ORCID Profile
0000-0002-3195-8591
Current Organisations
Fluminense Federal University
,
Victoria University
Does something not look right? The information on this page has been harvested from data sources that may not be up to date. We continue to work with information providers to improve coverage and quality. To report an issue, use the Feedback Form.
In Research Link Australia (RLA), "Research Topics" refer to ANZSRC FOR and SEO codes. These topics are either sourced from ANZSRC FOR and SEO codes listed in researchers' related grants or generated by a large language model (LLM) based on their publications.
Biomedical Engineering | Systems Theory And Control | Biomedical Engineering Not Elsewhere Classified | Simulation And Modelling | Biomechanics | Biomechanical Engineering | Biomechanical Engineering | Artificial Intelligence and Image Processing | Electrical and Electronic Engineering | Calculus of Variations, Systems Theory and Control Theory | Human Movement and Sports Science | Electrical Engineering | Diagnostic Applications | Biomechanics | Pattern Recognition |
Medical instrumentation | Health Related to Ageing | "Occupational, speech and physiotherapy" | Diagnostic methods | Mathematical sciences | Skeletal system and disorders (incl. arthritis) | Injury Control | Diagnostics | Computer hardware and electronic equipment not elsewhere classified | Other
Publisher: IGI Global
Date: 31-07-2015
Publisher: SAGE Publications
Date: 18-11-2020
Abstract: The aim of this review was to determine how exoskeletons could assist Australian Defence Force personnel with manual handling tasks. Musculoskeletal injuries due to manual handling are physically damaging to personnel and financially costly to the Australian Defence Force. Exoskeletons may minimize injury risk by supporting, augmenting, and/or lifying the user’s physical abilities. Exoskeletons are therefore of interest in determining how they could support the unique needs of military manual handling personnel. Industrial and military exoskeleton studies from 1990 to 2019 were identified in the literature. This included 67 unique exoskeletons, for which Information about their current state of development was tabulated. Exoskeleton support of manual handling tasks is largely through squat/deadlift (lower limb) systems (64%), with the proposed use case for these being load carrying (42%) and 78% of exoskeletons being active. Human–exoskeleton analysis was the most prevalent form of evaluation (68%) with reported reductions in back muscle activation of 15%–54%. The high frequency of citations of exoskeletons targeting load carrying reflects the need for devices that can support manual handling workers. Exoskeleton evaluation procedures varied across studies making comparisons difficult. The unique considerations for military applications, such as heavy external loads and load asymmetry, suggest that a significant adaptation to current technology or customized military-specific devices would be required for the introduction of exoskeletons into a military setting. Exoskeletons in the literature and their potential to be adapted for application to military manual handling tasks are presented.
Publisher: Springer Science and Business Media LLC
Date: 06-2006
DOI: 10.1007/BF03178892
Publisher: Springer International Publishing
Date: 2014
Publisher: IEEE
Date: 11-2013
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 12-2007
Publisher: IEEE
Date: 08-2007
Publisher: Informa UK Limited
Date: 06-07-2022
Publisher: IEEE
Date: 11-2013
Publisher: Springer Berlin Heidelberg
Date: 2005
DOI: 10.1007/11573067_38
Publisher: IEEE
Date: 04-2010
Publisher: IEEE
Date: 11-2005
Publisher: MDPI AG
Date: 19-11-2021
DOI: 10.3390/APP112210947
Abstract: Knee osteoarthritis (OA) is a degenerative condition that critically affects locomotor ability and quality of life and, the condition is particularly prevalent in the senior population. The current review presents a gait biomechanics conceptual framework for designing active knee orthoses to prevent and remediate knee OA. Constant excessive loading diminishes knee joint articular cartilage and, therefore, measures to reduce kinetic stresses due to the fact of adduction moments and joint compression are an essential target for OA prevention. A powered orthosis enables torque generation to support knee joint motions and machine-learning-driven “smart systems” can optimise the magnitude and timing of joint actuator forces. Although further research is required, recent findings raise the possibility of exoskeleton-supported, non-surgical OA interventions, increasing the treatment options for this prevalent, painful and seriously debilitating disease. Combined with advances in regenerative medicine, such as stem cell implantation and manipulation of messenger ribonucleic acid (m-RNA) transcription, active knee orthoses can be designed to incorporate electro-magnetic stimulators to promote articular cartilage resynthesis.
Publisher: Public Library of Science (PLoS)
Date: 05-08-2021
DOI: 10.1371/JOURNAL.PONE.0255597
Abstract: 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.
Publisher: IEEE
Date: 12-2019
Publisher: Springer Science and Business Media LLC
Date: 27-11-2011
Publisher: Informa UK Limited
Date: 2006
DOI: 10.1080/03091900500224675
Abstract: Ground reaction force (GRF) time recordings are frequently corrupted due to faulty stepping on a force platform during gait, and this results in the loss of valuable data and the need for additional data acquisition. This paper proposes a new approach based on artificial neural networks for the estimation of lost key gait parameters using the available features of an affected GRF-time trace. GRF-time plots were recorded using a force platform during normal walking of 14 young and 13 elderly in iduals. Back-propagation neural network models were developed using features extracted from 466 vertical GRF-time characteristics that would be unaffected as inputs, and the likely affected gait features (e.g. stance time (ST), push-off force, (Fmax2) and push-off time (Tmax2)) as output. Performance of the models in predicting ST, Fmax2 and Tmax2 were tested using data from 30 new gait trials. The neural network model predicted the missing STs with 96.5% (+/-2.6%) accuracy (r>0.9). Accuracy of the ST prediction deteriorated when push-off force/time data were unavailable for the prediction model. Fmax2 and its time were reconstructed with an accuracy of 95.7% (+/-2.8%) and 97.6% (+/-1.7%) respectively. These results suggest that an artificial neural network may be applied to estimate missing ST, Fmax2 or Tmax2 information using features from an affected vertical GRF-time plot, and the method shows good promise for reconstructing gait forces from a corrupted force-time trace.
Publisher: World Scientific Pub Co Pte Lt
Date: 09-2008
DOI: 10.1142/S1469026808002314
Abstract: Trip-related falls are a major problem in the elderly population and research in the area has received much attention recently. The focus has been on devising ways of identifying in iduals at risk of sustaining such falls. The main aim of this work is to explore the effectiveness of models based on Support Vector Machines (SVMs) for the automated recognition of gait patterns that exhibit falling behavior. Minimum toe clearance (MTC) during continuous walking on a treadmill was recorded on 10 healthy elderly and 10 elderly with balance problems and with a history of tripping falls. Statistical features obtained from MTC histograms were used as inputs to the SVM model to classify between the healthy and balance-impaired subjects. The leave-one-out technique was utilized for training the SVM model in order to find the optimal model parameters. Tests were conducted with various kernels (linear, Gaussian and polynomial) and with a change in the regularization parameter, C, in an effort to identify the optimum model for this gait data. The receiver operating characteristic (ROC) plots of sensitivity and specificity were further used to evaluate the diagnostic performance of the model. The maximum accuracy was found to be 90% using a Gaussian kernel with σ 2 = 10 and the maximum ROC area 0.98 (80% sensitivity and 100% specificity), when all statistical features were used by the SVM models to diagnose gait patterns of healthy and balance-impaired in iduals. This accuracy was further improved by using a feature selection method in order to reduce the effect of redundant features. It was found that two features (standard deviation and maximum value) were adequate to give an improved accuracy of 95% (90% sensitivity and 100% specificity) using a polynomial kernel of degree 2. These preliminary results are encouraging and could be useful not only for diagnostic applications but also for evaluating improvements in gait function in the clinical/rehabilitation contexts.
Publisher: IEEE
Date: 12-2013
DOI: 10.1109/AIMS.2013.89
Publisher: IEEE
Date: 08-2006
Publisher: Springer Science and Business Media LLC
Date: 31-05-2019
Publisher: Elsevier BV
Date: 02-2007
DOI: 10.1016/J.GAITPOST.2006.03.008
Abstract: This paper models minimum foot clearance (MFC) data during steady-state gait to investigate how the various descriptive statistics of the MFC distribution differ in healthy young and elderly females. A minimum of 20min of treadmill walking was analysed for 17 young and 16 elderly females using a Peak Motus motion analysis system. The results indicated that none of the 33 participants' MFC data sets were Normally distributed. The deviation from a Normal distribution was systematic (always skewness>0 and kurtosis>0). Skewness and kurtosis in MFC data was highly correlated (young: r=0.60, p=0.01 elderly: r=0.95, p<0.01). MFC descriptive statistics provide useful information about basic strategies used by in iduals to minimize the likelihood of tripping. Possible strategies to minimize tripping include: (a) increasing MFC height central tendency, (b) reducing MFC variability, and/or (c) increasing right skewness. A low median MFC was often associated with a low IQR or high skewness to compensate. Further research is required to establish how, or if at all, these strategies are modified in populations that are more at risk of falling.
Publisher: Springer Science and Business Media LLC
Date: 12-07-2015
Publisher: Elsevier BV
Date: 10-2016
DOI: 10.1016/J.JBIOMECH.2016.08.029
Abstract: Anterior cruciate ligament (ACL) injury can be a painful, debilitating and costly consequence of participating in sporting activities. Prophylactic knee bracing aims to reduce the number and severity of ACL injury, which commonly occurs during landing maneuvers and is more prevalent in female athletes, but a consensus on the effectiveness of prophylactic knee braces has not been established. The lower-limb muscles are believed to play an important role in stabilizing the knee joint. The purpose of this study was to investigate the changes in lower-limb muscle function with prophylactic knee bracing in male and female athletes during landing. Fifteen recreational athletes performed double-leg drop landing tasks from 0.30m and 0.60m with and without a prophylactic knee brace. Motion analysis data were used to create subject-specific musculoskeletal models in OpenSim. Static optimization was performed to calculate the lower-limb muscle forces. A linear mixed model determined that the hamstrings and vasti muscles produced significantly greater flexion and extension torques, respectively, and greater peak muscle forces with bracing. No differences in the timings of peak muscle forces were observed. These findings suggest that prophylactic knee bracing may help to provide stability to the knee joint by increasing the active stiffness of the hamstrings and vasti muscles later in the landing phase rather than by altering the timing of muscle forces. Further studies are necessary to quantify whether prophylactic knee bracing can reduce the load placed on the ACL during intense dynamic movements.
Publisher: Human Kinetics
Date: 07-2006
DOI: 10.1123/MCJ.10.3.201
Abstract: Visual reaction time (RT) was measured in 10 older men (mean age, 71.1 years) and gender-matched controls (mean age, 26.3 years) when standing (single task) and when walking on a motor-driven treadmill (dual task). There were 90 quasirandomly presented trials over 15 min in each condition. Longer mean and median RTs were observed in the dual task compared to the single task. Older males had significantly slower mean and median RTs (315 and 304 ms, respectively) than the younger group (273 and 266 ms, respectively) in both task conditions. There were no age or condition effects on within-subject variability. Both groups showed a trend of increasing RT over the 90 single task trials but when walking only the younger group slowed. These novel findings demonstrate high but sustained attention by older adults when walking. It is proposed that the motor task’s attentional demands might contribute to their slower preferred walking speed.
Publisher: ICST
Date: 2015
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 08-2008
Publisher: Elsevier BV
Date: 02-2017
Publisher: IGI Global
Date: 2006
DOI: 10.4018/978-1-59140-670-9.CH008
Abstract: In today’s global market economy, currency exchange rates play a vital role in national economy of the trading nations. In this chapter, we present an overview of neural network-based forecasting models for foreign currency exchange (forex) rates. To demonstrate the suitability of neural network in forex forecasting, a case study on the forex rates of six different currencies against the Australian dollar is presented. We used three different learning algorithms in this case study, and a comparison based on several performance metrics and trading profitability is provided. Future research direction for enhancement of neural network models is also discussed.
