Displaying publications 1 - 20 of 103 in total

Abstract:
Sort:
  1. Different Running Patterns Along the Aerial-Terrestrial Continuum Can Result in Similar Running Economy
    Lussiana T, Gindre C, Hébert-Losier K, Sagawa Y, Gimenez P, Mourot L
    Int J Sports Physiol Perform, 2016 Sep 6.
    PMID: 27617625
    There is no unique or 'ideal' running pattern that is the most economical for all runners. Classifying the global running patterns of individuals into two categories (aerial and terrestrial) using the Volodalen® method could permit a better understanding of the relationship between running economy (RE) and biomechanics. The main purpose was to compare RE between aerial and terrestrial runners.
    Matched MeSH terms: Gait
  2. Effect of simulated sensorimotor noise on kinematic variability and stability of a biped walking model
    Mehdizadeh S, Glazier PS
    Comput Methods Biomech Biomed Engin, 2021 Aug;24(10):1097-1103.
    PMID: 33426927 DOI: 10.1080/10255842.2020.1867852
    Whether higher variability in older adults' walking is an indication of increased instability has been challenged recently. We performed a computer simulation to investigate the effect of sensorimotor noise on the kinematic variability and stability in a biped walking model. Stochastic differential equations of the system with additive Gaussian white noise was constructed and solved. Sensorimotor noise mainly resulted in higher kinematic variability but its influence on gait stability is minimal. This implies that kinematic variability evident in walking gaits of older adults could be the result of internal sensorimotor noise and not an indication of instability.
    Matched MeSH terms: Gait*
  3. Fulltext Automated Gait Analysis Based on a Marker-Free Pose Estimation Model
    Hii CST, Gan KB, Zainal N, Mohamed Ibrahim N, Azmin S, Mat Desa SH, et al.
    Sensors (Basel), 2023 Jul 18;23(14).
    PMID: 37514783 DOI: 10.3390/s23146489
    Gait analysis is an essential tool for detecting biomechanical irregularities, designing personalized rehabilitation plans, and enhancing athletic performance. Currently, gait assessment depends on either visual observation, which lacks consistency between raters and requires clinical expertise, or instrumented evaluation, which is costly, invasive, time-consuming, and requires specialized equipment and trained personnel. Markerless gait analysis using 2D pose estimation techniques has emerged as a potential solution, but it still requires significant computational resources and human involvement, making it challenging to use. This research proposes an automated method for temporal gait analysis that employs the MediaPipe Pose, a low-computational-resource pose estimation model. The study validated this approach against the Vicon motion capture system to evaluate its reliability. The findings reveal that this approach demonstrates good (ICC(2,1) > 0.75) to excellent (ICC(2,1) > 0.90) agreement in all temporal gait parameters except for double support time (right leg switched to left leg) and swing time (right), which only exhibit a moderate (ICC(2,1) > 0.50) agreement. Additionally, this approach produces temporal gait parameters with low mean absolute error. It will be useful in monitoring changes in gait and evaluating the effectiveness of interventions such as rehabilitation or training programs in the community.
    Matched MeSH terms: Gait*
  4. Fulltext Exoskeletal wearable robot on ambulatory function in patients with stroke: a protocol for an international, multicentre, randomised controlled study
    Chang WH, Kim TW, Kim HS, Hanapiah FA, Kim DH, Kim DY
    BMJ Open, 2023 Aug 11;13(8):e065298.
    PMID: 37567748 DOI: 10.1136/bmjopen-2022-065298
    INTRODUCTION: The purpose of this study is to determine the effect of overground gait training using an exoskeletal wearable robot (exoskeleton) on the recovery of ambulatory function in patients with subacute stroke. We also investigate the assistive effects of an exoskeleton on ambulatory function in patients with subacute stroke.

