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

Step-by-step type data dimension reduction method based on cluster

A step-by-step, dimensionality reduction technology, applied in electrical digital data processing, special data processing applications, character and pattern recognition, etc. The effect of efficiency

Inactive Publication Date: 2018-01-09
XIAN UNIV OF TECH
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, the main dimensionality reduction methods include PCA, LDA, local linear dimensionality reduction LLE, nonlinear dimensionality reduction kernel PCA, multi-layer automatic coding, etc., but due to the limitations of their respective methods, the efficiency is low when the data dimension is high , it is difficult to meet the urgent needs of data development

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
  • Step-by-step type data dimension reduction method based on cluster
  • Step-by-step type data dimension reduction method based on cluster
  • Step-by-step type data dimension reduction method based on cluster

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033] The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0034] A clustering-based step-by-step dimensionality reduction method of the present invention, the specific overall process is as follows figure 1 As shown, the specific steps are as follows:

[0035] Step 1, clustering the industrial monitoring data according to the distance between data points;

[0036] Step 2. Perform dimensionality reduction on each type of data of the clustering data generated in step 1, that is, partition dimensionality reduction;

[0037]Step 3: Perform a series of adjustments on the dimensionally reduced data generated in step 2, and then perform dimensionality reduction again.

[0038] The specific flow chart of step 1 is as follows figure 2 Indicated: Follow the steps below to implement:

[0039] Step 1 is specifically implemented according to the following steps:

[0040] Step (1.1), industrial monitoring d...

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 step-by-step type data dimension reduction method based on a cluster. The method includes the steps of firstly, conducting clustering on the distances between data points forindustrial monitoring data; secondly, conducting dimension reduction, namely partition dimension reduction, on each type of data of clustered data generated in the first step; thirdly, processing thedata generated in the second step, and conducting direction reduction again on the processed data. By means of the method, direction reduction can be conducted in the line direction and the row direction at the same time, the dimension reduction effectiveness is improved, and the dimension reduction efficiency is improved; a contribution is made to effective information extraction in future dataprocessing.

Description

technical field [0001] The invention belongs to the field of data mining, and in particular relates to an efficient data dimensionality reduction method combining clustering and dimensionality reduction. Background technique [0002] In recent years, a large amount of industrial monitoring data has been generated, and how to extract effective information from a large amount of data has become an important research topic in the industry. In existing research, data dimensionality reduction methods can represent high-dimensional data through low-dimensional space while retaining most of the effective information and eliminating data redundancy. It has become an effective means of information extraction and has been widely studied. At present, the main dimensionality reduction methods include PCA, LDA, local linear dimensionality reduction LLE, nonlinear dimensionality reduction kernel PCA, multi-layer automatic coding, etc., but due to the limitations of their respective method...

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): G06F17/30G06K9/62
Inventor 谢国张永艳张春丽刘伟黑新宏钱富才
Owner XIAN UNIV OF TECH