Quadruped animals in the nature realize high energy efficiency locomotion by automatically changing their gait at different speeds.Inspired by this character,an efficient adaptive diagonal gait locomotion controller i...Quadruped animals in the nature realize high energy efficiency locomotion by automatically changing their gait at different speeds.Inspired by this character,an efficient adaptive diagonal gait locomotion controller is designed for quadruped robot.A unique gait planning method is proposed in this paper.As the speed of robot varies,the gait cycle time and the proportion of stance and swing phase of each leg are adjusted to form a variety of gaits.The optimal joint torque is calculated by the controller combined with Virtual Model Control(VMC)and Whole-Body Control(WBC)to realize the desired motion.The gait and step frequency of the robot can automatically adapt to the change of speed.Several experiments are done with a quadruped robot made by our laboratory to verify that the gait can change automatically from slow-trotting to flying-trot during the period when speed is from 0 to 4 m/s.The ratio of swing phase is from less than 0.5 to more than 0.5 to realize the running motion with four feet off the ground.Experiments have shown that the controller can indeed consume less energy when robot runs at a wide range of speeds comparing to the basic controller.展开更多
The demand for a non-contact biometric approach for candidate identification has grown over the past ten years.Based on the most important biometric application,human gait analysis is a significant research topic in c...The demand for a non-contact biometric approach for candidate identification has grown over the past ten years.Based on the most important biometric application,human gait analysis is a significant research topic in computer vision.Researchers have paid a lot of attention to gait recognition,specifically the identification of people based on their walking patterns,due to its potential to correctly identify people far away.Gait recognition systems have been used in a variety of applications,including security,medical examinations,identity management,and access control.These systems require a complex combination of technical,operational,and definitional considerations.The employment of gait recognition techniques and technologies has produced a number of beneficial and well-liked applications.Thiswork proposes a novel deep learning-based framework for human gait classification in video sequences.This framework’smain challenge is improving the accuracy of accuracy gait classification under varying conditions,such as carrying a bag and changing clothes.The proposed method’s first step is selecting two pre-trained deep learningmodels and training fromscratch using deep transfer learning.Next,deepmodels have been trained using static hyperparameters;however,the learning rate is calculated using the particle swarmoptimization(PSO)algorithm.Then,the best features are selected from both trained models using the Harris Hawks controlled Sine-Cosine optimization algorithm.This algorithm chooses the best features,combined in a novel correlation-based fusion technique.Finally,the fused best features are categorized using medium,bi-layer,and tri-layered neural networks.On the publicly accessible dataset known as the CASIA-B dataset,the experimental process of the suggested technique was carried out,and an improved accuracy of 94.14% was achieved.The achieved accuracy of the proposed method is improved by the recent state-of-the-art techniques that show the significance of this work.展开更多
Objective:To analyze the effects of repetitive transcranial magnetic stimulation combined with motor control training on the treatment of stroke-induced hemiplegia,specifically focusing on the impact on patients’bala...Objective:To analyze the effects of repetitive transcranial magnetic stimulation combined with motor control training on the treatment of stroke-induced hemiplegia,specifically focusing on the impact on patients’balance function and gait.Methods:Fifty-two cases of hemiplegic stroke patients were randomly divided into two groups,26 in the control group and 26 in the observation group,using computer-generated random grouping.All participants underwent conventional treatment and rehabilitation training.In addition to these,the control group received repetitive transcranial magnetic pseudo-stimulation therapy+motor control training,while the observation group received repetitive transcranial magnetic stimulation therapy+motor control training.The balance function and gait parameters of both groups were compared before and after the interventions and assessed the satisfaction of the interventions in both groups.Results:Before the invention,there were no significant differences in balance function scores and each gait parameter between the two groups(P>0.05).However,after the intervention,the observation group showed higher balance function scores compared to the control group(P<0.05).The observation group also exhibited higher step speed and step frequency,longer step length,and a higher overall satisfaction level with the intervention compared to the control group(P<0.05).Conclusion:The combination of repetitive transcranial magnetic stimulation and motor control training in the treatment of stroke-induced hemiplegia has demonstrated positive effects.It not only improves the patient’s balance function and gait but also contributes to overall physical rehabilitation.展开更多
Biometric gait recognition is a lesser-known but emerging and effective biometric recognition method which enables subjects’walking patterns to be recognized.Existing research in this area has primarily focused on fe...Biometric gait recognition is a lesser-known but emerging and effective biometric recognition method which enables subjects’walking patterns to be recognized.Existing research in this area has primarily focused on feature analysis through the extraction of individual features,which captures most of the information but fails to capture subtle variations in gait dynamics.Therefore,a novel feature taxonomy and an approach for deriving a relationship between a function of one set of gait features with another set are introduced.The gait features extracted from body halves divided by anatomical planes on vertical,horizontal,and diagonal axes are grouped to form canonical gait covariates.Canonical Correlation Analysis is utilized to measure the strength of association between the canonical covariates of gait.Thus,gait assessment and identification are enhancedwhenmore semantic information is available through CCA-basedmulti-feature fusion.Hence,CarnegieMellon University’s 3D gait database,which contains 32 gait samples taken at different paces,is utilized in analyzing gait characteristics.The performance of Linear Discriminant Analysis,K-Nearest Neighbors,Naive Bayes,Artificial Neural Networks,and Support Vector Machines was improved by a 4%average when the CCA-utilized gait identification approachwas used.Asignificant maximumaccuracy rate of 97.8%was achieved throughCCA-based gait identification.Beyond that,the rate of false identifications and unrecognized gaits went down to half,demonstrating state-of-the-art for gait identification.展开更多
