Input data when using neural networks to estimate lower-body torques from wearable sensors during gait: Is it of great influence?

ABSTRACT Recent advancements in wearable sensors and machine learning show promise for estimating lower-body joint torques outside of laboratory settings. Inertial Measurement Units combined with Convolutional Neural Networks have proven effective for this task. However, the impact of different input data types and formats remains underexplored. This study investigates how variations in input data influence the prediction of lower-body joint torques during walking. Results indicate that while dataset choice causes only minor differences in prediction performance, the overall quality of the dataset plays a more critical role than the specific input variables in achieving accurate torque predictions using wearable sensors. Competing Interest Statement The authors have declared no competing interest. Footnotes simon.ozan{at}univ-rennes2.fr Disclosure statement. The authors report there are no competing interests to declare. Fundings and acknowledgments: The authors would like to thank the participants of this study for their contribution, and Ms Hogan for proofreading the article. This study was supported in part by the New Aquitaine region and the European Union through the Habisan program (CPER□FEDER).