added on the basis of image recognition by traditional machines to obtain advanced emotional representation. Since the acquisition of EEG data requires the stimulation experiment of emotional images on the subjects, the experimental design is completed in E-pirme, and the images are displayed in order of categories, and...

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 recognition method based on brain-computer cross-modal migration. For an emotion recognition task, cognitive representation with emotions is obtained after a human brain processes information, what is obtained by machine learning is only the formal representation of an image, and if a migration relation between the cognitive representation and the formal representation can be established, machine learning is guided through the human brain, and the machine is endowed with the emotion cognitive ability of the human brain; in order to give information perceived by the human brain to the machine, a cross-modal migration model of an image mode and an electroencephalogram mode needs to be established, so that the migration relation between the formal representation and cognitive representation is obtained. According to the method, the migration relation between the electroencephalogram mode and the image mode is explored, the relation between formal representation and cognitive representation is established, and brain-computer collaborative intelligence is achieved. In order to reduce the difference between the cognitive representation and formal representation and enable the formal representation to infinitely approach the cognitive representation, the invention designs the emotion recognition method based the brain-computer cross-modal migration.

Description

technical field [0001] The invention belongs to the intersecting field of brain-computer collaboration and emotion recognition, and specifically relates to a method for emotion recognition based on brain-computer cross-modal transfer technology. Background technique [0002] Brain-computer collaboration is an important way to achieve a more powerful form of intelligence in the artificial age. Emotion recognition is an important interdisciplinary research topic involving neuroscience, psychology, cognitive science, computer science and artificial intelligence. Transfer learning is a machine learning method that takes the model developed for task A as the starting point and reuses it in the process of developing the model for task B. Transfer learning emphasizes the process of transferring knowledge from one domain to another. [0003] Emotion recognition technology based on machine learning. In recent years, breakthroughs have been made in deep learning algorithms applied ...

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): A61B5/16A61B5/369A61B5/378A61B5/00G06K9/62G06N3/04G06N3/08
CPCA61B5/165A61B5/369A61B5/378A61B5/7235A61B5/7267A61B5/7203A61B5/725G06N3/088G06N3/047G06N3/048G06N3/045G06F18/2155G06F18/24
Inventor 孔万增刘栋军金宣妤章杭奎崔岂铨曹泽阳白云
Owner HANGZHOU DIANZI 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