BACKGROUND Gait is influenced by race,age,and diseases type.Reference values for gait are closely related to numerous health outcomes.To gain a comprehensive understanding of gait patterns,particularly in relation to ...BACKGROUND Gait is influenced by race,age,and diseases type.Reference values for gait are closely related to numerous health outcomes.To gain a comprehensive understanding of gait patterns,particularly in relation to race-related pathologies and disorders,it is crucial to establish reference values for gait in daily life considering sex and age.Therefore,our objective was to present sex and age-based reference values for gait in daily life,providing a valuable foundation for further research and clinical applications.AIM To establish reference values for lower extremity joint kinematics and kinetics during gait in asymptomatic adult women and men.METHODS Spatiotemporal,kinematics and kinetics parameters were measured in 171 healthy adults(70 males and 101 females)using the computer-aided soft tissue foot model.Full curve statistical parametric mapping was performed using independent and paired-samples t-tests.RESULTS Compared with females,males required more time(cycle time,double-limb support time,stance time,swing time,and stride time),and the differences were statistically significant.In addition,the step and stride lengths of males were longer.Compared to males,female cadence was faster,and statures-per-second and stride-per-minute were higher.There were no statistical differences in speed and stride width between the two groups.After adjusting for height,it was observed that women walked significantly faster than men,and they also had a higher cadence.However,in terms of step length,stride length,and stride width,both genders exhibited similarities.CONCLUSION We established reference values for gait speed and spatiotemporal gait parameters in Chinese university students.This contributes to a valuable database for gait assessment and evaluation of preventive or rehabilitative programs.展开更多
Assessment of locomotion recovery in preclinical studies of experimental spinal cord injury remains challenging. We studied the CatWalk XT■gait analysis for evaluating hindlimb functional recovery in a widely used an...Assessment of locomotion recovery in preclinical studies of experimental spinal cord injury remains challenging. We studied the CatWalk XT■gait analysis for evaluating hindlimb functional recovery in a widely used and clinically relevant thoracic contusion/compression spinal cord injury model in rats. Rats were randomly assigned to either a T9 spinal cord injury or sham laminectomy. Locomotion recovery was assessed using the Basso, Beattie, and Bresnahan open field rating scale and the CatWalk XT■gait analysis. To determine the potential bias from weight changes, corrected hindlimb(H) values(divided by the unaffected forelimb(F) values) were calculated. Six weeks after injury, cyst formation, astrogliosis, and the deposition of chondroitin sulfate glycosaminoglycans were assessed by immunohistochemistry staining. Compared with the baseline, a significant spontaneous recovery could be observed in the CatWalk XT■parameters max intensity, mean intensity, max intensity at%, and max contact mean intensity from 4 weeks after injury onwards. Of note, corrected values(H/F) of CatWalk XT■parameters showed a significantly less vulnerability to the weight changes than absolute values, specifically in static parameters. The corrected CatWalk XT■parameters were positively correlated with the Basso, Beattie, and Bresnahan rating scale scores, cyst formation, the immunointensity of astrogliosis and chondroitin sulfate glycosaminoglycan deposition. The CatWalk XT■gait analysis and especially its static parameters, therefore, seem to be highly useful in assessing spontaneous recovery of hindlimb function after severe thoracic spinal cord injury. Because many CatWalk XT■parameters of the hindlimbs seem to be affected by body weight changes, using their corrected values might be a valuable option to improve this dependency.展开更多
Medical research on neurologic ailments requires representative animal models to validate treatments before they are translated to human clinical trials.Rodents are the predominant animal model used in neurological re...Medical research on neurologic ailments requires representative animal models to validate treatments before they are translated to human clinical trials.Rodents are the predominant animal model used in neurological research despite limited anatomic and physiologic similarities to humans.As a result,functional testing designed to assess locomotor recovery after neurologic impairment is well established in rodent models.Comparatively,large r,more clinically relevant models have not been as well studied.To achieve similar locomotor testing standardization in larger animals,the models must be accessible to a wide array of researchers.Non-human primates are the most relevant animal model fo r translational research,however ethical and financial barriers limit their accessibility.This review focuses on swine,sheep,and goats as large animal alternatives for transitional studies between rodents and non-human primates.The objective of this review is to compare motor testing and data collection methods used in swine,sheep,and goats to encourage testing standardization in these larger animal models.The PubMed database was analyzed by searching combinations of swine,sheep,and goats,neurologic injuries,and functional assessments.Findings were categorized by animal model,data collection method,and assessment design.Swine and sheep were used in the majority of the studies,while only two studies were found using goats.The functional assessments included open pen analysis,treadmill walking,and guided free walking.Data collection methods included subjective behavioral rating scales and objective tools such as pressure-sensitive mats and image-based analysis software.Overall,swine and sheep were well-suited for a variety of assessment designs,with treadmill walking and guided free walking offering the most consistency across multiple trials.Data collection methods varied,but image-based gait analysis software provided the most robust analysis.Future studies should be conducted to standardize functional testing methods after neurologic impairment in large animals.展开更多
