arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2412.05403eess.SPcs.CEcs.HCcs.LGphysics.bio-ph
收藏

面向高效逆动力学的基于知识的深度学习

Knowledge-Based Deep Learning for Time-Efficient Inverse Dynamics

School of Electronic and Electrical Engineering, University of Leeds(利兹大学电子与电气工程学院);School of Mechanical Engineering, Tianjin University(天津大学机械工程学院);International Institute for Innovative Design and Intelligent Manufacturing of Tianjin University in Zhejiang(天津大学浙江创新设计与智能制造国际研究院);Estun Medical Ltd(埃斯顿医疗有限公司)

Shuhao Ma, Yu Cao, Ian D. Robertson, Chaoyang Shi, Jindong Liu, Zhi-Qiang Zhang

AI总结:

针对肌肉骨骼逆动力学分析计算耗时的问题,提出融合正向动力学先验与生理准则损失的BiGRU深度学习框架,无需标签即可从关节运动学预测肌肉激活与肌力,在上下肢数据集上验证了有效性与鲁棒性。

摘要:

准确理解肌肉激活与肌肉力在神经康复和肌肉骨骼疾病治疗中发挥着关键作用。计算肌肉骨骼建模作为一种强大的无创工具,已被广泛用于通过静态优化的逆动力学方法估算上述参数,但其固有的计算复杂性导致分析过程耗时较长。本文提出了一种基于知识的深度学习框架,用于实现高效的逆动力学分析,该框架可直接从关节运动学数据预测肌肉激活与肌肉力,且模型训练过程中无需任何标签信息。模型选用双向门控循环单元(Bidirectional Gated Recurrent Unit, BiGRU)神经网络作为骨干网络,因其擅长处理时序数据。将来自正向动力学的先验物理知识,以及基于预选逆动力学的生理准则整合到损失函数中,以指导神经网络的训练。研究在两个数据集上开展了实验验证,包括一个基准上肢运动数据集,以及一个由6名健康受试者组成的自行采集的下肢运动数据集。实验结果表明,采用本文专门设计的损失函数训练时,所选的BiGRU架构性能优于其他神经网络模型,证明了所提框架的有效性与鲁棒性。

英文摘要:

Accurate understanding of muscle activation and muscle forces plays an essential role in neuro-rehabilitation and musculoskeletal disorder treatments. Computational musculoskeletal modeling has been widely used as a powerful non-invasive tool to estimate them through inverse dynamics using static optimization, but the inherent computational complexity results in time-consuming analysis. In this paper, we propose a knowledge-based deep learning framework for time-efficient inverse dynamic analysis, which can predict muscle activation and muscle forces from joint kinematic data directly while not requiring any label information during model training. The Bidirectional Gated Recurrent Unit (BiGRU) neural network is selected as the backbone of our model due to its proficient handling of time-series data. Prior physical knowledge from forward dynamics and pre-selected inverse dynamics based physiological criteria are integrated into the loss function to guide the training of neural networks. Experimental validations on two datasets, including one benchmark upper limb movement dataset and one self-collected lower limb movement dataset from six healthy subjects, are performed. The experimental results have shown that the selected BiGRU architecture outperforms other neural network models when trained using our specifically designed loss function, which illustrates the effectiveness and robustness of the proposed framework.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