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

Algorithm performance evaluation method based on multi-dimensional model

An efficiency evaluation and multi-dimensional technology, which is applied in computing, computer components, character and pattern recognition, etc., can solve the problems of inability to comprehensively evaluate the pros and cons of ship target recognition models in SAR images, and achieves rich efficiency evaluation dimensions and high performance reliable effect

Active Publication Date: 2021-04-23
AEROSPACE INFORMATION RES INST CAS
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, it is impossible to comprehensively evaluate the advantages and disadvantages of the SAR image ship target recognition model in all aspects by only evaluating these most important performances.

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
  • Algorithm performance evaluation method based on multi-dimensional model
  • Algorithm performance evaluation method based on multi-dimensional model
  • Algorithm performance evaluation method based on multi-dimensional model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0178] 1. Construction of performance evaluation model

[0179] build as figure 2 The effectiveness evaluation model shown evaluates the effectiveness of the SAR image ship target recognition model. Among them, the first-level index of core capability performance evaluation takes: data resolution better than 1m and data resolution better than 0.5m.

[0180] 2. Data collection

[0181] Collect relevant data applicable to the SAR ship target recognition model in this embodiment, specifically including collecting the data of the secondary indicators of each basic capability effectiveness evaluation and the data of each core capability effectiveness assessment secondary indicator.

[0182] 3. Parameter setting

[0183] In this embodiment, according to the evaluation purpose and the actual situation of the ship target recognition model in SAR images, expert judgment method, similar model analogy method and manager's experience are comprehensively used to set the weight paramete...

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 an intelligent algorithm efficiency evaluation method based on a multi-dimensional model, and the method comprises the steps: building an efficiency evaluation model of an SAR image ship target recognition model, wherein the efficiency evaluation model comprises a basic capability efficiency evaluation index and a core capability efficiency evaluation index; collecting data of each basic capability and efficiency evaluation secondary index and data of each core capability and efficiency evaluation secondary index; setting weight coefficients of the basic capability efficiency evaluation indexes and the core capability efficiency evaluation indexes; calculating a basic capability efficiency evaluation score according to the data of each basic capability efficiency evaluation secondary index and the weight coefficient corresponding to each level of index; calculating a core capability efficiency evaluation score according to the data of each core capability efficiency evaluation secondary index and the weight coefficient corresponding to each level of index; calculating a comprehensive performance evaluation score according to the basic capability performance evaluation score and the core capability performance evaluation score; and determining the software comprehensive maturity of the model according to the comprehensive performance evaluation score.

Description

technical field [0001] The present disclosure relates to the field of computer technology and model evaluation, in particular to an algorithm performance evaluation method based on a multi-dimensional model. Background technique [0002] For the evaluation of SAR image ship target recognition model, traditional evaluation methods can only measure the main performance of the model, such as accuracy rate, recall rate, etc. However, it is impossible to comprehensively evaluate the advantages and disadvantages of the SAR image ship target recognition model in all aspects only by evaluating these main performances. With the deployment of the model into practical applications, how to comprehensively evaluate the effectiveness of the ship target recognition model in SAR images has become an urgent problem to be solved. Contents of the invention [0003] In view of this, the present disclosure provides an algorithm performance evaluation method based on a multi-dimensional model ...

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): G06Q10/06G06K9/00
CPCG06Q10/06393G06V20/13
Inventor 孙显刁文辉付琨杨怡冉赵良瑾张文凯吴有明
Owner AEROSPACE INFORMATION RES INST CAS
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