Department of Measurement and Technology, Faculty of Electrical Engineering, University of West Bohemia, 30100 Pilsen, Czech Republic.
Reseach and Innovation Center, Faculty of Electrical Engineering, University of West Bohemia, 30100 Pilsen, Czech Republic.
Sensors (Basel). 2022 May 19;22(10):3865. doi: 10.3390/s22103865.
The estimation of the speed of human motion from wearable IMU sensors is required in applications such as pedestrian dead reckoning. In this paper, we test deep learning methods for the prediction of the motion speed from raw readings of a low-cost IMU sensor. Each subject was observed using three sensors at the shoe, shin, and thigh. We show that existing general-purpose architectures outperform classical feature-based approaches and propose a novel architecture tailored for this task. The proposed architecture is based on a semi-supervised variational auto-encoder structure with innovated decoder in the form of a dense layer with a sinusoidal activation function. The proposed architecture achieved the lowest average error on the test data. Analysis of sensor placement reveals that the best location for the sensor is the shoe. Significant accuracy gain was observed when all three sensors were available. All data acquired in this experiment and the code of the estimation methods are available for download.
从可穿戴式 IMU 传感器估计人类运动速度在行人航位推算等应用中是必需的。在本文中，我们测试了深度学习方法，以从低成本 IMU 传感器的原始读数中预测运动速度。每位受试者都使用三个传感器在鞋、小腿和大腿处进行观察。我们表明，现有的通用体系结构优于基于经典特征的方法，并为该任务提出了一种新的架构。所提出的架构基于半监督变分自动编码器结构，具有创新的解码器形式，为密集层，带有正弦激活函数。所提出的架构在测试数据上实现了最低的平均误差。传感器位置的分析表明，传感器的最佳位置是鞋。当三个传感器都可用时，观察到了显著的准确性提高。本实验中获取的所有数据和估计方法的代码都可下载。