Publisher: Springer International Publishing
Date: 07-12-2013
Publisher: IEEE
Date: 12-2008
Publisher: IEEE
Date: 12-2013
Publisher: MDPI AG
Date: 28-08-2018
DOI: 10.3390/SU10093065
Abstract: Impacts of climate change are likely to be marked in areas with steep climatic transitions. Species turnover, spread of invasive species, altered productivity, and modified processes such as fire regimes can all spread rapidly along ecotones, which challenge the current paradigms of ecosystem management. We conducted a literature review at a continental-wide scale of South-Western European forests, where the drier and warmer conditions of the Mediterranean have been widely used as ex les of what is expected in more temperate areas. Results from the literature point to: (a) an expansion of slow-growing evergreen hardwood trees (b) increased dieback and mortality episodes in forests (both natural and planted) mostly related to competition and droughts, and mainly affecting conifers and (c) an increase in emergent diseases and pests of keystone-trees used in agroforestry zones. There is no consensus in the literature that fire regimes are directly increasing due to climate change, but available satellite data of fire intensity in the last 17 years has been lower in zones where agroforestry practices are dominant compared to unmanaged forests. In contrast, there is agreement in the literature that the current spread of fire events is probably related to land abandonment patterns. The practice of agroforestry, common in all Mediterranean countries, emerges as a frequent recommendation in the literature to cope with drought, reduce fire risk, and maintain bio erse landscapes and rural jobs. However, it is unknown the extent to which the open vegetation resulting from agroforestry is of interest to forest managers in temperate areas used to exploiting closed forest vegetation. Hence, many transitional areas surrounding the Mediterranean Basin may be left unmanaged with potentially higher climate-change risks, which require active monitoring in order to understand and help ongoing natural adaptation processes.
Publisher: Springer Berlin Heidelberg
Date: 2006
DOI: 10.1007/11811305_33
Publisher: IEEE
Date: 12-2008
Publisher: World Scientific Pub Co Pte Lt
Date: 06-2010
DOI: 10.1142/S146902681000280X
Abstract: Abstract-Cardiac arrhythmia is one of the major causes of human death, and most of the time it cannot be predicted well in advance at the right time. Computational intelligence algorithms can help in extracting the hidden patterns of biological datasets. This paper explores the use of advanced and intelligent computational algorithms for automated detection, classification and clustering of cardiac arrhythmia (CA). Application of Fuzzy C-Mean and Extended Fuzzy C-Mean method to the arrhythmia dataset (165 normal healthy and 138 with CA) demonstrated their good CA classification capabilities. Fuzzy C Mean algorithm was able to classify the two group of data set with an overall accuracy of 97.2% [sensitivity 96.4%, specificity 98.12% and area under the receiver operating curve (AUC-ROC = 0.963)]. The classification accuracy improved significantly when GK-based extended Fuzzy was employed, and an overall accuracy of 99.14% was achieved (sensitivity 97.11%, specificity 99.18% and AUC-ROC = 0.995). These accuracy results were respectively, 19.02%, 7%, 9.14% and 11.06% higher when compared to multi-input single layer perceptron (SLP), feed forward back propagation (FFBP), self organizing maps (SOM) and support vector machine (SVM). The performance measures of fuzzy techniques were found to be better if a Principal Component Analysis (PCA) technique was used to preprocess the arrhythmia datasets.
Publisher: Informa UK Limited
Date: 30-11-2015
DOI: 10.1080/02640414.2015.1117120
Abstract: With the aim of determining both the acute and the chronic effects of textured insoles on the ankle discrimination and performance ability of dancers, 60 ballet dancers from the Australian Ballet School, aged 14-19 years, were ided into three groups (two intervention groups and a control group), age- and level-matched. In the first 5 weeks (weeks 1 to 5), the first intervention group (GRP1) was asked to wear textured insoles in their ballet shoes and the second intervention group (GRP2) was not given textured insoles to wear. In the next 5 weeks (weeks 6 to 10), GRP2 was asked to wear the same type of textured insoles and GRP1 did not wear the textured insoles. The control group (CTRL) did not wear textured insoles during the whole 10 weeks. All participants were tested preintervention, after 5 weeks and after 10 weeks for ankle discrimination score (AUC scores). Dance performance was assessed by 5-7 dance teachers. Pre-to-post change in AUC scores was significantly greater for the groups wearing insoles than for the controls (P = .046) and the size of pre-to-post changes did not differ between the two intervention groups (P = .834). Significant correlation was found between ankle discrimination score and performance scores, using the textured insoles (r = .412 P = .024). In conclusion, the stimulation to the proprioceptive system arising from textured insoles worn for five weeks was sufficient to improve the proprioceptive ability and performance ability of ballet dancers.
Publisher: MDPI AG
Date: 10-11-2019
DOI: 10.3390/S19224908
Abstract: Wearable sensors are being applied to real-world motion monitoring and the focus of this work is assessing health status and wellbeing. An extensive literature has documented the effects on gait control of impaired physical health, but in this project, the aim was to determine whether emotional states associated with older people’s mental health are also associated with walking mechanics. If confirmed, wearable sensors could be used to monitor affective responses. Lower limb gait mechanics of 126 healthy in iduals (mean age 66.2 ± 8.38 years) were recorded using a high-speed 3D motion sensing system and they also completed a 12-item mental health status questionnaire (GHQ-12). Mean step width and minimum foot-ground clearance (MFC), indicative of tripping risk, were moderately correlated with GHQ-12. Ageing and variability (SD) of gait parameters were not significantly correlated with GHQ-12. GHQ-12 scores were, however, highly correlated with left-right gait control, indicating that greater gait symmetry was associated with better mental health. Maintaining good mental health with ageing may promote safer gait and wearable sensor technologies could be applied to gait asymmetry monitoring, possibly using a single inertial measurement unit attached to each shoe.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 11-2016
Publisher: Elsevier BV
Date: 07-2020
Publisher: IEEE
Date: 11-2008
Publisher: Springer Science and Business Media LLC
Date: 06-03-2021
DOI: 10.1186/S12877-021-02117-W
Abstract: Falls-related injuries are particularly serious for older people, causing pain, reduced community engagement and associated medical costs. Tripping is the leading cause of falls and the current study examined whether minimum ground clearance (MFC) of the swing foot, indicating high tripping risk, would be differentiated across cohorts of healthy 50-, 60- and 70-years old community residents in Japan. A cross-sectional population comprising the three groups (50s, 60s and 70s) of 123 Konosu City residents consented to be recorded when walking on an unobstructed surface at preferred speed. Gait biomechanics was measured using high speed (100 Hz) motion capture (OptiTrack – Natural Point Inc.), including step length and width, double support, foot contact angle and MFC (swing toe height above the ground). Multivariate Analysis of Variance (MANOVA) was used to confirm ageing effects on MFC and fundamental gait parameters. Pearson’s correlations were performed to identify the relationships between mean MFC and other MFC characteristics (SD and SI), step length, step width, double support time and foot contact angle. Compared to 50s, lower step length was seen (2.69 cm and 6.15 cm) for 60s and 70s, respectively. No other statistical effects were identified for spatio-temporal parameters between the three groups. The 50s cohort MFC was also significantly higher than 60s and 70s, while step-to-step MFC variability was greater in the 70s than 50s and 60s. Pearson’s correlations demonstrated that more symmetrical gait patterns were associated with greater MFC height, as reflected in greater symmetry in step width (50s), MFC (60s) and foot contact angle (70s). In the 70s increased MFC height correlated with higher MFC variability and reduced foot contact angle. MFC height reduces from 60 years but more variable MFC appears later, from 70 years. While symmetrical gait was accompanied by increased MFC height, in the 70s group attempts to increase MFC height may have caused more MFC variability and lower foot contact angles, compromising foot-ground clearance. Assessments of swing foot mechanics may be a useful component of community falls prevention.
Publisher: Springer Science and Business Media LLC
Date: 23-09-2017
DOI: 10.1007/S11657-017-0378-4
Abstract: The association between vitamin D and muscle function associated with balance recovery and falls in people with knee osteoarthritis is unclear. Those with vitamin D insufficiency demonstrated poorer knee function during balance recovery, greater pain and locomotor dysfunction. Vitamin D insufficiency may have an adverse effect on muscle power function. Low vitamin D status in people with knee osteoarthritis (OA) is often reported to be associated with increased pain and locomotor dysfunction. However, despite the growing evidence of the effect of vitamin D on the pathogenesis of knee OA, its role remains conflicting. Importantly, muscle function is important for knee joint health however, the association between vitamin D levels and muscle function associated with balance recovery and falls is unclear. This study investigated the effect of circulating 25-hydroxyvitamin D (25 (OH) D) on pain, quadriceps strength, lower limb muscle mass and knee power function during balance recovery in people with knee OA. Twenty-four participants with clinical symptoms of knee OA (68.6 ± 6.2 years) participated in the study. Serum levels of 25 (OH) D were assessed and participants were classified as follows: vitamin D insufficiency ≤ 50 nmol/L and vitamin D sufficiency > 50 nmol/L. The groups were compared on knee function during balance recovery tasks, lower limb strength and muscle mass as well as perceived pain and function. Seven patients (29.1%) were classified as vitamin D-insufficient. Vitamin D insufficiency was associated with reduced knee muscle function during the balance recovery task, increased pain (Western Ontario and McMasters University Osteoarthritis Index (WOMAC) subscore), dysfunction (WOMAC subscore) and total WOMAC score (p < 0.05). People with knee OA with vitamin D insufficiency demonstrated poorer knee function during balance recovery, greater pain and locomotor dysfunction. Vitamin D insufficiency may have an adverse effect on muscle power function.
Publisher: Springer Science and Business Media LLC
Date: 28-04-2010
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 05-2005
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 09-2009
Publisher: Elsevier BV
Date: 2008
DOI: 10.1016/J.JBIOMECH.2007.11.023
Abstract: Despite tripping being one of the frequently reported causes of falls, currently there is no method of quantifying the probability of an in idual's foot contacting obstacles during gait. This paper describes a statistical modeling technique based on variability in minimum toe clearance (MTC) data during treadmill walking to estimate the probability of the toe contacting an obstacle. MTC data were calculated from two foot markers and using a 2D geometric model of the distal end of the foot. Probability of tripping (PT) was calculated by modeling and then integrating the MTC s le distribution. Results from a young male subject continuously walking for 1 hour show the MTC distribution is not normally distributed with mean=1.03 cm, S.D.=0.25 cm, skew=1.01 and kurtosis=3.47. For this distribution, PT for an unseen 0.2 cm high obstacle is calculated to be 1 in every 10,363 strides. Without skew- and kurtosis-modeling PT reduced to 1 in every 1901 strides, which highlights the importance of skew and kurtosis-modeling for PT estimation. Predicted PT is seen to increase with increasing obstacle heights (e.g. PT for an unseen 0.5 cm obstacle is 1 in 95 strides and PT for an unseen 1.0 cm obstacle is 1 in 2 strides). The method presented in this paper shows that variability in MTC data can be modeled to quantify the probability/risk of tripping on obstructions/obstacles in the travel terrain, and has the potential for wide application in the areas of falls prediction and falls minimization.
