scholarly journals Estimation of Three-Dimensional Lower Limb Kinetics Data during Walking Using Machine Learning from a Single IMU Attached to the Sacrum

Sensors ◽  
2020 ◽  
Vol 20 (21) ◽  
pp. 6277
Author(s):  
Myunghyun Lee ◽  
Sukyung Park
Keyword(s):  
Center Of Pressure ◽  
Center Of Mass ◽  
Three Dimensional ◽  
Lower Limbs ◽  
Three Dimensions ◽  
Measurement Unit ◽  
Ann Model ◽  
Joint Torques ◽  
Reaction Forces ◽  
Mean Square Errors

Kinetics data such as ground reaction forces (GRFs) are commonly used as indicators for rehabilitation and sports performance; however, they are difficult to measure with convenient wearable devices. Therefore, researchers have attempted to estimate accurately unmeasured kinetics data with artificial neural networks (ANNs). Because the inputs to an ANN affect its performance, they must be carefully selected. The GRF and center of pressure (CoP) have a mechanical relationship with the center of mass (CoM) in the three dimensions (3D). This biomechanical characteristic can be used to establish an appropriate input and structure of an ANN. In this study, an ANN for estimating gait kinetics with a single inertial measurement unit (IMU) was designed; the kinematics of the IMU placed on the sacrum as a proxy for the CoM kinematics were applied based on the 3D spring mechanics. The walking data from 17 participants walking at various speeds were used to train and validate the ANN. The estimated 3D GRF, CoP trajectory, and joint torques of the lower limbs were reasonably accurate, with normalized root-mean-square errors (NRMSEs) of 6.7% to 15.6%, 8.2% to 20.0%, and 11.4% to 24.1%, respectively. This result implies that the biomechanical characteristics can be used to estimate the complete three-dimensional gait data with an ANN model and a single IMU.

scholarly journals Prediction of Lower Limb Kinetics and Kinematics during Walking by a Single IMU on the Lower Back Using Machine Learning

Sensors ◽  
2019 ◽  
Vol 20 (1) ◽  
pp. 130 ◽  
Author(s):  
Lim ◽  
Kim ◽  
Park
Keyword(s):  
Machine Learning ◽  
Learning Algorithm ◽  
Center Of Mass ◽  
Lower Limbs ◽  
Joint Kinetics ◽  
Joint Torques ◽  
Dynamic Relationship ◽  
Reaction Forces ◽  
Artificial Neural Network Ann ◽  
Parameter Values

Recent studies have reported the application of artificial neural network (ANN) techniques on data of inertial measurement units (IMUs) to predict ground reaction forces (GRFs), which could serve as quantitative indicators of sports performance or rehabilitation. The number of IMUs and their measurement locations are often determined heuristically, and the rationale underlying the selection of these parameter values is not discussed. Using the dynamic relationship between the center of mass (CoM), the GRFs and joint kinetics, we propose the CoM as a single measurement location with which to predict the dynamic data of the lower limbs, using an ANN. Data from seven subjects walking on a treadmill at various speeds were collected from a single IMU worn near the sacrum. The data was segmented by step and numerically processed for integration. Six segment angles of the stance and swing leg, three joint torques, and two GRFs were estimated from the kinematics of the CoM measured from a single IMU sensor, with fair accuracy. These results indicate the importance of the CoM as a dynamic determinant of multi-segment kinetics during walking. The tradeoff between data quantity and wearable convenience can be solved by utilizing a machine learning algorithm based on the dynamic characteristics of human walking.

scholarly journals Kinematic and Kinetic Analysis of Horticultural Activities for Postural Control and Balance Training

HortScience ◽  
2018 ◽  
Vol 53 (10) ◽  
pp. 1541-1552
Author(s):  
A-Young Lee ◽  
Sin-Ae Park ◽  
Young-Jin Moon ◽  
Ki-Cheol Son
Keyword(s):  
Postural Control ◽  
Muscle Activation ◽  
Center Of Pressure ◽  
Center Of Mass ◽  
Reaction Force ◽  
Three Dimensional ◽  
Balance Training ◽  
Lower Limbs ◽  
Kinetic Characteristics ◽  
3D Motion Analysis

