Details
| Original language | English |
|---|---|
| Place of Publication | Düsseldorf |
| Number of pages | 170 |
| ISBN (electronic) | 9783186877109 |
| Publication status | Published - 2022 |
Publication series
| Name | Fortschritt-Berichte VDI |
|---|---|
| Publisher | VDI Verlag |
| Volume | 877 |
Abstract
Keywords
- Maschinelles Lernen, menschliche Bewegung, Künstliche Neuronale Netze, inverse Dynamik, self-supervised learning, inverse dynamics, selbstüberwachtes Lernen, Machine Learning, gait analysis, artificial neural networks, human motion, joint moments, Gelenkmomente, Ganganalyse
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
Düsseldorf, 2022. 170 p. (Fortschritt-Berichte VDI; Vol. 877).
Research output: Book/Report › Monograph › Research
}
TY - BOOK
T1 - Learning-based inverse dynamics for human motion analysis
AU - Zell, Petrissa
PY - 2022
Y1 - 2022
N2 - This dissertation deals with machine learning techniques for inverse dynamics of human motion. Inverse dynamics refers to the derivation of acting forces and moments from the motion of a kinematic model. More precisely, the objective is to estimate joint torques, ground reaction forces and ground reaction moments at both feet based on the three-dimensional input motion of a skeletal model. The problem is solved using a data-driven machine learning approach, proposing several regression models that are particularly suitable with respect to limited data availability. The goal is to exploit the inherent strengths of machine learning, such as fast and noiseresistant data analysis. The described methods are able to predict underlying joint torques and exterior forces with high precision (on gait sequences: relative root mean squared errors of 7.0 %, 16.1 % and 11.9 % for reaction forces, reaction moments and joint moments which correspond to Pearson‘s correlation coefficients of 0.91, 0.83 and 0.82), while reducing computation times by two orders of magnitude compared to traditional optimization
AB - This dissertation deals with machine learning techniques for inverse dynamics of human motion. Inverse dynamics refers to the derivation of acting forces and moments from the motion of a kinematic model. More precisely, the objective is to estimate joint torques, ground reaction forces and ground reaction moments at both feet based on the three-dimensional input motion of a skeletal model. The problem is solved using a data-driven machine learning approach, proposing several regression models that are particularly suitable with respect to limited data availability. The goal is to exploit the inherent strengths of machine learning, such as fast and noiseresistant data analysis. The described methods are able to predict underlying joint torques and exterior forces with high precision (on gait sequences: relative root mean squared errors of 7.0 %, 16.1 % and 11.9 % for reaction forces, reaction moments and joint moments which correspond to Pearson‘s correlation coefficients of 0.91, 0.83 and 0.82), while reducing computation times by two orders of magnitude compared to traditional optimization
KW - Maschinelles Lernen
KW - menschliche Bewegung
KW - Künstliche Neuronale Netze
KW - inverse Dynamik
KW - self-supervised learning
KW - inverse dynamics
KW - selbstüberwachtes Lernen
KW - Machine Learning
KW - gait analysis
KW - artificial neural networks
KW - human motion
KW - joint moments
KW - Gelenkmomente
KW - Ganganalyse
U2 - 10.51202/9783186877109
DO - 10.51202/9783186877109
M3 - Monograph
SN - 9783183877102
T3 - Fortschritt-Berichte VDI
BT - Learning-based inverse dynamics for human motion analysis
CY - Düsseldorf
ER -