    METHODS AND ANALYSIS: This study is an international, multicentre, randomised controlled study at five institutions with a total of 150 patients with subacute stroke. Participants will be randomised into two groups (75 patients in the robot-assisted gait training (RAGT) group and 75 patients in the control group). The gait training will be performed with a total of 20 sessions (60 min/session); 5 sessions a week for 4 weeks. The RAGT group will receive 30 min of gait training using an exoskeleton (ANGEL LEGS M20, Angel Robotics) and 30 min of conventional gait training, while the control group will receive 60 min conventional gait training. In all the patients, the functional assessments such as ambulation, motor and balance will be evaluated before and after the intervention. Follow-up monitoring will be performed to verify whether the patient can walk without physical assistance for 3 months. The primary outcome is the improvement of the Functional Ambulatory Category after the gait training. The functional assessments will also be evaluated immediately after the last training session in the RAGT group to assess the assistive effects of an exoskeletal wearable robot. This trial will provide evidence on the effects of an exoskeleton to improve and assist ambulatory function in patients with subacute stroke.

    ETHICS AND DISSEMINATION: This protocol has been approved by the Institutional Review Board of each hospital and conforms to the Declaration of Helsinki. The results will be disseminated through publication.

    TRIAL REGISTRATION NUMBER: Protocol was registered at ClinicalTrials.gov (NCT05157347) on 15 December 2021 and CRIS (KCT0006815) on 19 November 2021.

    Matched MeSH terms: Gait; Gait Disorders, Neurologic*
  5. Fulltext Postural Control and Gait Performance in the Diabetic Peripheral Neuropathy: A Systematic Review
    Mustapa A, Justine M, Mohd Mustafah N, Jamil N, Manaf H
    Biomed Res Int, 2016;2016:9305025.
    PMID: 27525281
    Purpose. The aim of this paper is to review the published studies on the characteristics of impairments in the postural control and gait performance in diabetic peripheral neuropathy (DPN). Methods. A review was performed by obtaining publication of all papers reporting on the postural control and gait performance in DPN from Google Scholar, Ovid, SAGE, Springerlink, Science Direct (SD), EBSCO Discovery Service, and Web of Science databases. The keywords used for searching were "postural control," "balance," "gait performance," "diabetes mellitus," and "diabetic peripheral neuropathy." Results. Total of 4,337 studies were hit in the search. 1,524 studies were screened on their titles and citations. Then, 79 studies were screened on their abstract. Only 38 studies were eligible to be selected: 17 studies on postural control and 21 studies on the gait performance. Most previous researches were found to have strong evidence of postural control impairments and noticeable gait deficits in DPN. Deterioration of somatosensory, visual, and vestibular systems with the pathologic condition of diabetes on cognitive impairment causes further instability of postural and gait performance in DPN. Conclusions. Postural instability and gait imbalance in DPN may contribute to high risk of fall incidence, especially in the geriatric population. Thus, further works are crucial to highlight this fact in the hospital based and community adults.
    Matched MeSH terms: Gait
  6. A computational method for reliable gait event detection and abnormality detection for feedback in rehabilitation
    Senanayake C, Senanayake SM
    Comput Methods Biomech Biomed Engin, 2011 Oct;14(10):863-74.
    PMID: 20924859 DOI: 10.1080/10255842.2010.499866
    In this paper, a gait event detection algorithm is presented that uses computer intelligence (fuzzy logic) to identify seven gait phases in walking gait. Two inertial measurement units and four force-sensitive resistors were used to obtain knee angle and foot pressure patterns, respectively. Fuzzy logic is used to address the complexity in distinguishing gait phases based on discrete events. A novel application of the seven-dimensional vector analysis method to estimate the amount of abnormalities detected was also investigated based on the two gait parameters. Experiments were carried out to validate the application of the two proposed algorithms to provide accurate feedback in rehabilitation. The algorithm responses were tested for two cases, normal and abnormal gait. The large amount of data required for reliable gait-phase detection necessitate the utilisation of computer methods to store and manage the data. Therefore, a database management system and an interactive graphical user interface were developed for the utilisation of the overall system in a clinical environment.
