Estimation of Lower Extremity Joint Moments and 3D Ground Reaction Forces Using IMU Sensors in Multiple Walking Conditions: A Deep Learning Approach

Hossain, Md Sanzid Bin; Guo, Zhishan; Choi, Hwan

doi:10.1109/jbhi.2023.3262164

Cited by 16 publications

(17 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Also, the performance of our pretrained models is comparable to or slightly higher than those reported in prior studies that used the same downstream datasets for vGRF estimation. Specifically, a prior deep learning model achieved a correlation coefficient of 0.96 ± 0.01 for overground walking and 0.96 ± 0.01 for treadmill walking [50], while our models achieved 0.95 ± 0.02 and 0.97 ± 0.01, respectively. Another prior deep learning model achieved a correlation coefficient of 0.92±0.11 [27] for vGRF estimation during drop landing, while our model achieved 0.93 ± 0.04.…”

Section: Discussionmentioning

confidence: 73%

Self-Supervised Learning Improves Accuracy and Data Efficiency for IMU-Based Ground Reaction Force Estimation

Tan,

Shull,

Hicks

et al. 2023

Preprint

View full text Add to dashboard Cite

ObjectiveRecent deep learning techniques hold promise to enable IMU-driven gait assessment; however, they require large extents of marker-based motion capture and ground reaction force (GRF) data to serve as labels for supervised model training. We thus propose a self-supervised learning (SSL) framework to leverage large IMU datasets for pre-training deep learning models, which can improve the accuracy and data efficiency of IMU-based vertical GRF (vGRF) estimation.MethodsTo pre-train the models, we performed SSL by masking a random portion of the input IMU data and training a transformer model to reconstruct the masked portion. We systematically compared a series of masking ratios across three pre-training datasets that included real IMU data, synthetic IMU data, or a combination of the two. Finally, we built models that used pre-training and labeled data to estimate vGRF during three prediction tasks: overground walking, treadmill walking, and drop landing.ResultsWhen using the same amount of labeled data, SSL pre-training improved the accuracy of vGRF estimation during walking compared to baseline models trained by conventional supervised learning. The correlation coefficients for vGRF estimation improved from 0.92 to 0.95 for overground waking and from 0.94 to 0.97 for treadmill walking. Also, using 1–10% of walking data to fine-tune pre-trained models yielded comparable accuracy to the baseline model that was trained on 100% of walking data.ConclusionThe proposed SSL framework leveraged large real and synthetic IMU datasets to increase the accuracy and data efficiency of deep-learning-based vGRF estimation, reducing the need of labels.SignificanceThis work may unlock broader use cases of IMU-driven assessment where only small labeled datasets are available.

show abstract

Section: Discussionmentioning

confidence: 73%

Self-Supervised Learning Improves Accuracy and Data Efficiency for IMU-Based Ground Reaction Force Estimation

Tan,

Shull,

Hicks

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…However, many machine learning models do not provide a complete analysis but estimate only a small number of variables for a specific application, for example, vertical GRF and knee flexion angle ( Wouda et al, 2018 ) or knee flexion and adduction moments ( Stetter et al, 2020 ). Moreover, separate machine learning models were trained for kinematics and kinetics without taking the physical relation of the estimated variables into account ( Mundt et al, 2021 ; Hossain et al, 2023 ). These drawbacks make machine learning models poorly generalizable to other applications and hinder explainability of potential biomechanical findings.…”

Section: Introductionmentioning

confidence: 99%

Estimating 3D kinematics and kinetics from virtual inertial sensor data through musculoskeletal movement simulations

Nitschke,

Dorschky,

Leyendecker

et al. 2024

Front. Bioeng. Biotechnol.

