Unlock instant, AI-driven research and patent intelligence for your innovation.
Single-trial EEG p300 component detection method and device based on image prior
What is Al technical title?
Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
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
This helps you quickly interpret patents by identifying the three key elements:
Problems solved by technology
Method used
Benefits of technology
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
Click on the blue label to locate the original text in one second.
Reading with bidirectional positioning of images and text.
Smart Image
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
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 retrievalsystem 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
Application Date:The date an application was filed.
Publication Date:The date a patent or application was officially published.
First Publication Date:The earliest publication date of a patent with the same application number.
Issue Date:Publication date of the patent grant document.
PCT Entry Date:The Entry date of PCT National Phase.
Estimated Expiry Date:The statutory expiry date of a patent right according to the Patent Law, and it is the longest term of protection that the patent right can achieve without the termination of the patent right due to other reasons(Term extension factor has been taken into account ).
Invalid Date:Actual expiry date is based on effective date or publication date of legal transaction data of invalid patent.