Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Implantable brain-computer interface neuron spike potential classification method

A technology of brain-computer interface and classification method, which is applied in computer parts, character and pattern recognition, pattern recognition in signals, etc. It can solve problems such as difficult clustering, difficult detection of neuron spike data, and low signal-to-noise ratio

Pending Publication Date: 2021-09-10
HEBEI UNIVERSITY
View PDF2 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to provide an implantable brain-computer interface neuron spike classification method to solve the problem of low signal-to-noise ratio and low-amplitude neuron spike data that is difficult to detect, and it is difficult to cluster due to the high similarity of spike shapes The problem

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
  • Implantable brain-computer interface neuron spike potential classification method
  • Implantable brain-computer interface neuron spike potential classification method
  • Implantable brain-computer interface neuron spike potential classification method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] Such as figure 1 Shown, the implementation process of the present invention is as follows:

[0032] A) filtering

[0033] Filter the collected EEG signals, use the 300-3000Hz band-pass elliptic filter ellip function [b,a]=ellip(n,Rp,Rs,Wn,'ftype') in matlab to filter the collected original EEG signals The signal is filtered, and the parameters of the elliptic filter are set. After continuous tuning and tuning, the Rp of the filter is finally adjusted to 1×10 -6 dB, such as figure 2 As shown, so that the useful signal can be passed through without attenuation as much as possible, and the waveform of the low-amplitude spike signal in the collected original signal is retained, and the filtered signal x is obtained.

[0034] B) detection

[0035] Use the improved heuristic threshold detection formula to detect the spike potential on the filtered signal, the improved formula is Among them, l represents the length of the filtered signal, x represents the filtered signa...

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 provides an implantable brain-computer interface neuron spike potential classification method. The method comprises the following steps of: a, filtering an original signal by using a band-pass elliptical filter, and filtering out local field potential of a low-frequency band and background noise of a part of a high-frequency band in the signal; b, using an improved heuristic threshold detection algorithm to extract and retain spike potential data in the filtered signal; c, performing feature extraction on the spike potential data by using principal component analysis; and d, aggregating the data which represents the spike potential and is mapped in the feature space into different clusters by using a K multi-mean clustering algorithm based on improved dynamic time warping. Through the processing of the method provided by the invention, the low-amplitude spike potential is fully reserved from the original signal, and the effective classification of the high-precision spike potential is realized.

Description

technical field [0001] The invention relates to the technical field of detection and clustering of implantable brain-computer interface spikes, in particular to a method for classifying spikes of implantable brain-computer interface neurons. Background technique [0002] For centuries, brain science and research on the nervous system have shown that the nervous system precisely regulates and controls various limb activities of living things. Since the discovery that neurons and muscles generate electricity, the exploration of brain science has largely relied on the ability of acquisition devices to simultaneously record a large number of cells and the ability to accurately decode neuron signals, allowing researchers to understand information in How to express and transmit in neurons. [0003] One of the most popular techniques for acquiring cellular biological activity (ie, recording electrophysiological signals) is to use extracellular electrode arrays, and electrophysiolo...

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): G06K9/00G06K9/62A61B5/00A61B5/372A61B5/388
CPCA61B5/7264A61B5/372A61B5/388G06F2218/04G06F2218/08G06F2218/12G06F18/2135G06F18/23213G06F18/24
Inventor 刘秀玲熊鹏杨建利杜海曼王洁郭天翔
Owner HEBEI UNIVERSITY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com