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

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving01:29

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

56
Mechanistic models play a crucial role in algorithms for numerical problem-solving, particularly in nonlinear mixed effects modeling (NMEM). These models aim to minimize specific objective functions by evaluating various parameter estimates, leading to the development of systematic algorithms. In some cases, linearization techniques approximate the model using linear equations.
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
56

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

Configuring Parallelism for Hybrid Layouts Using Multi-Objective Optimization.

Big data·2020
Same author

Discovery of decomposed and mummified corpses in the domestic setting--a marker of social isolation?

Journal of forensic sciences·2002
查看所有相关文章

相关实验视频

Updated: Jul 10, 2025

Measuring Sub-23 Nanometer Real Driving Particle Number Emissions Using the Portable DownToTen Sampling System
08:59

Measuring Sub-23 Nanometer Real Driving Particle Number Emissions Using the Portable DownToTen Sampling System

Published on: May 22, 2020

5.5K

evalPM:用于评估用于颗粒物预测的机器学习模型的框架.

Lucas Woltmann1, Jonas Deepe2, Claudio Hartmann2

  • 1TU Dresden, Dresden Database Research Group, Dresden, Germany. lucas.woltmann@tu-dresden.de.

Environmental monitoring and assessment
|November 18, 2023
PubMed
概括

颗粒物 (PM) 污染对健康构成重大风险. 评估PM框架简化了机器学习模型的创建和比较,以准确预测PM度,帮助环境健康研究.

科学领域:

  • 环境科学 环境科学
  • 数据科学数据科学数据科学
  • 公共卫生 公共卫生

背景情况:

  • 颗粒物 (PM) 空气污染是全球主要的健康问题.
  • 准确预测未来的PM度对于制定有效的缓解策略至关重要.
  • 现有的用于PM预测的机器学习 (ML) 模型缺乏标准化的评估,阻碍了比较和选择.

研究的目的:

  • 引入evalPM,这是一个灵活的框架,用于构建,评估和比较用于PM预测的ML模型.
  • 为了应对由于数据集和评估指标的多样性而导致不同的ML模型进行比较的挑战.
  • 为了方便选择最佳的ML模型用于特定的PM吸入预测任务.

主要方法:

  • 开发了一个模块化框架, evalPM,在数据集,特性,目标变量,模型类型,超参数和评估指标方面提供灵活性.
  • 在evalPM框架内从现有文献中实现了16种不同的ML模型.
  • 使用四个不同的欧洲数据集进行了PM度的时间预测.

主要成果:

  • 通过对16个ML模型的比较分析,展示了evalPM框架的功能和优势.
  • 展示了框架能够快速创建和评估基于ML的PM预测模型的能力.
  • 强调了框架在评估不同数据集和预测任务中的模型性能方面的实用性.
关键词:
我们的框架框架框架.机器学习是机器学习.颗粒物质是颗粒物质中的一种.预测 预测 预测

更多相关视频

Assessing the Particulate Matter Removal Abilities of Tree Leaves
05:07

Assessing the Particulate Matter Removal Abilities of Tree Leaves

Published on: October 7, 2018

6.8K
Evaluating Regional Pulmonary Deposition using Patient-Specific 3D Printed Lung Models
07:56

Evaluating Regional Pulmonary Deposition using Patient-Specific 3D Printed Lung Models

Published on: November 11, 2020

4.3K

相关实验视频

Last Updated: Jul 10, 2025

Measuring Sub-23 Nanometer Real Driving Particle Number Emissions Using the Portable DownToTen Sampling System
08:59

Measuring Sub-23 Nanometer Real Driving Particle Number Emissions Using the Portable DownToTen Sampling System

Published on: May 22, 2020

5.5K
Assessing the Particulate Matter Removal Abilities of Tree Leaves
05:07

Assessing the Particulate Matter Removal Abilities of Tree Leaves

Published on: October 7, 2018

6.8K
Evaluating Regional Pulmonary Deposition using Patient-Specific 3D Printed Lung Models
07:56

Evaluating Regional Pulmonary Deposition using Patient-Specific 3D Printed Lung Models

Published on: November 11, 2020

4.3K

结论:

  • 评估PM框架显著简化了开发和评估用于PM预测的ML模型的过程.
  • 它提供了一种标准化和灵活的方法,克服了以前比较研究的局限性.
  • EvalPM支持知情决策,为环境PM预测选择最适合的ML模型.