Jove
Visualize
联系我们
JoVE
x logofacebook logolinkedin logoyoutube logo
关于 JoVE
概览领导团队博客JoVE 帮助中心
作者
出版流程编辑委员会范围与政策同行评审常见问题投稿
图书馆员
用户评价订阅访问资源图书馆顾问委员会常见问题
研究
JoVE JournalMethods CollectionsJoVE Encyclopedia of Experiments存档
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教师资源中心教师网站
使用条款与条件
隐私政策
政策

相关概念视频

Mechanical Characteristics of Steel01:18

Mechanical Characteristics of Steel

939
The mechanical characteristics of steel are assessed through various tests that evaluate its strength, toughness, and flexibility. These tests include tension, torsion, impact, bending, and hardness assessments, each providing crucial information about steel's suitability for specific applications.
The tension test is fundamental for determining tensile strength. In this test, a steel specimen is stretched using a gripping device until it breaks. The data collected during this test are used...
939

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序
Same author

<i>Wearanize+</i>: a multimodal dataset for evaluating wearable technologies in sleep research.

Sleep advances : a journal of the Sleep Research Society·2026
Same author

A Pneumonia Diagnosis Scheme Based on Hybrid Features Extracted from Chest Radiographs Using an Ensemble Learning Algorithm.

Journal of healthcare engineering·2021
Same author

<b>A Machine Learning Approach to Diagnosing Lung and Colon Cancer Using a Deep Learning-Based Classification Framework</b>.

Sensors (Basel, Switzerland)·2021
Same author

A Novel Method to Identify Pneumonia through Analyzing Chest Radiographs Employing a Multichannel Convolutional Neural Network.

Sensors (Basel, Switzerland)·2020

相关实验视频

Updated: May 3, 2026

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns
13:44

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

43.5K

基于平均轮班的原型网络用于钢表面异常识别.

Canan Tastimur1

  • 1Computer Engineering, Erzincan Binali Yildirim University, Erzincan, Turkey. ctastimur@erzincan.edu.tr.

Scientific reports
|December 30, 2025
PubMed
概括

一个新的基于平均变速的原型网络 (MSPro-Net) 显著改善了钢表面缺陷的分类. 这种方法提高了准确性,特别是在短暂的学习场景中,优于经典方法.

科学领域:

  • 材料科学与工程 材料科学与工程
  • 计算机视觉和机器学习

背景情况:

  • 热钢板的表面缺陷严重影响产品质量和市场接受度.
  • 早期发现这些缺陷对于高效的钢铁生产至关重要.

研究的目的:

  • 引入和评估基于平均变速的原型网络 (MSPro-Net) 以提高钢表面缺陷分类.
  • 证明MSPro-Net在经典原型网络上的优势,特别是在少数人学习的环境中.

主要方法:

  • 开发MSPro-Net,使用通过平均转移方法进行自适应原型计算.
  • 与经典原型网络 (CL-ProNet) 进行比较分析,使用多个N-way K-shot场景.
  • 在基准数据集上的验证包括NEU,XSDD和GC10-Det.

主要成果:

  • 与CL-ProNet相比,MSPro-Net在各种数据集和少数镜头设置中实现了明显更高的缺陷分类准确性.
  • 在NEU数据集上 (6-way 25-shot),MSPro-Net达到98.67%的准确率,而CL-ProNet.Net的准确率为50.67%.
  • 在XSDD (96.00%) 和GC10-Det (90.00%) 数据集上也观察到优异的性能,证明了稳定性.

结论:

更多相关视频

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

987
Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines
08:27

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Published on: January 5, 2024

1.6K

相关实验视频

Last Updated: May 3, 2026

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns
13:44

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

43.5K
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

987
Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines
08:27

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Published on: January 5, 2024

1.6K
  • MSPro-Net提供了更具代表性的类原型计算,从而在钢表面缺陷检测方面取得了重大改进.
  • 拟议的方法在短暂的学习中表现出色,为制造业早期缺陷识别提供了强大的工具.