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

Inductively Coupled Plasma Atomic Emission Spectroscopy: Instrumentation01:26

Inductively Coupled Plasma Atomic Emission Spectroscopy: Instrumentation

194
Inductively coupled plasma (ICP) is the common plasma source used in atomic emission spectroscopy (AES), a technique that detects and analyzes various elements in a sample. This method is often called inductively coupled plasma atomic emission spectroscopy (ICP-AES).
There are three main types of inductively coupled plasma atomic emission spectroscopy  (ICP-AES) instruments: sequential, simultaneous multichannel, and Fourier transform instruments, with the latter being less commonly used....
194

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

Brain and Muscle ARNT-Like 1 Ameliorates Sepsis-Induced Acute Lung Injury by Orchestrating Endoplasmic Reticulum-Phagy and Mitochondrial Metabolism.

Critical care medicine·2026
Same author

Mechanics-free speckle contrast optical spectroscopy with liquid-lens-based adaptive illumination.

Optics letters·2026
Same author

Tetrahedral DNA Nanostructure-Based Biomimetic Nanovesicles Attenuate Sepsis-Associated ARDS by Suppressing Glycolysis via the BMAL1/PFKFB3 Axis.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2026
Same author

Macrophage-Targeted Nanocarriers Based on Tetrahedral DNA Nanostructure Alleviate Sepsis-Induced Acute Lung Injury by Triple-Pathway Suppression of Pyroptosis.

ACS applied materials & interfaces·2026
Same author

Identification of MTURN as a trained immunity-related biomarker for heart failure <i>via</i> integrative transcriptomic machine learning analysis and experimental validation.

Frontiers in immunology·2026
Same author

Assessing liquid light guides in diffuse correlation spectroscopy systems.

Biomedical optics express·2025

相关实验视频

Updated: Jun 7, 2025

Direct Comparison of Hyperspectral Stimulated Raman Scattering and Coherent Anti-Stokes Raman Scattering Microscopy for Chemical Imaging
09:46

Direct Comparison of Hyperspectral Stimulated Raman Scattering and Coherent Anti-Stokes Raman Scattering Microscopy for Chemical Imaging

Published on: April 28, 2022

3.9K

走向高性能深度学习架构和硬件加速器设计,以在扩散相关谱学中进行可靠的分析.

Zhenya Zang1, Quan Wang1, Mingliang Pan1

  • 1Department of Biomedical Engineering, University of Strathclyde, Glasgow, United Kingdom.

Computer methods and programs in biomedicine
|November 12, 2024
PubMed
概括
此摘要是机器生成的。

本研究介绍了一种紧的深度学习模型和硬件平台,用于在扩散相关谱学中更快地重建血液流量指数. 该系统提供了更高的准确性和实时处理,缩小了分散相关性光谱系统.

关键词:
血液流量指数 血液流量指数深度神经网络是一个神经网络.深度学习硬件加速器扩散的相关性光谱仪光谱仪.

更多相关视频

High Resolution Phonon-assisted Quasi-resonance Fluorescence Spectroscopy
10:40

High Resolution Phonon-assisted Quasi-resonance Fluorescence Spectroscopy

Published on: June 28, 2016

7.5K
Observation and Analysis of Blinking Surface-enhanced Raman Scattering
05:52

Observation and Analysis of Blinking Surface-enhanced Raman Scattering

Published on: January 11, 2018

7.4K

相关实验视频

Last Updated: Jun 7, 2025

Direct Comparison of Hyperspectral Stimulated Raman Scattering and Coherent Anti-Stokes Raman Scattering Microscopy for Chemical Imaging
09:46

Direct Comparison of Hyperspectral Stimulated Raman Scattering and Coherent Anti-Stokes Raman Scattering Microscopy for Chemical Imaging

Published on: April 28, 2022

3.9K
High Resolution Phonon-assisted Quasi-resonance Fluorescence Spectroscopy
10:40

High Resolution Phonon-assisted Quasi-resonance Fluorescence Spectroscopy

Published on: June 28, 2016

7.5K
Observation and Analysis of Blinking Surface-enhanced Raman Scattering
05:52

Observation and Analysis of Blinking Surface-enhanced Raman Scattering

Published on: January 11, 2018

7.4K

科学领域:

  • 生物医学光学 生物医学光学
  • 计算成像技术的成像
  • 硬件加速器 硬件加速器

背景情况:

  • 扩散相关谱 (DCS) 对于非侵入性血流监测至关重要.
  • 准确的血液流量指数 (BFi) 重建是计算密集的.
  • 现有的方法通常需要大量的后处理,缺乏小型化.

研究的目的:

  • 在DCS中开发一个紧的深度学习 (DL) 架构,用于BFi重建.
  • 创建一个高度并行计算硬件平台,用于实时BFi计算.
  • 通过将BFi重建集成到芯片上来缩小DCS系统.

主要方法:

  • 一个轻量级的DL架构使用模拟自相关函数 (ACF) 来训练,这些函数是从分析模型中生成的.
  • 在FPGA (Zynq-7000和Zynq-UltraScale+) 上硬件实现,使用解卷,管道和像素智能并行.
  • 简化DL计算原体使用减法来提取特征和固定点定量化.

主要成果:

  • 与合成数据上的CNN相比,BFi和一致性因子β的平均平方误差 (MSE) 提高了66.7%和18.5%.
  • 在Zynq-7000和Zynq-UltraScale+ FPGAs上分别启用了每秒10和15个ACF的实时处理.
  • 证明了从强度光子数据到BFi和β的端到端芯片上的转换,超过独立硬件加速器的性能.

结论:

  • 拟议的紧型DL架构和FPGA平台为微型DCS系统提供了高效的实时BFi重建.
  • 这种集成的芯片解决方案消除了对后处理的需求,提高了DCS的实用性.
  • FPGA加速器的计算效率与CPU和GPU解决方案进行了全面的比较.