Assistive lower limb exoskeleton robot has been developed to help paraplegic patients walk again.A gait planning method of this robot must be able to plan a gait based on gait parameters,which can be changed during th...Assistive lower limb exoskeleton robot has been developed to help paraplegic patients walk again.A gait planning method of this robot must be able to plan a gait based on gait parameters,which can be changed during the stride according to human intention or walking conditions.The gait is usually planned in cartesian space,which has shortcomings such as singularities that may occur in inverse kinematics equations,and the angular velocity of the joints cannot be entered into the calculations.Therefore,it is vital to have a gait planning method in the joint space.In this paper,a minimum-time and minimum-jerk planner is proposed for the robot joints.To do so,a third-order system is defined,and the cost function is introduced to minimize the jerk of the joints throughout the stride.The minimum time required is calculated to keep the angular velocity trajectory within the range specified by the motor’s maximum speed.Boundary conditions of the joints are determined to secure backward balance and fulfill gait parameters.Finally,the proposed gait planning method is tested by its implementation on the Exoped®exoskeleton.展开更多
Existing microprocessor-controlled passive prosthetic knees(PaPKs)and active prosthetic knees(AcPKs)cannot truly simulate the muscle activity characteristics of the active–passive hybrid action of the knee during the...Existing microprocessor-controlled passive prosthetic knees(PaPKs)and active prosthetic knees(AcPKs)cannot truly simulate the muscle activity characteristics of the active–passive hybrid action of the knee during the normal gait.Differences in EMG between normal and different prosthetic gait for different phases were never separately analyzed.In this study,a novel hybrid active–passive prosthetic knee(HAPK)is proposed and if and how muscle activity and kinematics changes in different prosthetic gait are analyzed.The hybrid hydraulic-motor actuator is adopted to fully integrate the advantages of hydraulic compliance damping and motor efficiency,and the hierarchical control strategy is adopted to realize the adaptive predictive control of the HAPK.The kinematic data and EMG data of normal gait and different prosthetic gait were compared by experiments,so as to analyze the changes in the muscle activity and spatio-temporal data per phase compared to normal walking and the adaptations of amputees when walking with a different kind of prosthesis(the mechanical prosthesis(MePK),the PaPK and the HAPK).The results show that changes in prosthetic gait mainly consisted of decreased self-selected walking speed,gait symmetry and maximum knee flexion,increased first double support phase duration,muscle activation in both opposed and prosthetic limb and inter-subject variability.The differences between controls and MePK,PaPK and HAPK decreases sequentially.These results indicate that the hybrid active–passive actuating mode can have positive effects on improving the approximation of healthy gait characteristics.展开更多
Ladder climbing is a relatively new but practical locomotion style for robots. Unfortunately, due to their size and weight, ladder climbing by human-sized robots developed so far is struggling with the speedup of ladd...Ladder climbing is a relatively new but practical locomotion style for robots. Unfortunately, due to their size and weight, ladder climbing by human-sized robots developed so far is struggling with the speedup of ladder climbing motion itself. Therefore, in this paper, a new ladder climbing gait for the robot WAREC-1R is proposed by the authors, which is both faster than the former ones and stable. However, to realize such a gait, a point that has to be taken into consideration is the deformation caused by the self-weight of the robot. To deal with this issue, extra hardware (sensor) and software (position and force control) systems and extra time for sensing and calculation were required. For a complete solution without any complicated systems and time only for deformation compensation, limb stiffness improvement plan by the minimal design change of mechanical parts of the robot is also proposed by the authors, with a thorough study about deformation distribution in the robot. With redesigned parts, ladder climbing experiments by WAREC-1R proved that both the new ladder climbing gait and the limb stiffness improvement are successful, and the reduced deformation is very close to the estimated value as well.展开更多
Human gait recognition(HGR)is the process of identifying a sub-ject(human)based on their walking pattern.Each subject is a unique walking pattern and cannot be simulated by other subjects.But,gait recognition is not e...Human gait recognition(HGR)is the process of identifying a sub-ject(human)based on their walking pattern.Each subject is a unique walking pattern and cannot be simulated by other subjects.But,gait recognition is not easy and makes the system difficult if any object is carried by a subject,such as a bag or coat.This article proposes an automated architecture based on deep features optimization for HGR.To our knowledge,it is the first architecture in which features are fused using multiset canonical correlation analysis(MCCA).In the proposed method,original video frames are processed for all 11 selected angles of the CASIA B dataset and utilized to train two fine-tuned deep learning models such as Squeezenet and Efficientnet.Deep transfer learning was used to train both fine-tuned models on selected angles,yielding two new targeted models that were later used for feature engineering.Features are extracted from the deep layer of both fine-tuned models and fused into one vector using MCCA.An improved manta ray foraging optimization algorithm is also proposed to select the best features from the fused feature matrix and classified using a narrow neural network classifier.The experimental process was conducted on all 11 angles of the large multi-view gait dataset(CASIA B)dataset and obtained improved accuracy than the state-of-the-art techniques.Moreover,a detailed confidence interval based analysis also shows the effectiveness of the proposed architecture for HGR.展开更多
