Boukhennoufa Issam, Altai Zainab, Zhai Xiaojun, Utti Victor, McDonald-Maier Klaus D, Liew Bernard X W
School of Computer Science and Electrical Engineering, University of Essex, Colchester, United Kingdom.
School of Sport, Rehabilitation and Exercise Sciences, University of Essex, Colchester, United Kingdom.
Front Bioeng Biotechnol. 2022 May 12;10:877347. doi: 10.3389/fbioe.2022.877347. eCollection 2022.
Knee joint moments are commonly calculated to provide an indirect measure of knee joint loads. A shortcoming of inverse dynamics approaches is that the process of collecting and processing human motion data can be time-consuming. This study aimed to benchmark five different deep learning methods in using walking segment kinematics for predicting internal knee abduction impulse during walking. Three-dimensional kinematic and kinetic data used for the present analyses came from a publicly available dataset on walking (participants = 33). The outcome for prediction was the internal knee abduction impulse over the stance phase. Three-dimensional (3D) angular and linear displacement, velocity, and acceleration of the seven lower body segment's center of mass (COM), relative to a fixed global coordinate system were derived and formed the predictor space (126 time-series predictors). The total number of observations in the dataset was 6,737. The datasets were split into training (75%, = 5,052) and testing (25%, = 1685) datasets. Five deep learning models were benchmarked against inverse dynamics in quantifying knee abduction impulse. A baseline 2D convolutional network model achieved a mean absolute percentage error (MAPE) of 10.80%. Transfer learning with InceptionTime was the best performing model, achieving the best MAPE of 8.28%. Encoding the time-series as images then using a 2D convolutional model performed worse than the baseline model with a MAPE of 16.17%. Time-series based deep learning models were superior to an image-based method when predicting knee abduction moment impulse during walking. Future studies looking to develop wearable technologies will benefit from knowing the optimal network architecture, and the benefit of transfer learning for predicting joint moments.
膝关节力矩通常用于间接测量膝关节负荷。逆动力学方法的一个缺点是收集和处理人体运动数据的过程可能很耗时。本研究旨在对五种不同的深度学习方法进行基准测试，这些方法利用步行段运动学来预测步行过程中膝关节内收冲量。用于本分析的三维运动学和动力学数据来自一个公开的步行数据集（参与者 = 33）。预测的结果是站立阶段的膝关节内收冲量。相对于固定的全局坐标系，得出七个下半身节段质心（COM）的三维（3D）角位移和线性位移、速度和加速度，并形成预测空间（126个时间序列预测器）。数据集中的观测总数为6737。数据集被分为训练集（75%，= 5052）和测试集（25%，= 1685）。在量化膝关节内收冲量方面，将五种深度学习模型与逆动力学进行了基准比较。一个基线二维卷积网络模型的平均绝对百分比误差（MAPE）为10.80%。使用InceptionTime进行迁移学习是性能最佳的模型，实现了8.28%的最佳MAPE。将时间序列编码为图像，然后使用二维卷积模型的性能比基线模型差，MAPE为16.17%。在预测步行过程中的膝关节内收力矩冲量时，基于时间序列的深度学习模型优于基于图像的方法。未来旨在开发可穿戴技术的研究将受益于了解最佳网络架构以及迁移学习在预测关节力矩方面的优势。
