Steady-state motion visual evoked potential brain-computer interface method based on CSFL-GDBN

A technology of visual evoked potential and computer interface, which is applied in the field of brain-computer interface, can solve the problems of limiting the development of brain-computer interface technology, easy to lose useful features of signals, and unstable classification accuracy, so as to shorten the signal sampling time, signal Effect of short sampling time, improved reliability and feasibility

Active Publication Date: 2017-09-01
XI AN JIAOTONG UNIV
View PDF8 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

But at the same time, due to the extremely complex brain-computer interface, the method of artificial design features of CCA is very easy to lose useful features in the signal, resulting in unstable classif

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
  • Steady-state motion visual evoked potential brain-computer interface method based on CSFL-GDBN
  • Steady-state motion visual evoked potential brain-computer interface method based on CSFL-GDBN
  • Steady-state motion visual evoked potential brain-computer interface method based on CSFL-GDBN

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0047] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments.

[0048] The CSFL-GDBN-based steady-state motor visual evoked potential brain-computer interface method includes the following steps:

[0049] Step 1), refer to figure 1 , respectively place measuring electrodes A1, A2, A3 on the occipital regions O1, O2, Oz of the subject's head X, place the reference electrode D on the unilateral earlobe of the subject's head X, place The ground electrode E is placed on the forehead Fpz of X, the output terminals of the measuring electrodes A1, A2, A3 are connected to the input terminals F1, F2, F3 of the EEG collector F, and the output terminal of the reference electrode D is connected to the input terminal of the collector F F4, the output terminal of the ground electrode E is connected to the input terminal F5 of the collector F, the output terminal of the collector F is connected to the input terminal of ...

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 steady-state motion visual evoked potential (SSMVEP) brain-computer interface method based on a CSFL-GDBN. According to the method, first, hardware connection is performed, and then SSMVEP data with tags is collected to train the CSFL-GDBN so that the CSFL-GDBN can perform effective classification on SSMVEP signals, wherein the CSFL-GDBN is formed by stacking GRBMs and RBMs; multi-GRBM training is performed on data from different channels on an input data layer on the bottom layer of the CSFL-GDBN, and signal features of all the channels are extracted; next, extracted subchannel features are fused on a next feature fusion layer; and last, the fused features are classified after being abstracted again to obtain excitation target information of SSMVEP. Through the method, the signal features can be automatically extracted, useful information is not prone to loss, the multichannel fusion mechanism enables the extracted features to contain spatial information in multichannel brain electrical signals, and the method has the advantages that recognition speed is high, and recognition accuracy is stable among individuals.

Description

technical field [0001] The invention relates to the technical field of brain-computer interface, in particular to a CSFL-GDBN (Channel Separated Feature Learning Gaussian Deep Belief Networks)-based brain-computer interface method for steady-state motor visual evoked potentials. Background technique [0002] The brain-computer interface is a human-computer interaction system that establishes between the human brain and the outside world without relying on the conventional brain information output pathway. As a kind of human-computer interface, the brain-computer interface opens up a new way for the brain to communicate and control information with the outside world because it does not rely on conventional brain output pathways, enabling people to directly control external devices through the brain. Due to its great application potential in the fields of game entertainment, rehabilitation medicine, aerospace, military and other fields, brain-computer interface technology has ...

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
IPC IPC(8): G06F3/01G06K9/00G06K9/62
CPCG06F3/015G06F2203/011G06F2218/12G06F18/2414
Inventor 谢俊贾亚光徐光华罗爱玲李敏韩兴亮
Owner XI AN JIAOTONG 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