Gait refers to a person’s particular movements and stance while moving around.Although each person’s gait is unique and made up of a variety of tiny limb orientations and body positions,they all have common characte...Gait refers to a person’s particular movements and stance while moving around.Although each person’s gait is unique and made up of a variety of tiny limb orientations and body positions,they all have common characteristics that help to define normalcy.Swiftly identifying such characteristics that are difficult to spot by the naked eye,can help in monitoring the elderly who require constant care and support.Analyzing silhouettes is the easiest way to assess and make any necessary adjustments for a smooth gait.It also becomes an important aspect of decision-making while analyzing and monitoring the progress of a patient during medical diagnosis.Gait images made publicly available by the Chinese Academy of Sciences(CASIA)Gait Database was used in this study.After evaluating using the CASIA B and C datasets,this paper proposes a Convolutional Neural Network(CNN)and a CNN Long Short-TermMemory Network(CNN-LSTM)model for classifying the gait silhouette images.Transfer learningmodels such as MobileNetV2,InceptionV3,Visual Geometry Group(VGG)networks such as VGG16 and VGG19,Residual Networks(ResNet)like the ResNet9 and ResNet50,were used to compare the efficacy of the proposed models.CNN proved to be the best by achieving the highest accuracy of 94.29%.This was followed by ResNet9 and CNN-LSTM,which arrived at 93.30%and 87.25%accuracy,respectively.展开更多
Gait recognition is an active research area that uses a walking theme to identify the subject correctly.Human Gait Recognition(HGR)is performed without any cooperation from the individual.However,in practice,it remain...Gait recognition is an active research area that uses a walking theme to identify the subject correctly.Human Gait Recognition(HGR)is performed without any cooperation from the individual.However,in practice,it remains a challenging task under diverse walking sequences due to the covariant factors such as normal walking and walking with wearing a coat.Researchers,over the years,have worked on successfully identifying subjects using different techniques,but there is still room for improvement in accuracy due to these covariant factors.This paper proposes an automated model-free framework for human gait recognition in this article.There are a few critical steps in the proposed method.Firstly,optical flow-based motion region esti-mation and dynamic coordinates-based cropping are performed.The second step involves training a fine-tuned pre-trained MobileNetV2 model on both original and optical flow cropped frames;the training has been conducted using static hyperparameters.The third step proposed a fusion technique known as normal distribution serially fusion.In the fourth step,a better optimization algorithm is applied to select the best features,which are then classified using a Bi-Layered neural network.Three publicly available datasets,CASIA A,CASIA B,and CASIA C,were used in the experimental process and obtained average accuracies of 99.6%,91.6%,and 95.02%,respectively.The proposed framework has achieved improved accuracy compared to the other methods.展开更多
Human Activity Recognition(HAR)has always been a difficult task to tackle.It is mainly used in security surveillance,human-computer interaction,and health care as an assistive or diagnostic technology in combination w...Human Activity Recognition(HAR)has always been a difficult task to tackle.It is mainly used in security surveillance,human-computer interaction,and health care as an assistive or diagnostic technology in combination with other technologies such as the Internet of Things(IoT).Human Activity Recognition data can be recorded with the help of sensors,images,or smartphones.Recognizing daily routine-based human activities such as walking,standing,sitting,etc.,could be a difficult statistical task to classify into categories and hence 2-dimensional Convolutional Neural Network(2D CNN)MODEL,Long Short Term Memory(LSTM)Model,Bidirectional long short-term memory(Bi-LSTM)are used for the classification.It has been demonstrated that recognizing the daily routine-based on human activities can be extremely accurate,with almost all activities accurately getting recognized over 90%of the time.Furthermore,because all the examples are generated from only 20 s of data,these actions can be recognised fast.Apart from classification,the work extended to verify and investigate the need for wearable sensing devices in individually walking patients with Cerebral Palsy(CP)for the evaluation of chosen Spatio-temporal features based on 3D foot trajectory.Case-control research was conducted with 35 persons with CP ranging in weight from 25 to 65 kg.Optical Motion Capture(OMC)equipment was used as the referral method to assess the functionality and quality of the foot-worn device.The average accuracy±precision for stride length,cadence,and step length was 3.5±4.3,4.1±3.8,and 0.6±2.7 cm respectively.For cadence,stride length,swing,and step length,people with CP had considerably high inter-stride variables.Foot-worn sensing devices made it easier to examine Gait Spatio-temporal data even without a laboratory set up with high accuracy and precision about gait abnormalities in people who have CP during linear walking.展开更多
Gait speed is a valid measure of both physical function and vestibular health.Vestibular rehabilitation is useful to improve gait speed for patients with vestibular hypofunction,yet there is little data to indicate ho...Gait speed is a valid measure of both physical function and vestibular health.Vestibular rehabilitation is useful to improve gait speed for patients with vestibular hypofunction,yet there is little data to indicate how changes in gait speed reflect changes in patient-reported health outcomes.We determined the minimal clinically important difference in the gait speed of patients with unilateral vestibular hypofunction,mostly due to deafferentation surgery,as anchored to the Dizziness Handicap Index and the Activities Balance Confidence scale,validated using regression analysis,change difference,receiveroperator characteristic curve,and average change methods.After six weeks of vestibular rehabilitation,a change in gait speed from 0.20 to 0.34 m/s with 95%confidence was required for the patients to perceive a significant reduction in perception of dizziness and improved balance confidence.展开更多