    Matched MeSH terms: Gait*
  7. Investigation of EMG parameter for transtibial prosthetic user with flexion and extension of the knee and normal walking gait: A preliminary study
    Sobh KNM, Abd Razak NA, Abu Osman NA
    Proc Inst Mech Eng H, 2021 Apr;235(4):419-427.
    PMID: 33517847 DOI: 10.1177/0954411920985753
    Electromyography signal has been used widely as input for prosthetic's leg movements. C-Leg, for example, is among the prosthetics devices that use electromyography as the main input. The main challenge facing the industrial party is the position of the electromyography sensor as it is fixed inside the socket. The study aims to investigate the best positional parameter of electromyography for transtibial prosthetic users for the device to be effective in multiple movement activities and compare with normal human muscle's activities. DELSYS Trigno wireless electromyography instrument was used in this study to achieve this aim. Ten non-amputee subjects and two transtibial amputees were involved in this study. The surface electromyography signals were recorded from two anterior and posterior below the knee muscles and above the knee muscles, respectively: tibial anterior and gastrocnemius lateral head as well as rectus femoris and biceps femoris during two activities (flexion and extension of knee joint and gait cycle for normal walking). The result during flexion and extension activities for gastrocnemius lateral head and biceps femoris muscles was found to be more useful for the control subjects, while the tibial anterior and also gastrocnemius lateral head are more active for amputee subjects. Also, during normal walking activity for biceps femoris and gastrocnemius lateral head, it was more useful for the control subjects, while for transtibial amputee subject-1, the rectus femoris was the highest signal of the average normal walking activity (0.0001 V) compared to biceps femoris (0.00007 V), as for transtibial amputee subject-2, the biceps femoris was the highest signals of the average normal walking activity (0.0001 V) compared to rectus femoris (0.00004 V). So, it is difficult to rely entirely on the static positioning of the electromyography sensor within the socket as there is a possibility of the sensor to contact with inactive muscle, which will be a gap in the control, leading to a decrease in the functional efficiency of the powered prostheses.
    Matched MeSH terms: Gait*
  8. Fulltext Muscles Affecting Minimum Toe Clearance
    Perera CK, Gopalai AA, Ahmad SA, Gouwanda D
    Front Public Health, 2021;9:612064.
    PMID: 34136448 DOI: 10.3389/fpubh.2021.612064
    The aim of this study was to investigate how the anterior and posterior muscles in the shank (Tibialis Anterior, Gastrocnemius Lateralis and Medialis), influence the level of minimum toe clearance (MTC). With aging, MTC deteriorates thus, greatly increasing the probability of falling or tripping. This could result in injury or even death. For this study, muscle activity retention taping (MART) was used on young adults, which is an accepted method of simulating a poor MTC-found in elderly gait. The subject's muscle activation was measured using surface electromyography (SEMG), and the kinematic parameters (MTC, knee and ankle joint angles) were measured using an optical motion capture system. Our results indicate that MART produces significant reductions in MTC (P < α), knee flexion (P < α) and ankle dorsiflexion (P < α), as expected. However, the muscle activity increased significantly, contrary to the expected result (elderly individuals should have lower muscle activity). This was due to the subject's muscle conditions (healthy and strong), hence the muscles worked harder to counteract the external restriction. Yet, the significant change in muscle activity (due to MART) proves that the shank muscles do play an important role in determining the level of MTC. The Tibialis Anterior had the highest overall muscle activation, making it the primary muscle active during the swing phase. With aging, the shank muscles (specifically the Tibialis Anterior) would weaken and stiffen, coupled with a reduced joint range of motion. Thus, ankle-drop would increase-leading to a reduction in MTC.
    Matched MeSH terms: Gait*
  9. Fulltext Estimation of body segmental orientation for prosthetic gait using a nonlinear autoregressive neural network with exogenous inputs
    Tham LK, Al Kouzbary M, Al Kouzbary H, Liu J, Abu Osman NA
    Phys Eng Sci Med, 2023 Dec;46(4):1723-1739.
