Evaluation of gait transitional phases using neuromechanical outputs and somatosensory inputs in an overground walk

Mahmood, Imran; Martinez-Hernandez, Uriel; Dehghani-Sanij, Abbas A.

doi:10.1016/j.humov.2019.102558

Cited by 14 publications

(16 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In our abnormal gait database 2 , 18 healthy volunteers (16 male and 2 female) were recruited and instructed to walk normally and imitate four pathological gait patterns (i.e., toe-in, toe-out, supination, and pronation), following the settings of previous simulation based works [58], [59], [60]. The recruited subjects were with no lower-limb injury history and did not undergo any joint instability during the course of the past six months.…”

Section: A Data Collectionmentioning

confidence: 99%

Cross-Subject and Cross-Modal Transfer for Generalized Abnormal Gait Pattern Recognition

Guo

Deligianni

et al. 2021

IEEE Trans. Neural Netw. Learning Syst.

View full text Add to dashboard Cite

For abnormal gait recognition, pattern-specific features indicating abnormalities are interleaved with the subject-specific differences representing biometric traits. Deep representations are therefore prone to overfitting and the models derived cannot generalize well to new subjects. Furthermore, there is limited availability of abnormal gait data obtained from precise Motion Capture (Mocap) systems because of regulatory issues and slow adaptation of new technologies in health care. On the other hand, data captured from markerless vision sensors or wearable sensors can be obtained in home environments but noises from such devices may prevent effective extraction of relevant features. To address these challenges, we propose a cascade of deep architectures that can encode cross-modal and cross-subject transfer for abnormal gait recognition. Cross-modal transfer maps noisy data obtained from RGBD and wearable sensors to accurate four-dimensional (4D) representations of the lower limb and joints obtained from the Mocap system. Subsequently, cross-subject transfer allows to disentangle subject-specific from abnormal pattern-specific gait features based on a multi-encoder autoencoder architecture. To validate the proposed methodology, we obtained multi-modal gait data based on a multi-camera motion capture system along with synchronized recordings of Electromyography (EMG) data and 4D skeleton data extracted from a single RGBD camera. Classification accuracy was improved significantly in both Mocap and noisy modalities.

show abstract

Section: A Data Collectionmentioning

confidence: 99%

Cross-Subject and Cross-Modal Transfer for Generalized Abnormal Gait Pattern Recognition

Guo

Deligianni

et al. 2021

IEEE Trans. Neural Netw. Learning Syst.

View full text Add to dashboard Cite

show abstract

“…Prior to recording the experiments, each participant was asked to perform a few trials to get familiar with his preferred normal pace and to ensure this pace in all walking conditions. The preferred walking speed trials were recorded following previously reported similar studies [35][36][37]. A total of five trials were recorded per subject per walking condition.…”

Section: Experimental Protocol and Setupmentioning

confidence: 99%

“…2. The RMS of CoM-oscillations was computed following prior similar studies [37,39,40] where higher order signals (derivative) were reported to be rectified in-order to analyse or characterise important features in the frequency domain.…”

Section: Data Processingmentioning

confidence: 99%

A model identification approach to quantify impact of whole-body vertical vibrations on limb compliant dynamics and walking stability

Mahmood

Martinez-Hernandez

Dehghani-Sanij

2020

Medical Engineering & Physics

Self Cite

View full text Add to dashboard Cite

show abstract

“…Walking is essential in daily life, and its dynamic stability is essential to perform everyday activities independently [4,5]. People with a history of LAS might thus experience imbalance, increased lateral ankle pressures during the gait cycle stance phase, as well as repeated occurrence of ankle sprains [6] Moreover, it has been suggested that a large number of ankle sprains appear as a result of maximum supination torque in the subtalar joint, often due to the extent and the position of the vertical Ground Reaction Force (vGRF) at the onset of the contact time of the foot [7].…”

Section: Introductionmentioning

confidence: 99%

“…The results of studies in this field have similarly demonstrated that patients with LAS reluctantly put their weight on the front third [5]. Increased changes in foot and ankle movements may further multiply the risks of recurrent ankle sprains, even if there is no mechanical damage to the ligament.…”

Section: Introductionmentioning

confidence: 99%

Comparison Between Spatiotemporal Parameters and Vertical Ground Reaction Force in Ankle Sprain Coper and Healthy Athletes: A Cross Sectional Study

Raeisi

2021

PTJ

View full text Add to dashboard Cite

Purpose: It is essential to maintain dynamic stability during walking to perform daily tasks independently. The present study aimed at comparing the spatiotemporal parameters and the values of the vertical Ground Reaction Force (vGRF) as well as determining the time to reach them in ankle-sprain coper and healthy athletes during the stance phase of gait. Methods: A total of 28 female university athletes were recruited in this cross-sectional study and assigned into two groups: ankle-sprain coper (n=14) and healthy control (n=14). The gait cycle analysis was then performed on a 10-m path, and the information related to the stance phase was recorded by a foot scanning device. The spatiotemporal parameters (gait line and contact time) and the values of the vGRF along with the time to reach them were subsequently obtained from each test. The repeated measures Analysis of Variance (ANOVA) was additionally used to analyze the data (P≤0.05). Results: The study results revealed no differences between the injured and the healthy feet in the ankle-sprain coper group in any of the variables (P>0.05). As well, the spatiotemporal gait cycle parameters between the ankle-sprain coper group and the healthy controls were not significantly different (P>0.05). However, significant differences were observed between the ankle-sprain coper and healthy controls in terms of the variables of the vGRF in the mid-stance (F=5.25, P=0.03) and the time to reach the second peak of the vGRF (F=9.13, P=0.006). Conclusion: The spatiotemporal gait parameters were not significantly different between the ankle-sprain coper and the control groups, but the vGRF in the ankle-sprain coper was greater than that in the control group. With regard to the correlation between the reduction in the vGRF and the secondary injury, it is recommended to pay much attention to this point in rehabilitation programs following the first injury in female athletes.

show abstract

Evaluation of gait transitional phases using neuromechanical outputs and somatosensory inputs in an overground walk

Cited by 14 publications

References 43 publications

Cross-Subject and Cross-Modal Transfer for Generalized Abnormal Gait Pattern Recognition

Cross-Subject and Cross-Modal Transfer for Generalized Abnormal Gait Pattern Recognition

A model identification approach to quantify impact of whole-body vertical vibrations on limb compliant dynamics and walking stability

Comparison Between Spatiotemporal Parameters and Vertical Ground Reaction Force in Ankle Sprain Coper and Healthy Athletes: A Cross Sectional Study

Contact Info

Product

Resources

About