Machine-learning techniques are suitably employed for gait-event prediction from only surface electromyographic (sEMG) signals in control subjects during walking. Nevertheless, a reference approach is not available in cerebral-palsy hemiplegic children, likely due to the large variability of foot-floor contacts. This study is designed to investigate a machine-learning-based approach, specifically developed to binary classify gait events and to predict heel-strike (HS) and toe-off (TO) timing from sEMG signals in hemiplegic-child walking. To this objective, sEMG signals are acquired from five hemiplegic-leg muscles in nearly 2500 strides from 20 hemiplegic children, acknowledged as Winters’ group 1 and 2. sEMG signals, segmented in overlapping windows of 600 samples (pace = 5 samples), are used to train a multi-layer perceptron model. Intra-subject and inter-subject experimental settings are tested. The best-performing intra-subject approach is able to provide in the hemiplegic population a mean classification accuracy (±SD) of 0.97±0.01 and a suitable prediction of HS and TO events, in terms of average mean absolute error (MAE, 14.8±3.2 ms for HS and 17.6±4.2 ms for TO) and F1-score (0.95±0.03 for HS and 0.92±0.07 for TO). These results outperform previous sEMG-based attempts in cerebral-palsy populations and are comparable with outcomes achieved by reference approaches in control populations. In conclusion, the findings of the study prove the feasibility of neural networks in predicting the two main gait events using surface EMG signals, also in condition of high variability of the signal to predict as in hemiplegic cerebral palsy.

中文翻译：

---

基于机器学习的脑瘫儿童肌电图步态事件预测


机器学习技术适用于仅根据控制对象行走期间的表面肌电图（sEMG）信号来预测步态事件。然而，对于脑瘫偏瘫儿童来说，没有可用的参考方法，这可能是由于脚底接触的变化很大。本研究旨在研究一种基于机器学习的方法，该方法专门用于对步态事件进行二元分类，并根据偏瘫儿童行走中的 sEMG 信号预测脚跟着地 (HS) 和脚趾离地 (TO) 时间。为了实现这一目标，从 20 名偏瘫儿童（被称为 Winters 组 1 和 2）的近 2500 步的 5 个偏瘫腿部肌肉中采集了 sEMG 信号。sEMG 信号在 600 个样本的重叠窗口中进行分段（步速 = 5 个样本），如下所示：用于训练多层感知器模型。测试受试者内和受试者间的实验设置。表现最佳的受试者内方法能够为偏瘫人群提供 0.97±0.01 的平均分类精度 (±SD)，并根据平均平均绝对误差 (MAE，14.8± HS 为 3.2 ms，TO 为 17.6±4.2 ms) 和 F1 分数（HS 为 0.95±0.03，TO 为 0.92±0.07）。这些结果优于之前在脑瘫人群中基于表面肌电图的尝试，并且与对照人群中参考方法所取得的结果相当。总之，该研究的结果证明了神经网络使用表面肌电图信号预测两种主要步态事件的可行性，以及在信号高度可变的情况下预测偏瘫脑瘫的情况。