    PMID: 37870729 DOI: 10.1007/s13246-023-01332-6
    Assessment of the prosthetic gait is an important clinical approach to evaluate the quality and functionality of the prescribed lower limb prosthesis as well as to monitor rehabilitation progresses following limb amputation. Limited access to quantitative assessment tools generally affects the repeatability and consistency of prosthetic gait assessments in clinical practice. The rapidly developing wearable technology industry provides an alternative to objectively quantify prosthetic gait in the unconstrained environment. This study employs a neural network-based model in estimating three-dimensional body segmental orientation of the lower limb amputees during gait. Using a wearable system with inertial sensors attached to the lower limb segments, thirteen individuals with lower limb amputation performed two-minute walk tests on a robotic foot and a passive foot. The proposed model replicates features of a complementary filter to estimate drift free three-dimensional orientation of the intact and prosthetic limbs. The results indicate minimal estimation biases and high correlation, validating the ability of the proposed model to reproduce the properties of a complementary filter while avoiding the drawbacks, most notably in the transverse plane due to gravitational acceleration and magnetic disturbance. Results of this study also demonstrates the capability of the well-trained model to accurately estimate segmental orientation, regardless of amputation level, in different types of locomotion task.
    Matched MeSH terms: Gait*
  10. Gait disorder rehabilitation using vision and non-vision based sensors: a systematic review
    Ali A, Sundaraj K, Ahmad B, Ahamed N, Islam A
    Bosn J Basic Med Sci, 2012 Aug;12(3):193-202.
    PMID: 22938548
    Even though the amount of rehabilitation guidelines has never been greater, uncertainty continues to arise regarding the efficiency and effectiveness of the rehabilitation of gait disorders. This question has been hindered by the lack of information on accurate measurements of gait disorders. Thus, this article reviews the rehabilitation systems for gait disorder using vision and non-vision sensor technologies, as well as the combination of these. All papers published in the English language between 1990 and June, 2012 that had the phrases "gait disorder", "rehabilitation", "vision sensor", or "non vision sensor" in the title, abstract, or keywords were identified from the SpringerLink, ELSEVIER, PubMed, and IEEE databases. Some synonyms of these phrases and the logical words "and", "or", and "not" were also used in the article searching procedure. Out of the 91 published articles found, this review identified 84 articles that described the rehabilitation of gait disorders using different types of sensor technologies. This literature set presented strong evidence for the development of rehabilitation systems using a markerless vision-based sensor technology. We therefore believe that the information contained in this review paper will assist the progress of the development of rehabilitation systems for human gait disorders.
    Matched MeSH terms: Gait Disorders, Neurologic/physiopathology; Gait Disorders, Neurologic/rehabilitation*
  11. Wireless gyroscope suit for gait stability estimation
    Gouwanda D, Senanayake NA
    Annu Int Conf IEEE Eng Med Biol Soc, 2011;2011:7824-8.
    PMID: 22256153 DOI: 10.1109/IEMBS.2011.6091928
    Gait stability is primary in assessing individuals with high risk of falling, particularly the elderly. Custom made self-adjustable wireless gyroscope suit is used as a sensing device to quantify gait stability. A nonlinear time series analysis i.e. maximum Lyapunov exponent (λ*) was employed to estimate the short term and long term stability and it is closely related to the ability of human neuro-muscular control system in maintaining gait stability. Experimental analysis and tests validated the efficacy of this novel approach. The results achieved are comparable with the findings of multiple kinematic and dynamic parameters derived from optical motion capture system and force platform which are widely used as gold standard.
    Matched MeSH terms: Gait/physiology*
  12. The effect of asymmetrical gait induced by unilateral knee brace on the knee flexor and extensor muscles
    Yap YT, Gouwanda D, Gopalai AA, Chong YZ
    Med Biol Eng Comput, 2021 Mar;59(3):711-720.
