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

Kernel k-means method based on local density and single-pass

A local density, k-means technology, applied in computer parts, character and pattern recognition, instruments, etc., can solve the problem of uncertainty of initial center point and high time complexity, so as to improve accuracy, improve computing efficiency, and reduce time. The effect of complexity

Inactive Publication Date: 2017-05-31
XI'AN POLYTECHNIC UNIVERSITY
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide a kernel k-means method based on local density and single-pass, which solves the problems of uncertain initial center point and high time complexity of the traditional kernel k-means algorithm

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
  • Kernel k-means method based on local density and single-pass
  • Kernel k-means method based on local density and single-pass
  • Kernel k-means method based on local density and single-pass

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0044] The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0045] The present invention is based on the kernel k-means method of local density and single-pass, specifically implements according to the following steps:

[0046] Step 1. Determine the data set D, select the initial class center point through the local density method, and implement it according to the following method:

[0047] Before clustering, the local density method is used to select the initial class midpoint, and the idea is as follows:

[0048] Any point p in the space and the distance from AverageDist (average distance between samples), with point p as the center, the area with the radius of AverageDist is the area of ​​point p, and the number of points in the area is called point p. Based on the density parameter of AverageDist, record It is density(p, AverageDist), the specific expression is as follows;

[0049]

[0050] ...

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 kernel k-means method based on local density and single-pass. According to the method, firstly, the local density is used for selecting initial cluster center points with high density and low similarity; secondly, randomly drawing sample data sets containing the initial center points from a data set; clustering the sample data sets by a traditional method; further optimizing each class in the clustering result by a gradient descent method; determining the accurate cluster center points; finally, sequentially dividing the rest data points into the class with the shortest distance. Experiments prove that compared with that of a traditional kernel k-means method, the calculating efficiency of the method is greatly improved; meanwhile, more accurate clustering results are realized. The kernel k-means method based on local density and single-pass solves the problems of initial center point uncertainty and high time complexity of the traditional kernel k-means method.

Description

technical field [0001] The invention belongs to the technical field of data mining methods, in particular to a kernel k-means method based on local density and single-pass. Background technique [0002] Clustering is the process of identifying groups in a given data set, dividing data with similar characteristics or associations into the same group. The traditional k-means algorithm can only deal with directional row and linearly separable data, but for undirected row and non-linearly separable data, ideal clustering results cannot be obtained. [0003] The kernel k-means algorithm is a k-means algorithm based on the kernel function, which is an extension of the traditional k-means algorithm. Through the mapping of nonlinear kernel functions, the data in the original space is mapped to the high-dimensional feature space. In , the clustering error is minimized in a high-dimensional feature space. However, the time complexity of the traditional kernel k-means algorithm is O(...

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): G06K9/62
CPCG06F18/23213
Inventor 薛涛王新星
Owner XI'AN POLYTECHNIC UNIVERSITY
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com