Brain signal identity recognition method based on multi-layer perceptron

A multi-layer perceptron and identity recognition technology, applied in the field of identity recognition, can solve the problems of low recognition accuracy, low accuracy of EEG signals, low signal-to-noise ratio of EEG data, etc., and achieve the effect of wide deployment

Inactive Publication Date: 2019-10-18
NANJING UNIV OF POSTS & TELECOMM
View PDF0 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, brain signal-based identification research is still in its infancy, with several key challenges
One of the most important issues is the low recognition accuracy due to the inherent low accuracy of EEG signals
Accurate identification is challenging because EEG data has a very low signal-to-noise ratio

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
  • Brain signal identity recognition method based on multi-layer perceptron
  • Brain signal identity recognition method based on multi-layer perceptron
  • Brain signal identity recognition method based on multi-layer perceptron

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019] See figure 1 , This embodiment provides a brain signal identification method based on a multilayer perceptron, such as figure 1 As shown, including the following steps

[0020] Step S1: Collect EEG samples of each brain area, perform individual difference analysis on the waveform of the EEG sample, and extract the Delta band signal in the EEG sample;

[0021] Step S2, preprocess the EEG samples from which the Delta band signal is extracted, remove the DC offset, and perform normalization processing on the sample signal.

[0022] Step S3: Input the EGG samples into the structure based on the multilayer perceptron for individual classification.

[0023] The specific implementation and parameters of each step are as follows

[0024] In step S1, the collected EEG signals can be divided into five non-overlapping frequency bands (Delta, Theta, Alpha, Beta, and Gamma) according to the strong intraband correlations with different behavior states. The signal associated with the informati...

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 brain signal identity recognition method based on a multilayer perceptron, and the method comprises the following steps: S1, collecting EEG samples of all brain regions, carrying out the individual difference analysis of the waveforms of the EEG samples, and extracting Delta waveband signals in the EEG samples; and S2, preprocessing the EEG sample from which the Delta waveband signal is extracted, removing DC offset, and normalizing the sample signal; and S3, inputting the EGG sample into a structure based on a multi-layer perceptron for individual classification. Thebrain signals of different individuals are classified by adopting a multi-layer perceptron method, so that the classification precision and accuracy can be effectively improved.

Description

Technical field [0001] The invention belongs to the technical field of identification, and specifically relates to a brain signal identification method based on a multilayer perceptron. Background technique [0002] In the past ten years, biometric information has been widely used for identification and has gained more recognition due to its reliability and adaptability. Existing biometric identification systems are mainly based on the individual's unique internal physiological characteristics such as face, iris, retina, voice and fingerprints. However, currently widely used identification systems are fragile. For example, anti-surveillance prosthetic masks can prevent face recognition, contact lenses can deceive iris recognition, vocoders can compromise voice recognition, and fingerprint films can deceive fingerprint sensors. From this perspective, the identification system based on brain signals has become a promising alternative due to its high resistance to attack. The brai...

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): G06K9/00G06K9/62G06N3/04
CPCG06N3/04G06V40/10G06F18/2431
Inventor 徐欣张艺炜陈赞
Owner NANJING UNIV OF POSTS & TELECOMM
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