Dataset Information

Upper Limb End-Effector Force Estimation During Multi-Muscle Isometric Contraction Tasks Using HD-sEMG and Deep Belief Network.

ABSTRACT: In this study, research was carried out on the end-effector force estimation of two representative multi-muscle contraction tasks: elbow flexion and palm-pressing. The aim was to ascertain whether an individual muscle or a combination of muscles is more suitable for the end-effector force estimation. High-density surface electromyography (HD-sEMG) signals were collected from four primary muscle areas of the upper arm and forearm: the biceps brachii (BB), brachialis (BR), triceps brachii (TB), brachioradialis (BRD), and extensor digitorum communis (EDC). The wrist pulling and palm-pressing forces were measured in elbow flexion and palm-pressing tasks, respectively. The deep belief network (DBN) was adopted to establish the relation between HD-sEMG and the measured force. The representative signals of the four primary areas, which were considered as the input signal of the force estimation model, were extracted by HD-sEMG using the principle component analysis (PCA) algorithm, and fed separately or together into the DBN. An index termed mean impact value (MIV) was proposed to describe the priority of different muscle groups for estimating the end-effector force. The experimental results demonstrated that, in multi-muscle isometric contraction tasks, the dominant muscles with the highest activation degree could track variations in the end-effector force more effectively, and are more suitable than a combination of muscles. The main contributions of this research are as follows: (1) To fuse the activation information from different muscles effectively, DBN was adopted to establish the relationship between HD-sEMG and the generated force, and achieved highly accurate force estimation. (2) Based on the well-trained DBN force estimation model, an index termed MIV was presented to evaluate the priority of muscles for estimating the generated force.

SUBMITTER: Hu R

PROVIDER: S-EPMC7221063 | biostudies-literature | 2020

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Upper Limb End-Effector Force Estimation During Multi-Muscle Isometric Contraction Tasks Using HD-sEMG and Deep Belief Network.

Hu Ruochen R Chen Xiang X Cao Shuai S Zhang Xu X Chen Xun X

Frontiers in neuroscience 20200507

In this study, research was carried out on the end-effector force estimation of two representative multi-muscle contraction tasks: elbow flexion and palm-pressing. The aim was to ascertain whether an individual muscle or a combination of muscles is more suitable for the end-effector force estimation. High-density surface electromyography (HD-sEMG) signals were collected from four primary muscle areas of the upper arm and forearm: the biceps brachii (BB), brachialis (BR), triceps brachii (TB), br ...[more]

PMID: 32457574

Similar Datasets

Project description:BackgroundDexterous hand function is crucial for completing activities of daily living (ADLs), which typically require precise hand-object interactions. Kinematic analyses of hand trajectory, hand velocity, and grip aperture provide valuable mechanistic insights into task performance, but there is a need for standardized tasks representative of ADLs that are amenable to motion capture and show consistent performance in non-disabled individuals. Our objective was to develop two standardized functional upper limb tasks and to quantitatively characterize the kinematics of normative hand movement.MethodsTwenty non-disabled participants were recruited to perform two tasks: the Pasta Box Task and Cup Transfer Task. A 12-camera motion capture system was used to collect kinematic data from which hand movement and grip aperture measures were calculated. Measures reported for reach-grasp and transport-release segments were hand distance travelled, hand trajectory variability, movement time, peak and percent-to-peak hand velocity, number of movement units, peak and percent-to-peak grip aperture, and percent-to-peak hand deceleration. A between-session repeatability analysis was conducted on 10 participants.ResultsMovement times were longer for transport-release compared to reach-grasp for every movement. Hand and grip aperture measures had low variability, with 55 out of 63 measures showing good repeatability (ICC > 0.75). Cross-body movements in the Pasta Box Task had longer movement times and reduced percent-to-peak hand velocity values. The Cup Transfer Task showed decoupling of peak grip aperture and peak hand deceleration for all movements. Movements requiring the clearing of an obstacle while transporting an object displayed a double velocity peak and typically a longer deceleration phase.DiscussionNormative hand kinematics for two standardized functional tasks challenging various aspects of hand-object interactions important for ADLs showed excellent repeatability. The consistency in normative task performance across a variety of task demands shows promise as a potential outcome assessment for populations with upper limb impairment.

