Self-adaptive Rulkov neuron clustering method

A clustering method and neuron technology, applied in the field of pattern recognition, can solve the problems of small distance between classes, poor separability, and poor clustering effect, and achieve the effect of excellent clustering performance and good clustering effect.

Pending Publication Date: 2021-11-30
西安现代控制技术研究所
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0019] The technical problem to be solved by the present invention is: how to provide an adaptive Rulkov neuron clustering method based on adaptive distance and shared neighbors, so as to solve the problem of clustering data sets with small inter-class distance and poor separability in existing methods. For problems with poor results, better clustering results can be obtained than existing methods

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
  • Self-adaptive Rulkov neuron clustering method
  • Self-adaptive Rulkov neuron clustering method
  • Self-adaptive Rulkov neuron clustering method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0143] In this embodiment, the adaptive Rulkov neuron clustering method uses adaptive distance and shared neighbors to construct a similarity matrix, which can avoid the problem of difficult selection of scale parameters in spectral clustering algorithms based on normalized Laplacian matrices. The present invention uses a clustering method based on Rulkov neuron self-learning for clustering, and further studies the similarity between samples to increase the distance between samples. It can avoid the problem of poor clustering effect caused by improper selection of the initial clustering center when the spectral clustering algorithm based on the normalized Laplacian matrix uses the K-means algorithm. The flow chart of the adaptive Rulkov neuron clustering method is as follows: figure 1 shown.

[0144] The specific implementation manner of the present invention will be described in further detail below in conjunction with the accompanying drawings and specific examples.

[014...

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 self-adaptive Rulkov neuron clustering method. The method includes: firstly, building a similarity matrix according to adaptive distances and shared neighbors, wherein the adaptive distances can process classes with different densities, and the shared neighbors can reduce intra-class distances and increase inter-class distances; then, further extracting sample features with better separability by using a main feature extraction method of Laplacian spectrum decomposition; and finally, mapping the sample into a Rulkov neuron, and further learning and adaptively clustering the obtained sample characteristics by using a Rulkov coupling neuron network. For a data set with relatively small inter-class distance and relatively poor separability, the method disclosed by the invention can obtain a better clustering effect compared with a comparison method.

Description

technical field [0001] The invention belongs to the technical field of pattern recognition, and in particular relates to an adaptive Rulkov neuron clustering method, in particular to a clustering method in data sets with small inter-class distances. Background technique [0002] Cluster analysis has been widely used in the fields of artificial intelligence, image segmentation, big data processing and pattern recognition, and it is also a hot topic in the research of pattern recognition in recent years. As an unsupervised learning method, clustering divides samples into different subsets according to the similarity between samples, so that the similarity of samples in a subset is larger, and the similarity between subsets is smaller. [0003] According to different sample distributions, it can be divided into two clustering methods that are only applicable to spherical structure sample space and suitable to arbitrary structure sample space. Clustering methods suitable for sp...

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): G06K9/62G06N3/04
CPCG06N3/04G06F18/2321G06F18/22
Inventor 邹汝平任海鹏周健焦迎杰
Owner 西安现代控制技术研究所
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