Department of Computer Science, KU Leuven, Celestijnenlaan 200A Box 2402, 3001, Heverlee, Belgium.
Department of Movement and Sports Sciences, Ghent University, Watersportlaan 2, 9000, Gent, Belgium.
Gait Posture. 2021 Feb;84:87-92. doi: 10.1016/j.gaitpost.2020.10.035. Epub 2020 Nov 10.
Gait event detection of the initial contact and toe off is essential for running gait analysis, allowing the derivation of parameters such as stance time. Heuristic-based methods exist to estimate these key gait events from tibial accelerometry. However, these methods are tailored to very specific acceleration profiles, which may offer complications when dealing with larger data sets and inherent biological variability.
Can a structured machine learning approach achieve a more accurate prediction of running gait event timings from tibial accelerometry, compared to the previously utilised heuristic approaches?
Force-based event detection acted as the criterion measure in order to assess the accuracy, repeatability and sensitivity of the predicted gait events. 3D tibial acceleration and ground reaction force data from 93 rearfoot runners were captured. A heuristic method and two structured machine learning methods were employed to derive initial contact, toe off and stance time from tibial acceleration signals.
Both a structured perceptron model (median absolute error of stance time estimation: 10.00 ± 8.73 ms) and a structured recurrent neural network model (median absolute error of stance time estimation: 6.50 ± 5.74 ms) significantly outperformed the existing heuristic approach (median absolute error of stance time estimation: 11.25 ± 9.52 ms). Thus, results indicate that a structured recurrent neural network machine learning model offers the most accurate and consistent estimation of the gait events and its derived stance time during level overground running.
The machine learning methods seem less affected by intra- and inter-subject variation within the data, allowing for accurate and efficient automated data output during rearfoot overground running. Furthermore offering possibilities for real-time monitoring and biofeedback during prolonged measurements, even outside the laboratory.
初始接触和脚趾离地的步态事件检测对于跑步步态分析至关重要，可用于推导支撑时间等参数。基于启发式的方法可用于从胫骨加速度计估算这些关键步态事件。然而，这些方法是针对非常特定的加速度曲线量身定制的，当处理更大的数据集和固有的生物学变异性时，可能会带来一些复杂情况。
与之前使用的启发式方法相比，结构化机器学习方法是否可以更准确地从胫骨加速度计预测跑步步态事件时间？
力触发事件检测作为标准措施，以评估预测步态事件的准确性、可重复性和敏感性。从 93 名后足跑步者中采集了三维胫骨加速度和地面反力数据。采用启发式方法和两种结构化机器学习方法，从胫骨加速度信号中提取初始接触、脚趾离地和支撑时间。
结构化感知机模型（支撑时间估计的中位数绝对误差：10.00 ± 8.73 毫秒）和结构化递归神经网络模型（支撑时间估计的中位数绝对误差：6.50 ± 5.74 毫秒）均显著优于现有的启发式方法（支撑时间估计的中位数绝对误差：11.25 ± 9.52 毫秒）。因此，结果表明，结构化递归神经网络机器学习模型在水平地面跑步过程中，对步态事件及其衍生的支撑时间提供了最准确和一致的估计。
机器学习方法似乎较少受到数据内和数据间个体差异的影响，允许在后足地面跑步期间进行准确和高效的自动数据输出。此外，即使在实验室之外，也可为长时间测量提供实时监测和生物反馈的可能性。