Human biometric analysis has gotten much attention due to itswidespread use in different research areas, such as security, surveillance,health, human identification, and classification. Human gait is one of the keyhum...Human biometric analysis has gotten much attention due to itswidespread use in different research areas, such as security, surveillance,health, human identification, and classification. Human gait is one of the keyhuman traits that can identify and classify humans based on their age, gender,and ethnicity. Different approaches have been proposed for the estimation ofhuman age based on gait so far. However, challenges are there, for which anefficient, low-cost technique or algorithm is needed. In this paper, we proposea three-dimensional real-time gait-based age detection system using a machinelearning approach. The proposed system consists of training and testingphases. The proposed training phase consists of gait features extraction usingthe Microsoft Kinect (MS Kinect) controller, dataset generation based onjoints’ position, pre-processing of gait features, feature selection by calculatingthe Standard error and Standard deviation of the arithmetic mean and bestmodel selection using R2 and adjusted R2 techniques. T-test and ANOVAtechniques show that nine joints (right shoulder, right elbow, right hand, leftknee, right knee, right ankle, left ankle, left, and right foot) are statisticallysignificant at a 5% level of significance for age estimation. The proposedtesting phase correctly predicts the age of a walking person using the resultsobtained from the training phase. The proposed approach is evaluated on thedata that is experimentally recorded from the user in a real-time scenario.Fifty (50) volunteers of different ages participated in the experimental study.Using the limited features, the proposed method estimates the age with 98.0%accuracy on experimental images acquired in real-time via a classical generallinear regression model.展开更多
Human personality assessment using gait pattern recognition is one of the most recent and exciting research domains.Gait is a person’s identity that can reflect reliable information about his mood,emotions,and substa...Human personality assessment using gait pattern recognition is one of the most recent and exciting research domains.Gait is a person’s identity that can reflect reliable information about his mood,emotions,and substantial personality traits under scrutiny.This research focuses on recognizing key personality traits,including neuroticism,extraversion,openness to experience,agreeableness,and conscientiousness,in line with the bigfive model of personality.We inferred personality traits based on the gait pattern recognition of individuals utilizing built-in smartphone sensors.For experimentation,we collected a novel dataset of 22 participants using an android application and further segmented it into six data chunks for a critical evaluation.After data pre-processing,we extracted selected features from each data segment and then applied four multiclass machine learning algorithms for training and classifying the dataset corresponding to the users’Big-Five Personality Traits Profiles(BFPT).Experimental results and performance evaluation of the classifiers revealed the efficacy of the proposed scheme for all big-five traits.展开更多
Gait is a biological typical that defines the method by that people walk.Walking is the most significant performance which keeps our day-to-day life and physical condition.Surface electromyography(sEMG)is a weak bioel...Gait is a biological typical that defines the method by that people walk.Walking is the most significant performance which keeps our day-to-day life and physical condition.Surface electromyography(sEMG)is a weak bioelectric signal that portrays the functional state between the human muscles and nervous system to any extent.Gait classifiers dependent upon sEMG signals are extremely utilized in analysing muscle diseases and as a guide path for recovery treatment.Several approaches are established in the works for gait recognition utilizing conventional and deep learning(DL)approaches.This study designs an Enhanced Artificial Algae Algorithm with Hybrid Deep Learning based Human Gait Classification(EAAA-HDLGR)technique on sEMG signals.The EAAA-HDLGR technique extracts the time domain(TD)and frequency domain(FD)features from the sEMG signals and is fused.In addition,the EAAA-HDLGR technique exploits the hybrid deep learning(HDL)model for gait recognition.At last,an EAAA-based hyperparameter optimizer is applied for the HDL model,which is mainly derived from the quasi-oppositional based learning(QOBL)concept,showing the novelty of the work.A brief classifier outcome of the EAAA-HDLGR technique is examined under diverse aspects,and the results indicate improving the EAAA-HDLGR technique.The results imply that the EAAA-HDLGR technique accomplishes improved results with the inclusion of EAAA on gait recognition.展开更多
基金supported in part by the National Key Research and Development Program of China[Grant No.2020AAA0108900]the National Natural Science Foundation of China[No.91948201,62003190,62203268,61973185]+1 种基金the Open Research Projects of Zhejiang Lab(No.2022NB0AB06)the National Natural Science Foundation of Shandong Province of China[No.ZR2022QF027].
文摘Quadruped animals in the nature realize high energy efficiency locomotion by automatically changing their gait at different speeds.Inspired by this character,an efficient adaptive diagonal gait locomotion controller is designed for quadruped robot.A unique gait planning method is proposed in this paper.As the speed of robot varies,the gait cycle time and the proportion of stance and swing phase of each leg are adjusted to form a variety of gaits.The optimal joint torque is calculated by the controller combined with Virtual Model Control(VMC)and Whole-Body Control(WBC)to realize the desired motion.The gait and step frequency of the robot can automatically adapt to the change of speed.Several experiments are done with a quadruped robot made by our laboratory to verify that the gait can change automatically from slow-trotting to flying-trot during the period when speed is from 0 to 4 m/s.The ratio of swing phase is from less than 0.5 to more than 0.5 to realize the running motion with four feet off the ground.Experiments have shown that the controller can indeed consume less energy when robot runs at a wide range of speeds comparing to the basic controller.
基金supported by the“Human Resources Program in Energy Technol-ogy”of the Korea Institute of Energy Technology Evaluation and Planning(KETEP)and Granted Financial Resources from the Ministry of Trade,Industry,and Energy,Republic of Korea(No.20204010600090)The funding of this work was provided by Princess Nourah bint Abdulrahman University Researchers Supporting Project Number(PNURSP2023R410),Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia.
