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

Multi-view clustering method based on constrained non-negative matrix factorization

A technology of non-negative matrix decomposition and clustering method, which is applied in the field of multi-view clustering based on constrained non-negative matrix decomposition, and can solve problems such as poor performance of multivariate time series data

Pending Publication Date: 2021-02-26
WUHAN UNIV
View PDF0 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The above studies mainly focus on the multi-view clustering problem. However, the existing research does not perform well on multivariate time-series data.

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
  • Multi-view clustering method based on constrained non-negative matrix factorization
  • Multi-view clustering method based on constrained non-negative matrix factorization
  • Multi-view clustering method based on constrained non-negative matrix factorization

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0070] The technical solution of the present invention will be described in detail below in conjunction with the drawings and embodiments.

[0071] Aiming at the clustering problem of high-dimensional multivariate time series, the present invention proposes a multi-view clustering method based on constrained non-negative matrix decomposition, and simultaneously considers the consistency between different views and the particularity information of each view to realize the multivariate time series Clustering of data with high accuracy.

[0072] The embodiment of the present invention takes the Auslan data set as a specific example. The Auslan data contains 95 categories, and each data includes 22 variables, that is, each data includes a time series of 3 variables, and the length of the time series in each data is 45 to 316 ranging, including a total of 1140 data. The number of neighbors in the multi-relational network is 7, the number of generated multi-views is 2, and the matr...

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

Aiming at the clustering problem of a high-dimensional multivariate time sequence, the invention provides a multi-view clustering method based on constrained non-negative matrix factorization, in order to effectively carry out sample clustering, multivariate time sequence data is firstly projected to a multi-relation network, and then a hierarchical method is adopted to generate a plurality of independent views. The method also includes, secondly, clustering the plurality of views by adopting a constrained non-negative matrix factorization method; and finally, solving in an alternate iterativeoptimization mode, and performing k-means clustering on the representation matrix obtained by calculation of the solving result to obtain a clustering result. The correctness and effectiveness of themethod and the algorithm provided by the invention are verified through experiments, and experimental results show that the clustering method has relatively high accuracy and effectiveness.

Description

technical field [0001] The invention relates to the technical field of time series data mining, in particular to a multi-view clustering method based on constrained non-negative matrix decomposition. Background technique [0002] Multivariate time-series data is widely used in daily life. However, for the clustering of multivariate time-series data, existing algorithms often deal with it from a single view, ignoring the hidden multi-view information in multivariate time-series data. Multi-view clustering can mine the consistent and complementary information in different views and improve the clustering effect, so it has become a current research hotspot. Scholars at home and abroad have proposed many algorithms. [0003] Graph-based multi-view clustering uses a unified graph matrix to represent the similarity relationship between data samples, and clusters on the basis of this graph matrix to obtain results. Zhan et al. learn a consistency map by minimizing the inconsistenc...

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): G06K9/62G06F17/16
CPCG06F17/16G06F18/23213
Inventor 何国良王晗刘申享
Owner WUHAN UNIV