卷积神经网络从MEG数据中学习的运动序列中解码手指运动
Aleksey Zabolotniy1, Russell Weili Chan2, Victoria Moiseeva1
1Institute of Cognitive Neuroscience, National Research University Higher School of Economics, Moscow, Russia.
Frontiers in neuroscience
|September 25, 2025
概括
现在可以使用非侵入性磁脑电图 (MEG) 来解读个别手指的移动. 一个紧的卷积神经网络 (CNN) 从MEG提供快速,可靠的手指运动分类,性能优于复杂的模型.
科学领域:
- 神经科学是一个神经科学.
- 生物医学工程 生物医学工程
- 机器学习 机器学习
背景情况:
- 非侵入性脑电脑接口 (BCI) 准确地分类了手的横向化.
- 由于运动皮层的表现重叠,区分单个手指运动是具有挑战性的.
研究的目的:
- 验证一个紧的卷积神经网络 (CNN) 来解码磁脑图 (MEG) 中的手指运动.
- 评估线性有限脉冲响应卷积神经网络 (LF-CNN) 与其他深度学习模型的性能和可解释性.
主要方法:
- 记录了从参与者执行串行反应时间任务 (SRTT) 的MEG数据,其中包括食指和中指的压力.
- 开发并将LF-CNN与EEGNet,FBCSP-ShallowNet和VGG19进行比较,以对手和手指运动进行分类.
主要成果:
- 所有模型都实现了>95%的精度,用于手侧向解码.
- 个人手指运动解码精度在80-85%之间.
- 在空间和光谱领域,LF-CNN展示了卓越的计算效率和可解释性.
结论:
- 一个量身定制的CNN (LF-CNN) 能够从非侵入性的MEG中实现个别手指运动的可行和准确的解码.
- 对于复杂的架构,LF-CNN提供了与复杂架构相匹配的性能,并提供更快,更易于解释的结果.
- 这种方法在认知神经科学中研究神经机制方面具有重大潜力.
相关概念视频
01:24Sequence Networks of Rotating Machines
485
A Y-connected synchronous generator, grounded through a neutral impedance, is designed to produce balanced internal phase voltages with only positive-sequence components. The generator's sequence networks include a source voltage that is exclusively in the positive-sequence network. The sequence components of line-to-ground voltages at the generator terminals illustrate this configuration.
Zero-sequence current induces a voltage drop across the generator's neutral impedance and other...
Zero-sequence current induces a voltage drop across the generator's neutral impedance and other...
485
01:18Hierarchy of Motor Control
5.9K
The hierarchy of motor control refers to the different levels of organization and processing involved in controlling movement in the body. These levels range from higher cortical areas involved in planning and decision-making to lower spinal cord reflexes that respond automatically to external stimuli.
5.9K