Publisher: IGI Global
Date: 2006
DOI: 10.4018/978-1-59140-670-9.CH001
Abstract: The primary aim of this chapter is to present an overview of the artificial neural network basics and operation, architectures, and the major algorithms used for training the neural network models. As can be seen in subsequent chapters, neural networks have made many useful contributions to solve theoretical and practical problems in finance and manufacturing areas. The secondary aim here is therefore to provide a brief review of artificial neural network applications in finance and manufacturing areas.
Publisher: IEEE
Date: 04-2009
Publisher: IEEE
Date: 2007
Publisher: Elsevier BV
Date: 08-1991
Publisher: MDPI AG
Date: 19-12-2023
DOI: 10.3390/S23052802
Abstract: Walking independently is essential to maintaining our quality of life but safe locomotion depends on perceiving hazards in the everyday environment. To address this problem, there is an increasing focus on developing assistive technologies that can alert the user to the risk destabilizing foot contact with either the ground or obstacles, leading to a fall. Shoe-mounted sensor systems designed to monitor foot-obstacle interaction are being employed to identify tripping risk and provide corrective feedback. Advances in smart wearable technologies, integrating motion sensors with machine learning algorithms, has led to developments in shoe-mounted obstacle detection. The focus of this review is gait-assisting wearable sensors and hazard detection for pedestrians. This literature represents a research front that is critically important in paving the way towards practical, low-cost, wearable devices that can make walking safer and reduce the increasing financial and human costs of fall injuries.
Publisher: Human Kinetics
Date: 04-2016
Abstract: Normalization of gait data is performed to reduce the effects of intersubject variations due to physical characteristics. This study reports a multiple regression normalization approach for spatiotemporal gait data that takes into account intersubject variations in self-selected walking speed and physical properties including age, height, body mass, and sex. Spatiotemporal gait data including stride length, cadence, stance time, double support time, and stride time were obtained from healthy subjects including 782 children, 71 adults, 29 elderly subjects, and 28 elderly Parkinson’s disease (PD) patients. Data were normalized using standard dimensionless equations, a detrending method, and a multiple regression approach. After normalization using dimensionless equations and the detrending method, weak to moderate correlations between walking speed, physical properties, and spatiotemporal gait features were observed (0.01 | r | 0.88), whereas normalization using the multiple regression method reduced these correlations to weak values (| r | 0.29). Data normalization using dimensionless equations and detrending resulted in significant differences in stride length and double support time of PD patients however the multiple regression approach revealed significant differences in these features as well as in cadence, stance time, and stride time. The proposed multiple regression normalization may be useful in machine learning, gait classification, and clinical evaluation of pathological gait patterns.
Publisher: MDPI AG
Date: 02-07-2022
DOI: 10.3390/APP12136716
Abstract: Globally, we are facing the tendency of aging, and demands for health enhancement among the older population have been steadily increasing. Among various exercise interventions, Pilates has been popularly utilized in rehabilitation therefore, it is considered suitable for vulnerable populations. In this study, frail late-stage older adults ( years) participated in a modified Pilates program (30 min per session, once a week for eight weeks). Age- and condition-matched Controls were also involved as the benchmark to reveal the effect of Pilates. While only the Pilates group participated in the exercise intervention, both groups undertook the health assessments twice (before and after the intervention period). Assessments included: (i) falling risk based on 3D motion capture systems and (ii) overall cognitive functions utilizing Mini-Mental State Examination and executive function with the use of Trail Making Test-A (TMT-A). Two-dimensional mood state was also used to measure changes in mood due to Pilates intervention. An 8-week Pilates intervention was effective in achieving higher and symmetrical swing foot control. Dynamic balance at heel contact was also improved by extending the spatial margin in case of slipping. Despite the trend of positive Pilates effects on executive functions (29% improvement) confirmed by TMT-A, no significant effects were observed for cognitive functions. Positive mood changes were achieved by Pilates intervention, which may be the key for late-stage seniors to continue their participation in exercise programs. While further studies with a larger s le size are essential, Pilates appears to provide adequate exercise for the frail late-stage older population to minimize frailty.
Publisher: IEEE
Date: 11-2013
Publisher: IEEE
Date: 12-2009
Publisher: Elsevier BV
Date: 03-2017
DOI: 10.1016/J.GAITPOST.2016.11.044
Abstract: Minimum-toe-clearance (MTC) above the walking surface is a critical representation of toe-trajectory control due to its association with tripping risk. Not all gait cycles exhibit a clearly defined MTC within the swing phase but there have been few previous accounts of the biomechanical characteristics of non-MTC gait cycles. The present report investigated the within-subject non-MTC gait cycle characteristics of 15 older adults (mean 73.1 years) and 15 young controls (mean 26.1 years). Participants performed the following tasks on a motorized treadmill: preferred speed walking, dual task walking (carrying a glass of water) and a dual-task speed-matched control. Toe position-time coordinates were acquired using a 3 dimensional motion capture system. When MTC was present, toe height at MTC (MTC
Publisher: Springer Berlin Heidelberg
Date: 2009
Publisher: Springer Berlin Heidelberg
Date: 2013
Publisher: Springer Science and Business Media LLC
Date: 02-02-2008
Publisher: Elsevier BV
Date: 06-2007
DOI: 10.1016/J.GAITPOST.2006.07.006
Abstract: Falls on stairs, kerbs and footpaths are a major cause of morbidity in older female adults. This investigation examined the stepping responses made by 48 elderly (mean age 67 years, S.D. 5.4 years) and 48 young (mean age 20 years, S.D. 2.4 years) healthy, community-dwelling adult females to approach and accommodate known surface height changes. The surface was designed to simulate an object like a kerb or step in the walking path. For ascent, the surface was 9 m long (height, 15 cm) with a 13 m ground-level approach. For descent, it was 15m long (height, 15 cm) with a 7 m ground-level departure. These tasks (particularly descent) perturbed the gait of the elderly more than the young. The elderly exerted more control or were more cautious. They made earlier and larger step adjustments (p<.05), primarily employed a short step crossing strategy (elderly, 60% young, 19%), exhibited less footfall variability (p<.05), moved slower across the step (p<.001) and spent more time in double foot support while crossing the step. In descent, the elderly preferred to land on the forefoot (p<.001). In both conditions, the elderly placed the feet closer to the step and cleared it by a lesser margin. Step descent appears to be particularly hazardous for older females since foot clearances were small and foot placement was closer to the step.
Publisher: Elsevier BV
Date: 09-1990
DOI: 10.1016/0141-5425(90)90021-E
Abstract: A microcomputer-based video vector system has been developed to display the resultant ground reaction force vector on a television image of the subject in real-time. For each television field the force platform signals are acquired and processed and the resultant force vector superimposed on the video image of the walking subject. The force platform results are stored on disc and the composite video signals recorded on video tape for further analysis. The system is easy to set up and use and the results can be readily interpreted. The external moments produced at the joint centers by the ground reaction forces can be observed visually and, if required, quantification of the external moments can be achieved following data collection. The spatial resolution of the system is 0.342% vertically and 0.156% horizontally. The force vector visualization technique has routine applications in orthotics and prosthetics. It is also a useful technique for the teaching of biomechanics.
Publisher: Springer Science and Business Media LLC
Date: 03-06-2020
Publisher: IEEE
Date: 2005
Publisher: IEEE
Date: 08-2010
Publisher: Elsevier BV
Date: 08-1996
Publisher: Elsevier BV
Date: 11-2011
DOI: 10.1016/J.CLINBIOMECH.2011.05.013
Abstract: Foot-ground clearance during the gait cycle swing phase is a critical locomotor adaptation to uneven terrain and non-optimal lower limb control has been linked to tripping and falling. The aim of this research was to determine ageing effects on bilateral foot-ground clearance during overground and treadmill walking. Ageing and walking surface effects on bilateral foot trajectory control were investigated in 11 older (mean age 73.8 years) and 11 young (mean age 22.5 years) participants. First maximum clearance after toe-off, minimum foot-ground clearance and second maximum clearance prior to heel contact were determined from s led 3-dimensional marker coordinates during preferred-speed treadmill walking and walking overground. Preferred walking speed was lower in treadmill walking for both groups. In both groups non-dominant minimum foot-ground clearance and first maximum clearance were greater than for the dominant foot. A high positive correlation was found between these two swing foot clearances when older adults walked on the treadmill. Second maximum clearance was reduced in the older group but this was the only overall age effect. Treadmill walking reduced minimum foot-ground clearance relative to overground locomotion except in the older adults' non-dominant limb that revealed greater vertical clearance height in the non-dominant foot. Decreased second maximum clearance in the older group may be linked to reduced dorsiflexion. Greater minimum foot-ground clearance in the older adults' non-dominant foot may reflect functional asymmetry, in which the non-dominant limb primarily secures or stabilizes gait. The high positive correlation between first maximum and minimum foot-ground clearances suggests that intervention designed to increase first maximum clearance may also increase minimum foot-ground clearance. A direction for future research is to further understand ageing effects on lower limb trajectory variables in response to a range of walking surface characteristics.
Publisher: IEEE
Date: 2009
DOI: 10.1109/IEMBS.2009.5334512
Abstract: This paper investigates the use of machine learning to predict a sensitive gait parameter based on acceleration information from previous gait cycles. We investigate a k-step look-ahead prediction which attempts to predict gait variable values based on acceleration information in the current gait cycle. The variable is the minimum toe clearance which has been demonstrated to be a sensitive falls risk predictor. Toe clearance data was collected under normal walking conditions and 9 features consisting of peak acceleration and their normalized occurrences times were extracted. A standard least squares estimator, a generalized regression neural network (GRNN) and a support vector regressor (SVR) were trained using 60% of the data to estimate the minimum toe clearance and the remaining 40% was used to validate the model. It was found that when the training data contained data from all subjects (inter-subject) the best GRNN model provided a root mean square error (RMSE) of 2.8 mm, the best SVR had RMSE of 2.7 mm while the standard least squares linear regression method obtained 3.3 mm. When the training and test data consisted of different subject ex les (inter-subject) data, the linear SVR demonstrated superior generalization capability (RMSE=3.3 mm) compared to other competing models. Validation accuracies up to 5-step look-ahead predictions revealed robust performances for both GRNN and SVR models with no clear degradation in prediction accuracy.
Publisher: Elsevier BV
Date: 10-2017
Publisher: MDPI AG
Date: 14-09-2022
DOI: 10.3390/S22186960
Abstract: Efficient, adaptive, locomotor function is critically important for maintaining our health and independence, but falls-related injuries when walking are a significant risk factor, particularly for more vulnerable populations such as older people and post-stroke in iduals. Tripping is the leading cause of falls, and the swing-phase event Minimum Foot Clearance (MFC) is recognised as the key biomechanical determinant of tripping probability. MFC is defined as the minimum swing foot clearance, which is seen approximately mid-swing, and it is routinely measured in gait biomechanics laboratories using precise, high-speed, camera-based 3D motion capture systems. For practical intervention strategies designed to predict, and possibly assist, swing foot trajectory to prevent tripping, identification of the MFC event is essential however, no technique is currently available to determine MFC timing in real-life settings outside the laboratory. One strategy has been to use wearable sensors, such as Inertial Measurement Units (IMUs), but these data are limited to primarily providing only tri-axial linear acceleration and angular velocity. The aim of this study was to develop Machine Learning (ML) algorithms to predict MFC timing based on the preceding toe-off gait event. The ML algorithms were trained using 13 young adults’ foot trajectory data recorded from an Optotrak 3D motion capture system. A Deep Learning configuration was developed based on a Recurrent Neural Network with a Long Short-Term Memory (LSTM) architecture and Huber loss-functions to minimise MFC-timing prediction error. We succeeded in predicting MFC timing from toe-off characteristics with a mean absolute error of 0.07 s. Although further algorithm training using population-specific inputs are needed. The ML algorithms designed here can be used for real-time actuation of wearable active devices to increase foot clearance at critical MFC and reduce devastating tripping falls. Further developments in ML-guided actuation for active exoskeletons could prove highly effective in developing technologies to reduce tripping-related falls across a range of gait impaired populations.
