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

A Joint Denoising Method of Corrosion Sources for Multi-source Heterogeneous Big Data

A multi-source heterogeneous and big data technology, applied in the information field, can solve problems such as inability to handle heterogeneous data

Active Publication Date: 2019-04-16
INST OF INFORMATION ENG CHINESE ACAD OF SCI
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the drawback of the KTLQD method is that it cannot handle heterogeneous 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
  • A Joint Denoising Method of Corrosion Sources for Multi-source Heterogeneous Big Data
  • A Joint Denoising Method of Corrosion Sources for Multi-source Heterogeneous Big Data
  • A Joint Denoising Method of Corrosion Sources for Multi-source Heterogeneous Big Data

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0063] The present invention will be further described below through specific examples.

[0064] The corrosion source joint denoising method for multi-source heterogeneous big data provided by the present invention is composed of heterogeneous linear metric learning HLML and multi-source semi-supervised joint denoising MSCD algorithm, and the gradual optimization of the model is realized through a cyclic iterative process.

[0065] The HLML model in formula (7) can be simplified as:

[0066]

[0067] in, is a smooth objective function, Z=[A Z B Z ] represent optimization variables, is a closed convex set with respect to a single variable:

[0068]

[0069] Since D( ) is a continuously differentiable function with respect to the Lipschitz continuous gradient L (reference: Y. Nesterov. Introductory lectures on convex optimization, volume 87. SpringerScience & Business Media, 2004.):

[0070]

[0071] . Therefore, it is suitable to use the Accelerated Projected ...

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 relates to a corrosion source joint denoising method for multi-source heterogeneous big data. The method consists of two models, one is a heterogeneous linear metric learning (HLML) model and the other is a multi-source semi-supervised joint denoising (MSCD) model. Among them, by learning multiple heterogeneous linear metrics, the HLML model linearly projects multi-source heterogeneous data into a high-dimensional feature isomorphic space, and fully embeds complementary information between heterogeneous sources in this space, so that it can effectively capture Semantic complementarity and distributional similarity between different sources. In order to eliminate intra-source and inter-source noise, the MSCD model uses elementary transformation constraints and gradient energy competition strategies to repair the complementary relationship between heterogeneous and noisy descriptions in the feature isomorphism space learned by the HLML model, thereby purifying the multi-source heterogeneous data. Corrosion sources for accurate and robust multi-source data evaluation analysis results.

Description

technical field [0001] The invention belongs to the field of information technology, and aims at the problem of intra-source noise and inter-source noise in a massive multi-source heterogeneous corrosion data environment, and proposes a joint denoising method for corrosion sources of multi-source heterogeneous big data. Background technique [0002] In recent years, with the emergence of a large number of high-tech digital products, the multi-source heterogeneous data (Multi-source Heterogeneous Data) generated by these heterogeneous electronic devices has spread to every corner of people's real life. The so-called multi-source heterogeneous data refers to data that comes from different sources or channels, but expresses similar content, and appears in various styles such as different forms, different modalities, different perspectives, and different backgrounds. For example, Sina Weibo, Tencent WeChat, and Sohu.com report different forms of the same news; the brains of Alzh...

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 Patents(China)
IPC IPC(8): G06K9/62
CPCG06F18/2155G06F18/23
Inventor 张磊王树鹏云晓春
Owner INST OF INFORMATION ENG CHINESE ACAD OF SCI
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