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

Pulse rhythm01:30

Pulse rhythm

782
Pulse rhythm refers to the pattern of pulsations within specific intervals, offering valuable insights into the regularity or irregularity of the heart's beats as observed through the pattern of pulsation within specific intervals. A regular pulse exhibits a consistent heart rate with uniform waveforms and pulsation force, variations of which can be classified as normal, weak, or bounding.
Conversely, an irregular pulse pattern is termed dysrhythmia, stemming from disruptions in cardiac...
782

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

Multimodal Biometric Framework for Evaluating Emotional Impact of Chromatic Manipulation in Cinematic Content.

Sensors (Basel, Switzerland)·2026
Same author

Localized Temperature Monitoring in Mouse Brain during Light Delivery via a Non-Planar Tapered Fiber-Integrated µRTD Sensor.

Advanced materials (Deerfield Beach, Fla.)·2026
Same author

Optoelectrical Devices for Neural Interfacing: Engineering Integration, Stability, and Multimodal Sensing.

Advanced healthcare materials·2026
Same author

Sparse Temporal AutoEncoder for ECG Anomaly Detection.

Sensors (Basel, Switzerland)·2026
Same author

A Laboratory-Based Federated Learning Deployment on Real Devices for ECG-Based Clinical Decision Support Systems.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2025
Same author

Forehead and In-Ear EEG Acquisition and Processing: Biomarker Analysis and Memory-Efficient Deep Learning Algorithm for Sleep Staging with Optimized Feature Dimensionality.

Sensors (Basel, Switzerland)·2025

相关实验视频

Updated: Jun 22, 2025

A Novel Digital Platform for a Monitored Home-based Cardiac Rehabilitation Program
04:24

A Novel Digital Platform for a Monitored Home-based Cardiac Rehabilitation Program

Published on: April 19, 2019

11.5K

机器学习算法用于处理和分类未分割的声心图信号:一种有效的边缘计算解决方案,适用于可穿戴设备.

Roberto De Fazio1, Lorenzo Spongano1,2, Massimo De Vittorio1,2

  • 1Department of Innovation Engineering, University of Salento, 73100 Lecce, Italy.

Sensors (Basel, Switzerland)
|June 27, 2024
PubMed
概括
此摘要是机器生成的。

这项研究开发了对心电图 (PCG) 信号的机器学习分类器,在检测心脏病如冠状动脉疾病和心心门缩等心脏病时实现了高准确性,而无需细分. 神经网络为这些负担得起的心脏监测工具提供了良好的性能和记忆效率平衡.

关键词:
二进制分类器二进制分类器这是分类分类的分类.机器学习是机器学习.多类分类器是多类分类器.不分段的心电图和心电图.

更多相关视频

Design and Analysis for Fall Detection System Simplification
08:05

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

10.7K
A Single-Channel and Non-Invasive Wearable Brain-Computer Interface for Industry and Healthcare
06:34

A Single-Channel and Non-Invasive Wearable Brain-Computer Interface for Industry and Healthcare

Published on: July 7, 2023

2.3K

相关实验视频

Last Updated: Jun 22, 2025

A Novel Digital Platform for a Monitored Home-based Cardiac Rehabilitation Program
04:24

A Novel Digital Platform for a Monitored Home-based Cardiac Rehabilitation Program

Published on: April 19, 2019

11.5K
Design and Analysis for Fall Detection System Simplification
08:05

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

10.7K
A Single-Channel and Non-Invasive Wearable Brain-Computer Interface for Industry and Healthcare
06:34

A Single-Channel and Non-Invasive Wearable Brain-Computer Interface for Industry and Healthcare

Published on: July 7, 2023

2.3K

科学领域:

  • 生物医学工程 生物医学工程
  • 心脏病学 心脏病学
  • 机器学习 机器学习

背景情况:

  • 声心图 (PCG) 信号提供了一种可负担的方法来监测心脏状况.
  • 准确的PCG信号分类对于诊断各种心脏病理至关重要.
  • 现有的方法可能需要复杂的心声细分,限制了它们的适用性.

研究的目的:

  • 训练和测试机器学习分类器 (SVM,k-NN,NN) 用于PCG信号的二进制和多类分类.
  • 在不依赖心声细分算法的情况下评估分类器性能.
  • 评估分类器性能和内存占用之间的权衡,以在资源有限的系统中潜在实施.

主要方法:

  • 使用了两个Physionet/CinC 2016数据集,包括482个 (二进制) 和826个 (多类) PCG信号.
  • 预处理的PCG信号,包括尖峰去除,消噪,过和正常化.
  • 从5秒中提取的特征,每次转移1秒,用于训练和测试SVM,k-NN和NN分类器.

主要成果:

  • 二进制分类实现了从92.4%到98.7%的精度,内存使用量从92.7kB到11.1MB.
  • 多类分类 (正常,CAD,MVP,良性) 的准确率从95.3%到98.6%,内存使用量从233kB到14.1MB.
  • 神经网络 (NN) 提供了最佳的性能-内存权衡;k-NN提供了最高性能与更高的内存成本.
  • 无效改进信号噪声比 (SNR) 15-30 dB,对分类器性能影响最小.

结论:

  • 机器学习分类器,特别是NN,可以有效地对PCG信号进行分类,以便在不进行细分的情况下监测心脏状况.
  • 开发的模型表现出高精度和相对较低的内存占用,适用于资源有限的设备.
  • 这种方法为广泛的心脏病查和诊断提供了一个有希望的,负担得起的工具.