Publisher: IEEE
Date: 08-2007
Publisher: IEEE
Date: 12-2011
Publisher: IEEE
Date: 08-2010
Publisher: Frontiers Media SA
Date: 08-05-2014
Publisher: Ovid Technologies (Wolters Kluwer Health)
Date: 07-2011
Publisher: IEEE
Date: 12-2007
Publisher: Informa UK Limited
Date: 05-2013
DOI: 10.1080/10255842.2011.628943
Abstract: Ageing influences gait patterns which in turn can affect the balance control of human locomotion. Entropy-based regularity and complexity measures have been highly effective in analysing a broad range of physiological signals. Minimum toe clearance (MTC) is an event during the swing phase of the gait cycle and is highly sensitive to the spatial balance control properties of the locomotor system. The aim of this research was to investigate the regularity and complexity of the MTC time series due to healthy ageing and locomotors' disorders. MTC data from 30 healthy young (HY), 27 healthy elderly (HE) and 10 falls risk (FR) elderly subjects with balance problems were analysed. Continuous MTC data were collected and using the first 500 data points, MTC mean, standard deviation (SD) and entropy-based complexity analysis were performed using s le entropy (S En) for different window lengths (m) and filtering levels (r). The MTC S En values were lower in the FR group compared to the HY and HE groups for all m and r. The HY group had a greater mean S En value than both HE and FR reflecting higher complexity in their MTC series. The mean S En values of HY and FR groups were found significantly different for m = 2, 4, 5 and r = (0.1-0.9) × SD, (0.3-0.9) × SD and (0.3-0.9) × SD, respectively. They were also significant difference between HE and FR groups for m = 4-5 and r = (0.3-0.7) × SD, but no significant differences were seen between HY and HE groups for any m and r. A significant correlation of S En with SD of MTC was revealed for the HY and HE groups only, suggesting that locomotor disorders could significantly change the regularity or the complexity of the MTC series while healthy ageing does not. These results can be usefully applied to the early diagnosis of common gait pathologies.
Publisher: IGI Global
Date: 2008
DOI: 10.4018/978-1-59904-887-1.CH030
Abstract: This chapter describes the application of machine learning techniques to solve biomedical problems in a variety of clinical domains. First, the concept of development and the main elements of a basic machine learning system for medical diagnostics are presented. This is followed by an introduction to the design of a diagnostic model for the identification of balance impairments in the elderly using human gait pattern, as well as a diagnostic model for predicating sleep apnoea syndrome from electrocardiogram recordings. Ex les are presented using support vector machines (a machine learning technique) to build a reliable model that utilizes key indices of physiological measurements (gait/electrocardiography [ECG] signals). A number of recommendations have been proposed for choosing the right classifier model in designing a successful medical diagnostic system. The chapter concludes with a discussion of the importance of signal processing techniques and other future trends in enhancing the performance of a diagnostic system.
Publisher: ACM
Date: 10-09-2010
Publisher: IEEE
Date: 12-2008
Publisher: Elsevier BV
Date: 12-2015
DOI: 10.1016/J.KNEE.2015.06.016
Abstract: Knee osteoarthritis is commonly associated with ageing and long-term walking. In this study the effects of flexing motions on knee kinetics during stance were simulated. Extended knees do not facilitate efficient loading. It was therefore, hypothesised that knee flexion would promote power absorption and negative work, while possibly reducing knee adduction moment. Three-dimensional (3D) position and ground reaction forces were collected from the right lower limb stance phase of one healthy young male subject. 3D position was s led at 100 Hz using three Optotrak Certus (Northern Digital Inc.) motion analysis camera units, set up around an eight metre walkway. Force plates (AMTI) recorded ground reaction forces for inverse dynamics calculations. The Visual 3D (C-motion) 'Landmark' function was used to change knee joint positions to simulate three knee flexion angles during static standing. Effects of the flexion angles on joint kinetics during the stance phase were then modelled. The static modelling showed that each 2.7° increment in knee flexion angle produced 2.74°-2.76° increments in knee flexion during stance. Increased peak extension moment was 6.61 Nm per 2.7° of increased knee flexion. Knee flexion enhanced peak power absorption and negative work, while decreasing adduction moment. Excessive knee extension impairs quadriceps' power absorption and reduces eccentric muscle activity, potentially leading to knee osteoarthritis. A more flexed knee is accompanied by reduced adduction moment. Research is required to determine the optimum knee flexion to prevent further damage to knee-joint structures affected by osteoarthritis.
Publisher: Informa UK Limited
Date: 04-09-2015
DOI: 10.3109/17483107.2015.1080767
Abstract: This study aimed to develop a low-cost real-time biofeedback system to assist with rehabilitation for patients following total knee replacement (TKR) and to assess its feasibility of use in a post-TKR patient case study design with a comparison group. The biofeedback system consisted of Microsoft Kinect(TM) and Nintendo Wii balance board with a dedicated software. A six-week inpatient rehabilitation program was augmented by biofeedback and tested in a single patient following TKR. Three patients underwent a six weeks standard rehabilitation with no biofeedback and served as a control group. Gait, function and pain were assessed and compared before and after the rehabilitation. The biofeedback software incorporated real time visual feedback to correct limb alignment, movement pattern and weight distribution. Improvements in pain, function and quality of life were observed in both groups. The strong improvement in the knee moment pattern demonstrated in the case study indicates feasibility of the biofeedback-augmented intervention. This novel biofeedback software has used simple commercially accessible equipment that can be feasibly incorporated to augment a post-TKR rehabilitation program. Our preliminary results indicate the potential of this biofeedback-assisted rehabilitation to improve knee function during gait. Research is required to test this hypothesis. Implications for Rehabilitation The real-time biofeedback system developed integrated custom-made software and simple low-cost commercially accessible equipment such as Kinect and Wii board to provide augmented information during rehabilitation following TKR. The software incorporated key rehabilitation principles and visual feedback to correct alignment of the lower legs, pelvic and trunk as well as providing feedback on limbs weight distribution. The case study patient demonstrated greater improvement in their knee function where a more normal biphasic knee moment was achieved following the six-week biofeedback intervention.
Publisher: Research Square Platform LLC
Date: 19-03-2019
DOI: 10.21203/RS.2.147/V2
Abstract: Background The risk of falling is significantly higher in people with chronic stroke and it is, therefore, important to design interventions to improve mobility and decrease falls risk. Minimum Toe Clearance (MTC) is the key gait cycle event for predicting tripping-falls because it occurs mid-swing during the walking cycle where forward velocity of the foot is maximum. High forward velocity coupled with low MTC increases the probability of unanticipated foot-ground contacts. Training procedures to increase toe-ground clearance (MTC) have potential, therefore, as a falls prevention intervention. The aim of this project is to determine whether augmented sensory information via real-time visual biofeedback during gait training can increase MTC. Methods Participants will be over 18 years, have sustained a single stroke (ischaemic or hemorrhagic) at least 6 months previously, able to walk 50 metres independently and capable of informed consent. Using a secure web-based application (REDCap) 150 participants will be randomly assigned to either no-feedback (Control) or feedback (Experimental) groups, all will receive 10 sessions of treadmill training for up to 10 minutes at a self-selected speed over five to six weeks. The intervention group will receive real-time, visual biofeedback of MTC during training and will be asked to modify their gait pattern to match a required “target” criterion. Biofeedback is continuous for the first six sessions then progressively reduced (faded) across the remaining four sessions. Control participants will walk on the treadmill without biofeedback. Gait assessments are conducted at baseline, immediately following the final training session and then during follow-up, at 1, 3 and 6 months. The primary outcome measure is MTC. Monthly falls calendars will also be collected for 12 months from enrolment. Discussion The project will contribute to understanding how stroke-related changes to sensory and motor processes influence gait biomechanics and associated tripping risk. The research findings will guide our work in gait rehabilitation following stroke and may reduce falls rates. Treadmill training procedures incorporating continuous real-time feedback may need to be modified to accommodate stroke patients who have greater difficulties with treadmill walking.
Publisher: IEEE
Date: 07-2013
Publisher: MDPI AG
Date: 23-07-2012
DOI: 10.3390/S120709884
Publisher: Elsevier BV
Date: 02-2012
DOI: 10.1016/J.GAITPOST.2011.09.020
Abstract: Knee osteoarthritis (OA) has been shown to be a risk factor for falls. Reductions in foot clearance during the swing phase of walking can cause a trip and potentially lead to a fall. This study examined the swing phase mechanics of people with and without knee OA during walking. Minimum toe clearance (MTC) height, joint angles at the time of MTC and the influence of the angular changes of the hip, knee and ankle of the swing leg on foot clearance using sensitivity analysis were investigated in 50 knee OA participants and 28 age-matched asymptomatic controls. Although both groups had a similar MTC height (controls: 12.8±6.7 mm, knee OA: 13.4±7.0 mm), the knee OA group used a different strategy to achieve the same foot clearance, as evidenced by greater knee flexion (52.5±5.3° vs 49.4±4.8°, p=0.007), greater hip abduction (-3.6±3.3° vs -1.8±3.3°, p=0.03) and less ankle adduction (2.8±1.9° vs 4.2±2.1°, p=0.01). MTC height was comparable between the groups, however a different swing phase mechanism was used by the knee OA. Although adequate MTC is an important component of safe locomotion, it does not appear to be impaired in people with knee OA. Other factors, such as inadequate responses to postural perturbation, may be responsible for falls in this group.
Publisher: IEEE
Date: 08-2015
Publisher: Research Square Platform LLC
Date: 27-12-2018
DOI: 10.21203/RS.2.147/V1
Abstract: Background: The risk of falling is significantly higher in people with chronic stroke and it is, therefore, important to design interventions to improve mobility and decrease falls risk. Minimum Toe Clearance (MTC) is the key gait cycle event for predicting tripping-falls because it occurs mid-swing during the walking cycle where forward velocity of the foot is maximum. High forward velocity coupled with low MTC increases the probability of unanticipated foot-ground contacts. Training procedures to increase toe-ground clearance (MTC) have potential, therefore, as a falls prevention intervention. The aim of this project is to determine whether augmented sensory information via real-time visual biofeedback during gait training can increase MTC. Methods: Participants will be over 18 years, have sustained a single stroke (ischaemic or hemorrhagic) at least 6 months previously, able to walk 50 metres independently and capable of informed consent. Using a secure web-based application (REDCap) 150 participants will be randomly assigned to either no-feedback (Control) or feedback (Experimental) groups, all will receive 10 sessions of treadmill training for up to 10 minutes at a self-selected speed over five to six weeks. The intervention group will receive real-time, visual biofeedback of MTC during training and will be asked to modify their gait pattern to match a required “target” criterion. Biofeedback is continuous for the first six sessions then progressively reduced (faded) across the remaining four sessions. Control participants will walk on the treadmill without biofeedback. Gait assessments are conducted at baseline, immediately following the final training session and then during follow-up, at 1, 3 and 6 months. The primary outcome measure is MTC. Monthly falls calendars will also be collected for 12 months from enrolment. Discussion: This project will evaluate the impact of augmented sensory information, via visually presented biofeedback, for improving gait function in people with stroke. This has implications for the rehabilitation of gait disorders following stroke and may have the potential to reduce falls in this population.
