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

Cross-mode electroencephalogram signal identification method considering individual differences

An EEG signal and recognition method technology, applied in character and pattern recognition, neural learning methods, biological neural network models, etc., can solve the problems of time-consuming, a large amount of new subject data, etc., to reduce data collection time and improve performance. , to avoid negative boosting effects

Pending Publication Date: 2021-11-09
HANGZHOU DIANZI UNIV
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the above methods all need to use a large amount of unlabeled new subject data in the process of training the model, resulting in a lot of time spent in actual use to collect new subject data

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
  • Cross-mode electroencephalogram signal identification method considering individual differences
  • Cross-mode electroencephalogram signal identification method considering individual differences
  • Cross-mode electroencephalogram signal identification method considering individual differences

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0054] The method for identifying cross-modal EEG signals based on individual EEG differences of the present invention will be described in detail below in conjunction with the accompanying drawings.

[0055] Aiming at the characteristics of cross-modal EEG signals, the present invention proposes a multi-branch network model algorithm, and screens the training set before model training. In this embodiment, the following steps are included:

[0056] Step 1. EEG signal preprocessing.

[0057] Based on the SEED data set, the present invention conducts a cross-subject experiment of three emotional classifications to verify the effectiveness of the algorithm. A total of 15 subjects participated in the experiment in the SEED data set. At the same time, in each experiment, 15 movie clips were played to stimulate the corresponding emotions, and the ESI NeuroScan System with 62 channels was used to record the EEG signals with a sampling frequency of 1000Hz. In order to reduce the sto...

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 cross-mode electroencephalogram signal identification method considering individual differences. Unifying an electroencephalogram signal data format into a 3D tensor structure, then dividing electroencephalogram signals into a data set, and inputting the electroencephalogram signals into classifiers formed by branch networks for training so as to respectively extract background features and task features; using the extracted background features to calculate the similarity between different subjects, and screening data in the data set to avoid model negative lifting caused by electroencephalogram signal data of which a difference degree is greater than a threshold value in a training process; finally, inputting the screened data set into a multi-branch network model for training. According to the method, features of different subjects can be better extracted while a small amount of new subject data is collected as much as possible, so that the performance of the model in cross-subject tasks is improved.

Description

technical field [0001] The invention belongs to the field of EEG signal processing and the field of human-computer interaction, and specifically relates to a cross-mode EEG signal recognition method considering individual differences. Background technique [0002] With the development of brain science research, more and more brain computer interface (Brain computer interface, BCI) applications have received attention and research. A brain-computer interface is a combination of hardware and software that uses brain waves to control an external device, such as a brain-controlled robotic arm. BCI technology involves multiple disciplines such as neuroscience, human-computer interaction, information processing, pattern recognition, etc., through feature extraction and classification of physiological signals collected from the human brain, to identify the real thoughts of the subjects, and then convert these thoughts into Different commands, so as to realize the interaction and c...

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): G06K9/00G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06N3/048G06N3/045G06F2218/08G06F2218/12G06F18/22G06F18/24G06F18/214Y02D10/00
Inventor 林广任彬张建海朱莉
Owner HANGZHOU DIANZI UNIV
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