scholarly journals Joint angle estimation with wavelet neural networks

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Saaveethya Sivakumar ◽  
Alpha Agape Gopalai ◽  
King Hann Lim ◽  
Darwin Gouwanda ◽  
Sunita Chauhan

AbstractThis paper presents a wavelet neural network (WNN) based method to reduce reliance on wearable kinematic sensors in gait analysis. Wearable kinematic sensors hinder real-time outdoor gait monitoring applications due to drawbacks caused by multiple sensor placements and sensor offset errors. The proposed WNN method uses vertical Ground Reaction Forces (vGRFs) measured from foot kinetic sensors as inputs to estimate ankle, knee, and hip joint angles. Salient vGRF inputs are extracted from primary gait event intervals. These selected gait inputs facilitate future integration with smart insoles for real-time outdoor gait studies. The proposed concept potentially reduces the number of body-mounted kinematics sensors used in gait analysis applications, hence leading to a simplified sensor placement and control circuitry without deteriorating the overall performance.

2012 ◽  
Vol 25 (01) ◽  
pp. 11-21 ◽  
Author(s):  
J. Böddeker ◽  
S. Drüen ◽  
A. Meyer-Lindenberg ◽  
M. Fehr ◽  
I. Nolte ◽  
...  

SummaryObjectives: To compare the improvement in degree of lameness following surgical repair of cranial cruciate ligament rupture in dogs using computer-assisted gait analysis.Methods: Two groups of 14 dogs were used. One group was treated by a capsular-fascial imbrication method, and the other group by tibial plateau levelling osteotomy (TPLO). All dogs underwent gait analysis prior to surgery, as well as at four days, four weeks, and four months after surgery. Symmetry indices of vertical ground reaction forces as well as vertical ground reaction forces in % body weight, joint angles and certain gait cycle parameters were evaluated.Results: Four months after surgery, the degree of lameness expressed as symmetry index for peak vertical force for the TPLO group (5.83%) was not significantly different to the capsular-fascial imbrication group (19.05%). Within the TPLO group, there was a significantly increased ability to extend the stifle joint four months after surgery. The stifle motion pattern of the capsular-fascial imbrication group as well as the range-of-motion in both groups showed very little change at the time of the last gait analysis. The complication rate was greater in the TPLO group than in the capsular-fascial group.Clinical significance: In conclusion the results suggest that the TPLO method leads to a faster recovery and improved limb function in comparison to the capsular-fascial imbrication method four months after surgery. Further analyses are needed to determine if the TPLO method is superior concerning long-term joint stability.Online supplementary material: A video of the three-dimensional kinematic model is available online at: http://www.vcot-online.com


2012 ◽  
Vol 25 (05) ◽  
pp. 375-384 ◽  
Author(s):  
S. Drüen ◽  
J. Böddeker ◽  
A. Meyer-Lindenberg ◽  
M. Fehr ◽  
I. Nolte ◽  
...  

SummaryTo date is it unclear whether cementless total hip replacement (THR) in dogs is of clinical advantage in comparison to cemented THR with regard to lameness improvement. Thus the aim of this study was to compare objectively the development of the gait pattern after cemented and cementless THR in dogs. For this purpose, 18 adult dogs with hip dysplasia underwent computer-based gait analysis on an instrumented treadmill prior to unilateral THR and then again ten days, four weeks and four months after surgery. Analysed kinetic parameters were symmetry indices (SI) of vertical ground reaction forces (GRF), which included peak vertical forces (PFz), mean vertical forces (MFz), vertical impulse (IFz), and vertical ground reaction forces of the arthroplasty limbs only. Analysed kinematic parameters were range-of-motion and the flexion and extension angles of hip, stifle and hock joints. The symmetry indice for PVF, MFz and IFz decreased to a value less than six in both THR groups four months after surgery, which is defined as not lame. Improvement in lameness of the arthroplasty limbs during the examination period of four months was not significantly different between the cemented and cementless groups. The results suggest that within a short-term observation period of four months after surgery, neither cementless nor cemented THR have a greater advantage with regard to lameness improvement. Additional studies with larger pools of subjects and longer time periods for follow-up examinations are necessary to verify these findings.


1981 ◽  
Vol 91 (1) ◽  
pp. 73-86 ◽  
Author(s):  
F. E. Zajac ◽  
M. R. Zomlefer ◽  
W. S. Levine

Cats were trained to jump from a force platform to their maximum achievable heights. Vertical ground reaction forces developed by individual hindlimbs showed that the propulsion phase consists of two epochs. During the initial “preparatory phase' the cat can traverse many different paths. Irrespective of the path traversed, however, the cat always attains the same position, velocity and momentum at the end of this phase. Starting from this dynamic state the cat during the subsequent “launching phase' (about 150 ms long) generates significant propulsion as its hindlimbs develop force with identical, stereotypic profiles. Cinematographic data, electromyographic data, and computed torques about the hip, knee and ankle joints indicate that during the jump proximal extensor musculature is activated before distal musculature. During terminal experiments when the hindlimb was set at positions corresponding to those in the jump, isometric torques produced by tetanic stimulation of groups of extensor and flexor muscles were compared with computed torques developed by the same cat during previous jumps. These comparisons suggest that extensor muscles of the hindlimb are fully activated during the maximal vertical jump.


2018 ◽  
Vol 53 (2) ◽  
pp. 144-159 ◽  
Author(s):  
Adam S. Lepley ◽  
Christopher M. Kuenze

Objective:  To evaluate the current evidence concerning kinematic and kinetic strategies adopted during dynamic landing tasks by patients with anterior cruciate ligament reconstruction (ACLR). Data Sources:  PubMed, Web of Science. Study Selection:  Original research articles that evaluated kinematics or kinetics (or both) during a landing task in those with a history of ACLR were included. Data Extraction:  Methodologic quality was assessed using the modified Downs and Black checklist. Means and standard deviations for knee or hip (or both) kinematics and kinetics were used to calculate Cohen d effect sizes and corresponding 95% confidence intervals between the injured limb of ACLR participants and contralateral or healthy matched limbs. Data were further stratified by landing tasks, either double- or single-limb landing. A random-effects–model meta-analysis was used to calculate pooled effect sizes and 95% confidence intervals. Data Synthesis:  The involved limbs of ACLR patients demonstrated clinically and significantly lower knee-extension moments during double-legged landing compared with healthy contralateral limbs and healthy control limbs (Cohen d range = −0.81 to −1.23) and decreased vertical ground reaction forces when compared with healthy controls, regardless of task (Cohen d range = −0.39 to −1.75). Conclusions:  During single- and double-legged landing tasks, individuals with ACLR demonstrated meaningful reductions in injured-limb knee-extension moments and vertical ground reaction forces. These findings indicate potential unloading of the injured limb after ACLR, which may have significant implications for secondary ACL injury and long-term joint health.


1995 ◽  
Vol 3 (2) ◽  
pp. 86
Author(s):  
H.John Yack ◽  
Carole Tucker ◽  
Scott C White Heather Collins

2010 ◽  
Vol 71 (12) ◽  
pp. 1413-1416 ◽  
Author(s):  
David Levine ◽  
Denis J. Marcellin-Little ◽  
Darryl L. Millis ◽  
Verena Tragauer ◽  
Jason A. Osborne

Sign in / Sign up

Export Citation Format

Share Document