Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

EEG time-sharing frequency spectrum Riemannian-based semantic visual image classification method and device

A visual image and classification method technology, applied in the field of semantic visual image classification, can solve the problems of less research on semantic visual observation, less useful features of EEG signals, and lower classification accuracy, achieving considerable social and economic benefits, and improving Classification accuracy, effect of reducing burden

Pending Publication Date: 2022-01-28
TIANJIN UNIV
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Combining semantic judgment with visual observation is a way to improve the accuracy of visual image classification. However, there are few studies on semantic visual observation.
Many studies only study semantic or visual observation alone, without combining the two, which leads to fewer useful features in EEG signals, thereby reducing the classification accuracy

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
  • EEG time-sharing frequency spectrum Riemannian-based semantic visual image classification method and device
  • EEG time-sharing frequency spectrum Riemannian-based semantic visual image classification method and device
  • EEG time-sharing frequency spectrum Riemannian-based semantic visual image classification method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0032] The embodiment of the present invention designs an EEG-based time-sharing spectral Riemannian semantic visual image classification method. This method can distinguish the EEG response of the brain when observing different semantic visual images. Semantic Visual Observe (SVO) is a new paradigm of Brain-Computer Interface (BCI). When people observe visual images with different semantics, due to different cognitions and emotions, they will change the neuron activity state in different regions of the brain, thereby changing the energy of different frequency bands and the energy distribution in different spaces, and the visual images with different semantics Images also respond differently in the temporal domain. The embodiment of the present invention combines the features of time domain, frequency domain and space domain, and can improve the accuracy of classification of different semantic visual images. Its technical process is as follows:

[0033] 101: Collect the EEG ...

Embodiment 2

[0038] The scheme in embodiment 1 is further introduced below in conjunction with specific examples and calculation formulas, see the following description for details:

[0039] figure 1 It is a schematic diagram of a paradigm design of an embodiment of the present invention. The design mainly includes: stimulation interface, EEG acquisition module and signal processing module. The stimulation interface was written using the Matlab Psychtoolbox toolkit. The EEG acquisition module selected NeuroScan’s EEG cap and amplifier, and the signal processing module implemented data processing, feature extraction, and classification steps through python.

[0040] The experimental paradigm uses the "+" sign to indicate the beginning of the experiment, and the subjects need to rest for 2 seconds at the beginning of the experiment. After resting, the stimulus interface will remind the subject of the semantic category of the upcoming picture, and the semantic prompt lasts for 1 second. Af...

Embodiment 3

[0060] Combine below figure 1 with figure 2 , experimental data, table 1 and table 2, the scheme in embodiment 1 and 2 is further introduced, see the following description for details:

[0061] 1. Experimental process:

[0062] subjects according to figure 1 Schematic diagram of the paradigm design. At the beginning of the experiment, it is necessary to rest for 2 seconds. After resting, the stimulus interface will remind the subject of the semantic category of the upcoming picture, and the semantic prompt lasts for 1 second. After that, the subjects will observe the pictures for 4 seconds, and judge the semantic categories of the pictures while observing. There are three types of pictures in the experiment, the experiment is divided into 12 groups, each group has 24 trials (8 trials for each type of pictures), a total of 288 samples, 96 samples for each type of pictures.

[0063] Collect the EEG data of 12 subjects according to the above process. The EEG acquisition mod...

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 EEG time-sharing frequency spectrum Riemannian-based semantic visual image classification method and device. The method comprises the steps: designing an experiment normal form, collecting the electroencephalogram data of a subject through an electroencephalogram collection device, and carrying out corresponding preprocessing; dividing the preprocessed data into different data sets according to time periods, performing Fourier transform on the data sets in different time domains to obtain frequency domain features of the data sets, and extracting Riemannian space domain features from the frequency domain features of the data sets in the frequency domain; and splicing the Riemannian space domain features of different time periods, selecting final m-dimensional features from the spliced Riemannian space domain features through feature selection, classifying the selected final m-dimensional features, and judging the classification accuracy of the semantic visual image through a classification result. The device comprises a processor and a memory. According to the invention, the classification accuracy of visual stimulation among different semantics is improved by extracting the time domain, frequency domain, spatial domain and other features of the VEP component and the N400 component.

Description

technical field [0001] The present invention relates to the field of brain-computer interface, in particular to a time-sharing spectrum Riemannian semantic visual image classification method and device based on EEG (electroencephalogram). Improving the accuracy of visual image classification with different semantics. Background technique [0002] Brain-computer interface is a system that can convert various neural activities of the central nervous system into computer commands, which can control external devices to perform required actions or instructions, and complete the interaction between the brain and the external environment. Collect the EEG signals of the subjects under different tasks through the EEG acquisition equipment, and then complete the decoding of the EEG signals through preprocessing, feature extraction, pattern recognition and other methods, so as to establish a communication channel between the external environment and the human brain , BCI (Brain-Comput...

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): A61B5/378A61B5/372A61B5/374A61B5/00
CPCA61B5/378A61B5/372A61B5/374A61B5/7267A61B5/7264A61B5/7257A61B5/7235
Inventor 李长赟明东陈龙王仲朋刘爽许敏鹏
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
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