    PMID: 33625670 DOI: 10.1007/s11517-021-02337-7
    Asymmetrical stiff knee gait is a mechanical pathology that can disrupt lower extremity muscle coordination. A better understanding of this condition can help identify potential complications. This study proposes the use of dynamic musculoskeletal modelling simulation to investigate the effect of induced mechanical perturbation on the kneeand to examine the muscle behaviour without invasive technique. Thirty-eight healthy participants were recruited. Asymmetrical gait was simulated using knee brace. Knee joint angle, joint moment and knee flexor and extensor muscle forces were computed using OpenSim. Differences inmuscle force between normal and abnormal conditions were investigated using ANOVA and Tukey-Kramer multiple comparison test.The results revealed that braced knee experienced limited range of motion with smaller flexion moment occuring at late swing phase. Significant differences were found in all flexormuscle forces and in several extensor muscle forces (p<0.05). Normal knee produced larger flexor muscle force than braced knee. Braced knee generated the largest extensor muscle force at early swing phase. In summary, musculoskeletal modelling simulation can be a computational tool to map and detect the differences between normal and asymmetrical gaits.
    Matched MeSH terms: Gait*
  13. Computational intelligent gait-phase detection system to identify pathological gait
    Senanayake CM, Senanayake SM
    IEEE Trans Inf Technol Biomed, 2010 Sep;14(5):1173-9.
    PMID: 20801745 DOI: 10.1109/TITB.2010.2058813
    An intelligent gait-phase detection algorithm based on kinematic and kinetic parameters is presented in this paper. The gait parameters do not vary distinctly for each gait phase; therefore, it is complex to differentiate gait phases with respect to a threshold value. To overcome this intricacy, the concept of fuzzy logic was applied to detect gait phases with respect to fuzzy membership values. A real-time data-acquisition system was developed consisting of four force-sensitive resistors and two inertial sensors to obtain foot-pressure patterns and knee flexion/extension angle, respectively. The detected gait phases could be further analyzed to identify abnormality occurrences, and hence, is applicable to determine accurate timing for feedback. The large amount of data required for quality gait analysis necessitates the utilization of information technology to store, manage, and extract required information. Therefore, a software application was developed for real-time acquisition of sensor data, data processing, database management, and a user-friendly graphical-user interface as a tool to simplify the task of clinicians. The experiments carried out to validate the proposed system are presented along with the results analysis for normal and pathological walking patterns.
    Matched MeSH terms: Gait/physiology*; Gait Disorders, Neurologic/diagnosis
  14. Fulltext Using a Deep Learning Method and Data from Two-Dimensional (2D) Marker-Less Video-Based Images for Walking Speed Classification
    Sikandar T, Rabbi MF, Ghazali KH, Altwijri O, Alqahtani M, Almijalli M, et al.
    Sensors (Basel), 2021 Apr 17;21(8).
    PMID: 33920617 DOI: 10.3390/s21082836
    Human body measurement data related to walking can characterize functional movement and thereby become an important tool for health assessment. Single-camera-captured two-dimensional (2D) image sequences of marker-less walking individuals might be a simple approach for estimating human body measurement data which could be used in walking speed-related health assessment. Conventional body measurement data of 2D images are dependent on body-worn garments (used as segmental markers) and are susceptible to changes in the distance between the participant and camera in indoor and outdoor settings. In this study, we propose five ratio-based body measurement data that can be extracted from 2D images and can be used to classify three walking speeds (i.e., slow, normal, and fast) using a deep learning-based bidirectional long short-term memory classification model. The results showed that average classification accuracies of 88.08% and 79.18% could be achieved in indoor and outdoor environments, respectively. Additionally, the proposed ratio-based body measurement data are independent of body-worn garments and not susceptible to changes in the distance between the walking individual and camera. As a simple but efficient technique, the proposed walking speed classification has great potential to be employed in clinics and aged care homes.
    Matched MeSH terms: Gait
  15. A study on body movement analysis by the foot slip pattern in a fall
    Kim SH, Kim DW
    Sains Malaysiana, 2015;44:1745-1750.