The objective of this study was to analyze the kinematic and kinetic characteristics of eight horticultural activities (HAs): digging, raking, sowing seeds, transplanting plants, near-distance weeding, far-distance weeding, low-height harvesting, and high-height harvesting. Twenty-four male university students (average age, 23.4 ± 2.9 years) participated in this study. Balance and postural stability factors [e.g., center of mass (CoM), ground reaction force (GRF), and center of pressure (CoP)] and postural control strategy factors (e.g., joint angles, joint moment, and muscle activation of the trunk and lower limbs) were assessed using a three-dimensional (3D) motion analysis system, force platform, and surface electromyography. A total of eight HAs were distinguished in three motions: stepping, squatting, and stooping. In performing the eight HAs, CoM shifting occurred and balance of the subjects became unstable. These forced compensatory motor strategies to maintain balance by exertion of GRF from the two feet, movement of the CoP, and a combination of musculoskeletal system exercises of the lower limbs and trunk occurred. The kinematic and kinetic characteristics of lower limb motions were significantly different across the HAs (P = 0.05). The kinematic and kinetic characteristics of HAs were similar to those of the functional tasks during balance improvement training motions and activities of daily living. The current study provides useful reference data for developing a horticultural therapy program for balance improvement in patients who need physical rehabilitation.

scholarly journals Active foot placement control ensures stable gait: Effect of constraints on foot placement and ankle moments

PLoS ONE ◽  
2020 ◽  
Vol 15 (12) ◽  
pp. e0242215
Author(s):  
A. M. van Leeuwen ◽  
J. H. van Dieën ◽  
A. Daffertshofer ◽  
S. M. Bruijn
Keyword(s):  
Steady State ◽  
Center Of Pressure ◽  
Center Of Mass ◽  
Reaction Force ◽  
Stride Frequency ◽  
Tight Control ◽  
Foot Placement ◽  
Ankle Moment ◽  
Reaction Forces ◽  
Moment Control

Step-by-step foot placement control, relative to the center of mass (CoM) kinematic state, is generally considered a dominant mechanism for maintenance of gait stability. By adequate (mediolateral) positioning of the center of pressure with respect to the CoM, the ground reaction force generates a moment that prevents falling. In healthy individuals, foot placement is complemented mainly by ankle moment control ensuring stability. To evaluate possible compensatory relationships between step-by-step foot placement and complementary ankle moments, we investigated the degree of (active) foot placement control during steady-state walking, and under either foot placement-, or ankle moment constraints. Thirty healthy participants walked on a treadmill, while full-body kinematics, ground reaction forces and EMG activities were recorded. As a replication of earlier findings, we first showed step-by-step foot placement is associated with preceding CoM state and hip ab-/adductor activity during steady-state walking. Tight control of foot placement appears to be important at normal walking speed because there was a limited change in the degree of foot placement control despite the presence of a foot placement constraint. At slow speed, the degree of foot placement control decreased substantially, suggesting that tight control of foot placement is less essential when walking slowly. Step-by-step foot placement control was not tightened to compensate for constrained ankle moments. Instead compensation was achieved through increases in step width and stride frequency.

scholarly journals Effects of additional load at different heights on gait initiation: A statistical parametric mapping of center of pressure and center of mass behavior

PLoS ONE ◽  
2021 ◽  
Vol 16 (6) ◽  
pp. e0242892
Author(s):  
Marcus Fraga Vieira ◽  
Fábio Barbosa Rodrigues ◽  
Alfredo de Oliveira Assis ◽  
Eduardo de Mendonça Mesquita ◽  
Thiago Santana Lemes ◽  
...  
Keyword(s):  
Time Series ◽  
Center Of Pressure ◽  
Center Of Mass ◽  
Statistical Parametric Mapping ◽  
Gait Initiation ◽  
Experimental Conditions ◽  
Distributed Load ◽  
Uniformly Distributed Load ◽  
Reaction Forces ◽  
Controlled Object

The purpose of this study was to investigate the effects of different vertical positions of an asymmetrical load on the anticipatory postural adjustments phase of gait initiation. Sixty-eight college students (32 males, 36 females; age: 23.65 ± 3.21 years old; weight: 69.98 ± 8.15 kg; height: 1.74 ± 0.08 m) were enrolled in the study. Ground reaction forces and moments were collected using two force platforms. The participants completed three trials under each of the following random conditions: no-load (NL), waist uniformly distributed load (WUD), shoulder uniformly distributed load (SUD), waist stance foot load (WST), shoulder stance foot load (SST), waist swing foot load (WSW), and shoulder swing foot load (SSW). The paired Hotelling’s T-square test was used to compare the experimental conditions. The center of pressure (COP) time series were significantly different for the SUD vs. NL, SST vs. NL, WST vs. NL, and WSW vs. NL comparisons. Significant differences in COP time series were observed for all comparisons between waist vs. shoulder conditions. Overall, these differences were greater when the load was positioned at the shoulders. For the center of mass (COM) time series, significant differences were found for the WUD vs. NL and WSW vs. NL conditions. However, no differences were observed with the load positioned at the shoulders. In conclusion, only asymmetrical loading at the waist produced significant differences, and the higher the extra load, the greater the effects on COP behavior. By contrast, only minor changes were observed in COM behavior, suggesting that the changes in COP (the controller) behavior are adjustments to maintain the COM (controlled object) unaltered.

