KTH MoveAbility Lab, Department of Engineering Mechanics, KTH Royal Institute of Technology, 10044 Stockholm, Sweden.
Department of Women's and Children's Health, Karolinska Institute, 17177 Stockholm, Sweden.
Sensors (Basel). 2021 Nov 10;21(22):7473. doi: 10.3390/s21227473.
People walk on different types of terrain daily; for instance, level-ground walking, ramp and stair ascent and descent, and stepping over obstacles are common activities in daily life. Movement patterns change as people move from one terrain to another. The prediction of transitions between locomotion modes is important for developing assistive devices, such as exoskeletons, as the optimal assistive strategies may differ for different locomotion modes. The prediction of locomotion mode transitions is often accompanied by gait-event detection that provides important information during locomotion about critical events, such as foot contact (FC) and toe off (TO). In this study, we introduce a method to integrate locomotion mode prediction and gait-event identification into one machine learning framework, comprised of two multilayer perceptrons (MLP). Input features to the framework were from fused data from wearable sensors-specifically, electromyography sensors and inertial measurement units. The first MLP successfully identified FC and TO, FC events were identified accurately, and a small number of misclassifications only occurred near TO events. A small time difference (2.5 ms and -5.3 ms for FC and TO, respectively) was found between predicted and true gait events. The second MLP correctly identified walking, ramp ascent, and ramp descent transitions with the best aggregate accuracy of 96.3%, 90.1%, and 90.6%, respectively, with sufficient prediction time prior to the critical events. The models in this study demonstrate high accuracy in predicting transitions between different locomotion modes in the same side's mid- to late stance of the stride prior to the step into the new mode using data from EMG and IMU sensors. Our results may help assistive devices achieve smooth and seamless transitions in different locomotion modes for those with motor disorders.
人们每天在不同类型的地形上行走；例如，平地行走、斜坡和楼梯的上升和下降，以及跨越障碍物都是日常生活中的常见活动。当人们从一种地形移动到另一种地形时，运动模式会发生变化。预测运动模式的转变对于开发辅助设备（如外骨骼）非常重要，因为不同的运动模式可能需要不同的最佳辅助策略。运动模式转变的预测通常伴随着步态事件检测，该检测在运动过程中提供有关关键事件（例如脚接触 (FC) 和脚趾离地 (TO)）的重要信息。在这项研究中，我们引入了一种将运动模式预测和步态事件识别集成到一个机器学习框架中的方法，该框架由两个多层感知机 (MLP) 组成。框架的输入特征来自可穿戴传感器（特别是肌电图传感器和惯性测量单元）融合后的数据。第一个 MLP 成功识别了 FC 和 TO，FC 事件被准确识别，只有少数错误分类仅发生在 TO 事件附近。在预测和真实步态事件之间发现了很小的时间差异（FC 和 TO 分别为 2.5 毫秒和-5.3 毫秒）。第二个 MLP 正确识别了行走、斜坡上升和斜坡下降的过渡，总体准确率分别为 96.3%、90.1%和 90.6%，在关键事件之前有足够的预测时间。本研究中的模型使用来自 EMG 和 IMU 传感器的数据，在步幅的中间到后期的同一边预测不同运动模式之间的过渡，在进入新模式之前，展示了高准确性。这些结果可能有助于为运动障碍患者的辅助设备实现不同运动模式之间的平稳、无缝过渡。