    A fracture, which mostly results from a fall, is fatal for the elderly. A fall occurred when a person cannot maintain the
    body position. Most falls occurred when a person walks on a slippery surface or trips over an object on the ground during
    a gait. Most people try to avoid falls instinctively and fall when their attempt fails. As such, this study investigated the
    difference between two movements- a movement to avoid falls and a forward-falling movement without a fall-avoiding
    movement- by analyzing the body movements of the subjects. A fast-moving fall-guiding device with a pneumatic actuator
    was used to guide falls. The movement of the device could simulate a foot slip that may happen during daily activities.
    A three-axis acceleration sensor and a Bluetooth module were used to avoid disturbing the body movement during a fall
    as a wire sensor or a movement analysis system does.
    Matched MeSH terms: Gait
  16. Fulltext Minimum number of inertial measurement units needed to identify significant variations in walk patterns of overweight individuals walking on irregular surfaces
    Sikandar T, Rabbi MF, Ghazali KH, Altwijri O, Almijalli M, Ahamed NU
    Sci Rep, 2023 Sep 27;13(1):16177.
    PMID: 37758958 DOI: 10.1038/s41598-023-43428-9
    Gait data collection from overweight individuals walking on irregular surfaces is a challenging task that can be addressed using inertial measurement unit (IMU) sensors. However, it is unclear how many IMUs are needed, particularly when body attachment locations are not standardized. In this study, we analysed data collected from six body locations, including the torso, upper and lower limbs, to determine which locations exhibit significant variation across different real-world irregular surfaces. We then used deep learning method to verify whether the IMU data recorded from the identified body locations could classify walk patterns across the surfaces. Our results revealed two combinations of body locations, including the thigh and shank (i.e., the left and right shank, and the right thigh and right shank), from which IMU data should be collected to accurately classify walking patterns over real-world irregular surfaces (with classification accuracies of 97.24 and 95.87%, respectively). Our findings suggest that the identified numbers and locations of IMUs could potentially reduce the amount of data recorded and processed to develop a fall prevention system for overweight individuals.
    Matched MeSH terms: Gait
  17. Fulltext Tuning attention based long-short term memory neural networks for Parkinson's disease detection using modified metaheuristics
    Cuk A, Bezdan T, Jovanovic L, Antonijevic M, Stankovic M, Simic V, et al.
    Sci Rep, 2024 Feb 21;14(1):4309.
    PMID: 38383690 DOI: 10.1038/s41598-024-54680-y
    Parkinson's disease (PD) is a progressively debilitating neurodegenerative disorder that primarily affects the dopaminergic system in the basal ganglia, impacting millions of individuals globally. The clinical manifestations of the disease include resting tremors, muscle rigidity, bradykinesia, and postural instability. Diagnosis relies mainly on clinical evaluation, lacking reliable diagnostic tests and being inherently imprecise and subjective. Early detection of PD is crucial for initiating treatments that, while unable to cure the chronic condition, can enhance the life quality of patients and alleviate symptoms. This study explores the potential of utilizing long-short term memory neural networks (LSTM) with attention mechanisms to detect Parkinson's disease based on dual-task walking test data. Given that the performance of networks is significantly inductance by architecture and training parameter choices, a modified version of the recently introduced crayfish optimization algorithm (COA) is proposed, specifically tailored to the requirements of this investigation. The proposed optimizer is assessed on a publicly accessible real-world clinical gait in Parkinson's disease dataset, and the results demonstrate its promise, achieving an accuracy of 87.4187 % for the best-constructed models.
    Matched MeSH terms: Gait
  18. Dairy farmers' knowledge, awareness and practices regarding bovine lameness in Malaysian dairy farms
    Sadiq MB, Ramanoon SZ, Mansor R, Syed-Hussain SS, Mossadeq WMS
    Trop Anim Health Prod, 2024 Jan 17;56(2):45.
