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

Cardiovascular toxicity of CDK4/6 inhibitors combined with endocrine therapy versus endocrine therapy alone in HR+/HER2- breast cancer: a real-world study based on the FAERS database.

Frontiers in pharmacology·2026
Same author

Dual inhibition of glycolysis and epigenetics via a nanodelivery system for colorectal cancer treatment.

Nanomedicine : nanotechnology, biology, and medicine·2026
Same author

The regulatory roles of non-coding RNAs in aerobic glycolysis and therapeutic potential in pancreatic ductal adenocarcinoma.

Annals of medicine·2026
Same author

Sleep microstructure correlates of the first-night effect: sleep spindles and slow-wave activity in healthy adults.

Sleep & breathing = Schlaf & Atmung·2026
Same author

Enrichment of lithium by lithium-accumulating bacteria and its enhancement by electrical stimulation.

Bioresource technology·2026
Same author

A Study of 3-Substituted 7-Methoxy-2,3,4,5-tetrahydro-1<i>H</i>-benzo[<i>d</i>]azepin-1-ols Leading to Candidate PET Radioligands for Imaging Brain GluN2B: Design, Synthesis, and Structure-Activity Relationships.

Molecules (Basel, Switzerland)·2026

相关实验视频

Updated: May 8, 2025

Noninvasive, In-pen Approach Test for Laboratory-housed Pigs
06:30

Noninvasive, In-pen Approach Test for Laboratory-housed Pigs

Published on: June 5, 2019

8.3K

一个基于深度学习的新预测模型,用于猪舍环境.

Zhidong Wu1,2,3, Kaixiang Xu4, Yanwei Chen4

  • 1School of Mechanical and Electrical Engineering, Qiqihar University, Qiqihar, 161006, China. wzd139446@163.com.

Scientific reports
|December 27, 2024
PubMed
概括

一种新的贝叶斯优化 (BO) 增强了挤压和刺激卷积神经网络 (SE-CNN) 与门式循环单元 (GRU) 准确地预测了猪舍环境. 这种模型通过精确的环境控制来改善动物福利,优于现有的方法.

关键词:
贝叶斯优化算法贝叶斯优化算法卷积神经网络是一种卷积神经网络.环境预测模型环境预测模型有门的经常性单位.猪舍的猪舍,就是一个猪舍.挤压和激发可以进行.

更多相关视频

A Pipeline using Bilateral In Utero Electroporation to Interrogate Genetic Influences on Rodent Behavior
06:59

A Pipeline using Bilateral In Utero Electroporation to Interrogate Genetic Influences on Rodent Behavior

Published on: May 21, 2020

4.0K
Tracking Rats in Operant Conditioning Chambers Using a Versatile Homemade Video Camera and DeepLabCut
08:32

Tracking Rats in Operant Conditioning Chambers Using a Versatile Homemade Video Camera and DeepLabCut

Published on: June 15, 2020

12.3K

相关实验视频

Last Updated: May 8, 2025

Noninvasive, In-pen Approach Test for Laboratory-housed Pigs
06:30

Noninvasive, In-pen Approach Test for Laboratory-housed Pigs

Published on: June 5, 2019

8.3K
A Pipeline using Bilateral In Utero Electroporation to Interrogate Genetic Influences on Rodent Behavior
06:59

A Pipeline using Bilateral In Utero Electroporation to Interrogate Genetic Influences on Rodent Behavior

Published on: May 21, 2020

4.0K
Tracking Rats in Operant Conditioning Chambers Using a Versatile Homemade Video Camera and DeepLabCut
08:32

Tracking Rats in Operant Conditioning Chambers Using a Versatile Homemade Video Camera and DeepLabCut

Published on: June 15, 2020

12.3K

科学领域:

  • 农业工程 农业工程
  • 人工智能在农业中的应用
  • 环境监测 环境监测

背景情况:

  • 准确预测室内猪舍的环境参数 (温度,湿度,CO2,NH3) 对于动物福利和有效的农场管理至关重要.
  • 现有的预测模型经常与复杂的环境动态作斗争,并实现高预测准确度.

研究的目的:

  • 为猪舍环境开发一个先进的预测模型,使用贝叶斯优化 (BO),挤压激发卷积神经网络 (SE-CNN) 和封闭循环单元 (GRU) 的组合.
  • 提高关键环境参数的预测准确性和稳定性,从而支持积极的环境控制和改善动物福利.

主要方法:

  • 提出了一个混合模型,集成BO用于超参数调,SE-CNN用于特征提取,GRU用于序列建模.
  • SE-CNN 块提取本地特征,SE 块优化特征频道权重以改善歧视.
  • GRU捕捉了环境数据序列中的长期依赖性,以预测未来的价值.

主要成果:

  • 与CNN-LSTM,CNN-BiLSTM和CNN-GRU模型相比,BO-SE-CNN-GRU模型在预测温度,湿度,CO2和NH3度方面表现优异.
  • 实现了高预测准确度,由0.9883的确定系数 (R2) 证明,0.03243的平均绝对误差 (MSE) 和0.01536的氨预测的平均绝对百分比误差 (MAPE).
  • 该模型在预测准确性和稳定性方面表现出显著的优势,提供可靠的决策支持.

结论:

  • 开发的BO-SE-CNN-GRU模型为预测室内猪环境提供了高度准确和稳定的解决方案.
  • 这种先进的预测能力使得及时的干预和控制措施成为可能,大大有助于改善动物福利和优化农场管理.
  • 该模型的有效性凸显了将先进的人工智能技术集成到精密畜牧业的潜力.