Community evolution prediction method based on Shapelet

A prediction method and community technology, applied in the field of prediction of community evolution, can solve problems such as inability to deal with large-scale data sets, without considering the time characteristics of time series data, etc., to achieve good generalization ability, improved algorithm efficiency, and classification accuracy Improved effect

Inactive Publication Date: 2016-11-09
SICHUAN UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Most of the existing Shapelet-based time series classification algorithms are for small-scale data sets, and can only handle hundreds or thousands of time-series data sets, and cannot handle larger-scale data sets.
In addition, the existing Shapelet-based time series classification algorithms do not consider the temporal characteristics of time series data, that is, the time series data at different times have the same impact on the prediction results of the 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
  • Community evolution prediction method based on Shapelet
  • Community evolution prediction method based on Shapelet
  • Community evolution prediction method based on Shapelet

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0049] All features disclosed in this specification, or steps in all methods or processes disclosed, may be combined in any manner, except for mutually exclusive features and / or steps.

[0050] Any feature disclosed in this specification (including any appended claims, abstract and drawings), unless expressly stated otherwise, may be replaced by alternative features which are equivalent or serve a similar purpose. That is, unless expressly stated otherwise, each feature is one example only of a series of equivalent or similar features.

[0051] The specific implementation manners of the present invention will be described in detail below in conjunction with the drawings and embodiments.

[0052]According to an embodiment of the present invention, this embodiment discloses a community evolution prediction method based on Shapelet. This method transforms the complex community evolution prediction problem into a time series classification problem, and proposes a time series clas...

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 community evolution prediction method based on Shapelet. The community evolution prediction method comprises steps of combining the Shapelet with a radial basis function network, using the found Shapelet representing characteristics of time series data classes as a hidden layer node of a RBF network, and using gradient descending study to obtain connection weights of the hidden layer and an output layer. The community evolution prediction method based on Shapelet is high in precision and good in generalization capability; efficiency of the algorithm is improved by 1-2 orders of magnitude through two optimization strategies proposed by the community evolution prediction method; and classification accuracy of the algorithm is improved by 2% on average by performing weighting on a distance function according to time.

Description

technical field [0001] The invention relates to the technical field of community evolution prediction, in particular to a Shapelet-based community evolution prediction method. Background technique [0002] Community is an important characteristic ubiquitous in complex networks in the real world, and it is in the process of continuous evolution. The research on the community and its evolution process in the network is helpful to analyze the characteristics of the network, understand the network structure, and discover the evolution law hidden in the network, which has extremely important theoretical significance and application value [1-5]. Such as figure 1 As shown, the evolution trajectory of the known community history, how to predict the state of the community after a period of time. Community evolution prediction is a very complicated problem. The community at each moment is a network, and it is very difficult to predict the network structure. As a preliminary explora...

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): G06K9/62G06Q10/04G06Q50/00
CPCG06Q10/04G06Q50/01G06F18/24
Inventor 李川张永辉
Owner SICHUAN UNIV
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