Publisher: Elsevier BV
Date: 10-2010
DOI: 10.1016/J.GAITPOST.2010.07.010
Abstract: Minimum foot clearance (MFC) is the minimum vertical distance between the lowest point of the foot of the swing leg and the walking surface during the swing phase of the gait cycle. MFC is a gait variable that is linked to the mechanism of a trip because reduced MFC for a given step during walking increases the susceptibility to tripping on an unseen obstacle or due to undetected changes in surface height. Given that tripping is a common cause of falls in older persons, this review was undertaken to determine whether ageing and/or history of falls in older adults influences MFC characteristics during level walking. Studies that assessed MFC characteristics including measures of central tendency (mean and/or median), variability (linear and non-linear measures) and shape (skewness, kurtosis) of the MFC distribution were included in the review. The final yield from a search of seven electronic research databases was 12 unique articles that met all the inclusion criteria. Ageing does not appear to alter measures of central tendency or shape of the MFC distribution. However greater MFC variability was observed in older compared to younger adults and older fallers compared to older non-fallers in the majority of studies. Greater MFC variability may contribute to increased risk of trips and associated falls in older compared to young adults and older fallers compared to older non-fallers.
Publisher: IEEE
Date: 02-2012
DOI: 10.1109/ISMS.2012.21
Publisher: IEEE
Date: 02-2012
DOI: 10.1109/ISMS.2012.20
Publisher: IEEE
Date: 07-2013
Publisher: MDPI AG
Date: 14-10-2021
DOI: 10.3390/S21206836
Abstract: Radar technology is constantly evolving, and new applications are arising, particularly for the millimeter wave bands. A novel application for radar is gait monitoring for fall prevention, which may play a key role in maintaining the quality of life of people as they age. Alarming statistics indicate that one in three adults aged 65 years or older will experience a fall every year. A review of the sensors used for gait analysis and their applications to technology-based fall prevention interventions was conducted, focusing on wearable devices and radar technology. Knowledge gaps were identified, such as wearable radar development, application specific signal processing and the use of machine learning algorithms for classification and risk assessment. Fall prevention through gait monitoring in the natural environment presents significant opportunities for further research. Wearable radar could be useful for measuring gait parameters and performing fall risk-assessment using statistical methods, and could also be used to monitor obstacles in real-time.
Publisher: IGI Global
Date: 2006
Publisher: Elsevier BV
Date: 03-2010
DOI: 10.1016/J.COMPBIOMED.2009.11.003
Abstract: This paper presents an ensemble of feature selection and classification technique for classifying two types of breast lesion, benign and malignant. Features are selected based on their area under the ROC curves (AUC) which are then classified using a hybrid hidden Markov model (HMM)-fuzzy approach. HMM generated log-likelihood values are used to generate minimized fuzzy rules which are further optimized using gradient descent algorithms in order to enhance classification performance. The developed model is applied to Wisconsin breast cancer dataset to test its performance. The results indicate that a combination of selected features and the HMM-fuzzy approach can classify effectively the lesion types using only two fuzzy rules. Our experimental results also indicate that the proposed model can produce better classification accuracy when compared to most other computational tools.
Publisher: IEEE
Date: 06-2012
Publisher: SAGE Publications
Date: 13-04-2016
Abstract: Anterior cruciate ligament (ACL) injuries commonly occur during landing maneuvers. Prophylactic knee braces were introduced to reduce the risk of ACL injuries, but their effectiveness is debated. We hypothesized that bracing would improve biomechanical factors previously related to the risk of ACL injuries, such as increased hip and knee flexion angles at initial contact and at peak vertical ground-reaction force (GRF), increased ankle plantar flexion angles at initial contact, decreased peak GRFs, and decreased peak knee extension moment. We also hypothesized that bracing would increase the negative power and work of the hip joint and would decrease the negative power and work of the knee and ankle joints. Controlled laboratory study. Three-dimensional motion and force plate data were collected from 8 female and 7 male recreational athletes performing double-leg drop landings from 0.30 m and 0.60 m with and without a prophylactic knee brace. GRFs, joint angles, moments, power, and work were calculated for each athlete with and without a knee brace. Prophylactic knee bracing increased the hip flexion angle at peak GRF by 5.56° ( P .001), knee flexion angle at peak GRF by 4.75° ( P = .001), and peak hip extension moment by 0.44 N·m/kg ( P .001). Bracing also increased the peak hip negative power by 4.89 W/kg ( P = .002) and hip negative work by 0.14 J/kg ( P = .001) but did not result in significant differences in the energetics of the knee and ankle. No differences in peak GRFs and peak knee extension moment were observed with bracing. The application of a prophylactic knee brace resulted in improvements in important biomechanical factors associated with the risk of ACL injuries. Prophylactic knee braces may help reduce the risk of noncontact knee injuries in recreational and professional athletes while playing sports. Further studies should investigate different types of prophylactic knee braces in conjunction with existing training interventions so that the sports medicine community can better assess the effectiveness of prophylactic knee bracing.
Publisher: MDPI AG
Date: 13-12-2020
Abstract: Hemiplegic stroke often impairs gait and increases falls risk during rehabilitation. Tripping is the leading cause of falls, but the risk can be reduced by increasing vertical swing foot clearance, particularly at the mid-swing phase event, minimum foot clearance (MFC). Based on previous reports, real-time biofeedback training may increase MFC. Six post-stroke in iduals undertook eight biofeedback training sessions over a month, in which an infrared marker attached to the front part of the shoe was tracked in real-time, showing vertical swing foot motion on a monitor installed in front of the subject during treadmill walking. A target increased MFC range was determined, and participants were instructed to control their MFC within the safe range. Gait assessment was conducted three times: Baseline, Post-training and one month from the final biofeedback training session. In addition to MFC, step length, step width, double support time and foot contact angle were measured. After biofeedback training, increased MFC with a trend of reduced step-to-step variability was observed. Correlation analysis revealed that MFC height of the unaffected limb had interlinks with step length and ankle angle. In contrast, for the affected limb, step width variability and MFC height were positively correlated. The current pilot-study suggested that biofeedback gait training may reduce tripping falls for post-stroke in iduals.
Publisher: Elsevier BV
Date: 07-2016
DOI: 10.1016/J.GAITPOST.2016.04.031
Abstract: People with knee osteoarthritis (OA) are at twice the risk of falling compared to older people without knee OA, however the mechanism for this is poorly understood. This study investigated the biomechanical response of the trunk and lower limb joints during a forward induced fall under different task conditions in people with and without knee OA. Twenty-four participants with OA (68.6±6.2 years) and 15 asymptomatic controls (72.4±4.8 years) participated in the study. Forward fall was induced by releasing participants from a static forward leaning position. Participants were required to recover balance during three conditions: normal, physical (obstacle clearance) and cognitive dual tasks (counting backwards). Spatiotemporal parameters, lower limb joint kinematics and kinetics of the recovery limb were compared between the two groups and across the three task conditions. The OA group demonstrated slower spatio-temporal characteristics and reduced hip and knee flexion angles, joint moments owers and reduced muscle negative work at the knee and ankle (p<0.05). Cognitive dual task resulted in reduced centre of mass velocity and step length (p=0.03) compared to the physical dual task condition. Reduced knee (p=0.02) and hip joint powers (p=0.03) were demonstrated in the OA group in the physical task condition. When simulating a forward fall, participants with OA demonstrated difficulty in absorbing the impact and slowing down the forward momentum of the body during a recovery step. Moreover, poor dynamic postural control was demonstrated as task complexity increased.
Publisher: Elsevier BV
Date: 2016
Publisher: Elsevier BV
Date: 12-2015
DOI: 10.1016/J.JBIOMECH.2015.10.040
Abstract: Falls are the primary cause of accidental injuries (52%) and one of the leading causes of death in in iduals aged 65 and above. More than 50% of falls in healthy older adults are due to tripping while walking. Minimum toe clearance (i.e., minimum height of the toe above the ground during the mid-swing phase - MTC) has been investigated as an indicator of tripping risk. There is increasing demand for practicable gait monitoring using wearable sensors such as Inertial Measurement Units (IMU) comprising accelerometers and gyroscopes due to their wearability, compactness and low cost. A major limitation however, is intrinsic noise making acceleration integration unreliable and inaccurate for estimating MTC height from IMU data. A machine learning approach to MTC height estimation was investigated in this paper incorporating features from both raw and integrated inertial signals to train Generalized Regression Neural Networks (GRNN) models using a hill-climbing feature-selection method. The GRNN based MTC height predictions demonstrated root-mean-square-error (RMSE) of 6.6mm with 9 optimum features for young adults and 7.1mm RMSE with 5 features for the older adults during treadmill walking. The GRNN based MTC height estimation method devised in this project represents approximately 68% less RMSE than other estimation techniques. The research findings show a strong potential for gait monitoring outside the laboratory to provide real-time MTC height information during everyday locomotion.
Publisher: IEEE
Date: 12-2012
Publisher: IEEE
Date: 08-2007
Publisher: Informa UK Limited
Date: 1989
DOI: 10.3109/03091908909016204
Abstract: This paper reviews the currently available instrumentation used for gait studies and discusses the clinical suitability of the various methods of recording gait parameters. Most of the presently available motion analysis systems appear to be more suited to research than to the routine clinical situation. However the video vector visualization technique appears to be the most useful clinically since it produces a real time display, is simple to operate and interpretation of the data is easier than other systems available. Some further development of the video vector visualization system is necessary to improve its accuracy and to produce quantitative information.
Publisher: IEEE
Date: 04-2013
Publisher: IGI Global
Date: 2008
DOI: 10.4018/978-1-60566-050-9.CH057
Abstract: Now-a-days, researchers are increasingly looking into new and innovative techniques with the help of information technology to overcome the rapid surge in healthcare costs facing the community. Research undertaken in the past has shown that artificial intelligence (AI) tools and techniques can aid in the diagnosis of disease states and assessment of treatment outcomes. This has been demonstrated in a number of areas, including: help with medical decision support system, classification of heart disease from electrocardiogram (ECG) waveforms, identification of epileptic seizure from electroencephalogram (EEG) signals, ophthalmology to detect glaucoma disease, abnormality in movement pattern (gait) recognition for rehabilitation and potential falls risk minimization, assisting functional electrical stimulation (FES) control in rehabilitation setting of spinal cord injured patients, and clustering of medical images (Begg et al., 2003 Garrett et al., 2003 Masulli et al., 1998 Papadourokis et al., 1998 Silva & Silva, 1998). Recent developments in information technology and AI tools, particularly in neural networks, fuzzy logic and support vector machines, have provided the necessary support to develop highly efficient automated diagnostic systems. Despite plenty of future challenges, these new advances in AI tools hold much promise for future developments in AI-based approaches in solving medical and health-related problems. This article is organized as follows: Following an overview of major AI techniques, a brief review of some of the applications of AI in healthcare is provided. Future challenges and directions in automated diagnostics are discussed in the summary and conclusion sections.
