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

Epigenetic regulation of mesenchymal BMP signaling directs postnatal organ innervation.

Proceedings of the National Academy of Sciences of the United States of America·2026

Same author

<i>Peribacillus simplex</i> P10 Enhances Salt Tolerance in Asparagus by Modulating Amino Acid and Phenylpropanoid Metabolism.

Plants (Basel, Switzerland)·2026

Same author

Diversity Analysis of Global White Clover (<i>Trifolium repens</i> L.) Germplasm Based on Agronomic and Photosynthetic Traits and SLAF-Seq Technology.

International journal of molecular sciences·2026

Same author

Factors associated with the occurrence of breast nodules in perimenopausal women: A cross-sectional study in China.

Medicine·2026

Same author

KDM6B safeguards mineralized tissue homeostasis from mechanical stress through epigenetic control of PIEZO1-mediated mechanotransduction in the mouse incisor.

Bone research·2026

Same author

An indel in the FAD5 promoter confers cold tolerance by enhancing transcriptional activation of unsaturated fatty acid synthesis in grapevines.

Plant communications·2026

Search research articles

相关实验视频

Updated: Jun 17, 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

通过从sEMG的多维特征学习预测连续运动模式.

Peiwen Fu, Wenjuan Zhong, Yuyang Zhang

IEEE journal of biomedical and health informatics

|August 12, 2024

概括

此摘要是机器生成的。

深度STF是一种使用表面电肌图 (sEMG) 信号的深度学习模型,可以准确地预测人类的运动模式和步行辅助设备的过渡. 它即使在较长的预测间隔下也能达到高精度,并且在最小的校准下适应新地形.

更多相关视频

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

Published on: July 26, 2013

Author Spotlight: Advancing Large-Scale Neural Dynamics Through HD-MEA Technology

Author Spotlight: Advancing Large-Scale Neural Dynamics Through HD-MEA Technology

Published on: March 8, 2024

相关实验视频

Last Updated: Jun 17, 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

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

Published on: July 26, 2013

Author Spotlight: Advancing Large-Scale Neural Dynamics Through HD-MEA Technology

Author Spotlight: Advancing Large-Scale Neural Dynamics Through HD-MEA Technology

Published on: March 8, 2024

科学领域:

机器人和人机交互的人机交互
生物医学工程生物医学工程
机器学习用于医疗保健

背景情况:

步行辅助设备的自适应控制需要先进的方法来预测人类的运动模式.
过渡的早期检测 (例如,平行到爬楼梯) 对于增强机器人系统智能和用户交互至关重要.
表面电肌图 (sEMG) 信号提供了丰富的生理数据,用于推断人类运动意图.

研究的目的:

开发和验证Deep-STF,这是一个统一的深度学习模型,用于从sEMG信号中集成的特征提取.
为了能够准确和强大的连续预测多个运动模式和过渡.
评估模型在不同的预测时间间隔中的性能及其适应新环境的适应性.

主要方法:

提出了Deep-STF,这是一个端到端的深度学习架构,用于从sEMG中提取空间,时间和频率特征.
训练并评估了预测9种运动模式和15种转变的模型.
在100毫秒至500毫秒的间隔测试了预测准确性,并通过微调在新地形上评估了性能.

主要成果:

深度STF实现了96.60%的准确度,预测100ms前,超过了七个基准模型.
准确度仍然很高 (93.22%),即使在500毫秒的预测时间里.
该模型表现出强大的适应性,在15次校准试验中,在新地形上精度从71.12%提高到96.27%.

结论:

深度STF提供了一个强大的,统一的方法来预测人类的运动模式和过渡使用sEMG.
该模型的高精度,强度和适应性显示出将其集成到未来的行走辅助设备中的巨大潜力.
成功实施可以带来更顺,更直观,更响应的用户体验与辅助机器人.