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

Method for classifying dynamic data on basis of multi-classifier fusion

A multi-classifier fusion and dynamic data technology, which is applied in the direction of electrical digital data processing, special data processing applications, instruments, etc., can solve the problem that the dynamic data classification mode cannot adapt to new requirements, etc., to improve storage performance and storage efficiency , the effect of improving accuracy

Inactive Publication Date: 2015-05-20
LANGCHAO ELECTRONIC INFORMATION IND CO LTD
View PDF4 Cites 19 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The present invention aims at the problem that with the expansion of the scale of the data center, more and more types of data, and more and more complex application scenarios, the dynamic data classification mode based on a single classifier can no longer meet the new requirements, and provides a multi-classification based The dynamic data grading method based on machine fusion improves the accuracy of data grading in complex application environments, and more reasonably expresses the storage level of multi-application and multi-type 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
  • Method for classifying dynamic data on basis of multi-classifier fusion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019] To further specify the present invention, a group of a large number of character picture data is dynamically graded. The specific process is as follows.

[0020] A dynamic data classification method based on multi-classifier fusion, the specific steps are:

[0021] ① Extract the data features of the image set data to form an initial data feature set; this data feature extraction can be carried out manually or by machine, and the original features are reduced in dimension by the transformation method, and transformed into a smaller number than the original features The new features form the initial data feature set.

[0022] ② For the set of initial data features, select the feature with the most classification information. This time, select the feature with the most linear classification information as the feature with the most classification information, and use PCA to filter out the optimal feature subset; where PCA is Optimal orthogonal linear transformation, corre...

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 method for classifying dynamic data on the basis of multi-classifier fusion, and belongs to the field of storage technologies for computers. The method includes particular steps of 1, extracting data features of data of training sets and forming initial data feature sets; 2, preprocessing data features of the initial data feature sets and screening the data features to obtain the optimal feature subsets; 3, training multiple classifiers for the optimal feature subsets to obtain different classification models; 4, fusing the different classification models via the classifiers to form dynamic data classification models, and classifying the dynamic data by the aid of the dynamic data classification models. The method has the advantages that the data classification accuracy can be improved in complicated application environments, storage hierarchies of the multi-application and multi-type data can be reasonably expressed, and the storage performance can be enhanced while the data classification accuracy is improved.

Description

technical field [0001] The invention discloses a dynamic data grading method, which belongs to the technical field of computer storage, and specifically relates to a dynamic data grading method based on multi-classifier fusion. Background technique [0002] With the advent of the era of big data and cloud storage, cloud data centers have developed rapidly, making intelligent data management with high performance and low cost a research hotspot. Due to the complex application environment, the data has the characteristics of timeliness and space, data access and processing complexity, and storage access requirements diversity, so it is necessary to classify and hierarchically process various dynamic data to meet application requirements and storage resources. Reasonable mapping between them improves the cost performance of storage devices. For example, divide data into hot data and cold data through the data classification model, place hot data on storage devices with better ...

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): G06F17/30G06K9/62
Inventor 赵雅倩陈继承
Owner LANGCHAO ELECTRONIC INFORMATION IND CO LTD
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