View full text Add to dashboard Cite

Portable measurement systems using inertial sensors enable motion capture outside the lab, facilitating longitudinal and large-scale studies in natural environments. However, estimating 3D kinematics and kinetics from inertial data for a comprehensive biomechanical movement analysis is still challenging. Machine learning models or stepwise approaches performing Kalman filtering, inverse kinematics, and inverse dynamics can lead to inconsistencies between kinematics and kinetics. We investigated the reconstruction of 3D kinematics and kinetics of arbitrary running motions from inertial sensor data using optimal control simulations of full-body musculoskeletal models. To evaluate the feasibility of the proposed method, we used marker tracking simulations created from optical motion capture data as a reference and for computing virtual inertial data such that the desired solution was known exactly. We generated the inertial tracking simulations by formulating optimal control problems that tracked virtual acceleration and angular velocity while minimizing effort without requiring a task constraint or an initial state. To evaluate the proposed approach, we reconstructed three trials each of straight running, curved running, and a v-cut of 10 participants. We compared the estimated inertial signals and biomechanical variables of the marker and inertial tracking simulations. The inertial data was tracked closely, resulting in low mean root mean squared deviations for pelvis translation (≤20.2 mm), angles (≤1.8 deg), ground reaction forces (≤1.1 BW%), joint moments (≤0.1 BWBH%), and muscle forces (≤5.4 BW%) and high mean coefficients of multiple correlation for all biomechanical variables (≥0.99). Accordingly, our results showed that optimal control simulations tracking 3D inertial data could reconstruct the kinematics and kinetics of individual trials of all running motions. The simulations led to mutually and dynamically consistent kinematics and kinetics, which allows researching causal chains, for example, to analyze anterior cruciate ligament injury prevention. Our work proved the feasibility of the approach using virtual inertial data. When using the approach in the future with measured data, the sensor location and alignment on the segment must be estimated, and soft-tissue artifacts are potential error sources. Nevertheless, we demonstrated that optimal control simulation tracking inertial data is highly promising for estimating 3D kinematics and kinetics for a comprehensive biomechanical analysis.

show abstract

“…(2) We simplify the inertial forces and moments distributed in the human body, resulting in a pair of forces and moments in the same direction ( F and T in Figure 4). The specific calculation process is described in Equations ( 13)- (15). First, the resultant force and the resultant moment at point O 0 can be calculated as…”

Section: Reducing the Moment Components Based On The Centers Of Press...mentioning

confidence: 99%

“…Generally, dynamics-modeling-based methods calculate the moments of exoskeletons' joints according to the contact forces and moments (CFMs) as well as inverse dynamics [11][12][13][14]. CFMs can be detected using well-designed high-precision force sensors [15][16][17][18][19]. However, comfortable, portable, and high-precision force sensors for measuring these CFMs are difficult to design and manufacture [20][21][22][23].…”

Section: Introductionmentioning

confidence: 99%

Ground Contact Force and Moment Estimation for Human–Exoskeleton Systems Using Dynamic Decoupled Coordinate System and Minimum Energy Hypothesis

Li,

Ju,

Liu

et al. 2023

Biomimetics

View full text Add to dashboard Cite

Estimating the contact forces and moments (CFMs) between exoskeletons’ feet and the ground is a prerequisite for calculating exoskeletons’ joint moments. However, comfortable, portable, and high-precision force sensors for CFM detection are difficult to design and manufacture. In addition, there are many unknown CFM components (six force components and six moment components in the double-support phase). These reasons make it challenging to estimate CFMs precisely. In this paper, we propose a novel method for estimating these CFMs based on a proposed dynamic decoupled coordinate system (DDCS) and the minimum energy hypothesis. By decomposing these CFMs into a DDCS, the number of unknowns can be significantly reduced from twelve to two. Meanwhile, the minimum energy hypothesis provides a relatively reliable target for optimizing the remaining two unknown variables. We verify the accuracy of this method using a public data set about human walking. The validation shows that the proposed method is capable of estimating CFMs. This study provides a practical way to estimate the CFMs under the soles, which contributes to reducing the research and development costs of exoskeletons by avoiding the need for expensive plantar sensors. The sensor-free approach also reduces the dependence on high-precision, portable, and comfortable CFM detection sensors, which are usually difficult to design.

show abstract

Estimation of Lower Extremity Joint Moments and 3D Ground Reaction Forces Using IMU Sensors in Multiple Walking Conditions: A Deep Learning Approach

Cited by 16 publications

References 54 publications

Self-Supervised Learning Improves Accuracy and Data Efficiency for IMU-Based Ground Reaction Force Estimation

Self-Supervised Learning Improves Accuracy and Data Efficiency for IMU-Based Ground Reaction Force Estimation

Estimating 3D kinematics and kinetics from virtual inertial sensor data through musculoskeletal movement simulations

Ground Contact Force and Moment Estimation for Human–Exoskeleton Systems Using Dynamic Decoupled Coordinate System and Minimum Energy Hypothesis

Contact Info

Product

Resources

About