scholarly journals Estimation of Lower Limb Kinematics during Squat Task in Different Loading Using sEMG Activity and Deep Recurrent Neural Networks

Sensors ◽  
2021 ◽  
Vol 21 (23) ◽  
pp. 7773
Author(s):  
Alireza Rezaie Zangene ◽  
Ali Abbasi ◽  
Kianoush Nazarpour
Keyword(s):  
Neural Networks ◽  
Lower Limb ◽  
Short Term Memory ◽  
Ankle Joints ◽  
Limb Kinematics ◽  
Lstm Network ◽  
Fully Connected ◽  
Lower Limb Kinematics ◽  
Semg Activity ◽  
Semg Signals

The aim of the present study was to predict the kinematics of the knee and the ankle joints during a squat training task of different intensities. Lower limb surface electromyographic (sEMG) signals and the 3-D kinematics of lower extremity joints were recorded from 19 body builders during squat training at four loading conditions. A long-short term memory (LSTM) was used to estimate the kinematics of the knee and the ankle joints. The accuracy, in terms root-mean-square error (RMSE) metric, of the LSTM network for the knee and ankle joints were 6.774 ± 1.197 and 6.961 ± 1.200, respectively. The LSTM network with inputs processed by cross-correlation (CC) method showed 3.8% and 4.7% better performance in the knee and ankle joints, respectively, compared to when the CC method was not used. Our results showed that in the prediction, regardless of the intensity of movement and inter-subject variability, an off-the-shelf LSTM decoder outperforms conventional fully connected neural networks.

scholarly journals Prediction of gait trajectories based on the Long Short Term Memory neural networks

PLoS ONE ◽  
2021 ◽  
Vol 16 (8) ◽  
pp. e0255597
Author(s):  
Abdelrahman Zaroug ◽  
Alessandro Garofolini ◽  
Daniel T. H. Lai ◽  
Kurt Mudie ◽  
Rezaul Begg
Keyword(s):  
Lower Limb ◽  
Short Term Memory ◽  
Series Data ◽  
Short Term ◽  
Term Memory ◽  
Wide Range ◽  
Limb Kinematics ◽  
Long Short Term Memory ◽  
Balance Loss ◽  
Lower Limb Kinematics

The forecasting of lower limb trajectories can improve the operation of assistive devices and minimise the risk of tripping and balance loss. The aim of this work was to examine four Long Short Term Memory (LSTM) neural network architectures (Vanilla, Stacked, Bidirectional and Autoencoders) in predicting the future trajectories of lower limb kinematics, i.e. Angular Velocity (AV) and Linear Acceleration (LA). Kinematics data of foot, shank and thigh (LA and AV) were collected from 13 male and 3 female participants (28 ± 4 years old, 1.72 ± 0.07 m in height, 66 ± 10 kg in mass) who walked for 10 minutes at preferred walking speed (4.34 ± 0.43 km.h-1) and at an imposed speed (5km.h-1, 15.4% ± 7.6% faster) on a 0% gradient treadmill. The sliding window technique was adopted for training and testing the LSTM models with total kinematics time-series data of 10,500 strides. Results based on leave-one-out cross validation, suggested that the LSTM autoencoders is the top predictor of the lower limb kinematics trajectories (i.e. up to 0.1s). The normalised mean squared error was evaluated on trajectory predictions at each time-step and it obtained 2.82–5.31% for the LSTM autoencoders. The ability to predict future lower limb motions may have a wide range of applications including the design and control of bionics allowing improved human-machine interface and mitigating the risk of falls and balance loss.

scholarly journals Sarcasm Detection of Sentiments in Telugu Language

2020 ◽  
Vol 10 (1) ◽  
pp. 401-406
Keyword(s):  
Neural Networks ◽  
Short Term Memory ◽  
Dense Layer ◽  
Indian Languages ◽  
Proposed Model ◽  
Popular Language ◽  
Lstm Network ◽  
Fully Connected ◽  
Deep Learning Model ◽  
News Headlines

Sarcasm is usually used by people to either tease/irritate others or simply for comic purposes. The presence of sarcasm becomes certain as it is difficult to be identified by basic sentiment analysis method. Sarcasm detection is addressed with various rule-based methods, statistical approaches, and classifiers in machine learning , most of these are introduced to identify sarcasm in text written in English as it is a popular language on the internet. Although the groundwork done on sarcasm detection on various Indian languages like Telugu is limited. Hence, this paper presents a Deep learning model based on neural networks to detect sarcasm in Telugu news headlines taken from various websites . The proposed model comprises of Convolutional Neural Networks(CNN) and next a Long short-term memory(LSTM) Network which is a modified version of Recurrent neural networks (RNN) and lastly a fully connected dense layer is added to classify the sentiments into sarcastic and non-sarcastic. A pre-trained word embeddings GloVe are used in the model

Analysis of the Relationships between Balance Ability and Walking in Terms of Muscle Activities and Lower Limb Kinematics and Kinetics

Biomechanics ◽  
2021 ◽  
Vol 1 (2) ◽  
pp. 190-201
Author(s):  
Pathmanathan Cinthuja ◽  
Graham Arnold ◽  
Rami J. Abboud ◽  
Weijie Wang
Keyword(s):  
Regression Analysis ◽  
Lower Limb ◽  
Linear Regression Analysis ◽  
Multivariate Linear Regression Analysis ◽  
Vastus Medialis ◽  
Balance Test ◽  
Balance Ability ◽  
Limb Kinematics ◽  
Lower Limb Kinematics ◽  
Kinematics And Kinetics

