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

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

The role of medical equipment reliability assessment in improving healthcare service quality: a scoping review.

BMC health services research·2026
Same author

Chromosome-Level Genome Assembly of Tea Cultivar "Aijiaowulong" Elucidates the Molecular Mechanism of Osmanthus-like Aroma Formation.

Journal of agricultural and food chemistry·2026
Same author

Green Extraction of Luteolin from Chrysanthemi Indici Flos Using Deep Eutectic Solvents: Mechanistic Insights, Antioxidant Activities, and Synergistic α-Glucosidase Inhibition.

Journal of agricultural and food chemistry·2026
Same author

Circadian rhythm of dendritic cells directs the time-dependent efficacy of photodynamic therapy.

Cell communication and signaling : CCS·2026
Same author

Recombinant expression and purification of a hybrid antimicrobial peptide Aur-Defb3 in Komagataellaphaffii.

Protein expression and purification·2026
Same author

Prediction of massive intraoperative blood transfusion requirement in lung transplantation.

Frontiers in medicine·2026

相关实验视频

Updated: Jul 27, 2025

On-Site Molecular Detection of Soil-Borne Phytopathogens Using a Portable Real-Time PCR System
14:15

On-Site Molecular Detection of Soil-Borne Phytopathogens Using a Portable Real-Time PCR System

Published on: February 23, 2018

16.7K

一种基于动态修剪门的高精度植物疾病检测方法,适合低计算平台.

Yufei Liu1, Jingxin Liu2, Wei Cheng1

  • 1College of Information and Electrical Engineering, China Agricultural University, Beijing 100083, China.

Plants (Basel, Switzerland)
|June 10, 2023
PubMed
概括

本研究介绍了一种动态修剪方法,用于自动检测植物疾病,即使是在低功耗设备上. 该模型达到94%的准确性,为各种计算环境提供了实用解决方案.

关键词:
深度学习是一种深度学习.动态修剪 动态修剪低计算平台友好型的低计算平台.重新参数化的重新参数化

更多相关视频

Imaging the Root Hair Morphology of Arabidopsis Seedlings in a Two-layer Microfluidic Platform
09:23

Imaging the Root Hair Morphology of Arabidopsis Seedlings in a Two-layer Microfluidic Platform

Published on: August 15, 2017

8.6K
Automating Citrus Budwood Processing for Downstream Pathogen Detection Through Instrument Engineering
11:30

Automating Citrus Budwood Processing for Downstream Pathogen Detection Through Instrument Engineering

Published on: April 21, 2023

795

相关实验视频

Last Updated: Jul 27, 2025

On-Site Molecular Detection of Soil-Borne Phytopathogens Using a Portable Real-Time PCR System
14:15

On-Site Molecular Detection of Soil-Borne Phytopathogens Using a Portable Real-Time PCR System

Published on: February 23, 2018

16.7K
Imaging the Root Hair Morphology of Arabidopsis Seedlings in a Two-layer Microfluidic Platform
09:23

Imaging the Root Hair Morphology of Arabidopsis Seedlings in a Two-layer Microfluidic Platform

Published on: August 15, 2017

8.6K
Automating Citrus Budwood Processing for Downstream Pathogen Detection Through Instrument Engineering
11:30

Automating Citrus Budwood Processing for Downstream Pathogen Detection Through Instrument Engineering

Published on: April 21, 2023

795

科学领域:

  • 农业科学 农业科学
  • 计算机视觉 计算机视觉
  • 机器学习 机器学习

背景情况:

  • 准确及时检测植物疾病对农业至关重要.
  • 现有的方法通常需要高计算资源,限制它们在低计算环境中的使用.
  • 需要有效和适应性的疾病检测模型.

研究的目的:

  • 提出一种基于动态修剪的方法,用于自动检测植物疾病.
  • 为了使植物疾病检测在低计算情况.
  • 开发一种可适应不同计算能力的硬件平台的模型.

主要方法:

  • 在三年内收集了四种作物和12种疾病的数据集.
  • 提出了一种重新参数化的方法,以提高卷积神经网络 (CNN) 的准确性.
  • 引入了用于自适应网络结构控制的动态修剪门.
  • 实现了理论模型并开发了相关的应用程序.

主要成果:

  • 该模型展示了多功能性,在高性能GPU和低功耗移动平台上有效运行.
  • 实现了每秒58 (FPS) 的高推断速度,超过了主流模型.
  • 通过数据增强和通过废弃实验验验证,提高了挑战子类的检测准确性.
  • 实现了0.94.4的整体模型准确度.

结论:

  • 动态修剪方法为植物疾病检测提供了高效和准确的解决方案.
  • 该模型的适应性使其适用于各种硬件,从强大的服务器到移动设备.
  • 这项研究为农业监测和疾病管理提供了一个实用的工具.