文摘The demand for a non-contact biometric approach for candidate identification has grown over the past ten years.Based on the most important biometric application,human gait analysis is a significant research topic in computer vision.Researchers have paid a lot of attention to gait recognition,specifically the identification of people based on their walking patterns,due to its potential to correctly identify people far away.Gait recognition systems have been used in a variety of applications,including security,medical examinations,identity management,and access control.These systems require a complex combination of technical,operational,and definitional considerations.The employment of gait recognition techniques and technologies has produced a number of beneficial and well-liked applications.Thiswork proposes a novel deep learning-based framework for human gait classification in video sequences.This framework’smain challenge is improving the accuracy of accuracy gait classification under varying conditions,such as carrying a bag and changing clothes.The proposed method’s first step is selecting two pre-trained deep learningmodels and training fromscratch using deep transfer learning.Next,deepmodels have been trained using static hyperparameters;however,the learning rate is calculated using the particle swarmoptimization(PSO)algorithm.Then,the best features are selected from both trained models using the Harris Hawks controlled Sine-Cosine optimization algorithm.This algorithm chooses the best features,combined in a novel correlation-based fusion technique.Finally,the fused best features are categorized using medium,bi-layer,and tri-layered neural networks.On the publicly accessible dataset known as the CASIA-B dataset,the experimental process of the suggested technique was carried out,and an improved accuracy of 94.14% was achieved.The achieved accuracy of the proposed method is improved by the recent state-of-the-art techniques that show the significance of this work.
文摘Objective:To analyze the effects of repetitive transcranial magnetic stimulation combined with motor control training on the treatment of stroke-induced hemiplegia,specifically focusing on the impact on patients’balance function and gait.Methods:Fifty-two cases of hemiplegic stroke patients were randomly divided into two groups,26 in the control group and 26 in the observation group,using computer-generated random grouping.All participants underwent conventional treatment and rehabilitation training.In addition to these,the control group received repetitive transcranial magnetic pseudo-stimulation therapy+motor control training,while the observation group received repetitive transcranial magnetic stimulation therapy+motor control training.The balance function and gait parameters of both groups were compared before and after the interventions and assessed the satisfaction of the interventions in both groups.Results:Before the invention,there were no significant differences in balance function scores and each gait parameter between the two groups(P>0.05).However,after the intervention,the observation group showed higher balance function scores compared to the control group(P<0.05).The observation group also exhibited higher step speed and step frequency,longer step length,and a higher overall satisfaction level with the intervention compared to the control group(P<0.05).Conclusion:The combination of repetitive transcranial magnetic stimulation and motor control training in the treatment of stroke-induced hemiplegia has demonstrated positive effects.It not only improves the patient’s balance function and gait but also contributes to overall physical rehabilitation.
基金supported by Istanbul University Scientific Research Project Department with IRP-51706 Project Number.
文摘Biometric gait recognition is a lesser-known but emerging and effective biometric recognition method which enables subjects’walking patterns to be recognized.Existing research in this area has primarily focused on feature analysis through the extraction of individual features,which captures most of the information but fails to capture subtle variations in gait dynamics.Therefore,a novel feature taxonomy and an approach for deriving a relationship between a function of one set of gait features with another set are introduced.The gait features extracted from body halves divided by anatomical planes on vertical,horizontal,and diagonal axes are grouped to form canonical gait covariates.Canonical Correlation Analysis is utilized to measure the strength of association between the canonical covariates of gait.Thus,gait assessment and identification are enhancedwhenmore semantic information is available through CCA-basedmulti-feature fusion.Hence,CarnegieMellon University’s 3D gait database,which contains 32 gait samples taken at different paces,is utilized in analyzing gait characteristics.The performance of Linear Discriminant Analysis,K-Nearest Neighbors,Naive Bayes,Artificial Neural Networks,and Support Vector Machines was improved by a 4%average when the CCA-utilized gait identification approachwas used.Asignificant maximumaccuracy rate of 97.8%was achieved throughCCA-based gait identification.Beyond that,the rate of false identifications and unrecognized gaits went down to half,demonstrating state-of-the-art for gait identification.
基金Supported by Major Project of the Co-construction Science and Technology Program between the Science and Technology Department of the National Administration of Traditional Chinese Medicine and the Zhejiang Administration of Traditional Chinese Medicine,No.GZY-ZJ-KJ-23040Zhejiang Medical and Health Science and Technology Project,No.2022497035+2 种基金Quzhou City Science and Technology Project,No.2022K75Zhejiang Chinese Medical University Scientific Research Fund Project,No.2021FSYYZZ09,No.2021FSYYZZ14The study was reviewed and approved by the Department of Orthopedics,The First Affiliated Hospital of Zhejiang Chinese Medical University(Zhejiang Provincial Hospital of Traditional Chinese Medicine)Institutional Review Board[Approval No.2023-K-162-01].
