Data expansion and classification method and system

A data classification and data technology, applied in the direction of neural learning methods, neural architecture, biological neural network models, etc., can solve the problems of different classification capabilities, complexity, and lack of good models for weld data, and achieve improved classification accuracy, The effect of stable model and simple structure

Pending Publication Date: 2021-08-10
XIAN UNIV OF POSTS & TELECOMM
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the traditional CNN model has a different structure, and its ability to classify weld data is also different, and the deep network does not work well for data with uncomplex features, which will also complicate the model.

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
  • Data expansion and classification method and system
  • Data expansion and classification method and system
  • Data expansion and classification method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0048]In order to enable those skilled in the art to better understand the technical solutions in the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described The embodiments are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0049] Such as figure 1 As shown, the technical solution of the present invention provides a method for data expansion and classification, including the following steps:

[0050] Step 1: Improve the DCGAN model by adding a random inactivation layer to the DCGAN model, and expand the data that needs to be enhanced through the improved DCGAN mod...

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 provides a data expansion and classification method and system. The method comprises the following steps: improving a DCGAN model through adding a random inactivation layer in the DCGAN model, and carrying out the expansion of data needing to be enhanced through the improved DCGAN model; and designing a multi-scale compression excitation network model, carrying out model parameter reduction and dimension reduction improvement, and carrying out data classification after expansion through the improved model. Based on the improved DCGAN model, the model is more stable, the quality of the generated picture is better, and a rich data set is provided for classification. Based on the improvement, the calculation amount is reduced, and the classification accuracy is improved.

Description

technical field [0001] The invention relates to the technical field of data expansion and classification, in particular to a method and system for data expansion and classification. Background technique [0002] In the production process, due to the influence of external factors such as the production environment and human and machine errors, welding products cannot be 100% correct. According to the survey, there are many products that have great potential safety hazards in product quality due to failure to detect defects in time or inaccurate detection of defect sizes, resulting in major accidents. Therefore, it is necessary to test and evaluate the products before putting them on the market to avoid industry losses. At present, most of the detection and identification of weld defects are observed and judged by experienced people through human eyes. This manual detection method has a series of problems such as time-consuming, low efficiency, and strong subjectivity. And i...

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): G06N3/04G06N3/08
CPCG06N3/08G06N3/045
Inventor 谷静朱恒安张可帅马豆豆谢泽群
Owner XIAN UNIV OF POSTS & TELECOMM
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap