Search research articles

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 Journal Methods Collections JoVE Encyclopedia of Experiments 存档

教育

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual 教师资源中心教师网站

使用条款与条件

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

Delamination Localization in CFRP Laminates Using One-Way Mixing of Ultrasonic Guided Waves.

Sensors (Basel, Switzerland)·2026

Same author

MMG-Based Motion Segmentation and Recognition of Upper Limb Rehabilitation Using the YOLOv5s-SE.

Sensors (Basel, Switzerland)·2025

Same author

Replay-Based Incremental Learning Framework for Gesture Recognition Overcoming the Time-Varying Characteristics of sEMG Signals.

Sensors (Basel, Switzerland)·2024

Same author

Investigation of Viscoelastic Guided Wave Properties in Anisotropic Laminated Composites Using a Legendre Orthogonal Polynomials Expansion-Assisted Viscoelastodynamic Model.

Polymers·2024

Same author

Mechanomyography Signal Pattern Recognition of Knee and Ankle Movements Using Swarm Intelligence Algorithm-Based Feature Selection Methods.

Sensors (Basel, Switzerland)·2023

Same author

Unsupervised Monocular Depth and Camera Pose Estimation with Multiple Masks and Geometric Consistency Constraints.

Sensors (Basel, Switzerland)·2023

Search research articles

相关实验视频

Updated: Jul 2, 2025

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

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

Published on: March 28, 2025

机械表学信号识别手动的图案,使用集群智能算法,基于加速传感器的优化支向量机器.

Yue Zhang¹, Gangsheng Cao², Maoxun Sun³

¹School of Mechanical Engineering, Nantong University, Nantong 226019 China.

Medical engineering & physics

|February 28, 2024

概括

这项研究通过机械学 (MMG) 信号和优化的支持矢量机器 (SVM) 来增强手部运动分类. 使用时间域 (TD) 和频域 (FD) 功能的灰狼优化 (GWO) 实现了93.55%的准确性,优于小型数据集的其他方法.

关键词:

头搜索搜索搜索头搜索搜索卷积神经网络是一种卷积神经网络.灰狼优化优化灰狼优化机械力学图谱 (Mechanomyography) 是一种机械力学图谱.模式识别模式识别模式识别斯帕罗搜索算法 (Sparrow search algorithm) 是一个非常简单的搜索算法.

更多相关视频

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

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

Published on: November 6, 2015

Author Spotlight: Enhancing Neurorehabilitation Through EEG, Motor Imagery, and Virtual Reality

Author Spotlight: Enhancing Neurorehabilitation Through EEG, Motor Imagery, and Virtual Reality

Published on: May 10, 2024

相关实验视频

Last Updated: Jul 2, 2025

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

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

Published on: March 28, 2025

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

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

Published on: November 6, 2015

Author Spotlight: Enhancing Neurorehabilitation Through EEG, Motor Imagery, and Virtual Reality

Author Spotlight: Enhancing Neurorehabilitation Through EEG, Motor Imagery, and Virtual Reality

Published on: May 10, 2024

科学领域:

生物医学工程生物医学工程
信号处理信号处理
机器学习机器学习

背景情况:

机械肌图 (MMG) 信号分析为手动分类提供了潜力.
准确的分类对于人机交互和可穿戴设备至关重要.
优化机器学习模型是改善基于MMG的识别的关键.

研究的目的:

调查小群智能算法的有效性,以优化支持矢量机 (SVM) 以使用MMG信号进行手动模式识别.
为了比较不同特征提取方法 (时间域,波形包节点能量,频域,卷积神经网络) 的性能,当与优化的SVM相结合时.
确定特征提取和优化算法的最佳组合,以准确高效地分类手动.

主要方法:

从MMG信号中提取的时间域 (TD),波形包节点能量 (WPNE),频域 (FD) 和卷积神经网络 (CNN) 特性.
采用了三种群体智能算法: Bald Eagle Search (BES),Sparrow Search Algorithm (SSA) 和 Grey Wolf Optimization (GWO) 来优化SVM分类器. 为了优化SVM分类器,我们使用了三种群体智能算法.
训练并测试了优化的SVM模型,使用不同的功能集来识别手动.

主要成果:

与BES和SSA相比,灰狼优化 (GWO) 的时间消耗较低.
将GWO优化的SVM与TD+FD功能相结合,实现了93.55%的分类准确度,超过了其他测试方法.
CNN的特征提取提供了域名知识独立性.
具有TD+FD功能的GWO-SVM在分类小型MMG数据集方面被证明是优越的.

结论:

群体智能优化,特别是GWO,显著提高了基于MMG的手动分类SVM性能.
将TD和FD功能与GWO-SVM相结合,为识别手动提供了高度准确和高效的方法,特别是在数据有限的情况下.
这些发现支持优化MMG信号分析在先进的人机界面和可穿戴技术中的应用.