文摘BACKGROUND Gait is influenced by race,age,and diseases type.Reference values for gait are closely related to numerous health outcomes.To gain a comprehensive understanding of gait patterns,particularly in relation to race-related pathologies and disorders,it is crucial to establish reference values for gait in daily life considering sex and age.Therefore,our objective was to present sex and age-based reference values for gait in daily life,providing a valuable foundation for further research and clinical applications.AIM To establish reference values for lower extremity joint kinematics and kinetics during gait in asymptomatic adult women and men.METHODS Spatiotemporal,kinematics and kinetics parameters were measured in 171 healthy adults(70 males and 101 females)using the computer-aided soft tissue foot model.Full curve statistical parametric mapping was performed using independent and paired-samples t-tests.RESULTS Compared with females,males required more time(cycle time,double-limb support time,stance time,swing time,and stride time),and the differences were statistically significant.In addition,the step and stride lengths of males were longer.Compared to males,female cadence was faster,and statures-per-second and stride-per-minute were higher.There were no statistical differences in speed and stride width between the two groups.After adjusting for height,it was observed that women walked significantly faster than men,and they also had a higher cadence.However,in terms of step length,stride length,and stride width,both genders exhibited similarities.CONCLUSION We established reference values for gait speed and spatiotemporal gait parameters in Chinese university students.This contributes to a valuable database for gait assessment and evaluation of preventive or rehabilitative programs.
文摘Assessment of locomotion recovery in preclinical studies of experimental spinal cord injury remains challenging. We studied the CatWalk XT■gait analysis for evaluating hindlimb functional recovery in a widely used and clinically relevant thoracic contusion/compression spinal cord injury model in rats. Rats were randomly assigned to either a T9 spinal cord injury or sham laminectomy. Locomotion recovery was assessed using the Basso, Beattie, and Bresnahan open field rating scale and the CatWalk XT■gait analysis. To determine the potential bias from weight changes, corrected hindlimb(H) values(divided by the unaffected forelimb(F) values) were calculated. Six weeks after injury, cyst formation, astrogliosis, and the deposition of chondroitin sulfate glycosaminoglycans were assessed by immunohistochemistry staining. Compared with the baseline, a significant spontaneous recovery could be observed in the CatWalk XT■parameters max intensity, mean intensity, max intensity at%, and max contact mean intensity from 4 weeks after injury onwards. Of note, corrected values(H/F) of CatWalk XT■parameters showed a significantly less vulnerability to the weight changes than absolute values, specifically in static parameters. The corrected CatWalk XT■parameters were positively correlated with the Basso, Beattie, and Bresnahan rating scale scores, cyst formation, the immunointensity of astrogliosis and chondroitin sulfate glycosaminoglycan deposition. The CatWalk XT■gait analysis and especially its static parameters, therefore, seem to be highly useful in assessing spontaneous recovery of hindlimb function after severe thoracic spinal cord injury. Because many CatWalk XT■parameters of the hindlimbs seem to be affected by body weight changes, using their corrected values might be a valuable option to improve this dependency.
文摘Medical research on neurologic ailments requires representative animal models to validate treatments before they are translated to human clinical trials.Rodents are the predominant animal model used in neurological research despite limited anatomic and physiologic similarities to humans.As a result,functional testing designed to assess locomotor recovery after neurologic impairment is well established in rodent models.Comparatively,large r,more clinically relevant models have not been as well studied.To achieve similar locomotor testing standardization in larger animals,the models must be accessible to a wide array of researchers.Non-human primates are the most relevant animal model fo r translational research,however ethical and financial barriers limit their accessibility.This review focuses on swine,sheep,and goats as large animal alternatives for transitional studies between rodents and non-human primates.The objective of this review is to compare motor testing and data collection methods used in swine,sheep,and goats to encourage testing standardization in these larger animal models.The PubMed database was analyzed by searching combinations of swine,sheep,and goats,neurologic injuries,and functional assessments.Findings were categorized by animal model,data collection method,and assessment design.Swine and sheep were used in the majority of the studies,while only two studies were found using goats.The functional assessments included open pen analysis,treadmill walking,and guided free walking.Data collection methods included subjective behavioral rating scales and objective tools such as pressure-sensitive mats and image-based analysis software.Overall,swine and sheep were well-suited for a variety of assessment designs,with treadmill walking and guided free walking offering the most consistency across multiple trials.Data collection methods varied,but image-based gait analysis software provided the most robust analysis.Future studies should be conducted to standardize functional testing methods after neurologic impairment in large animals.
文摘Assistive lower limb exoskeleton robot has been developed to help paraplegic patients walk again.A gait planning method of this robot must be able to plan a gait based on gait parameters,which can be changed during the stride according to human intention or walking conditions.The gait is usually planned in cartesian space,which has shortcomings such as singularities that may occur in inverse kinematics equations,and the angular velocity of the joints cannot be entered into the calculations.Therefore,it is vital to have a gait planning method in the joint space.In this paper,a minimum-time and minimum-jerk planner is proposed for the robot joints.To do so,a third-order system is defined,and the cost function is introduced to minimize the jerk of the joints throughout the stride.The minimum time required is calculated to keep the angular velocity trajectory within the range specified by the motor’s maximum speed.Boundary conditions of the joints are determined to secure backward balance and fulfill gait parameters.Finally,the proposed gait planning method is tested by its implementation on the Exoped®exoskeleton.
基金supported in part by the National Natural Science Foundation of China under Grant 62073224the National Key Research and Development Program of China under Grant 2018YFB1307303the program of China Scholarships Council under Grant 202108310200.