Robust Bipedal Locomotion Based on a Hierarchical Control Structure

Robotica ◽  
2019 ◽  
Vol 37 (10) ◽  
pp. 1750-1767 ◽  
Author(s):  
Jianwen Luo ◽  
Yao Su ◽  
Lecheng Ruan ◽  
Ye Zhao ◽  
Donghyun Kim ◽  
...  
Keyword(s):  
Center Of Pressure ◽  
Center Of Mass ◽  
Hierarchical Control ◽  
Middle Level ◽  
Smooth Transition ◽  
Whole Body ◽  
Joint Torques ◽  
Low Level ◽  
Hybrid Controller ◽  
High Level

SummaryTo improve biped locomotion’s robustness to internal and external disturbances, this study proposes a hierarchical structure with three control levels. At the high level, a foothold sequence is generated so that the Center of Mass (CoM) trajectory tracks a planned path. The planning procedure is simplified by selecting the midpoint between two consecutive Center of Pressure (CoP) points as the feature point. At the middle level, a novel robust hybrid controller is devised to drive perturbed system states back to the nominal trajectory within finite cycles without chattering. The novelty lies in that the hybrid controller is not subject to linear CoM dynamic constraints. The hybrid controller consists of two sub-controllers: an oscillation controller and a smoothing controller. For the oscillation controller, the desired CoM height is specified as a sine-shaped function, avoiding a new attractive limit cycle. However, this controller results in the inevitable chattering because of discontinuities. A smoothing controller provides continuous properties and thus can inhibit the chattering problem, but has a smaller region of attraction compared with the oscillation controller. A hybrid controller merges the two controllers for a smooth transition. At the low level, the desired CoM motion is defined as tasks and embedded in a whole body operational space (WBOS) controller to compute the joint torques analytically. The novelty of the low-level controller lies in that within the WBOS framework, CoM motion is not subject to fixed CoM dynamics and thus can be generalized.

scholarly journals Human kinematic, kinetic and EMG data during different walking and stair ascending and descending tasks

2019 ◽  
Vol 6 (1) ◽  
Author(s):  
Tiziana Lencioni ◽  
Ilaria Carpinella ◽  
Marco Rabuffetti ◽  
Alberto Marzegan ◽  
Maurizio Ferrarin
Keyword(s):  
Lower Limb ◽  
Center Of Pressure ◽  
Center Of Mass ◽  
Simulation Models ◽  
Human Locomotion ◽  
Surface Emg ◽  
Whole Body ◽  
Bipedal Robots ◽  
Lower Limb Muscles ◽  
Reaction Forces

AbstractThis paper reports the kinematic, kinetic and electromyographic (EMG) dataset of human locomotion during level walking at different velocities, toe- and heel-walking, stairs ascending and descending. A sample of 50 healthy subjects, with an age between 6 and 72 years, is included. For each task, both raw data and computed variables are reported including: the 3D coordinates of external markers, the joint angles of lower limb in the sagittal, transversal and horizontal anatomical planes, the ground reaction forces and torques, the center of pressure, the lower limb joint mechanical moments and power, the displacement of the whole body center of mass, and the surface EMG signals of the main lower limb muscles. The data reported in the present study, acquired from subjects with different ages, represents a valuable dataset useful for future studies on locomotor function in humans, particularly as normative reference to analyze pathological gait, to test the performance of simulation models of bipedal locomotion, and to develop control algorithms for bipedal robots or active lower limb exoskeletons for rehabilitation.

scholarly journals BIOMECHANICS AND POTENTIAL INJURY MECHANISMS OF WRESTLING

2009 ◽  
Vol 21 (03) ◽  
pp. 215-222 ◽  
Author(s):  
Tsong-Rong Jang ◽  
Chu-Fen Chang ◽  
Sheng-Chang Chen ◽  
Yang-Chieh Fu ◽  
Tung-Wu Lu
Keyword(s):  
Center Of Pressure ◽  
Lower Limbs ◽  
Ankle Injuries ◽  
Joint Angles ◽  
Kinematic Data ◽  
Greco Roman ◽  
Injury Mechanisms ◽  
Male College ◽  
Reaction Forces ◽  
3D Motion Capture

