...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Neural computation >A Novel Optimization Framework to Improve the Computational Cost of Muscle Activation Prediction for a Neuromusculoskeletal System
【24h】

A Novel Optimization Framework to Improve the Computational Cost of Muscle Activation Prediction for a Neuromusculoskeletal System

机译：一种新型的优化框架，可提高神经肌肉骨骼系统的肌肉激活预测的计算成本

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

The high computational cost (CC) of neuromusculoskeletal modeling is usually considered a serious barrier in clinical applications. Different approaches have been developed to lessen CC and amplify the accuracy of muscle activation prediction based on forward and inverse analyses by applying different optimization algorithms. This study is aimed at proposing two novel approaches, inverse muscular dynamics with inequality constraints (IMDIC) and inverse-forward muscular dynamics with inequality constraints (IFMDIC), not only to reduce CC but also to amend the computational errors compared to the well-known approach of extended inverse dynamics (EID). To do that, the equality constraints of optimization problem, which are computationally tough to satisfy, are replaced by inequality constraints, which are easier to satisfy. To verify the practical application of the proposed approaches, the muscle activations of the lower limbs during the half of a gait cycle are quantified. The simulation results of the optimal muscle activations are then compared to the experimental ones. The results reveal that IMDIC requires less CC (87.5%) compared to EID. In addition, CC of IMDIC was about 33.3% improved by the application of IFMDIC. The findings of this study suggest that although the novel approach of IFMDIC decreases CC compared to IMDIC, the convergence of its results is very sensitive to the primary guess of the optimization variables.
机译：神经肌肉骨骼建模的高计算成本（CC）通常被认为是临床应用中的严重障碍。已经开发出了不同的方法来减少CC，并通过应用不同的优化算法，基于正向和反向分析来放大肌肉激活预测的准确性。这项研究旨在提出两种新颖的方法，具有不平等约束的逆向肌肉动力学（IMDIC）和具有不平等约束的逆向肌肉动力学（IFMDIC），与众所周知的方法相比，不仅减少了CC，而且还修正了计算误差扩展逆动力学（EID）的方法。为此，将计算上难以满足的优化问题的等式约束替换为更易于满足的不等式约束。为了验证所提出方法的实际应用，对步态周期的一半期间下肢的肌肉激活进行了量化。然后将最佳肌肉激活的模拟结果与实验结果进行比较。结果表明，与EID相比，IMDIC需要更少的CC（87.5％）。此外，通过应用IFMDIC，IMDIC的CC改善了约33.3％。这项研究的结果表明，尽管IFMDIC的新颖方法与IMDIC相比降低了CC，但其结果的收敛性对优化变量的主要猜测非常敏感。

著录项

  • 来源
    《Neural computation》 |2019年第3期|574-595|共22页
  • 作者

    Rahmati Seyed Mohammad Ali; Rostami Mostafa; Karimi Alireza;

  • 作者单位

    Amirkabir Univ Technol, Fac Biomed Engn, Biomech Grp, Tehran, Iran;

    Amirkabir Univ Technol, Fac Biomed Engn, Biomech Grp, Tehran, Iran;

    Kyushu Univ, Dept Mech Engn, Nishi Ku, Fukuoka, Fukuoka 8190395, Japan;

  • 收录信息 美国《科学引文索引》(SCI);美国《化学文摘》(CA);
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号