卷积神经网络用于使用单个惯性传感器估计时空和运动步行参数
概括
机器学习从单个惯性传感器准确估计关键步行参数,改进了对下肢残疾的客观步行分析. 这种方法增强了临床和现实世界的监测.
科学领域:
- 生物力学 生物力学
- 机器学习 机器学习
- 可穿戴技术可穿戴技术
背景情况:
- 下肢残疾显著损害了步态,需要有效的临床评估.
- 惯性传感器系统提供客观的步态监测,但通常需要多个传感器或复杂的集成.
- 最少的侵入性系统对于现实世界的步态评估至关重要.
研究的目的:
- 开发和验证一个机器学习模型,以使用最小的惯性传感器数据估计多个步态参数.
- 评估模型对时空和运动步态测量的准确性.
- 为了实践应用,研究独立于步态事件检测的步态细分方法.
主要方法:
- 卷积神经网络 (CNN) 用于处理原始惯性传感器数据.
- 该模型估计了六个时空和运动步态参数.
- 使用了一种新的数据细分方法,不需要步行事件检测.
主要成果:
- CNN模型在估计步态参数方面表现出高准确度,达到或超过文献基准.
- 对于立场时间对称率 (0.04 ± 0.03),步长 (4.78 ± 4.78厘米,4.50 ± 4.33厘米) 和步长 (6.47 ± 7.37厘米) 实现了低平均绝对误差.
- 膝盖和部运动范围的误差分别为2.31 ± 4.20°和1.73 ± 1.93°.
结论:
- 机器学习,特别是CNN,对于从单个惯性传感器数据中估计全面的步态参数是有效的.
- 拟议的方法允许准确,最少的侵入性步行质量评估,用于长期监测.
- 这种方法支持对下肢残疾人进行增强的临床干预和现实世界步态分析.
相关概念视频
Kinematic Equations - I
10.6K
When an object moves with constant acceleration, the velocity of the object changes at a constant rate throughout the motion. The kinematic equations of motions are derived for such cases where the acceleration of the object is constant. The first kinematic equation gives an insight into the relationship between velocity, acceleration, and time. We can see, for example:
10.6K
Kinematic Equations - II
9.6K
The second kinematic equation expresses the final position of an object in terms of its initial position, the distance traveled with the initial constant velocity, and the distance traveled due to a change in velocity. Similar to the first kinematic equation, this equation is also only valid when the acceleration is constant throughout the motion of an object.
Suppose a car merges into freeway traffic on a 200 m long ramp. If its initial velocity is 10 m/s and it accelerates at 2 m/s2, then the...
Suppose a car merges into freeway traffic on a 200 m long ramp. If its initial velocity is 10 m/s and it accelerates at 2 m/s2, then the...
9.6K