    PMID: 38231431 DOI: 10.1007/s11250-024-03889-0
    Given the data paucity on dairy farmers' perspectives regarding bovine lameness and hoof diseases, particularly in South East Asian countries, this study was conducted to assess the knowledge, attitude and practices toward lameness and hoof health among dairy cattle farmers in Malaysia. An online-based and face-to-face survey was conducted among 114 dairy farmers from four states in Peninsular Malaysia. Data were analysed using descriptive statistics, principal component analysis and an independent sample t-test. Overall, farmers demonstrated satisfactory knowledge and attitude regarding lameness and its impact on dairy cattle welfare and production. Lameness was ranked the second most important health issue in dairy farms after mastitis. Notably, 90% reported the presence of at least one lame cow on their farms, and 55% stated lameness as the reason for culling their cows. While sole ulcer was the hoof lesion mostly identified by farmers, 75% of them underestimated lameness prevalence on their farms and rarely implemented management strategies such as preventive hoof trimming and footbath. Farmers' educational qualification influenced their understanding of the impact of lameness on dairy cattle production. Despite reflecting satisfactory knowledge and attitude towards lameness in dairy cows, farmers in this study need to improve their current management practices to address lameness problem in their herds. Educating farmers on the importance of early detection and prompt treatment, and preventive measures are crucial for lameness control and improving hoof health in these dairy farms.
    Matched MeSH terms: Gait
  19. Quantitative Gait and Balance Outcomes for Ataxia Trials: Consensus Recommendations by the Ataxia Global Initiative Working Group on Digital-Motor Biomarkers
    Ilg W, Milne S, Schmitz-Hübsch T, Alcock L, Beichert L, Bertini E, et al.
    Cerebellum, 2024 Aug;23(4):1566-1592.
    PMID: 37955812 DOI: 10.1007/s12311-023-01625-2
    With disease-modifying drugs on the horizon for degenerative ataxias, ecologically valid, finely granulated, digital health measures are highly warranted to augment clinical and patient-reported outcome measures. Gait and balance disturbances most often present as the first signs of degenerative cerebellar ataxia and are the most reported disabling features in disease progression. Thus, digital gait and balance measures constitute promising and relevant performance outcomes for clinical trials.This narrative review with embedded consensus will describe evidence for the sensitivity of digital gait and balance measures for evaluating ataxia severity and progression, propose a consensus protocol for establishing gait and balance metrics in natural history studies and clinical trials, and discuss relevant issues for their use as performance outcomes.
    Matched MeSH terms: Gait Disorders, Neurologic/diagnosis; Gait Disorders, Neurologic/physiopathology; Gait Disorders, Neurologic/therapy
  20. Fulltext Deep supervised hashing for gait retrieval
    Sayeed S, Min PP, Ong TS
    F1000Res, 2021;10:1038.
    PMID: 35814625 DOI: 10.12688/f1000research.51368.2
    Background: Gait recognition is perceived as the most promising biometric approach for future decades especially because of its efficient applicability in surveillance systems. Due to recent growth in the use of gait biometrics across surveillance systems, the ability to rapidly search for the required data has become an emerging need. Therefore, we addressed the gait retrieval problem, which retrieves people with gaits similar to a query subject from a large-scale dataset. Methods: This paper presents the deep gait retrieval hashing (DGRH) model to address the gait retrieval problem for large-scale datasets. Our proposed method is based on a supervised hashing method with a deep convolutional network. We use the ability of the convolutional neural network (CNN) to capture the semantic gait features for feature representation and learn the compact hash codes with the compatible hash function. Therefore, our DGRH model combines gait feature learning with binary hash codes. In addition, the learning loss is designed with a classification loss function that learns to preserve similarity and a quantization loss function that controls the quality of the hash codes Results: The proposed method was evaluated against the CASIA-B, OUISIR-LP, and OUISIR-MVLP benchmark datasets and received the promising result for gait retrieval tasks. Conclusions: The end-to-end deep supervised hashing model is able to learn discriminative gait features and is efficient in terms of the storage memory and speed for gait retrieval.
    Matched MeSH terms: Gait
Related Terms
Filters
Contact Us

Please provide feedback to Administrator ([email protected])

External Links