Introduction: Children’s walking patterns evolve with age, exhibiting less repetitiveness at a young age and more variability than adults. Three-dimensional gait analysis (3DGA) is crucial for understanding and treating lower limb movement disorders in children, traditionally performed using Optical Motion Capture (OMC). Inertial Measurement Units (IMUs) offer a cost-effective alternative to OMC, although challenges like drift errors persist. Machine learning (ML) models can mitigate these issues in adults, prompting an investigation into their applicability to a heterogeneous pediatric population. This study aimed at 1) quantifying personalized and generalized ML models’ performance for predicting gait time series in typically developed (TD) children using IMUs data, 2) Comparing random forest (RF) and convolutional neural networks (CNN) models’ performance, 3) Finding the optimal number of IMUs required for accurate predictions.Methodology: Seventeen TD children, aged 6 to 15, participated in data collection involving OMC, force plates, and IMU sensors. Joint kinematics and kinetics (targets) were computed from OMC and force plates’ data using OpenSim. Tsfresh, a Python package, extracted features from raw IMU data. Each target’s ten most important features were input in the development of personalized and generalized RF and CNN models. This procedure was initially conducted with 7 IMUs placed on all lower limb segments and then performed using only two IMUs on the feet.Results: Findings suggested that the RF and CNN models demonstrated comparable performance. RF predicted joint kinematics with a 9.5% and 19.9% NRMSE for personalized and generalized models, respectively, and joint kinetics with an NRMSE of 10.7% for personalized and 15.2% for generalized models in TD children. Personalized models provided accurate estimations from IMU data in children, while generalized models lacked accuracy due to the limited dataset. Furthermore, reducing the number of IMUs from 7 to 2 did not affect the results, and the performance remained consistent.Discussion: This study proposed a promising personalized approach for gait time series prediction in children, involving an RF model and two IMUs on the feet.

中文翻译：

---

使用可穿戴传感器进行儿童 3D 步态分析：利用个性化机器学习模型和惯性测量单元预测关节运动学和动力学的可行性

简介：儿童的行走模式随着年龄的增长而变化，在年轻时表现出较少的重复性，并且比成人更具可变性。三维步态分析 (3DGA) 对于理解和治疗儿童下肢运动障碍至关重要，传统上使用光学运动捕捉 (OMC) 进行。尽管漂移误差等挑战仍然存在，但惯性测量单元 (IMU) 为 OMC 提供了一种经济高效的替代方案。机器学习 (ML) 模型可以缓解成人的这些问题，从而促使人们研究其对异质儿科人群的适用性。本研究旨在 1) 量化个性化和广义 ML 模型的性能，以使用 IMU 数据预测典型发育 (TD) 儿童的步态时间序列，2) 比较随机森林 (RF) 和卷积神经网络 (CNN) 模型的性能，3 ）找到准确预测所需的最佳 IMU 数量。方法：17 名 6 至 15 岁的 TD 儿童参与涉及 OMC、测力台和 IMU 传感器的数据收集。使用 OpenSim 根据 OMC 和测力台数据计算关节运动学和动力学（目标）。 Tsfresh 是一个 Python 包，从原始 IMU 数据中提取特征。每个目标的十个最重要的特征都被输入到个性化和通用 RF 和 CNN 模型的开发中。该程序最初是在所有下肢节段上放置 7 个 IMU 进行的，然后仅在脚上使用两个 IMU 进行。结果：研究结果表明 RF 和 CNN 模型表现出相当的性能。 RF 对 TD 儿童的个性化和广义模型的关节运动学预测分别为 9.5% 和 19.9% NRMSE，对个性化模型和广义模型的关节动力学预测 NRMSE 分别为 10.7% 和 15.2%。个性化模型根据儿童 IMU 数据提供了准确的估计，而广义模型由于数据集有限而缺乏准确性。此外，将 IMU 数量从 7 个减少到 2 个并不会影响结果，并且性能保持一致。讨论：本研究提出了一种有前途的儿童步态时间序列预测个性化方法，涉及 RF 模型和脚上的两个 IMU 。