使用长期短期记忆神经网络的坐走策略的下肢扭矩预测
概括
这项研究开发了一种编码解码器LSTM模型,用于预测关节和膝关节的扭矩,以便在坐到走动过程中提供个性化辅助设备,改善康复和日常任务辅助.
科学领域:
- 生物力学 生物力学
- 辅助技术 辅助技术 辅助技术
- 机器学习 机器学习
背景情况:
- 准确的关节扭矩预测对于生物力学研究,治疗评估和设计动力辅助设备至关重要.
- 坐到走 (STW) 运动需要个性化的扭矩辅助,适应个人策略和人体测量.
研究的目的:
- 开发和评估长期短期记忆 (LSTM) 神经网络,用于在STW期间预测部和膝关节关节扭矩.
- 为个性化辅助控制器生成特定于战略和面向用户的扭矩轨迹.
主要方法:
- 在来自不同年龄组的65名受试者的STW数据上训练了三个LSTM神经网络.
- 作为模型输入,利用了部和膝盖的角度和质量中心速度,并为实时适应提供了窗口.
- 基于STW策略的LSTM性能比较,重点关注时间和空间关系的识别.
主要成果:
- 编码解码器LSTM表现出最佳性能,准确地识别时间特征.
- 实现了低根平均平方误差 (0.24±0.07Nm/kg用于部,0.15±0.02Nm/kg用于膝盖) 和高的斯皮尔曼相关性 (93.43±2.86%和84.83±2.96%).
- 呈现出良好的类内相关系数 (>0.75),证实了模型的可靠性.
结论:
- 开发的编码解码器LSTM可靠地预测了辅助设备的用户和策略特定的参考扭矩.
- 在坐到走路的转变过程中,可以提供更自然和个性化的帮助.
- 强调深度学习在推进个性化康复和辅助技术方面的潜力.
更多相关视频
08:40Quantifying Arms and Legs Contributions during Repetitive Electrically-Assisted Sit-To-Stand Exercise in Paraplegics: A Pilot Study
Published on: November 11, 2022
1.1K
05:25Author Spotlight: Assessing Brain Activity in Robotic-Assisted Lower Limb Rehabilitation Using fNIRS
Published on: June 7, 2024
1.2K
相关概念视频
Long-term Potentiation
Long-term potentiation, or LTP, is one of the ways by which synaptic plasticity—changes in the strength of chemical synapses—can occur in the brain. LTP is the process of synaptic strengthening that occurs over time between pre- and postsynaptic neuronal connections. The synaptic strengthening of LTP works in opposition to the synaptic weakening of long-term depression (LTD) and together are the main mechanisms that underlie learning and memory.
Long-term Potentiation
Long-term potentiation, or LTP, is one of the ways by which synaptic plasticity—changes in the strength of chemical synapses—can occur in the brain. LTP is the process of synaptic strengthening that occurs over time between pre and postsynaptic neuronal connections. The synaptic strengthening of LTP works in opposition to the synaptic weakening of long-term depression (LTD) and together are the main mechanisms that underlie learning and memory.
Hebbian LTP
LTP can occur when presynaptic neurons...
Hebbian LTP
LTP can occur when presynaptic neurons...
