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

A Feature Hierarchical EEG Recognition and Analysis Method Based on Deep Convolutional Neural Network

A deep convolution and neural network technology, applied in the field of artificial intelligence, feature classification brain wave recognition and analysis based on deep convolution neural network, can solve the problems of superficial understanding, the working mechanism of the brain and nerve has not yet been identified, etc., to improve the accuracy sexual effect

Inactive Publication Date: 2020-07-10
LIAONING UNIVERSITY OF TECHNOLOGY
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Even with the development of modern medicine, even with supercomputers, human beings still have a superficial understanding of the brain, and the specific working mechanism of the brain and nerves has not yet been ascertained

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
  • A Feature Hierarchical EEG Recognition and Analysis Method Based on Deep Convolutional Neural Network
  • A Feature Hierarchical EEG Recognition and Analysis Method Based on Deep Convolutional Neural Network
  • A Feature Hierarchical EEG Recognition and Analysis Method Based on Deep Convolutional Neural Network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0048] The present invention will be further described in detail below in conjunction with the accompanying drawings, so that those skilled in the art can implement it with reference to the description.

[0049] Such as Figure 1-2 As shown, the feature-graded brain wave recognition and analysis method based on deep convolutional neural network provided by the present invention includes:

[0050] Step S110, collecting the tester's original brain wave signal;

[0051] Step S120, detecting the peak point of the electroencephalogram signal, and taking it as a reference point to intercept a certain number of sampling points forward and backward as a sampling block, and dividing the entire electroencephalogram signal into multiple sampling blocks;

[0052] The formula for calculating the number of intercepted sampling points is:

[0053] n n =[f n (I-I th )+f n CI th ]·t n / I th

[0054] Among them, f n Is the sampling frequency, I is the peak point peak value, I th is ...

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 feature-graded brain wave recognition and analysis method based on a deep convolutional neural network, comprising: step 1, collecting the original brain wave signal of a tester; The amplitude of the sampling block is preprocessed, and the independent component analysis method is used for denoising processing; step 4, calculating the influence weight corresponding to the amplitude of each sampling point in the sampling block, and calculating the characteristic contribution value of the sampling block; step 5, For the brainwave signals after pattern classification, a deep convolutional neural network model is established, and the characteristic parameters in the training samples are classified and trained; step 6, the template matching method is used to identify the test samples, and the identification and analysis results are obtained. The present invention is based on The classification categories are trained through the convolutional neural network model to form a feature library, which can correctly identify the brain waves of the test person, effectively improving the accuracy of brain wave recognition.

Description

technical field [0001] The invention relates to the field of artificial intelligence, in particular to the field of feature-graded brainwave recognition and analysis based on a deep convolutional neural network. Background technique [0002] With the improvement of science and technology and the rapid development of artificial intelligence, at this stage we have been able to remotely control various smart and non-smart devices in our homes through smart phones. Going a step further, we want to control smart home and medical equipment through brain waves. The brain is the most mysterious part of the human being. Even with the development of modern medicine, even with supercomputers, human beings still have a superficial understanding of the brain, and the specific working mechanism of the brain and nerves has not yet been ascertained. But since ancient times, human beings have dreamed of mind control, expecting to control objects and scenes around them with just a thought. ...

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): G06K9/00G06N3/04G06N3/08
CPCG06N3/08G06N3/045G06F2218/10G06F2218/04
Inventor 褚治广李昕张巍李帅
Owner LIAONING UNIVERSITY OF TECHNOLOGY