为准确的电机意图解码选择最佳的动力单元子集:朝着敏捷的实时接口
概括
优化机动单元 (MU) 解码对于人机接口至关重要. 选择关键的MU可以显著提高效率而不会牺牲准确性,从而实现更强大的解码技术.
科学领域:
- 生物医学工程 生物医学工程
- 神经科学是一个神经科学.
- 人机接口 人机接口
背景情况:
- 发动机单元 (MU) 放电时间对于编码人类运动意图至关重要.
- 目前的MU从表面信号解码方法很难满足灵巧的人机界面 (HMI) 的需求.
- 优化解码精度和效率对于推进HMI应用程序至关重要.
研究的目的:
- 为了提高HMI的MU解码的准确性和时间效率.
- 调查任务智能初始化和MU子集选择对解码性能的影响.
- 确定选择MU的最佳策略,以提高HMI的功能.
主要方法:
- 离线分析高密度表面电肌图 (HD-sEMG) 数据来自11名从事18个手腕/前臂运动任务的受试者.
- 应用任务智能分解来识别MUs.
- 从选定的子集中提取MU活动,以预测运动任务和关节动力学.
- 评估各种子集选择和估计算法 (基于回归和分类).
主要成果:
- 最低冗余最大相关性 (mRMR-MI) 标准有效地保留了具有高预测能力的MU.
- 将追踪的MU子集减少到25%,导致回归性能仅下降3% (R2=0.79).
- 在使用减少的MU子集时,基于内核的估计器的分类准确性下降了2.7% (至74%) .
结论:
- 战略性选择跟踪的MU可以显著优化MU驱动接口的效率.
- 优先考虑具有强大的非线性关系的 MU,特别是基于内核的估计器,可以增强解码.
- 这些发现有助于为未来的HMI实施更强大,更适应的MU解码技术.
相关概念视频
Motor Units
4.0K
The motor unit is a fundamental component of the neuromuscular system and plays a crucial role in coordinating muscle contractions. It consists of a somatic motor neuron, which connects and controls multiple skeletal muscle fibers, forming a single functional segment. The axon of the motor neuron branches out and establishes synaptic connections known as neuromuscular junctions with individual muscle fibers within the motor unit.
Motor units come in different sizes, with smaller units...
Motor units come in different sizes, with smaller units...
4.0K
Motor Unit Stimulation
1.6K
When the neuron of a motor unit fires an action potential, it triggers a series of events, leading to a twitch contraction in the muscle fibers. The process of excitation-contraction coupling is crucial in relaying the action potential to the muscle fibers.
The latent period of contraction marks the onset of excitation-contraction coupling, when the action potential propagates across the sarcolemma, preparing the muscle fibers for contraction. As the fibers enter the contraction phase, the...
The latent period of contraction marks the onset of excitation-contraction coupling, when the action potential propagates across the sarcolemma, preparing the muscle fibers for contraction. As the fibers enter the contraction phase, the...
1.6K


