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

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

Spiking neural network decoders of finger forces from high-density intramuscular microelectrode arrays.

Nature communications·2026
Same author

FEMBA on the Edge: Physiologically-Aware Pre-Training, Quantization, and Deployment of a Bidirectional Mamba EEG Foundation Model on an Ultra-Low Power Microcontroller.

IEEE transactions on bio-medical engineering·2026
Same author

Current Trends in Ultrasound Wearables: Spotlight on System Architecture.

IEEE reviews in biomedical engineering·2026
Same author

Beyond Subject-Specific Models in Dynamical Human-Machine Interaction: Benchmarking and Optimization Strategies.

IEEE transactions on neural networks and learning systems·2026
Same author

Decoding phantom limb movements from intraneural recordings.

Nature communications·2026
Same author

BioGAP-Ultra: A Modular Edge-AI Platform for Wearable Multimodal Biosignal Acquisition and Processing.

IEEE transactions on biomedical circuits and systems·2026

相关实验视频

Updated: Jun 23, 2025

Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision
08:15

Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision

Published on: March 28, 2025

434

用sEMG驱动的手动动力学估计与在平行超低功率微控制器上的增量在线学习.

Marcello Zanghieri, Pierangelo Maria Rapa, Mattia Orlandi

    IEEE transactions on biomedical circuits and systems
    |June 17, 2024
    PubMed
    概括

    本研究介绍了表面肌电图 (sEMG) 控制的增量在线培训方法,使多指力在设备上能够准确实时估计. 该方法实现了与离线方法可比的性能,同时适用于低功耗微控制器.

    科学领域:

    • 生物医学工程 生物医学工程
    • 机器学习 机器学习
    • 人与计算机的交互

    背景情况:

    • 表面电肌图 (sEMG) 是非侵入性人机接口的一个关键技术.
    • 在sEMG信号中固有的变性,特别是跨会话,阻碍了机器学习模型的泛化.
    • 进步正在将sEMG控制从分类静态位置转变为回归动态手动运动,以获得更多的流体控制.

    研究的目的:

    • 开发一个增量在线培训策略,用于基于sEMG的同时多指力估计.
    • 创建一个紧的时间卷积网络 (TCN),适合嵌入式,设备上的学习.
    • 在现实场景中验证方法的性能和效率.

    主要方法:

    • 通过使用一个小型时间卷积网络 (TCN) 实施了增量在线培训策略.
    • 该方法在HYSER数据集上进行了验证,用于跨日性能评估.
    • 该方法被部署在一个超低功耗的GAP9微控制器上,以评估延迟和能耗.

    主要成果:

    • 增量在线训练在具有挑战性的即兴力序数据集上实现了9.58±3.89%的最大自愿收缩的跨日平均绝对误差 (MAE).
    • 性能与非嵌入式,以准确度为导向的离线培训方法相当.
    • 在GAP9微控制器上部署导致1.49ms的低延迟和每更新步骤的40.4J的能源消耗.

    更多相关视频

    A Structured Rehabilitation Protocol for Improved Multifunctional Prosthetic Control: A Case Study
    06:58

    A Structured Rehabilitation Protocol for Improved Multifunctional Prosthetic Control: A Case Study

    Published on: November 6, 2015

    9.4K
    A Human-machine-interface Integrating Low-cost Sensors with a Neuromuscular Electrical Stimulation System for Post-stroke Balance Rehabilitation
    11:06

    A Human-machine-interface Integrating Low-cost Sensors with a Neuromuscular Electrical Stimulation System for Post-stroke Balance Rehabilitation

    Published on: April 12, 2016

    10.4K

    相关实验视频

    Last Updated: Jun 23, 2025

    Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision
    08:15

    Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision

    Published on: March 28, 2025

    434
    A Structured Rehabilitation Protocol for Improved Multifunctional Prosthetic Control: A Case Study
    06:58

    A Structured Rehabilitation Protocol for Improved Multifunctional Prosthetic Control: A Case Study

    Published on: November 6, 2015

    9.4K
    A Human-machine-interface Integrating Low-cost Sensors with a Neuromuscular Electrical Stimulation System for Post-stroke Balance Rehabilitation
    11:06

    A Human-machine-interface Integrating Low-cost Sensors with a Neuromuscular Electrical Stimulation System for Post-stroke Balance Rehabilitation

    Published on: April 12, 2016

    10.4K

    结论:

    • 拟议的增量在线培训策略能够准确,实时,在设备上估计来自sEMG信号的多指力.
    • 该解决方案解决了sEMG可变性的局限性,并满足嵌入式系统的要求.
    • 这种方法为各种应用中的人机接口提供了多功能和流动的控制.