Publisher: Springer Berlin Heidelberg
Date: 23-05-2018
Publisher: Springer Berlin Heidelberg
Date: 2006
DOI: 10.1007/11788485_9
Publisher: IEEE
Date: 08-2006
Publisher: IEEE
Date: 06-2012
Publisher: Elsevier BV
Date: 2008
DOI: 10.1016/J.JBIOMECH.2008.02.037
Abstract: Elderly tripping falls cost billions annually in medical funds and result in high mortality rates often perpetrated by pulmonary embolism (internal bleeding) and infected fractures that do not heal well. In this paper, we propose an intelligent gait detection system (AR-SVM) for screening elderly in iduals at risk of suffering tripping falls. The motivation of this system is to provide early detection of elderly gait reminiscent of tripping characteristics so that preventive measures could be administered. Our system is composed of two stages, a predictor model estimated by an autoregressive (AR) process and a support vector machine (SVM) classifier. The system input is a digital signal constructed from consecutive measurements of minimum toe clearance (MTC) representative of steady-state walking. The AR-SVM system was tested on 23 in iduals (13 healthy and 10 having suffered at least one tripping fall in the past year) who each completed a minimum of 10 min of walking on a treadmill at a self-selected pace. In the first stage, a fourth order AR model required at least 64 MTC values to correctly detect all fallers and non-fallers. Detection was further improved to less than 1 min of walking when the model coefficients were used as input features to the SVM classifier. The system achieved a detection accuracy of 95.65% with the leave one out method using only 16 MTC s les, but was reduced to 69.57% when eight MTC s les were used. These results demonstrate a fast and efficient system requiring a small number of strides and only MTC measurements for accurate detection of tripping gait characteristics.
Publisher: Informa UK Limited
Date: 2006
DOI: 10.1080/03091900500445353
Abstract: The objective of this research was to determine whether joint angles at critical gait events and during major energy generation/absorption phases of the gait cycle would reliably discriminate age-related degeneration during unobstructed walking. The gaits of 24 healthy adults (12 young and 12 elderly) were analysed using the PEAK Motus motion analysis system. The elderly participants showed significantly greater single (60.3% versus 62.3%, p < 0.01) and double ( p < 0.05) support times, reduced knee flexion (47.7 degrees versus 43.0 degrees , p < 0.05) and ankle plantarflexion (16.8 degrees compared to 3.3 degrees , p = 0.053) at toe off, reduced knee flexion during push-off and reduced ankle dorsiflexion (16.8 degrees compared to 22.0 degrees , p < 0.05) during the swing phase. The plantarflexing ankle joint motion during the stance to swing phase transition (A2) for the young group (31.3 degrees ) was about twice ( p < 0.05) that of the elderly (16.9 degrees ). Reduced knee extension range of motion suggests that the elderly favoured a flexed-knee gait to assist in weight acceptance. Reduced dorsiflexion by the elderly in the swing phase implies greater risk of toe contact with obstacles. Overall, the results suggest that joint angle measures at critical events hases in the gait cycle provide a useful indication of age-related degeneration in the control of lower limb trajectories during unobstructed walking.
Publisher: Elsevier BV
Date: 03-2005
DOI: 10.1016/J.JBIOMECH.2004.05.002
Abstract: This paper investigated application of a machine learning approach (Support vector machine, SVM) for the automatic recognition of gait changes due to ageing using three types of gait measures: basic temporal/spatial, kinetic and kinematic. The gaits of 12 young and 12 elderly participants were recorded and analysed using a synchronized PEAK motion analysis system and a force platform during normal walking. Altogether, 24 gait features describing the three types of gait characteristics were extracted for developing gait recognition models and later testing of generalization performance. Test results indicated an overall accuracy of 91.7% by the SVM in its capacity to distinguish the two gait patterns. The classification ability of the SVM was found to be unaffected across six kernel functions (linear, polynomial, radial basis, exponential radial basis, multi-layer perceptron and spline). Gait recognition rate improved when features were selected from different gait data type. A feature selection algorithm demonstrated that as little as three gait features, one selected from each data type, could effectively distinguish the age groups with 100% accuracy. These results demonstrate considerable potential in applying SVMs in gait classification for many applications.
Publisher: IEEE
Date: 12-2007
Publisher: Frontiers Media SA
Date: 08-05-2020
Publisher: IEEE
Date: 08-2007
Publisher: IEEE
Date: 08-2011
Publisher: IEEE
Date: 12-2010
Publisher: Human Kinetics
Date: 04-2013
DOI: 10.1123/JAB.29.2.188
Abstract: Although lower limb strength becomes asymmetrical with age, past studies of aging effects on gait biomechanics have usually analyzed only one limb. This experiment measured how aging and treadmill surface influenced both dominant and nondominant step parameters in older (mean 74.0 y) and young participants (mean 21.9 y). Step-cycle parameters were obtained from 3-dimensional position/time data during preferred-speed walking for 40 trials along a 10 m walkway and for 10 minutes of treadmill walking. Walking speed (young 1.23 m/s, older 1.24 m/s) and step velocity for the two age groups were similar in overground walking but older adults showed significantly slower walking speed (young 1.26 m/s, older 1.05 m/s) and step velocity on the treadmill due to reduced step length and prolonged step time. Older adults had shorter step length than young adults and both groups reduced step length on the treadmill. Step velocity and length of older adults’ dominant limb was asymmetrically larger. Older adults increased the proportion of double support in step time when treadmill walking. This adaptation combined with reduced step velocity and length may preserve balance. The results suggest that bilateral analyses should be employed to accurately describe asymmetric features of gait especially for older adults.
Publisher: Elsevier BV
Date: 04-2009
Publisher: Informa UK Limited
Date: 30-06-2021
Publisher: IEEE
Date: 2007
Publisher: MDPI AG
Date: 12-12-2020
DOI: 10.3390/APP10248881
Abstract: The prevalence of knee osteoarthritis (OA) increases with ageing and this research aimed to identify gait adaptations that could reduce OA by investigating ageing effects on knee joint biomechanics. Participants were 24 healthy young males (18–35 yrs) and 14 healthy older males (60–75 yrs). Three-dimensional motion capture (Optotrak) and walkway-embedded force plates (AMTI) recorded their natural preferred-speed walking and the following parameters were computed: knee adduction moment, knee joint vertical force, foot contact angle, toe-out angle, foot centre of pressure displacement, time to foot flat, step length, step width and double support time. A 2 × 2 (age × limb) repeated measures mixed model analysis of variance design determined main effects and interactions. Pearson’s correlations between knee kinetic parameters and stride phase variables were also calculated. Both knee adduction moment and vertical joint force were larger in the older group. Relative to the young controls, older in iduals showed a longer time to foot flat, less toe-out angle and wider steps. Correlation analysis suggested that reduced toe-out angle and increased step width were associated with lower knee adduction moment furthermore, knee joint vertical force reduced with greater step length. Future research could focus on intervention strategies for managing excessive knee joint stresses to prevent the ageing-related development of knee OA.
Publisher: IGI Global
Date: 2006
Publisher: Informa UK Limited
Date: 06-2013
DOI: 10.1080/00140139.2013.787122
Abstract: Slipping biomechanics was investigated on both non-contaminated and oil-contaminated surfaces during unconstrained straight-line walking ('walking'), turning, gait initiation and termination. In walking, backward slipping was more frequent, whereas forward slipping was more frequent when turning. Stopping and gait initiation engendered only forward and backward slipping, respectively. Based on slip distance and sliding velocity, severity of forward slipping was least in walking than for the other gait tasks, whereas the tasks had similar effects on backward slipping. Relative to the dry surface, heel and foot contact angles reduced and heel contact (HC) velocity increased for all gait tasks on the contaminated surface. Ground reaction forces were generally lower on the contaminated surface, suggesting kinetic adaptation immediately following HC. Required coefficient of friction (RCoF) did not correlate with slip distance suggesting that RCoF may not be a useful kinetic parameter for assessing slipping risk on contaminated surfaces. Slipping is hazardous in everyday locomotion and occupational settings. This study investigated foot control kinematics and kinetics across various gait tasks on both a non-contaminated and an oil-contaminated walking surface. Turning, gait termination and gait initiation were associated with a greater risk of slip-related falls than unconstrained walking.
Publisher: IEEE
Date: 09-2009
Publisher: Elsevier BV
Date: 03-1998
DOI: 10.1016/S0966-6362(97)00039-8
Abstract: In recent years there has been increasing interest in the kinetic and kinematic characteristics of adaptations to obstacles and the contribution of these measures to understanding processes of gait control. This study investigated the lead and trail foot kinetic characteristics of unobstructed walking and stepping over obstacles for unimpaired, healthy adult males (n=6) and females (n=6). Two strain-gauged force platforms were employed during free-speed ambulation and stepping over obstacles adjusted to 10, 20 and 30% of leg length. In stepping over obstacles subjects increased obstacle-crossing step lengths and reduced obstacle-crossing speed as a function of obstacle height. The force-time data revealed that, compared with the lead foot, the trail foot generated greater vertical and anterior-posterior force during the push-off ropulsive phase across all obstacle conditions, had lower vertical peak force during mid-stance and produced greater vertical and anterior posterior impulses. While maximum propulsive force increased with obstacle height, its timing in the normalized step cycle was uninfluenced by height. Collectively, the results showed that the constraints of stepping over obstacles imposed different kinetic demands on the lead and trail foot this is reflected in a complex interaction of braking and propulsive forces. Regulation of the step in this task was not mediated by a single parameter, such as vertical impulse. Copyright 1997 Elsevier Science B.V.
Publisher: Human Kinetics
Date: 02-2020
Abstract: Minimum toe clearance (MTC ∼10–30 mm) is a hazardous mid-swing gait event, characterized by high-foot velocity (∼4.60 m·s −1 ) and single-foot support. This experiment tested treadmill-based gait training effects on MTC. Participants were 10 young (4 males and 6 females) and 10 older (6 males and 4 females) healthy ambulant in iduals. The mean age, stature, and body mass for the younger group was 23 (2) years, 1.72 (0.10) m, and 67.5 (8.3) kg, and for older adults was 77 (9) years, 1.64 (0.10) m, and 71.1 (12.2) kg. Ten minutes of preferred speed treadmill walking (baseline) was followed by 20 minutes with MTC information (feedback) and 10 minutes without feedback (retention). There were no aging effects on MTC in baseline or feedback. The MTC in baseline for older adults was 14.2 (3.5) mm and feedback 27.5 (8.7) mm, and for the younger group, baseline was 12.7 (2.6) mm and feedback 28.8 (5.1) mm, respectively. Retention MTC was significantly higher for both groups, indicating a positive effect of augmented information: younger 40.8 (7.3) mm and older 27.7 (13.6) mm. Retention joint angles relative to baseline indicated that the young modulated joint angles control MTC differently using increased ankle dorsiflexion at toe off and modulating knee and hip angles later in swing closer to MTC.
