Unlock instant, AI-driven research and patent intelligence for your innovation.

Single-trial EEG p300 component detection method and device based on image prior

A component detection and image technology, used in diagnostic recording/measurement, medical science, diagnosis, etc., to achieve the effect of good detection accuracy

Active Publication Date: 2020-07-17
THE PLA INFORMATION ENG UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in the target image retrieval based on EEG signals, there is a problem that the P300 detection algorithm passively adapts to the change of P300 latency

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
  • Single-trial EEG p300 component detection method and device based on image prior
  • Single-trial EEG p300 component detection method and device based on image prior
  • Single-trial EEG p300 component detection method and device based on image prior

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0066] Such as figure 1 As shown, a kind of single-trial EEG P300 component detection method based on image prior of the present invention comprises the following steps:

[0067] Step S101: Calculate the complexity of the images in the stimulus image data set, and sort the images according to the complexity;

[0068] Step S102: training a classifier for EEG signals induced by images of different complexity;

[0069] Step S103: Score the EEG signal induced by the image.

Embodiment 2

[0071] Such as Figure 2-5 As shown, another kind of single trial EEG P300 component detection method based on image prior of the present invention comprises the following steps:

[0072] Step S201: Calculate the complexity of the images in the data set, and sort the images in the data set according to the complexity of the images; including:

[0073] Step S2011: Calculate the complexity of the images in the data set, the calculation formula is:

[0074]

[0075] Among them, IC is the complexity of the image, f i is the normalized feature weight vector of the image in the i-th layer network mapping of the convolutional neural network, fnum is the feature dimension in the i-th layer, k is a parameter and is greater than 1;

[0076] As an implementable manner, the value of k is 2;

[0077] Step S2012: sort the images in the data set from high to low according to the complexity of the images, and divide them into three parts on average, and name them as high-complexity data...

Embodiment 3

[0100] Such as image 3 As shown, a single-trial EEG P300 component detection device based on image prior of the present invention includes:

[0101] The complexity calculation and sorting module 301 is used to calculate the complexity of the images in the stimulus image data set, and sort the images according to the complexity;

[0102] A training module 302, configured to train a classifier for EEG signals induced by images of different complexity;

[0103] Scoring module 303, configured to score the EEG signal induced by the image.

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 is the field of human brain and machine visual fusion technology, and especially involves image -based single -testing method and devices based on image priority.Single -testing of Electric P300 ingredients based on image priority, including: calculate the complexity of the image data set of stimulating image data set, sort the image according to the complexity;Rating the electrical signal induced by the image.Single -trial of image -based single -testing Electric P300 component detection device, including: complexity calculation sorting module; training module; scoring module.The present invention can actively predict the scope of the P300 incubation period based on the complexity of the image.

Description

technical field [0001] The invention belongs to the technical field of fusion of human brain and machine vision, and in particular relates to a single-trial EEG P300 component detection method and device based on image prior. Background technique [0002] Because in the real-time system of target image detection based on EEG, the detection of P300 components still cannot achieve high precision. Therefore, some scholars consider making full use of the efficient comprehension ability of the human brain and the processing speed of the computer to build an image retrieval system that integrates the human brain and machine vision. These systems use the EEG interest scores of more trials to guide machine vision to search for images with high interest scores, which is a "decision-level" fusion method. [0003] The human visual system is the result of long-term evolution in nature, and the recognition of natural images has the characteristics of high speed and robustness. Machine ...

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 Patents(China)
IPC IPC(8): A61B5/0484A61B5/00G06K9/62
CPCA61B5/7267A61B5/378G06F18/2193G06F18/24G06F18/214
Inventor 闫镔王晓娟林志敏曾颖童莉张驰
Owner THE PLA INFORMATION ENG UNIV