Objective: Our aim is to determine if data collected with inertial measurement units (IMUs) during steady-state running could be used to estimate ground reaction forces (GRFs) and to derive biomechanical variables (e.g., contact time, impulse, change in velocity) using lightweight machine-learning approaches. In contrast, state-of-the-art estimation using LSTMs suffers from prohibitive inference times on edge devices, requires expensive training and hyperparameter optimization, and results in black box models.

Methods: We proposed a novel lightweight solution, SVD Embedding Regression (SER), using linear regression between SVD embeddings of IMU data and GRF data. We also compared lightweight solutions including SER and k-Nearest-Neighbors (KNN) regression with state-of-the-art LSTMs.

Results: We performed extensive experiments to evaluate these techniques under multiple scenarios and combinations of IMU signals and quantified estimation errors for predicting GRFs and biomechanical variables. We did this using training data from different athletes, from the same athlete, or both, and we explored the use of acceleration and angular velocity data from sensors at different locations (sacrum and shanks).

Conclusion: Our results illustrated that lightweight solutions such as SER and KNN can be similarly accurate or more accurate than LSTMs. The use of personal data reduced estimation errors of all methods, particularly for most biomechanical variables (as compared to GRFs); moreover, this gain was more pronounced in the lightweight methods.

Significance: The study of GRFs is used to characterize the mechanical loading experienced by individuals in movements such as running, which is clinically applicable to identify athletes at risk for stress-related injuries.

Download full-text PDF

Source
http://dx.doi.org/10.1109/TBME.2024.3465373DOI Listing

Publication Analysis

Top Keywords

biomechanical variables
12
ground reaction
8
reaction forces
8
lightweight solutions
8
estimation errors
8
data
6
lightweight
5
estimating ground
4
forces inertial
4
inertial sensors
4

Similar Publications

There is a growing interest in the development of methods for the detection of nanoparticle (NP) toxicity to living organisms based on the analysis of relevant multidimensional data sets. In particular the detection of preliminary signs of NPs toxicity effects would benefit from the selection of data featuring NPs-induced alterations of biological barriers. Accordingly, we present an original Topological Data Analysis (TDA) of the nanomechanical properties of Escherichia coli cell surface, evaluated by multiparametric Atomic Force Microscopy (AFM) after exposure of the cells to increasing concentrations of titanium dioxide nanoparticles (TiONPs).

View Article and Find Full Text PDF

Impact of Inflammation After Cardiac Surgery on 30-Day Mortality and Machine Learning Risk Prediction.

J Cardiothorac Vasc Anesth

December 2024

Division of Cardiac Surgery, Department of Medical and Surgical Sciences, University of Foggia, Foggia, Italy; Division of Cardiac Surgery, Santa Maria Hospital, GVM Care & Research, Bari, Italy. Electronic address:

Objectives: To investigate the impact of systemic inflammatory response syndrome (SIRS) on 30-day mortality following cardiac surgery and develop a machine learning model to predict SIRS.

Design: Retrospective cohort study.

Setting: Single tertiary care hospital.

View Article and Find Full Text PDF

Adaptation of functional gait parameters to a newly provided stiffness-optimized ankle-foot orthosis.

Clin Biomech (Bristol)

December 2024

Amsterdam UMC location University of Amsterdam, Rehabilitation Medicine, Meibergdreef 9, Amsterdam, the Netherlands; Amsterdam Movement Sciences, Rehabilitation and Development, Amsterdam, the Netherlands. Electronic address:

Background: Clinical decisions regarding ankle-foot-orthosis stiffness in people with calf muscle weakness are based on immediate evaluations, not taking gait adaptation into account. This study examined adaptation of step length, walking speed and energy cost of walking in the 3-months post-provision and whether individuals with higher gait variability adapt more compared to individuals with lower gait variability.

Methods: We conducted a post-hoc analysis in eighteen stiffness-optimized ankle-foot-orthosis users with bilateral calf muscle weakness.

View Article and Find Full Text PDF

Opportunistic screening is essential to improve the identification of individuals with osteoporosis. Our group has utilized image texture features to assess bone quality using clinical MRIs. We have previously demonstrated that greater heterogeneity of MRI texture related to history of fragility fractures, lower bone density, and worse microarchitecture.

View Article and Find Full Text PDF

Exercise influences clinical Achilles tendon health in humans, but animal models of exercise-related Achilles tendon changes are lacking. Moreover, previous investigations of the effects of treadmill running exercise on rat Achilles tendon demonstrate variable outcomes. Our objective was to assess the functional, structural, cellular, and biomechanical impacts of treadmill running exercise on rat Achilles tendon with sensitive in and ex vivo approaches.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!