IEEE Trans Biomed Eng. 2019 Mar;66(3):689-694. doi: 10.1109/TBME.2018.2854632. Epub 2018 Jul 9.
The accurate prediction of three-dimensional (3-D) ground reaction forces and moments (GRF/Ms) outside the laboratory setting would represent a watershed for on-field biomechanical analysis. To extricate the biomechanist's reliance on ground embedded force plates, this study sought to improve on an earlier partial least squares (PLS) approach by using deep learning to predict 3-D GRF/Ms from legacy marker based motion capture sidestepping trials, ranking multivariate regression of GRF/Ms from five convolutional neural network (CNN) models. In a possible first for biomechanics, tactical feature engineering techniques were used to compress space-time and facilitate fine-tuning from three pretrained CNNs, from which a model derivative of ImageNet called "CaffeNet" achieved the strongest average correlation to ground truth GRF/Ms [Formula: see text] 0.9881 and [Formula: see text] 0.9715 ([Formula: see text] 4.31 and 7.04%). These results demonstrate the power of CNN models to facilitate real-world multivariate regression with practical application for spatio-temporal sports analytics.
在实验室环境之外准确预测三维（3-D）地面反作用力和力矩（GRF/Ms）将代表着现场生物力学分析的一个分水岭。为了摆脱生物力学研究者对地面嵌入式测力板的依赖，本研究试图通过使用深度学习从基于遗留标记的运动捕捉侧身试验中预测 3-D GRF/Ms，对来自五个卷积神经网络（CNN）模型的 GRF/Ms 的多元回归进行排名，从而改进早期的偏最小二乘法（PLS）方法。在生物力学领域可能是首次，战术特征工程技术被用于压缩时空，并从三个预先训练的 CNN 中进行微调，其中一个名为“CaffeNet”的 ImageNet 模型衍生品实现了与地面真实 GRF/Ms 的最强平均相关性 [公式：见正文]0.9881 和 [公式：见正文]0.9715（[公式：见正文]4.31 和 7.04%）。这些结果表明了 CNN 模型在促进具有实际应用的现实世界多元回归方面的强大功能，适用于时空运动分析。
