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

When laterality fails: sublethal cyclosporin-A exposure impairs courtship and reproduction in Ostrinia furnacalis.

Journal of economic entomology·2026
Same author

Extracellular ssDNA from <i>Pittosporum tobira</i> Exerts Strong Insecticidal Activity on <i>Coccus hesperidum</i>: A Natural Parallel to 'Genetic Zipper' Technology.

International journal of molecular sciences·2026
Same author

Evidence of visual learning and wavelength differential responses in three podocopids (Crustacea: Ostracoda).

BMC biology·2026
Same author

Integration of temporal patterns, genotypic response, and environmental-determinants on aphid infestation in wheat.

Bulletin of entomological research·2026
Same author

YOLO11-based deep learning and machine vision framework for automated detection and counting of Rhopalosiphum padi (Hemiptera: Aphididae).

Journal of economic entomology·2026
Same author

Seasonal dynamics and environmental drivers of Aedes aegypti and Aedes albopictus (Diptera: Culicidae) in urban Punjab, Pakistan: evidence from larval surveillance.

Environmental entomology·2026

相关实验视频

Updated: Jun 10, 2025

Flying Insect Detection and Classification with Inexpensive Sensors
05:16

Flying Insect Detection and Classification with Inexpensive Sensors

Published on: October 15, 2014

25.1K

通过转移学习框架对虫虫害的发展阶段进行自动分类.

Wei-Bo Qin1, Arzlan Abbas1, Sohail Abbas1

  • 1College of Plant Protection, Jilin Agricultural University, 2888 Xincheng Road, Changchun 130118, Jilin Province, China.

Environmental entomology
|October 13, 2024
PubMed
概括
此摘要是机器生成的。

使用深度学习的自动化系统准确地识别了四种主要玉米害虫的幼虫阶段. 这项技术通过改进害虫管理策略,帮助精准农业.

关键词:
类动物 (Lepidoptera) 是一种类动物.卷积神经网络模型模型幼虫的发展 幼虫的发展转移学习转移学习

更多相关视频

Fully Automated Leg Tracking in Freely Moving Insects using Feature Learning Leg Segmentation and Tracking FLLIT
08:04

Fully Automated Leg Tracking in Freely Moving Insects using Feature Learning Leg Segmentation and Tracking FLLIT

Published on: April 23, 2020

6.8K
Author Spotlight: Analysis of Ovarian Anatomy in Migratory Insects to Overcome Experimental Challenges
04:41

Author Spotlight: Analysis of Ovarian Anatomy in Migratory Insects to Overcome Experimental Challenges

Published on: July 14, 2023

1.3K

相关实验视频

Last Updated: Jun 10, 2025

Flying Insect Detection and Classification with Inexpensive Sensors
05:16

Flying Insect Detection and Classification with Inexpensive Sensors

Published on: October 15, 2014

25.1K
Fully Automated Leg Tracking in Freely Moving Insects using Feature Learning Leg Segmentation and Tracking FLLIT
08:04

Fully Automated Leg Tracking in Freely Moving Insects using Feature Learning Leg Segmentation and Tracking FLLIT

Published on: April 23, 2020

6.8K
Author Spotlight: Analysis of Ovarian Anatomy in Migratory Insects to Overcome Experimental Challenges
04:41

Author Spotlight: Analysis of Ovarian Anatomy in Migratory Insects to Overcome Experimental Challenges

Published on: July 14, 2023

1.3K

科学领域:

  • 农业科学 农业科学
  • 计算机科学 计算机科学
  • 昆虫学 昆虫学是一门学科.

背景情况:

  • 玉米很容易受到虫虫害的影响,这使手动识别和控制幼虫阶段变得复杂.
  • 准确识别害虫幼虫阶段对于有效的综合性害虫管理 (IPM) 至关重要.

研究的目的:

  • 开发和评估一个自动化分类系统,用于识别四种主要的玉米虫害虫的幼虫发育阶段.
  • 为了比较五个卷积神经网络 (CNN) 架构的性能,用于此分类任务.

主要方法:

  • 使用了五个CNN架构 (ConvNeXt,Densenet121,EfficientNetv2,MobileNet,ResNet),并通过两个优化器进行了微调 (SGD与动量,Adam).
  • 基于准确性,精度,回忆和F1分数的评估模型,用于分类四种害虫物种中的23个实例.
  • 在自然现场环境中测试了表现最佳的模型.

主要成果:

  • 配有Adam优化器的Densenet121模型在实验室环境中实现了最高的分类准确率96.65%.
  • 这个模型展示了高性能指标:98.71%的精度,98.66%的回忆和98.66%的F1得分.
  • 在实地测试中,Adam_Densenet121模型在识别四种害虫的幼虫阶段时获得了90%的准确性.

结论:

  • 基于转移学习的CNN模型,特别是与Adam一起的Densenet121,有效地自动识别了玉米中类幼虫的身份.
  • 这种自动化系统提供了一个有前途的工具,用于提高农业中精确的综合性害虫管理策略.