使用机器学习预测运行时垂直地面反应力特征
Sieglinde Bogaert1, Jesse Davis2, Benedicte Vanwanseele1
1Human Movements Biomechanics Research Group, Department of Movement Sciences, KU Leuven, Leuven, Belgium.
这项研究引入了一种机器学习方法,使用圣骨加速来预测与跑步相关的受伤风险因素. 这种方法提供了一种实用的方法,可以在控制实验室设置之外运行时监测生物力学负载.
科学领域:
- 生物力学 生物力学
- 运动医学 运动医学
- 机器学习 机器学习
背景情况:
- 与跑步相关的伤害 (RRI) 是常见的,通常源于肌肉骨负荷失衡.
- 地面反应力 (GRF) 估计生物力学负载,但通常是在实验室测量.
- 便携式传感器和机器学习为现实世界伤害风险监测提供了潜力.
研究的目的:
- 开发和评估一个机器学习模型,该模型可以从十字加速中预测关键的垂直GRF特征.
- 评估模型在估计与跑步相关伤害相关的参数方面的准确性.
主要方法:
- 利用来自跑步者的三维圣骨加速数据.
- 训练有素的机器学习模型预测垂直GRF参数:接触时间,活跃峰值,冲击峰值和冲动.
- 将模型性能与基线和既定方法进行比较.
主要成果:
- 这些模型准确地预测了活跃峰值 (0.080 BW RMSE),撞击峰值 (0.198 BW RMSE),冲动 (0.0073 BWs RMSE) 和接触时间 (0.0101s RMSE).
- 拟议的机器学习方法与现有方法相比显示出更高的性能.
- 获得了0.080BW的活跃峰值的平方根平均误差,0.198BW的冲击峰值,0.0073BW的冲动,和0.0101s的接触时间.
结论:
- 圣器加速可以有效地使用机器学习来预测运行时重要的GRF指标.
- 这种方法显示了对生物力学负载的非侵入性实时监测的前景,以帮助预防与跑步相关的伤害.
- 这些发现表明,对于运动员和临床医生来说,在动态的跑步环境中评估受伤风险因素是一个有价值的工具.
更多相关视频
10:52Simulation of Human-induced Vibrations Based on the Characterized In-field Pedestrian Behavior
Published on: April 13, 2016
06:35Using Gold-standard Gait Analysis Methods to Assess Experience Effects on Lower-limb Mechanics During Moderate High-heeled Jogging and Running
Published on: September 14, 2017
相关概念视频
Cell-matrix's Response to Mechanical Forces
Anchoring junctions mechanically attach a cell to the...
Support Reactions
The purpose of the supports is to prevent the translational motion of the system by applying an equal and opposite force and to prevent the system's rotation by applying a...
Rolling Resistance
For instance, imagine a hard cylinder rolling on a comparatively soft surface. The cylinder's weight compresses the surface beneath it. As the cylinder moves, the material in front of it slows down due to...
Response Surface Methodology
The process of RSM involves several key steps:
Hydrostatic Pressure Force on a Plane Surface
Application of Linearization and Approximation
