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

An Online Classification Method of Neuronal Spikes Based on Density Spike Clustering Algorithm

A density peak, clustering algorithm technology, applied in computing, computer parts, instruments, etc., can solve problems that rely on manual or semi-manual processing

Active Publication Date: 2022-02-18
ZHEJIANG UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] Neuron spike signal (Spike) has the characteristics of high spatio-temporal resolution and large amount of information. It is an important means of real-time and precise control of complex tasks. Spike classification is one of the important steps in spike signal processing. However, the current method Mainly rely on manual or semi-manual processing
With the development of multi-channel neural cluster recording technology, the number of synchronously recorded neuron channels has increased sharply, from dozens of channels to thousands of channels, and the current manual and semi-manual methods have been unable to cope.

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
  • An Online Classification Method of Neuronal Spikes Based on Density Spike Clustering Algorithm
  • An Online Classification Method of Neuronal Spikes Based on Density Spike Clustering Algorithm
  • An Online Classification Method of Neuronal Spikes Based on Density Spike Clustering Algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0031] Embodiment 1 An online neuron spike classification method based on the density peak clustering algorithm, comprising the following steps:

[0032] figure 1 is the flow chart of the method.

[0033] (1) Perform principal component analysis on the training data to obtain the projection matrix and the three largest principal components; each spike waveform is represented by an eigenvector composed of three principal components.

[0034] (2) Use the density peak clustering method to cluster the data in the principal component feature space, and obtain the clustering result L. Computes the local density ρ of a vector and the minimum distance δ to a point with a local density greater than itself.

[0035] The local density is calculated as where d ij is the eigenvector y i with y j The distance, n is the total number of spike potentials.

[0036] The minimum distance to a point with a local density greater than itself and the corresponding point n_up i is calculated ...

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 an online neuron spike potential classification method based on a density peak clustering algorithm, comprising the following steps: extracting a waveform feature vector of a signal through dimensionality reduction and feature extraction; using a density peak clustering algorithm to cluster the feature vectors , and then use classification methods such as linear discriminant analysis to find the projection space of the best classification corresponding to the current clustering results and the eigenvectors obtained from the peak potential projection; find the best projection space and obtain the clustering results through an iterative method, and test the peak Potentials are mapped to projected space for classification. The method of the invention has the characteristics of good noise resistance, low complexity, unsupervised and online classification, and can be completely automatic without human participation, and can be applied to wireless implantable brain-computer interfaces.

Description

technical field [0001] The invention belongs to the field of online processing of neuron spike potential signals, and in particular relates to an online classification method of neuron spike potential based on a density peak clustering algorithm. Background technique [0002] Neuron spike signal (Spike) has the characteristics of high spatiotemporal resolution and large amount of information. It is an important means of real-time and precise control of complex tasks. Spike classification is one of the important steps in spike signal processing. However, the current method Mainly rely on manual or semi-manual processing. With the development of multi-channel neural cluster recording technology, the number of synchronously recorded neuron channels has increased dramatically, from dozens of channels to thousands of channels, and the current manual and semi-manual methods have been unable to cope. On the other hand, the increase in the number of recording channels also poses a ...

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): G06K9/00G06K9/62
CPCG06F2218/12G06F18/23213G06F18/241
Inventor 杨泽兰任轶佐张韶岷
Owner ZHEJIANG UNIV