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

Classification of Signals01:30

Classification of Signals

1.6K
In signal processing, signals are classified based on various characteristics: continuous-time versus discrete-time, periodic versus aperiodic, analog versus digital, and causal versus noncausal. Each category highlights distinct properties crucial for understanding and manipulating signals.
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...
1.6K

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 High-Performance Bimetallic Ru<sub>1</sub>Mo<sub>6</sub> Active Site for Thermal Ammonia Synthesis under Mild Conditions.

Journal of the American Chemical Society·2026
Same author

Realizing efficient ammonia electrosynthesis enabled by metal-organic framework-derived CuCo-LDH.

Physical chemistry chemical physics : PCCP·2026
Same author

Sustained-Release Reducing Microenvironment Tailors Highly Crystalline FeS<sub><i>x</i></sub> Shells on Zero-Valent Iron for Enhanced Electron Transfer.

Environmental science & technology·2026
Same author

Phosphate Supply-Driven Interfacial Coordination Microenvironment Dictates the Electronic Structure and Reactivity of Zero-Valent Iron.

Environmental science & technology·2026
Same author

Simultaneous detection of water content and ferulic acid content in Angelica sinensis using NIR-HSI and multi-task hierarchical attention CNN.

Spectrochimica acta. Part A, Molecular and biomolecular spectroscopy·2026
Same author

Plasma-Driven Single-Atom Catalysis: From Synthesis to Catalytic Reactions.

Nano letters·2026

相关实验视频

Updated: May 1, 2026

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
14:08

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

42.5K

一个多类心电图信号分类器,使用二进制深度可分离CNN与合并卷积聚合方法.

Rui Zhang1, Ranran Zhou1, Zuting Zhong1

  • 1School of Integrated Circuits, Shandong University, Jinan 250101, China.

Sensors (Basel, Switzerland)
|November 27, 2024
PubMed
概括

这项研究引入了一种新的二元化深度可分离卷积神经网络 (bDSCNN),用于从心电图信号中准确,低功率的心律失常的分类. 该系统实现了高精度,同时显著减少了硬件资源的使用.

关键词:
这是一个ECGECGECGECGECG.在FPGA中,FPGA是指FPGA.二元化深度可分离的卷积神经网络 (bDSCNN)区块wise增量计算的积分计算.合并卷积合并方法的方法.多个分类器的多个分类器.

更多相关视频

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
07:35

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

7.4K
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

470

相关实验视频

Last Updated: May 1, 2026

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
14:08

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

42.5K
Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
07:35

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

7.4K
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

470

科学领域:

  • 生物医学工程 生物医学工程
  • 人工智能的人工智能
  • 心脏病学 心脏病学

背景情况:

  • 由于高压缩率,二元卷积神经网络 (bCNNs) 为心律失常的分类提供了高效的解决方案.
  • 然而,在二元化过程中产生的多类心电图信号分类中,bCNN面临准确性挑战.

研究的目的:

  • 开发一种有效的ECG信号多分类器系统,使用二元化深度可分离卷积神经网络 (bDSCNN).
  • 通过将R峰值间隔数据与P-QRS-T特征集成,以解决多类心电图分类中的准确性损失.

主要方法:

  • 采用了二元化的深度可分离卷积神经网络 (bDSCNN) 与合并卷积聚合 (MCP) 方法.
  • 使用区块级增量计算来最大限度地减少硬件资源消耗.
  • 集成的R峰值间隔数据与P-QRS-T功能,以提高分类性能.

主要成果:

  • 在五个类别的ECG信号中获得了96.61%的分类准确度和89.08%的宏观F1得分.
  • 在五种类别的心电图信号分类中,证明了20μW的低动态功率消耗.
  • 与现有的bCNN心电图分类器相比,至少减少了2.94倍和1.74倍的硬件资源使用 (BRAM,LUTs+REGs).

结论:

  • 拟议的bDSCNN与MCP方法有效地提高了多类ECG信号分类的准确性,同时减少了计算复杂性和硬件资源.
  • 这种方法为嵌入式系统的实时心律失常检测提供了一个有希望的低功耗,低存储的解决方案.