Publisher: IEEE
Date: 06-2012
Publisher: IEEE
Date: 12-2008
Publisher: IEEE
Date: 2001
Publisher: IEEE
Date: 08-2008
Publisher: IEEE
Date: 12-2008
Publisher: Springer Science and Business Media LLC
Date: 15-11-2014
Publisher: MDPI AG
Date: 18-08-2015
DOI: 10.3390/S150820392
Publisher: IEEE
Date: 08-2008
Publisher: IEEE
Date: 12-2006
Publisher: IEEE
Date: 2001
Publisher: Wiley
Date: 20-06-2016
Publisher: IEEE
Date: 08-2008
Publisher: Elsevier BV
Date: 04-2012
DOI: 10.1016/J.HUMOV.2010.07.009
Abstract: Tripping and falling is a serious health problem for older citizens due to the high medical costs incurred and the high mortality rates precipitated mostly by hip fractures that do not heal well. Current falls prevention technology encompasses a broad range of interventions both passive (e.g., safer environments, hip protectors) and active (e.g., sensor-based fall detectors) which attempt to reduce the effects of tripping and falling. However the majority of these interventions minimizes the impact of falls and do not directly reduce the risk of falling. This paper investigates the prediction of gait parameters related to foot-to-ground clearance height during the leg swing phase which have been physically associated with tripping and falling risk in the elderly. The objective is to predict parameters of foot trajectory several walking cycles in advance so that anticipated low foot clearance could be addressed early with more volitional countermeasures, e.g., slowing down or stopping. In this primer study, foot kinematics was recorded with a highly accurate motion capture system for 10 healthy adults (25-32 years) and 11 older adults (65-82 years) with a history of falls who each performed treadmill walking for at least 10 min. Vertical foot displacement during the swing phase has three characteristic inflection points and we used these peak values and their normalized time as the target prediction values. These target variables were paired with features extracted from the corresponding foot acceleration signal (obtained through double differentiation). A generalized regression neural network (GRNN) was used to independently predict the gait variables over a prediction horizon (number of gait cycles ahead) of 1-10 gait cycles. It was found that the GRNN attained 0.32-1.10 cm prediction errors in the peak variables and 2-8% errors in the prediction of normalized peak times, with slightly better accuracies in the healthy group compared to elderly fallers. Prediction accuracy decreased linearly (best fit) at a slow rate with increasing prediction horizon ranging from 0.03 to 0.11 cm per step for peak displacement variables and 0.34 × 10(-3) - 1.81 × 10(-3)% per step for normalized peak time variables. Further time series analysis of the target gait variable revealed high autocorrelations in the faller group indicating the presence of cyclic patterns in elderly walking strategies compared to almost random walking patterns in the healthy group. The results are promising because the technique can be extended to portable sensor-based devices which measure foot accelerations to predict the onset of risky foot clearance, thus leading to a more effective falls prevention technology.
Publisher: IGI Global
Date: 2006
DOI: 10.4018/978-1-59140-848-2.CH001
Abstract: Artificial neural network (ANN) is one of the main constituents of the artificial intelligence techniques. Like in many other areas, ANN has made a significant mark in the domain of healthcare applications. In this chapter, we provide an overview of the basics of neural networks, their operation, major architectures that are widely employed for modeling the input-to-output relations, and the commonly used learning algorithms for training the neural network models. Subsequently, we briefly outline some of the major application areas of neural networks for the improvement and well being of human health.
Publisher: Elsevier BV
Date: 09-2015
DOI: 10.1016/J.GAITPOST.2015.05.014
Abstract: Falls during walking reflect susceptibility to balance loss and the in idual's capacity to recover stability. Balance can be recovered using either one step or multiple steps but both responses are impaired with ageing. To investigate older adults' (n=15, 72.5±4.8 yrs) recovery step control a tether-release procedure was devised to induce unanticipated forward balance loss. Three-dimensional position-time data combined with foot-ground reaction forces were used to measure balance recovery. Dependent variables were margin of stability (MoS) and available response time (ART) for spatial and temporal balance measures in the transverse and sagittal planes lower limb joint angles and joint negative ositive work and spatio-temporal gait parameters. Relative to multi-step responses, single-step recovery was more effective in maintaining balance, indicated by greater MoS and longer ART. MoS in the sagittal plane measure and ART in the transverse plane distinguished single step responses from multiple steps. When MoS and ART were negative (<0), balance was not secured and additional steps would be required to establish the new base of support for balance recovery. Single-step responses demonstrated greater step length and velocity and when the recovery foot landed, greater centre of mass downward velocity. Single-step strategies also showed greater ankle dorsiflexion, increased knee maximum flexion and more negative work at the ankle and knee. Collectively these findings suggest that single-step responses are more effective in forward balance recovery by directing falling momentum downward to be absorbed as lower limb eccentric work.
Publisher: Elsevier BV
Date: 07-2015
DOI: 10.1016/J.GAITPOST.2015.05.013
Abstract: Falls are an important healthcare concern in the older population and tripping is the primary cause. Greater swing foot-ground clearance is functional for tripping prevention. Trips frequently occur due to the lowest part of the shoe contacting the walking surface. Shoe design effects on swing foot-ground clearance are, therefore, important considerations. When a shoe is placed on a flat surface, there usually is small vertical margin (VM) between the walking surface and the minimum toe point (MTP). The current study examined the effects of VM on swing foot-ground clearance at a critical gait cycle event, minimum foot clearance (MFC). 3D coordinates of the swing foot (i.e. MTP and heel) were obtained during the swing phase. MTP represented the swing foot-ground clearance and various MTPs were modelled based on a range of VMs. The sagittal orientation of the toe and heel relative to the walking surface was also considered to evaluate effects of VM and swing foot angle on foot-ground clearance. Greater VM increased the swing foot-ground clearance. At MFC, for ex le, 0.09 cm increase was estimated for every 0.1cm VM. Foot angle throughout the swing phase was typically -30° and 70°. Increasing swing ankle dorsiflexion can maximise VM, which is effective for tripping prevention. Further research will be needed to determine the maximum thresholds of VM to be safely incorporated into a shoe.
Publisher: Human Kinetics
Date: 12-2022
Abstract: Dual-task walking and cell phone usage, which is associated with high cognitive load and reduced situational awareness, can increase risk of a collision, a fall event, or death. The objective of this study was to quantify the effect of dual-task cell phone talking, texting, and reading while walking on spatiotemporal gait parameters minimum foot clearance and dynamic stability of the lower limb joints, trunk, and head. Nineteen healthy male participants walked on an instrumented treadmill at their self-selected speed as well as walking while simultaneously (1) reading on a cell phone, (2) texting, and (3) talking on a cell phone. Gait analyses were performed using an optical motion analysis system, and dynamic stability was calculated using the Maximum Lyapunov Exponent. Dual-task cell phone usage had a significant destabilizing influence on the lower limb joints during walking. Cell phone talking while walking significantly increased step width and length and decreased minimum foot clearance height (P < .05). The findings suggest that dual-task walking and cell phone conversation may present a greater risk of a fall event than texting or reading. This may be due to the requirements for more rapid information processing and cognitive demand at the expense of motor control of joint stability.
Publisher: Elsevier BV
Date: 2009
DOI: 10.1016/J.GAITPOST.2008.07.004
Abstract: Knee osteoarthritis (OA) is one of the leading causes of disability among the elderly which, depending on severity, may require surgical intervention. Knee replacement surgery provides pain relief and improves physical function including gait. However gait dysfunction such as altered spatio-temporal measures may persist after the surgery. In this paper, we investigated the application of support vector machines (SVM) to classify gait patterns indicative of knee OA before surgery based on 12 spatio-temporal gait parameters and investigated whether SVMs could be used to predict gait improvement 2 and 12 months following knee replacement surgery. Test results for the pre-operative data indicated that the SVM could successfully identify in iduals with OA gait from the healthy using all of the spatio-temporal parameters with a maximum leave one out accuracy of 100% for the training set and 88.89% for the test set. Findings indicated that three patients still had altered gait patterns 2 months post-knee replacement surgery, but all in iduals showed improvement in gait 12 months following surgery. Consequently, the SVM detected improvement in gait function due to surgical intervention at 2 and 12 months following knee replacement which coincided with clinical assessment of the knee. This suggests that spatio-temporal parameters contain important discriminative information which may be used for the identification of pathological gait using an SVM classifier.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 09-2009
Publisher: Zhejiang University Press
Date: 07-2015
Publisher: Springer Science and Business Media LLC
Date: 12-10-2012
DOI: 10.1007/S10439-012-0673-6
Abstract: A number of variability analysis techniques, including Poincaré plots and detrended fluctuation analysis (DFA) were used to investigate minimum toe clearance (MTC) control during walking. Ten young adults walked on a treadmill for 10 min at preferred speed in three conditions: (i) no-intervention baseline, (ii) with biofeedback of MTC within a target range, and (iii) no-biofeedback retention. Mean, median, standard deviation (SD), and inter quartile range of MTC during biofeedback (45.57 ± 11.65, 44.98 ± 11.57, 7.08 ± 2.61, 8.58 ± 2.77 mm, respectively) and retention (56.95 ± 20.31, 56.69 ± 20.94, 10.68 ± 5.41, 15.38 ± 10.19 mm) were significantly greater than baseline (30.77 ± 9.49, 30.51 ± 9.49, 3.04 ± 0.77, 3.66 ± 0.91 mm). Relative to baseline, skewness was reduced in biofeedback and retention but only significantly for retention (0.88 ± 0.51, 0.63 ± 0.55, and 0.40 ± 0.40, respectively). Baseline Poincaré measures (SD1 = 0.25, SD2 = 0.34) and DFA (α1 = 0.72 and α2 = 0.64) were lower than biofeedback (SD1 = 0.58, SD2 = 0.83, DFA α1 = 0.76 and α2 = 0.92) with significantly greater variability in retention compared to biofeedback only in the long-term SD2 and α2 analyses. Increased DFA longer-term correlations α2 in retention confirm that a novel gait pattern was acquired with a longer-term variability structure. Short- and long-term variability analyses were both useful in quantifying gait adaptations with biofeedback. The findings provide evidence that MTC can be modified with feedback, suggesting future applications in gait training procedures for impaired populations designed to reduce tripping risk.
Publisher: IEEE
Date: 11-2008
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 12-2006
Publisher: IGI Global
Date: 2006
DOI: 10.4018/978-1-59140-836-9.CH001
Abstract: This chapter provides an overview of the commonly used motion analysis approaches and techniques and the key features that are extracted from movement patterns for characterizing gait. The ultimate goal of gait analysis should be to provide reliable, objective data on which to base clinical decisions (Kaufman, 1998). Thousands of gait features arameters have been used over the years. Selection of the correct gait features forms an important part of the research process, and often the success of the research outcomes depends heavily on selecting the most appropriate gait features. Analysis tools based on both statistical and machine-learning techniques use various types of gait features, ranging from the basic and directly measurable parameters to parameters that have undergone significant data processing and treatments. In this chapter, we attempt to introduce the commonly used methods to extract these features for use with the various statistical and computational intelligence analysis tools.
Publisher: IEEE
Date: 09-2014
Publisher: MDPI AG
Date: 15-08-2023
DOI: 10.20944/PREPRINTS202308.1076.V1
Abstract: Tripping is the largest cause of falls and low swing foot ground clearance during the mid-swing phase, particularly at the critical gait event known as Minimum Foot Clearance (MFC) is the major risk factor for tripping-related falls. Intervention strategies to increase MFC height can be effective if applied in real-time based on feed-forward prediction. The current study investigated the capability of machine learning models to classify the MFC into various categories using toe-off kinematics data. Specifically, three MFC sub-categories (less than 1.5cm, between 1.5-2.0cm and higher than 2.0cm) were predicted applying machine learning approaches. A total of 18,490 swing phase gait cycles’ data were extracted from six healthy young adults, each walking for 5-minutes at a constant speed of 4km/h on a motorised treadmill. Both K-Nearest Neighbour (KNN) and Random-Forest were utilised for prediction based on the data from toe-off for five consecutive frames (0.025s duration). Foot kinematics data were obtained from inertial measurement unit attached to the mid-foot, recording tri-axial linear accelerations and angular velocities of the local coordinate. KNN and Random-Forest achieved 84% and 86% accuracy, respectively, in classifying MFC into the three sub-categories with run time of 0.39 seconds and 13.98 seconds respectively. The KNN-based model was found to be more effective if incorporated into an active exoskeleton as the intelligent system to control MFC based on the preceding gait event, toe-off due to its quicker computation time. The machine learning based prediction model shows promise for the prediction of critical MFC data indicating higher tripping risk.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 04-2000
DOI: 10.1109/10.828154
Abstract: This paper proposes a method for the reconstruction of foot-ground reaction forces from force platform recordings of two consecutive footfalls. The reconstruction algorithm uses zero-derivative criterion (inflection point) to detect contralateral foot contacts and subtracts contralateral forces from the combined force-time curve in order to reconstruct force-time data. Experimental results suggest that the method can be applied to separate accurately foot-specific gait forces from corrupted force-time data as a result of incorrect stepping on a force platform.
