Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Emotion recognition method based on self-training maximization classifier difference

An emotion recognition and classifier technology, applied in the field of emotion recognition, can solve the problems of declining classification effect and ignoring spatial information, and achieve the effect of accurate emotion recognition results and good economic benefits.

Pending Publication Date: 2022-04-05
CHONGQING UNIV OF POSTS & TELECOMM
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Most studies directly input the artificially extracted features into the classifier, ignoring the relationship between frequency bands and the spatial information between channels, which reduces the classification effect

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 self-training maximization classifier difference
  • Emotion recognition method based on self-training maximization classifier difference
  • Emotion recognition method based on self-training maximization classifier difference

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach

[0059] A specific implementation of the training of the emotion recognition model based on the self-training maximization classifier difference is as follows:

[0060] The process from the original EEG data set to the final construction of 3D cube features is as follows: figure 2 As shown, the specific process is:

[0061] Preprocessing of raw EEG data: downsampling of raw EEG data on SEED and SEED-IV datasets from 1000 Hz to 200 Hz; further filtering out noise and removing artifacts using bandpass filtering at 0.3-75 Hz. The non-overlapping EEG signals filtered by each channel on the preprocessed SEED and SEED-IV datasets are divided into 1s and 4s segments respectively; these segments have their corresponding emotional labels.

[0062] The obtained fragments are filtered in five frequency bands; the five frequency bands are: delta (1-3Hz), theta (4-7Hz), alpha (8-13Hz), beta (14-30Hz) and gamma (31-50Hz ); Extract differential entropy (DE) features to five frequency bands...

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 belongs to the field of emotion recognition, and particularly relates to an emotion recognition method based on self-training maximization classifier difference. The method comprises the following steps: acquiring electroencephalogram EEG data of a subject in real time, preprocessing the EEG data, and inputting the preprocessed data into an emotion recognition model based on self-training maximization classifier difference to obtain an emotion recognition result of the subject; the invention provides a novel domain adaptive adversarial training method, the method adopts soft labels to perform interdisciplinary EEG emotion classification, not only considers decision boundaries of specific categories, but also uses the soft labels to further extract source domain information beneficial to target domain classification, the emotion recognition result is more accurate, and the method has good economic benefits.

Description

technical field [0001] The invention belongs to the field of emotion recognition, and in particular relates to an emotion recognition method based on self-training to maximize classifier differences. Background technique [0002] In recent years, emotion recognition is an important issue in scientific research and engineering, and has received extensive attention from scholars at home and abroad. In psychological research, emotion recognition provides a reference index for studying emotion-related behaviors. In engineering research, it promotes a more friendly human-computer interaction, enabling machines to recognize, process and interpret human emotions through systems or smart devices. In the field of medicine, emotion recognition helps to assist in the diagnosis and treatment of various mental diseases such as autism or depression, so that medical staff can accurately know the emotional state of patients with expression disorders, and provide patients with high-quality ...

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): G06K9/00G06K9/62G06N3/04
Inventor 张旭李含雨夏英
Owner CHONGQING UNIV OF POSTS & TELECOMM
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com