Project description:Background: Deficits in interjoint coordination, such as the inability to move out of synergy, are frequent symptoms in stroke subjects with upper limb impairments that hinder them from regaining normal motor function. Kinematic measurements allow a fine-grained assessment of movement pathologies, thereby complementing clinical scales, like the Fugl-Meyer Motor Assessment of the Upper Extremity (FMMA-UE). The study goal was to investigate the effects of the performed task, the tested arm, the dominant affected hand, upper limb function, and age on spatiotemporal parameters of the elbow, shoulder, and trunk. The construct validity of the metrics was examined by relating them with each other, the FMMA-UE, and its arm section. Methods: This is a cross-sectional observational study including chronic stroke patients with mild to moderate upper limb motor impairment. Kinematic measurements were taken using a wearable sensor suit while performing four movements with both upper limbs: (1) isolated shoulder flexion, (2) pointing, (3) reach-to-grasp a glass, and (4) key insertion. The kinematic parameters included the joint ranges of shoulder abduction/adduction, shoulder flexion/extension, and elbow flexion/extension; trunk displacement; shoulder-elbow correlation coefficient; median slope; and curve efficiency. The effects of the task and tested arm on the metrics were investigated using a mixed-model analysis. The validity of metrics compared to clinically measured interjoint coordination (FMMA-UE) was done by correlation analysis. Results: Twenty-six subjects were included in the analysis. The movement task and tested arm showed significant effects (p < 0.05) on all kinematic parameters. Hand dominance resulted in significant effects on shoulder flexion/extension and curve efficiency. The level of upper limb function showed influences on curve efficiency and the factor age on median slope. Relations with the FMMA-UE revealed the strongest and significant correlation for curve efficiency (r = 0.75), followed by shoulder flexion/extension (r = 0.68), elbow flexion/extension (r = 0.53), and shoulder abduction/adduction (r = 0.49). Curve efficiency additionally correlated significantly with the arm subsection, focusing on synergistic control (r = 0.59). Conclusion: The kinematic parameters of the upper limb after stroke were influenced largely by the task. These results underpin the necessity to assess different relevant functional movements close to real-world conditions rather than relying solely on clinical measures. Study Registration: clinicaltrials.gov, identifier NCT03135093 and BASEC-ID 2016-02075.

Project description:Background: Studies aiming to objectively quantify movement disorders during upper limb tasks using wearable sensors have recently increased, but there is a wide variety in described measurement and analyzing methods, hampering standardization of methods in research and clinics. Therefore, the primary objective of this review was to provide an overview of sensor set-up and type, included tasks, sensor features and methods used to quantify movement disorders during upper limb tasks in multiple pathological populations. The secondary objective was to identify the most sensitive sensor features for the detection and quantification of movement disorders on the one hand and to describe the clinical application of the proposed methods on the other hand. Methods: A literature search using Scopus, Web of Science, and PubMed was performed. Articles needed to meet following criteria: 1) participants were adults/children with a neurological disease, 2) (at least) one sensor was placed on the upper limb for evaluation of movement disorders during upper limb tasks, 3) comparisons between: groups with/without movement disorders, sensor features before/after intervention, or sensor features with a clinical scale for assessment of the movement disorder. 4) Outcome measures included sensor features from acceleration/angular velocity signals. Results: A total of 101 articles were included, of which 56 researched Parkinson's Disease. Wrist(s), hand(s) and index finger(s) were the most popular sensor locations. Most frequent tasks were: finger tapping, wrist pro/supination, keeping the arms extended in front of the body and finger-to-nose. Most frequently calculated sensor features were mean, standard deviation, root-mean-square, ranges, skewness, kurtosis/entropy of acceleration and/or angular velocity, in combination with dominant frequencies/power of acceleration signals. Examples of clinical applications were automatization of a clinical scale or discrimination between a patient/control group or different patient groups. Conclusion: Current overview can support clinicians and researchers in selecting the most sensitive pathology-dependent sensor features and methodologies for detection and quantification of upper limb movement disorders and objective evaluations of treatment effects. Insights from Parkinson's Disease studies can accelerate the development of wearable sensors protocols in the remaining pathologies, provided that there is sufficient attention for the standardisation of protocols, tasks, feasibility and data analysis methods.

Project description:Dyskinetic cerebral palsy (DCP) is characterised by involuntary movements, and the movement patterns of children with DCP have not been extensively studied during upper limb tasks. The aim of this study is to evaluate psychometric properties of upper limb kinematics in participants with DCP and typically developing (TD) participants. In current repeatability and validity study, forty individuals with typical development (n = 20) and DCP (n = 20) performed a reach forward/sideways and a reach and grasp task during motion analysis on two occasions. Joint angles at point of task achievement (PTA) and spatio-temporal parameters were evaluated within-and between-sessions using intra-class correlation coefficients (ICC) and standard error of measurement (SEM). Independent t-tests/Mann-Whitney-U tests were used to compare parameters between groups. Within-session ICC values ranged from 0.45 to 1.0 for all parameters for both groups. Within-session SEM values ranged from 1.1° to 11.7° for TD participants and from 1.9° to 13.0° for participants with DCP. Eight within-session repetitions resulted in the smallest change in ICC and SEM values for both groups. Within-session variability was higher for participants with DCP in comparison with the TD group for the majority of the joint angles and spatio-temporal parameters. Intrinsic variability over time was small for all angles and spatio-temporal parameters, whereas extrinsic variability was higher for elbow and scapula angles. Between-group differences revealed lower shoulder adduction and higher elbow flexion, pronation and wrist flexion, as well as higher trajectory deviation and a lower maximal velocity for participants with DCP. This is the first study to assess the psychometric properties of upper limb kinematics in children and adolescents with DCP, showing that children with DCP show higher variability during task execution, requiring a minimum of eight repetitions. However, their variable movement pattern can be reliably captured within-and between-sessions, confirming the potential of three-dimensional motion analysis for assessment of rehabilitation interventions in DCP.

Dataset Information

Upper Limb End-Effector Force Estimation During Multi-Muscle Isometric Contraction Tasks Using HD-sEMG and Deep Belief Network.

Publications

Upper Limb End-Effector Force Estimation During Multi-Muscle Isometric Contraction Tasks Using HD-sEMG and Deep Belief Network.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets