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

Affinity propagation clustering method based on genetic algorithm

A genetic algorithm and neighbor propagation technology, applied in the fields of genetic law, calculation, genetic model, etc., can solve the problem that the global optimal solution cannot be accurately obtained.

Inactive Publication Date: 2019-12-06
SOUTHWEAT UNIV OF SCI & TECH
View PDF0 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although the above method optimizes the algorithm to a certain extent, it cannot accurately obtain the global optimal solution

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
  • Affinity propagation clustering method based on genetic algorithm
  • Affinity propagation clustering method based on genetic algorithm
  • Affinity propagation clustering method based on genetic algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0016] In the drawings, the same parts are represented by the same symbols in different views, and the described elements are not necessarily drawn to scale. The present invention will be further described below in conjunction with the drawings and embodiments.

[0017] figure 1 It is a block diagram of an instruction manual and a system block diagram of the entire clustering algorithm.

[0018] figure 2 It is a flowchart of the GA_AP clustering algorithm of the present invention. Data preprocessing. Data missing values ​​are selected and filled with the attribute mean of all samples of the class to which the given tuple belongs; data standardization adopts zero-mean normalization. The formula is

[0019] (1)

[0020] in represents the mean value of the original data, Indicates the standard deviation of the original data. The value range of selection bias parameter is , where p_mean represents the mean value of the similarity matrix, and the value range of the ...

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 affinity propagation clustering method based on a genetic algorithm, and belongs to the field of data mining. The method is characterized by comprising the following steps of: preprocessing data, and performing clustering analysis on a data set by adopting an affinity propagation clustering algorithm. The clustering analysis comprises the following steps: firstly, takinga similarity matrix formed by similarities (negative Euclidean distances) among data points as a working basis, and taking all data objects as potential clustering centers; secondly, obtaining an optimal deviation parameter and a damping factor by utilizing a genetic algorithm; and finally, continuously updating and iterating in the attraction degree matrix and the affiliation degree matrix by utilizing the obtained optimal solution until a termination condition is met, finishing clustering and obtaining a clustering result. According to the algorithm, the problem that a standard affinity propagation clustering algorithm is sensitive to deviation parameters and damping factors is effectively solved, the accuracy of the clustering algorithm is improved, the clustering number is closer to the real data set clustering number, and the algorithm can be effectively applied to clustering analysis of various types of data.

Description

technical field [0001] The application background of the present invention is data mining technology, that is, mining knowledge from data. The content of the invention refers to the use of clustering algorithms to cluster data in the sea of ​​data, analyze the clustering results, find or obtain useful information, which aims to overcome the sensitivity of the nearest neighbor propagation clustering algorithm to bias parameters and damping factors, and improve The accuracy of the clustering algorithm is one of the most important components in the field of data mining technology. Background technique [0002] Cluster analysis, referred to as clustering, is the process of dividing a data object into subsets. Each subset is a cluster such that objects in a cluster are similar to each other but not to objects in other clusters. At present, cluster analysis has been widely used in business intelligence, image pattern recognition, Web search and digital medical treatment. [000...

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): G06K9/62G06N3/12
CPCG06N3/126G06F18/23
Inventor 周金治赖键琼
Owner SOUTHWEAT UNIV OF SCI & TECH
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