Estimation of vertical ground reaction force during running using neural network model and uniaxial accelerometer

Ngoh, Kieron Jie Han; Gouwanda, Darwin; Gopalai, Alpha Agape; Chong, Yu Zheng

doi:10.1016/j.jbiomech.2018.06.006

Cited by 73 publications

(73 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These factors limit the potential of monitoring in-field running biomechanics, whereas wearable inertial measurement units can accommodate this by predicting running gait parameters outside the laboratory (Falbriard et al, 2018;Wouda et al, 2018). In this respect, an ambulatory low-cost accelerometer was proposed as a potential surrogate candidate to estimate VILR when force platforms are not available (Ngoh et al, 2018). Previous research has identified a moderate to good correlation (range of r mean = 0.64-0.84) between the axial peak tibial acceleration (APTA) captured by a skin-mounted accelerometer at the tibia and VILR (Laughton et al, 2003;Pohl et al, 2009;Greenhalgh et al, 2012;Zhang et al, 2016;Van den Berghe et al, 2019).…”

Section: Introductionmentioning

confidence: 99%

Tibial Acceleration-Based Prediction of Maximal Vertical Loading Rate During Overground Running: A Machine Learning Approach

Derie

Robberechts

Berghe

et al. 2020

Front. Bioeng. Biotechnol.

View full text Add to dashboard Cite

Ground reaction forces are often used by sport scientists and clinicians to analyze the mechanical risk-factors of running related injuries or athletic performance during a running analysis. An interesting ground reaction force-derived variable to track is the maximal vertical instantaneous loading rate (VILR). This impact characteristic is traditionally derived from a fixed force platform, but wearable inertial sensors nowadays might approximate its magnitude while running outside the lab. The time-discrete axial peak tibial acceleration (APTA) has been proposed as a good surrogate that can be measured using wearable accelerometers in the field. This paper explores the hypothesis that applying machine learning to time continuous data (generated from bilateral tri-axial shin mounted accelerometers) would result in a more accurate estimation of the VILR. Therefore, the purpose of this study was to evaluate the performance of accelerometer-based predictions of the VILR with various machine learning models trained on data of 93 rearfoot runners. A subject-dependent gradient boosted regression trees (XGB) model provided the most accurate estimates (mean absolute error: 5.39 ± 2.04 BW•s −1 , mean absolute percentage error: 6.08%). A similar subject-independent model had a mean absolute error of 12.41 ± 7.90 BW•s −1 (mean absolute percentage error: 11.09%). All of our models had a stronger correlation with the VILR than the APTA (p < 0.01), indicating that multiple 3D acceleration features in a learning setting showed the highest accuracy in predicting the lab-based impact loading compared to APTA.

show abstract

Section: Introductionmentioning

confidence: 99%

Tibial Acceleration-Based Prediction of Maximal Vertical Loading Rate During Overground Running: A Machine Learning Approach

Derie

Robberechts

Berghe

et al. 2020

Front. Bioeng. Biotechnol.

View full text Add to dashboard Cite

show abstract

“…IMUs have recently become even more reliable as several methods to estimate GRFs using IMUs have been developed [9,10,[18][19][20][21][22]. A recent study analyzed the feasibility of using an IMU mounted underneath the walking surface and measured comparable accuracy to IMUs attached to the body [18].…”

Section: Discussionmentioning

confidence: 99%

“…An interesting trend is the addition of machine learning methods to estimate GRFs using IMUs. Most of the studies that have been previously discussed use machine learning methods to estimate GRFs with the use of IMUs [9,10,[19][20][21][22]. These studies have demonstrated promising results when estimating vertical and three-dimensional GRFs.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Real-Time Vertical Ground Reaction Force Estimation in a Unified Simulation Framework Using Inertial Measurement Unit Sensors

et al. 2020

View full text Add to dashboard Cite

Recent advances in computational technology have enabled the use of model-based simulation with real-time motion tracking to estimate ground reaction forces during gait. We show here that a biomechanical-based model including a foot-ground contact can reproduce measured ground reaction forces using inertial measurement unit data during single-leg support, single-support jump, side to side jump, jogging, and skipping. The framework is based on our previous work on integrating the OpenSim musculoskeletal models with the Unity environment. The validation was performed on a single subject performing several tasks that involve the lower extremity. The novelty of this paper includes the integration and real-time tracking of inertial measurement unit data in the current framework, as well as the estimation of contact forces using biologically based musculoskeletal models. The RMS errors of tracking the vertical ground reaction forces are 0.027 bodyweight, 0.174 bodyweight, 0.173 bodyweight, 0.095 bodyweight, and 0.10 bodyweight for single-leg support, single-support jump, side to side jump, jogging, and skipping, respectively. The average RMS error for all tasks and trials is 0.112 bodyweight. This paper provides a computational framework for further applications in whole-body human motion analysis.

show abstract

“…There are different methods that are used to measure the height of jumping including time taken to calculate the height of a vertical jump by using ground test strips to detect jumping and landing marks. Strain gauge, electrical switch [4][5][6][7][8][9], accelerometer [10][11] and optoelectronic [12] are also applied to above measurements. Training patterns may benefit from the measurements of jumping because athletes can be trained to jump more effectively.…”

Section: Introductionmentioning

confidence: 99%

Estimation of Vertical Jump Height Using Nintendo Wii Remote IR Camera

et al. 2018

View full text Add to dashboard Cite

In this article, we proposed to measure the heights of countermovement jumps which are recorded in term of vertical leap by using the Wii Remote infrared camera. According to the physical principles, positions of the movement were detected based on the rules regarding conservation of energy, motion under gravity, and coordinate system. The obtained results were compared with that of the slow-motion measurements. The experiment involved 30 basketball players whose jump results were slightly deviated from the vertical measurement of the coordinate system. Therefore, the results should be calibrated each time the new system is installed.

show abstract

Estimation of vertical ground reaction force during running using neural network model and uniaxial accelerometer

Cited by 73 publications

References 29 publications

Tibial Acceleration-Based Prediction of Maximal Vertical Loading Rate During Overground Running: A Machine Learning Approach

Tibial Acceleration-Based Prediction of Maximal Vertical Loading Rate During Overground Running: A Machine Learning Approach

Real-Time Vertical Ground Reaction Force Estimation in a Unified Simulation Framework Using Inertial Measurement Unit Sensors

Estimation of Vertical Jump Height Using Nintendo Wii Remote IR Camera

Contact Info

Product

Resources

About