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

Response Surface Methodology01:16

Response Surface Methodology

127
Response Surface Methodology (RSM) is a collection of statistical and mathematical techniques used to develop, improve, and optimize processes. It is particularly valuable when many input variables or factors potentially influence a response variable.
The process of RSM involves several key steps:
127

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

A prospective randomized controlled trial comparing the effect and safety of Piranha and VersaCut morcellation devices in transurethral holmium laser enucleation of the prostate.

International urology and nephrology·2022
Same author

The roles of inactivated vaccines in older patients with infection of Delta variant in Nanjing, China.

Aging·2022
Same author

Porosity Tunable Poly(Lactic Acid)-Based Composite Gel Polymer Electrolyte with High Electrolyte Uptake for Quasi-Solid-State Supercapacitors.

Polymers·2022
Same author

Effect of pyrolysis temperature on sulfur content, extractable fraction and release of sulfate in corn straw biochar.

RSC advances·2022
Same author

Preparation and properties of PTFE hollow fiber membranes for the removal of ultrafine particles in PM<sub>2.5</sub> with repetitive usage capability.

RSC advances·2022
Same author

Effects of dairy manure biochar on adsorption of sulfate onto light sierozem and its mechanisms.

RSC advances·2022

相关实验视频

Updated: Jun 27, 2025

Author Spotlight: Optimization of Airflow Velocities in Battery Cooling Systems for Enhanced Thermal Performance and Reduced Energy Consumption
10:36

Author Spotlight: Optimization of Airflow Velocities in Battery Cooling Systems for Enhanced Thermal Performance and Reduced Energy Consumption

Published on: November 3, 2023

1.5K

基于粒子群优化算法和图形处理器的雾预测模型的设计和优化.

Zuhan Liu1, Kexin Zhao2, Xuehu Liu2

  • 1School of Information Engineering, Nanchang Institute of Technology, Nanchang, 330099, China. lzh512@nit.edu.cn.

Scientific reports
|April 26, 2024
PubMed
概括

准确的细颗粒物 (PM2.5) 预测至关重要. 一个新的PSO-CPU-GPU-SVR模型显著加快了雾预测,为环境监测提供了更高的准确性和可靠性.

关键词:
图形处理单元 图形处理单元雾预测 雾预测并行计算是一种平行计算.支持矢量回归的支持矢量回归

更多相关视频

Spatial Multiobjective Optimization of Agricultural Conservation Practices using a SWAT Model and an Evolutionary Algorithm
11:53

Spatial Multiobjective Optimization of Agricultural Conservation Practices using a SWAT Model and an Evolutionary Algorithm

Published on: December 9, 2012

13.0K
Design and Optimization Strategies of a High-Performance Vented Box
14:23

Design and Optimization Strategies of a High-Performance Vented Box

Published on: June 9, 2023

1.1K

相关实验视频

Last Updated: Jun 27, 2025

Author Spotlight: Optimization of Airflow Velocities in Battery Cooling Systems for Enhanced Thermal Performance and Reduced Energy Consumption
10:36

Author Spotlight: Optimization of Airflow Velocities in Battery Cooling Systems for Enhanced Thermal Performance and Reduced Energy Consumption

Published on: November 3, 2023

1.5K
Spatial Multiobjective Optimization of Agricultural Conservation Practices using a SWAT Model and an Evolutionary Algorithm
11:53

Spatial Multiobjective Optimization of Agricultural Conservation Practices using a SWAT Model and an Evolutionary Algorithm

Published on: December 9, 2012

13.0K
Design and Optimization Strategies of a High-Performance Vented Box
14:23

Design and Optimization Strategies of a High-Performance Vented Box

Published on: June 9, 2023

1.1K

科学领域:

  • 环境科学 环境科学
  • 计算机科学 计算机科学
  • 数据科学数据科学数据科学

背景情况:

  • 微粒物质 (PM2.5) 污染是影响健康和生态系统的重大全球环境危机.
  • 准确的PM2.5预测是必不可少的,但受到数据量和模型准确性限制的挑战.
  • 现有的深度学习和支持向量回归 (SVR) 模型在优化,培训时间和数据处理方面存在缺点.

研究的目的:

  • 开发一个优化和高效的模型来预测PM2.5水平.
  • 在雾预测中克服传统和深度学习模型的局限性.
  • 提高空气质量预测的速度,稳定性和可靠性.

主要方法:

  • 开发了基于CUDA的代码来优化支持矢量回归 (SVR) 算法.
  • 结合SVR与智能算法:遗传算法 (GA),搜索算法 (SSA) 和粒子集群优化 (PSO).
  • 使用中央处理单元-图形处理单元 (CPU-GPU) 实现了异质并行计算方法.

主要成果:

  • 与CPU-GPU并行计算相结合的智能算法显著提高了SVR效率.
  • 粒子群集优化-中央处理单元-图形处理单元-支持向量回归 (PSO-CPU-GPU-SVR) 模型显示了实质性的速度改进 (比PSO-SVR快6.21-35.34倍).
  • 该PSO-CPU-GPU-SVR模型在雾预测中实现了高精度,增强稳定性和可靠性.

结论:

  • 该PSO-CPU-GPU-SVR模型代表了有效和准确的PM2.5预测的突破.
  • 这种方法比现有的实时空气质量监测方法具有显著的优势.
  • 这些发现为环境决策和公共卫生保护提供了宝贵的见解.