Publisher: IGI Global
Date: 2006
DOI: 10.4018/978-1-59140-836-9.CH004
Abstract: Computational intelligence (CI) encompasses approaches primarily based on artificial neural networks, fuzzy logic rules, evolutionary algorithms, support vector machines and also approaches that combine two or more techniques (hybrid). These methods have been applied to solve many complex and erse problems. Recent years have seen many new developments in CI techniques and, consequently, this has led to many applications in a variety of areas including engineering, finance, social and biomedical. In particular, CI techniques are increasingly being used in biomedical and human movement areas because of the complexity of the biological systems. The main objective of this chapter is to provide a brief description of the major computational intelligence techniques for pattern recognition and modelling tasks that often appear in biomedical, health and human movement research.
Publisher: MDPI AG
Date: 14-03-2022
DOI: 10.3390/S22062244
Abstract: Powered ankle exoskeletons (PAEs) are robotic devices developed for gait assistance, rehabilitation, and augmentation. To fulfil their purposes, PAEs vastly rely heavily on their sensor systems. Human–machine interface sensors collect the biomechanical signals from the human user to inform the higher level of the control hierarchy about the user’s locomotion intention and requirement, whereas machine–machine interface sensors monitor the output of the actuation unit to ensure precise tracking of the high-level control commands via the low-level control scheme. The current article aims to provide a comprehensive review of how wearable sensor technology has contributed to the actuation and control of the PAEs developed over the past two decades. The control schemes and actuation principles employed in the reviewed PAEs, as well as their interaction with the integrated sensor systems, are investigated in this review. Further, the role of wearable sensors in overcoming the main challenges in developing fully autonomous portable PAEs is discussed. Finally, a brief discussion on how the recent technology advancements in wearable sensors, including environment—machine interface sensors, could promote the future generation of fully autonomous portable PAEs is provided.
Publisher: IEEE
Date: 08-2007
Publisher: IGI Global
Date: 2006
DOI: 10.4018/978-1-59140-836-9.CH008
Abstract: Automated gait pattern recognition capability has many advantages. For ex le, it can be used for the detection of at-risk or faulty gait, or for monitoring the progress of treatment effects. In this chapter, we first provide an overview of the major automated techniques for detecting gait patterns. This is followed by a description of a gait pattern recognition technique based on a relatively new machine-learning tool, support vector machines (SVM). Finally, we show how SVM technique can be applied to detect changes in the gait characteristics as a result of the ageing process and discuss their suitability as an automated gait classifier.
Publisher: IEEE
Date: 08-2007
Publisher: IEEE
Date: 02-2014
Publisher: IEEE
Date: 2005
Publisher: IEEE
Date: 07-2017
Publisher: IEEE
Date: 04-2013
Publisher: IGI Global
Date: 2006
DOI: 10.4018/978-1-59140-848-2.CH010
Abstract: This chapter provides an overview of artificial neural network applications for the detection and classification of various gaits based on their typical characteristics. Gait analysis is routinely used for detecting abnormality in the lower limbs and also for evaluating the progress of various treatments. Neural networks have been shown to perform better compared to statistical techniques in some gait classification tasks. Various studies undertaken in this area are discussed with a particular focus on neural network’s potential in gait diagnostics. Ex les are presented to demonstrate the suitability of neural networks for automated recognition of gait changes due to aging from their respective gait patterns and their potential for identification of at-risk or non-functional gait.
Publisher: MDPI AG
Date: 08-05-2018
DOI: 10.3390/S18051468
Publisher: IEEE
Date: 2005
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 11-2015
Publisher: Elsevier BV
Date: 02-2016
DOI: 10.1016/J.CLINBIOMECH.2015.12.012
Abstract: Gait features characteristic of a cohort may be difficult to evaluate due to differences in subjects' demographic factors and walking speed. The aim of this study was to employ a multiple regression normalization method that accounts for subject age, height, body mass, gender, and self-selected walking speed in the evaluation of gait in unilateral total knee arthroplasty patients. Three-dimensional gait analysis was performed on 45 total knee arthroplasty patients and 31 aged-matched controls walking at their self-selected speed. Gait data peaks including joint angles, ground reaction forces, net joint moments, and net joint powers were normalized using subject body mass, standard dimensionless equations, and a multiple regression approach that modeled subject age, height, body mass, gender, and self-selected walking speed. Normalizing gait data using subject body mass, dimensionless equations, and multiple regression approach resulted in a significantly lower knee adduction moment and knee extensor power in total knee arthroplasty patients compared to controls (p<0.05). In contrast to normalization using body mass and dimensionless equations, multiple regression normalization greatly reduced variance in gait data by minimizing correlations with subject demographic factors and walking speed, resulting in significantly higher peak hip extension angles and peak hip flexion powers in total knee arthroplasty patients (p<0.05). Total knee arthroplasty patients generate greater hip extension angles and hip flexor power and have a lower knee adduction moment than healthy controls. This gait pattern may be a strategy to reduce muscle and joint loading at the knee.
Publisher: Trans Tech Publications, Ltd.
Date: 02-2011
DOI: 10.4028/WWW.SCIENTIFIC.NET/AMR.199-200.1465
Abstract: The thin-layered method (TLM) is very efficient to the wave propagation in layered ground and boundary element method (BEM) is very precise to solve infinite domain problems. In order to study the isolation vibration effectiveness of non-uniform three-dimensional (3D) layered ground wave impeding block (WIB), this paper is accomplished with the aid of a 3D semi-analytical BEM based on TLM, on which the Green’s function is regarded as fundamental solution of a stratified half-space. Then the active isolation effectiveness by WIB is studied under horizontal-rocking coupled loading in elastic half-space in the upper stiff-layer and lower soft-layer. The results show that the foundation of the stratification parameter and the characteristics of non-uniform have significant influence on the vibration isolation effect of the WIB, and the isolation vibration effectiveness of lower soft-layer is better than the upper stiff-layer.
Publisher: Elsevier BV
Date: 11-2018
DOI: 10.1016/J.JSAMS.2018.05.016
Abstract: Enhancing the capabilities of the dismounted combatant has been an enduring goal of international military research communities. Emerging developments in exoskeleton technology offers the potential to augment the dismounted combatant's capabilities. However, the ability to determine the value proposition of an exoskeleton in a military context is difficult due to the variety of methods and metrics used to evaluate previous devices. The aim of this paper was to present a standard framework for the evaluation and assessment of exoskeletons for use in the military. A structured and systematic methodology was developed from the end-user perspective and progresses from controlled laboratory conditions (Stage A), to simulated movements specific to the dismounted combatant (Stage B), and real-world military specific tasks (Stage C). A standard set of objective and subjective metrics were described to ensure a holistic assessment on the human response to wearing the exoskeleton and the device's mechanical performance during each stage. A standardised methodology will ensure further advancement of exoskeleton technology and support improved international collaboration across research and industry groups. In doing so, this better enables international military groups to evaluate a system's potential, with the hope of accelerating the maturity and ultimately the fielding of devices to augment the dismounted close combatant and small team capability.
Publisher: IEEE
Date: 12-2014
Publisher: Elsevier BV
Date: 11-2008
DOI: 10.1016/J.GAITPOST.2008.03.013
Abstract: The study's aim was to document ageing effects on gait control by analysing the distributions of both left and right step timing and minimum foot-ground clearance (MFC) in older men (mean 71.1 years) and gender-matched controls (mean 26.3 years). Step durations and MFC were obtained from continuously s led 3D markers during preferred-speed treadmill walking (single task) for 15 min and a dual-task condition in which participants walked at the same speed and also responded to the same 90 quasi-randomly presented visual reaction time (RT) stimuli. Significantly longer mean and median RTs were observed when treadmill walking compared to the standing-only control condition. Older males had significantly slower mean RTs for the standing and walking tasks (292 ms and 315 ms, respectively) than the younger group (265 ms and 273 ms). Older males walked more slowly, both groups had greater dual-task step durations but the effect was more pronounced in the older group. Older men's step durations were more positively skewed (longer) while the young had more negative skew. MFC was greater in the older group, and, importantly, in both groups right MFC was greater than the left foot. The data provide evidence of right-left limb asymmetry in preferred speed treadmill walking and it was hypothesised that behavioural slowing in locomotion could be a response to increase the safety of limb end-point control.
Publisher: Oxford University Press (OUP)
Date: 03-2000
Abstract: Falls in older in iduals are a major public health issue because of the financial cost of surgery and re habilitation and the human cost of associated pain and disability. Older in iduals are most likely to fall when negotiating an obstacle or obstruction during locomotion. This research was aimed at investigating lower limb motion while a subject negotiated a raised surface. The gait of six healthy young (Y) women (mean age 23.1 years) and six healthy older (O) women (mean age 67.6 years) were analyzed with a PEAK motion analyzer and a dual-force-platform system during unobstructed walking and when the subjects were stepping on and off a raised surface of 15 cm. The effect of age on foot clearance and force platform variables was analyzed. During stepping on, the young women cleared the step by the lead foot by a significantly greater margin than the older subjects did (Y = 10.6 cm, O = 9.1 cm p < .05) but trail-foot clearance was not significantly different (Y 9.4 cm, O = 8.8 cm). Foot clearance in stepping off was low compared with that of ascent, and the older in iduals had a significantly higher lead (Y = 1.5 cm, O = 3.3 cm, p < .05) and trail (Y = 1.0 cm, O = 2.1 cm) vertical clearance. Older in iduals positioned both the lead and the trail foot relatively farther from the step edge on ascending a raised surface, respectively, Y = 87% and O = 93% of the step cycle and Y = 29% and O = 34%. Foot placement in descent was qualitatively similar for the two groups. The force and the impulse data under the lead and the trail feet confirm modulations consistent with the foot clearance data. In negotiating a raised surface older in iduals appear to use a nonoptimal foot placement strategy in which, compared with that of young subjects, the trail foot is placed a long way from the edge of the step. The older subjects allowed very little correction time and little latitude in foot placement beyond the edge of the step, suggesting that the approach to the obstacle may be a critical determinant of safety.
Location: United Kingdom of Great Britain and Northern Ireland
Location: Bangladesh
Start Date: 2009
End Date: 2009
Funder: Australian Research Council
View Funded ActivityStart Date: 2009
End Date: 2012
Funder: Australian Research Council
View Funded ActivityStart Date: 2016
End Date: 2018
Funder: Australian Research Council
View Funded ActivityStart Date: 2010
End Date: 2012
Funder: Australian Research Council
View Funded ActivityStart Date: 2007
End Date: 2010
Funder: Australian Research Council
View Funded ActivityStart Date: 2010
End Date: 12-2015
Amount: $545,000.00
Funder: Australian Research Council
View Funded ActivityStart Date: 03-2008
End Date: 03-2011
Amount: $127,200.00
Funder: Australian Research Council
View Funded ActivityStart Date: 05-2016
End Date: 09-2019
Amount: $482,300.00
Funder: Australian Research Council
View Funded ActivityStart Date: 10-2009
End Date: 12-2011
Amount: $233,000.00
Funder: Australian Research Council
View Funded ActivityStart Date: 09-2020
End Date: 09-2024
Amount: $540,051.00
Funder: Australian Research Council
View Funded ActivityStart Date: 07-2009
End Date: 12-2014
Amount: $156,840.00
Funder: Australian Research Council
View Funded Activity