首页> 外文期刊>Neurocomputing >Feed forward artificial neural network to predict contact force at medial knee joint: Application to gait modification
【24h】

Feed forward artificial neural network to predict contact force at medial knee joint: Application to gait modification

机译:前馈人工神经网络预测膝内侧关节的接触力:在步态调整中的应用

获取原文
获取原文并翻译 | 示例

摘要

Knee contact force (KCF) is one of the most meaningful parameters to evaluate function of the knee joint However in vivo measurement of KCF is not always straight forward. Inverse dynamics analysis, as one of the most frequently used computational techniques to calculate KCF, has its own limitations. The purpose of this study was to develop a feed forward artificial neural network (FFANN) to predict the medial condyle KCF corresponding to two different gait modifications known as medial thrust and trunk sway. Four patients implanted with unilateral knee sensor-based prostheses were obtained from the literature. The network was trained based on pre-rehabilitation gait patterns and was recruited to predict the medial KCF associated with rehabilitation patterns. Generalization ability of the proposed network was tested within three different levels including intra subject (level 1), inter condition (level 2) and inter subject (level 3). FFANN predictions were validated against in vivo measurements. Results showed subject-specific neural network could predict KCF to a certain high level of accuracy (medial thrust: NRMSE = 10.6%, p=0.96; trunk sway: NRMSE = 9.6%, p=0.96) based on the ground reaction forces (GRFs) and some independent marker trajectories (level 1) which suggested that not all of the markers are necessary for knee force calculation. Moreover at level 2, a generic FFANN could predict the medial knee force based on electromyography (EMG) signals and GRFs (medial thrust:NRMSE = 11.2%, p = 0.96; trunk sway.NRMSE = 10.5%, p = 0.95) which released the necessity of motion capture and subject specific scaling of a musculoskeletal model. At level 3, neural network could predict the general pattern and features of KCF for a new subject that was not used in the network training (medial thrust: NRMSE = 12.6%, p = 0.95; trunk sway: NRMSE = 13.3%, p= 0.94). In conclusion, FFANN could predict the medial knee joint loading corresponding to two different knee rehabilitations based on pre-rehabilitatioa gait patterns. Compared to the inverse dynamics method, artificial intelligence represents a much easier and faster method; together they can be combined to calculate joint loading involving fewer markers and speed up the calculations.
机译:膝关节接触力(KCF)是评估膝关节功能的最有意义的参数之一。但是,体内KCF的测量并非总是一帆风顺的。逆动力学分析作为计算KCF的最常用计算技术之一,有其自身的局限性。这项研究的目的是开发一个前馈人工神经网络(FFANN)来预测与两个不同步态变化相对应的内侧con KCF,称为内侧推力和躯干摇摆。从文献中获得了四例植入了基于单侧膝关节传感器的假体的患者。该网络是根据康复前的步态模式进行训练的,并被招募来预测与康复模式相关的内侧KCF。在三个不同的级别(包括内部主题(级别1),内部条件(级别2)和主体间(级别3))中测试了所建议网络的泛化能力。 FFANN预测已针对体内测量结果进行了验证。结果表明,基于地面反作用力(GRF),特定于对象的神经网络可以将KCF预测到一定的准确性(中间推力:NRMSE = 10.6%,p = 0.96;躯干摇摆:NRMSE = 9.6%,p = 0.96)。 )和一些独立的标记轨迹(第1级),表明并非所有的标记都是计算膝力的必要条件。此外,在第2级时,通用FFANN可以根据肌电图(EMG)信号和GRF(内侧推力:NRMSE = 11.2%,p = 0.96;躯干摇摆NRMSE = 10.5%,p = 0.95)预测内侧膝关节力运动捕捉和肌肉骨骼模型的特定对象缩放的必要性。在第3级,神经网络可以预测未在网络训练中使用的新受试者的KCF的一般模式和特征(中位推力:NRMSE = 12.6%,p = 0.95;躯干摇摆:NRMSE = 13.3%,p = 0.94)。总之,FFANN可以根据康复前的步态模式预测与两种不同的膝关节康复相对应的膝关节内侧负荷。与逆动力学方法相比,人工智能代表了一种更加简便快捷的方法。可以将它们组合在一起以计算涉及较少标记的联合荷载,并加快计算速度。

著录项

  • 来源
    《Neurocomputing》 |2014年第2期|114-129|共16页
  • 作者单位

    State Key Laboratory for Manufacturing System Engineering, School of Mechanical Engineering, Xi'an Jiaotong University, 710054 Xi'an, Shaanxi, China;

    State Key Laboratory for Manufacturing System Engineering, School of Mechanical Engineering, Xi'an Jiaotong University, 710054 Xi'an, Shaanxi, China;

    State Key Laboratory for Manufacturing System Engineering, School of Mechanical Engineering, Xi'an Jiaotong University, 710054 Xi'an, Shaanxi, China;

    State Key Laboratory for Manufacturing System Engineering, School of Mechanical Engineering, Xi'an Jiaotong University, 710054 Xi'an, Shaanxi, China;

    State Key Laboratory for Manufacturing System Engineering, School of Mechanical Engineering, Xi'an Jiaotong University, 710054 Xi'an, Shaanxi, China;

    State Key Laboratory for Manufacturing System Engineering, School of Mechanical Engineering, Xi'an Jiaotong University, 710054 Xi'an, Shaanxi, China;

    State Key Laboratory for Manufacturing System Engineering, School of Mechanical Engineering, Xi'an Jiaotong University, 710054 Xi'an, Shaanxi, China;

    State Key Laboratory for Manufacturing System Engineering, School of Mechanical Engineering, Xi'an Jiaotong University, 710054 Xi'an, Shaanxi, China,Institute of Medical and Biological Engineering, School of Mechanical Engineering, University of Leeds, Leeds LS2 9JT, UK;

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

    Knee contact force; Gait modification; Feed forward artificial neural network; Fisher discriminant analysis; Partial correlation; Kernel mutual information;

    机译:膝盖接触力;步态调整;前馈人工神经网络;Fisher判别分析;偏相关;内核相互信息;

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