Convolutional neural network based ground reaction forces and center of pressure estimation during stair walking using multi-level kinematics

被引:0
作者
Liu, Dongwei [2 ]
Ma, Ye [1 ,3 ,4 ]
Wang, Jie [1 ]
Hou, Meijin [3 ,4 ]
Zhang, Chao [5 ]
机构
[1] Ningbo Univ, Fac Sports Sci, Res Acad Grand Hlth, Ningbo, Zhejiang, Peoples R China
[2] Zhejiang Univ Finance & Econ, Sch Informat Management & Artificial Intelligence, Hangzhou, Zhejiang, Peoples R China
[3] Fujian Univ Tradit Chinese Med, Natl Local Joint Engn Res Ctr Rehabil Med Technol, Fuzhou, Fujian, Peoples R China
[4] Fujian Univ Tradit Chinese Med, Key Lab Orthopaed & Traumatol Tradit Chinese Med &, Minist Educ, Fuzhou, Fujian, Peoples R China
[5] Tsinghua Univ, Dept Elect Engn, Beijing, Peoples R China
基金
中国国家自然科学基金;
关键词
Ground reaction force; Center of pressure; Estimation; Deep learning; Stair walking; GAIT PATTERNS; PARAMETERS; ASCENT; DESCENT; REPEATABILITY; EPIDEMIOLOGY; BIOMECHANICS; AMBULATION; PREDICTION; VARIABLES;
D O I
10.1016/j.eswa.2023.122868
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Ground reaction forces (GRFs) and center of pressure trajectories (CoPs) are required for a comprehensive biomechanical analysis. They are also important outcome measures in sports sciences or clinical areas. GRFs and CoPs are usually measured by force plates, which are rarely equipped on staircases in laboratories. We present a one-dimensional convolutional neural network for estimating GRFs and CoPs during stair ascent and descent using multi-level kinematics as input. We collected a dataset of 3782 trials from 172 subjects for training and validating this model. The recruited subjects include healthy subjects and individuals with knee osteoarthritis or moderate-to-high risk of cardiovascular diseases. Our model achieves the state-of-theart estimating performance with nRMSE of 2.755% similar to 7.633%, Pearson correlation of 0.950 similar to 0.996 on GRFs estimation, and with nRMSE of 5.519% similar to 14.669%, Pearson correlation of 0.918 similar to 0.991 on CoPs estimation. With our proposed model, GRFs and CoPs during stair walking can be estimated without force-plate-embedded staircases.
引用
收藏
页数:11
相关论文
共 77 条
[1]  
Benda B. J., 1994, IEEE Transactions on Rehabilitation Engineering, V2, P3, DOI 10.1109/86.296348
[2]   Data management in gait analysis for clinical applications [J].
Benedetti, MG ;
Catani, F ;
Leardini, A ;
Pignotti, E ;
Giannini, S .
CLINICAL BIOMECHANICS, 1998, 13 (03) :204-215
[3]   Ground reaction forces and bone parameters in females with tibial stress fracture [J].
Bennell, K ;
Crossley, K ;
Jayarajan, J ;
Walton, E ;
Warden, S ;
Kiss, ZS ;
Wrigley, T .
MEDICINE AND SCIENCE IN SPORTS AND EXERCISE, 2004, 36 (03) :397-404
[4]  
Brown C.E., 1998, Applied Multivariate Statistics in Geohydrology and Related Sciences, P155, DOI 10.1007/978-3-642-80328-4
[5]   Gait speed and gender effects on center of pressure progression during normal walking [J].
Chiu, Min-Chi ;
Wu, Hsin-Chieh ;
Chang, Li-Yu .
GAIT & POSTURE, 2013, 37 (01) :43-48
[6]   Machine learning approach to predict center of pressure trajectories in a complete gait cycle: a feedforward neural network vs. LSTM network [J].
Choi, Ahnryul ;
Jung, Hyunwoo ;
Lee, Ki Young ;
Lee, Sangsik ;
Mun, Joung Hwan .
MEDICAL & BIOLOGICAL ENGINEERING & COMPUTING, 2019, 57 (12) :2693-2703
[7]   Improved determination of dynamic balance using the centre of mass and centre of pressure inclination variables in a complete golf swing cycle [J].
Choi, Ahnryul ;
Sim, Taeyong ;
Mun, Joung Hwan .
JOURNAL OF SPORTS SCIENCES, 2016, 34 (10) :906-914
[8]   Individual Stair Ascent and Descent Walk Speeds Measured in a Korean High-Rise Building [J].
Choi, Jun-Ho ;
Galea, Edwin Richard ;
Hong, Won-Hwa .
FIRE TECHNOLOGY, 2014, 50 (02) :267-295
[9]   Enhancing the Accuracy of Vertical Ground Reaction Force Measurement During Walking Using Pressure-Measuring Insoles [J].
DeBerardinis, Jessica ;
Trabia, Mohamed B. ;
Dufek, Janet S. ;
Le Gall, Yann ;
Sacoto, Nicolas Da Silva .
JOURNAL OF BIOMECHANICAL ENGINEERING-TRANSACTIONS OF THE ASME, 2021, 143 (01)
[10]   INTRADAY RELIABILITY OF GROUND REACTION FORCE DATA [J].
DEVITA, P ;
BATES, BT .
HUMAN MOVEMENT SCIENCE, 1988, 7 (01) :73-85