期刊
MEASUREMENT
卷 198, 期 -, 页码 -出版社
ELSEVIER SCI LTD
DOI: 10.1016/j.measurement.2022.111344
关键词
Ground reaction forces estimation; Deep learning; Kinematics; Stair walking
资金
- National Natural Science Foundation of China [61802338, 12002177]
- Zhejiang Provincial Natural Science Foundation, China [LQ19A020001]
- K.C. Wong Magna Fund in Ningbo University
In this study, bilateral long short-term memory neural networks were trained to estimate ground reaction forces (GRFs) during stair ascent and descent using whole-body kinematics as input. A post-processing algorithm was developed to remove artifacts on GRFs in the swing phase. The models achieved excellent accuracy, allowing researchers to estimate 3D GRFs during stair walking without instrumented staircases.
Complete ground reaction forces (GRFs) are vital for biomechanical analysis. The GRFs are currently measured by force plates. The measurement of GRFs during stair walking is difficult due to the need for instrumented staircases. We trained two bi-lateral long short-term memory (BiLSTM) neural networks to estimate 3D GRFs during stair ascent and stair descent using the whole-body kinematics as the input. The dataset is collected from eighty subjects, including healthy and knee osteoarthritis individuals. We also developed a post-processing algorithm to remove artifacts on GRFs in the swing phase. Our models achieved excellent accuracy compared with the measured GRFs with the correlations of 0.908 & SIM; 0.991, the root mean squared error (RMSE) of 3.29% and 3.56% body weight (BW) and the normalized RMSE (nRMSE) lower than 5% and 8% for the complete GRFs during stair descent and ascent. Using our models, researchers can estimate 3D GRFs during stair walking without instrumented staircases.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据