Wrestling is one of the oldest and most popular competitive sports in the world, however, knowledge of the biomechanics of wrestling is not well established and the biomechanical risk factors of injuries unclear. The purpose of this study was to investigate the joint kinematics of the lower limbs and the center of pressure (COP) movements in Greco-Roman style (GR) and free style (FS) wrestlers during tackle defense. Eighteen male college wrestlers participated in the current study: 10 majored in GR (height: 171.1 ± 8.0 cm; weight: 73.9 ± 11.5, kg) and 8 in FS (height: 169.0 ± 5.2 cm; weight: 71.8 ± 11.4 kg). The wrestlers received tackle attacks from three different directions while their kinematic data measured by a 3D motion capture system and ground reaction forces from two AMTI forceplates. The wrestlers who majored in GR style tended to resist tackle attacks longer than the FS group. Compared to the GR group, the FS wrestlers tended to have greater A/P excursions of the COP with significant greater knee flexion. This flexed knee strategy may be related to the rule of the game and the training the FS wrestlers received. Significantly increased joint angles in the transverse and frontal planes at the knee and ankle found in the current study may be related to the risk of knee and ankle injuries commonly observed in wrestlers. Strengthening of the muscles of the lower extremity may be helpful for reducing these injuries during competitions.

scholarly journals Energy Efficient and Robust Balancing with Motion Primitive Switching

2017 ◽  
Vol 14 (03) ◽  
pp. 1750009 ◽  
Author(s):  
Sotiris Apostolopoulos ◽  
Marion Leibold ◽  
Martin Buss
Keyword(s):  
Energy Efficient ◽  
Euclidean Distance ◽  
Center Of Pressure ◽  
Center Of Mass ◽  
Quadratic Program ◽  
Control Lyapunov Function ◽  
Motion Primitives ◽  
Motion Primitive ◽  
Reaction Forces ◽  
Reference Trajectories

Balancing motions are usually designed using simplified models of the Center of Mass (CoM) and feedback control without accounting for energy efficiency. In order to tackle this shortcoming, we introduce a Motion Primitive switching methodology where samples of optimal motions (Motion Primitives) are chosen online based on a Euclidean distance metric. The chosen sample is used to provide reference trajectories, torques and ground reaction forces to be tracked. In order to satisfy all of the modeling assumptions while tracking the reference values, a Quadratic Program (QP) is solved online where the dynamics of the robot, friction, Center of Pressure and torque bounds are treated as constraints. Convergence to the desired trajectories is dictated by a Control Lyapunov Function constraint which is introduced in the QP. The methodology is evaluated on a four-link simulated robot where we show that switching between Motion Primitives provides energy efficient balancing motions for different disturbance situations. At the same time the methodology provides more efficient motions for different disturbance forces when compared to a nonswitching approach, where a Motion Primitive is chosen only once at the beginning.

The Effects of Uni- and Bilateral Fatigue on Postural and Power Tasks

2013 ◽  
Vol 29 (1) ◽  
pp. 44-48 ◽  
Author(s):  
Paulo H. Marchetti ◽  
Maria I.V. Orselli ◽  
Marcos Duarte
Keyword(s):  
Lower Limb ◽  
Healthy Subjects ◽  
Postural Sway ◽  
Center Of Pressure ◽  
Lower Limbs ◽  
Quiet Standing ◽  
Ground Reaction Forces ◽  
Before And After ◽  
Reaction Forces ◽  
The Mean

The aim of this study was to investigate the effects of unilateral and bilateral fatigue on both postural and power bipedal tasks. Ten healthy subjects performed two tasks: bipedal quiet standing and a maximal bipedal counter-movement jumping before and after unilateral (with either the dominant or nondominant lower limb) and bilateral (with both lower limbs) fatigue. We employed two force plates (one under each lower limb) to measure the ground reaction forces and center of pressure produced by subjects during the tasks. To quantify the postural sway during quiet standing, we calculated the resultant center of pressure (COP) speed and COP area of sway, as well as the mean weight distribution between lower limbs. To quantify the performance during the countermovement jumping, we calculated the jump height and the peak force of each lower limb. We observed that both unilateral and bilateral fatigue affected the performance of maximal voluntary jumping and standing tasks and that the effects of unilateral and bilateral fatigue were stronger in the dominant limb than in the nondominant limb during bipedal tasks. We conclude that unilateral neuromuscular fatigue affects both postural and power tasks negatively.

Sign in / Sign up

Export Citation Format

Share Document