There is a lack of evidence about the ways in which balance ability influences the kinematic and kinetic parameters and muscle activities during gait among healthy individuals. The hypothesis is that balance ability would be associated with the lower limb kinematics, kinetics and muscle activities during gait. Twenty-nine healthy volunteers (Age 32.8 ± 9.1; 18 males and 11 females) performed a Star Excursion Balance test to measure their dynamic balance and walked for at least three trials in order to obtain a good quality of data. A Vicon® 3D motion capture system and AMTI® force plates were used for the collection of the movement data. The selected muscle activities were recorded using Delsys® Electromyography (EMG). The EMG activities were compared using the maximum values and root mean squared (RMS) values within the participants. The joint angle, moment, force and power were calculated using a Vicon Plug-in-Gait model. Descriptive analysis, correlation analysis and multivariate linear regression analysis were performed using SPSS version 23. In the muscle activities, positive linear correlations were found between the walking and balance test in all muscles, e.g., in the multifidus (RMS) (r = 0.800 p < 0.0001), vastus lateralis (RMS) (r = 0.639, p < 0.0001) and tibialis anterior (RMS) (r = 0.539, p < 0.0001). The regression analysis models showed that there was a strong association between balance ability (i.e., reaching distance) and the lower limb muscle activities (i.e., vastus medialis–RMS) (R = 0.885, p < 0.0001), and also between balance ability (i.e., reaching distance) and the lower limb kinematics and kinetics during gait (R = 0.906, p < 0.0001). In conclusion, the results showed that vastus medialis (RMS) muscle activity mainly contributes to balance ability, and that balance ability influences the lower limb kinetics and kinematics during gait.

Rate of loading, but not lower limb kinematics or muscle activity, is moderated by limb and aerial variation when surfers land aerials

2021 ◽  
pp. 1-9
Author(s):  
James R. Forsyth ◽  
Christopher J. Richards ◽  
Ming-Chang Tsai ◽  
John W. Whitting ◽  
Diane L. Riddiford-Harland ◽  
...  
Keyword(s):  
Lower Limb ◽  
Muscle Activity ◽  
Limb Kinematics ◽  
Lower Limb Kinematics ◽  
Rate Of Loading

Changes in drive phase lower limb kinematics during a 60min cycling time trial

2012 ◽  
Vol 15 (2) ◽  
pp. 169-174 ◽  
Author(s):  
Mark G.L. Sayers ◽  
Amanda L. Tweddle ◽  
Joshua Every ◽  
Aaron Wiegand
Keyword(s):  
Lower Limb ◽  
Time Trial ◽  
Cycling Time Trial ◽  
Limb Kinematics ◽  
Lower Limb Kinematics ◽  
Cycling Time

scholarly journals Effects of gait retraining with focus on impact versus gait retraining with focus on cadence on pain, function and lower limb kinematics in runners with patellofemoral pain: Protocol of a randomized, blinded, parallel group trial with 6-month follow-up

PLoS ONE ◽  
2021 ◽  
Vol 16 (5) ◽  
pp. e0250965
Author(s):  
José Roberto de Souza Júnior ◽  
Pedro Henrique Reis Rabelo ◽  
Thiago Vilela Lemos ◽  
Jean-Francois Esculier ◽  
João Pedro da Silva Carto ◽  
...  
Keyword(s):  
Lower Limb ◽  
Intervention Group ◽  
Patellofemoral Pain ◽  
Control Group ◽  
Gait Retraining ◽  
Positive Effects ◽  
Clinical Applicability ◽  
Limb Kinematics ◽  
Lower Limb Kinematics

Patellofemoral pain (PFP) is one of the most prevalent injuries in runners. Unfortunately, a substantial part of injured athletes do not recover fully from PFP in the long-term. Although previous studies have shown positive effects of gait retraining in this condition, retraining protocols often lack clinical applicability because they are time-consuming, costly for patients and require a treadmill. The primary objective of this study will be to compare the effects of two different two-week partially supervised gait retraining programs, with a control intervention; on pain, function and lower limb kinematics of runners with PFP. It will be a single-blind randomized clinical trial with six-month follow-up. The study will be composed of three groups: a group focusing on impact (group A), a group focusing on cadence (group B), and a control group that will not perform any intervention (group C). The primary outcome measure will be pain assessed using the Visual Analog Pain scale during running. Secondary outcomes will include pain during daily activities (usual), symptoms assessed using the Patellofemoral Disorders Scale and lower limb running kinematics in the frontal (contralateral pelvic drop; hip adduction) and sagittal planes (foot inclination; tibia inclination; ankle dorsiflexion; knee flexion) assessed using the MyoResearch 3.14—MyoVideo (Noraxon U.S.A. Inc.). The study outcomes will be evaluated before (t0), immediately after (t2), and six months (t24) after starting the protocol. Our hypothesis is that both partially supervised gait retraining programs will be more effective in reducing pain, improving symptoms, and modifying lower limb kinematics during running compared with the control group, and that the positive effects from these programs will persist for six months. Also, we believe that one gait retraining group will not be superior to the other. Results from this study will help improve care in runners with PFP, while maximizing clinical applicability as well as time and cost-effectiveness.

Sign in / Sign up

Export Citation Format

Share Document