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

A multi-task masked autoencoder with GAN-based augmentation for PD-L1 prediction from chest CT images.

Scientific reports·2026
Same author

Clinical and Radiological Outcomes of Skip-Level Cervical Disk Arthroplasty.

Neurosurgery·2026
Same author

Increasing autophagy activity suppresses <i>Helicobacter pylori</i> infection-related gastric cancer tumorigenesis both <i>in vitro</i> and <i>in vivo</i>.

American journal of cancer research·2026
Same author

Hemispherectomy in infants: an institutional experience with 21 patients.

Journal of neurosurgery. Pediatrics·2026
Same author

Cryosurgical cranioplasty using autologous bone for metastatic skull lesion from hepatocellular carcinoma: illustrative case.

Journal of neurosurgery. Case lessons·2026
Same author

Taiwan practical consensus for evaluation and management of small-bowel bleeding.

Journal of the Chinese Medical Association : JCMA·2026

相关实验视频

Updated: Jun 16, 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

421

通过使用可解释的3D卷积神经网络来解码微电皮质图信号,以预测手指的运动.

Chao-Hung Kuo1, Guan-Tze Liu2, Chi-En Lee3

  • 1Department of Neurosurgery, Neurological Institute, Taipei Veterans General Hospital, Taipei, Taiwan; School of Medicine, National Yang Ming Chiao Tung University, Taipei, Taiwan; Department of Biomedical Engineering, National Yang Ming Chiao Tung University, Taipei, Taiwan; Department of Neurological Surgery, University of Washington, Seattle, WA, USA; The Ph.D. Program for Neural Regenerative Medicine, College of Medical Science and Technology, Taipei Medical University, Taipei, Taiwan.

Journal of neuroscience methods
|August 16, 2024
PubMed
概括
此摘要是机器生成的。

一个新的3D-CNN模型高精度地从电皮质谱 (ECoG) 数据中解读了手指的运动. 可解释的人工智能突出显示高马波段.

关键词:
卷积神经网络是一种卷积神经网络.这是一个ECoG.电皮质谱学 电皮质谱学 电皮质谱学手指的动作和手指的运动.这是Grad-CAM.高高的玛高的玛.在SHAP中,价值是SHAP值.

更多相关视频

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding
11:25

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

Published on: July 26, 2013

43.3K
Author Spotlight: Understanding Processing of Olfactory and Spatial Information by Brain with Real-Time Behavioral Analysis
06:21

Author Spotlight: Understanding Processing of Olfactory and Spatial Information by Brain with Real-Time Behavioral Analysis

Published on: September 20, 2024

739

相关实验视频

Last Updated: Jun 16, 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

421
Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding
11:25

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

Published on: July 26, 2013

43.3K
Author Spotlight: Understanding Processing of Olfactory and Spatial Information by Brain with Real-Time Behavioral Analysis
06:21

Author Spotlight: Understanding Processing of Olfactory and Spatial Information by Brain with Real-Time Behavioral Analysis

Published on: September 20, 2024

739

科学领域:

  • 神经科学是一个神经科学.
  • 人工智能的人工智能
  • 生物医学工程 生物医学工程

背景情况:

  • 从脑电图 (EEG) 和心电图 (ECoG) 中解码手指运动的传统方法依赖于从带径功率变化中手动提取特征.
  • 现有的机器学习模型用于动作解码往往缺乏可解释性,充当"黑子".

研究的目的:

  • 引入一种新的3D卷积神经网络 (3D-CNN),用于使用ECoG数据解码手指运动.
  • 使用可解释AI (xAI) 技术,提高脑计算机接口 (BCI) 模型的可解释性.
  • 为了确定特定的大脑信号特征在运动控制中的生理相关性.

主要方法:

  • 开发了一种3D-CNN模型,该模型是根据患者的ECoG数据进行训练的,这些患者接受了清醒时的头骨切除术.
  • 处理ECoG信号以提取多个频段的功率光谱密度,形成一个3D数据矩阵.
  • 综合适应可解释AI (xAI) 技术,包括Grad-CAM和SHAP,用于模型解释.

主要成果:

  • 3D-CNN模型在预测手指运动方面取得了很高的准确性,根平均平方误差 (RMSE) 范围为0.20-0.38.
  • 可解释的AI确定高马 (HG) 波段对于运动预测至关重要.
  • 通过xAI分析阐明了与明显的手指运动有关的特定皮质区域,证实了HG带在运动控制中的重要性.

结论:

  • 3D-CNN模型与xAI相结合,显著提高了ECoG数据的指头运动解码精度.
  • 这种方法为脑计算机接口 (BCI) 应用提供了高效和可解释的解决方案.
  • 这项研究强化了高马 (HG) 波段在运动控制中的关键作用.