文摘Existing microprocessor-controlled passive prosthetic knees(PaPKs)and active prosthetic knees(AcPKs)cannot truly simulate the muscle activity characteristics of the active–passive hybrid action of the knee during the normal gait.Differences in EMG between normal and different prosthetic gait for different phases were never separately analyzed.In this study,a novel hybrid active–passive prosthetic knee(HAPK)is proposed and if and how muscle activity and kinematics changes in different prosthetic gait are analyzed.The hybrid hydraulic-motor actuator is adopted to fully integrate the advantages of hydraulic compliance damping and motor efficiency,and the hierarchical control strategy is adopted to realize the adaptive predictive control of the HAPK.The kinematic data and EMG data of normal gait and different prosthetic gait were compared by experiments,so as to analyze the changes in the muscle activity and spatio-temporal data per phase compared to normal walking and the adaptations of amputees when walking with a different kind of prosthesis(the mechanical prosthesis(MePK),the PaPK and the HAPK).The results show that changes in prosthetic gait mainly consisted of decreased self-selected walking speed,gait symmetry and maximum knee flexion,increased first double support phase duration,muscle activation in both opposed and prosthetic limb and inter-subject variability.The differences between controls and MePK,PaPK and HAPK decreases sequentially.These results indicate that the hybrid active–passive actuating mode can have positive effects on improving the approximation of healthy gait characteristics.
文摘Ladder climbing is a relatively new but practical locomotion style for robots. Unfortunately, due to their size and weight, ladder climbing by human-sized robots developed so far is struggling with the speedup of ladder climbing motion itself. Therefore, in this paper, a new ladder climbing gait for the robot WAREC-1R is proposed by the authors, which is both faster than the former ones and stable. However, to realize such a gait, a point that has to be taken into consideration is the deformation caused by the self-weight of the robot. To deal with this issue, extra hardware (sensor) and software (position and force control) systems and extra time for sensing and calculation were required. For a complete solution without any complicated systems and time only for deformation compensation, limb stiffness improvement plan by the minimal design change of mechanical parts of the robot is also proposed by the authors, with a thorough study about deformation distribution in the robot. With redesigned parts, ladder climbing experiments by WAREC-1R proved that both the new ladder climbing gait and the limb stiffness improvement are successful, and the reduced deformation is very close to the estimated value as well.
基金supported by the MSIT(Ministry of Science and ICT),Korea,under the ICAN(ICT Challenge and Advanced Network of HRD)program(IITP-2022-2020-0-01832)supervised by the IITP(Institute of Information&Communications Technology Planning&Evaluation)and the Soonchunhyang University Research Fund.
文摘Human gait recognition(HGR)is the process of identifying a sub-ject(human)based on their walking pattern.Each subject is a unique walking pattern and cannot be simulated by other subjects.But,gait recognition is not easy and makes the system difficult if any object is carried by a subject,such as a bag or coat.This article proposes an automated architecture based on deep features optimization for HGR.To our knowledge,it is the first architecture in which features are fused using multiset canonical correlation analysis(MCCA).In the proposed method,original video frames are processed for all 11 selected angles of the CASIA B dataset and utilized to train two fine-tuned deep learning models such as Squeezenet and Efficientnet.Deep transfer learning was used to train both fine-tuned models on selected angles,yielding two new targeted models that were later used for feature engineering.Features are extracted from the deep layer of both fine-tuned models and fused into one vector using MCCA.An improved manta ray foraging optimization algorithm is also proposed to select the best features from the fused feature matrix and classified using a narrow neural network classifier.The experimental process was conducted on all 11 angles of the large multi-view gait dataset(CASIA B)dataset and obtained improved accuracy than the state-of-the-art techniques.Moreover,a detailed confidence interval based analysis also shows the effectiveness of the proposed architecture for HGR.
文摘Gait refers to a person’s particular movements and stance while moving around.Although each person’s gait is unique and made up of a variety of tiny limb orientations and body positions,they all have common characteristics that help to define normalcy.Swiftly identifying such characteristics that are difficult to spot by the naked eye,can help in monitoring the elderly who require constant care and support.Analyzing silhouettes is the easiest way to assess and make any necessary adjustments for a smooth gait.It also becomes an important aspect of decision-making while analyzing and monitoring the progress of a patient during medical diagnosis.Gait images made publicly available by the Chinese Academy of Sciences(CASIA)Gait Database was used in this study.After evaluating using the CASIA B and C datasets,this paper proposes a Convolutional Neural Network(CNN)and a CNN Long Short-TermMemory Network(CNN-LSTM)model for classifying the gait silhouette images.Transfer learningmodels such as MobileNetV2,InceptionV3,Visual Geometry Group(VGG)networks such as VGG16 and VGG19,Residual Networks(ResNet)like the ResNet9 and ResNet50,were used to compare the efficacy of the proposed models.CNN proved to be the best by achieving the highest accuracy of 94.29%.This was followed by ResNet9 and CNN-LSTM,which arrived at 93.30%and 87.25%accuracy,respectively.
基金supported by“Human Resources Program in Energy Technology”of the Korea Institute of Energy Technology Evaluation and Planning(KETEP)granted financial resources from the Ministry of Trade,Industry&Energy,Republic of Korea.(No.20204010600090).
文摘Gait recognition is an active research area that uses a walking theme to identify the subject correctly.Human Gait Recognition(HGR)is performed without any cooperation from the individual.However,in practice,it remains a challenging task under diverse walking sequences due to the covariant factors such as normal walking and walking with wearing a coat.Researchers,over the years,have worked on successfully identifying subjects using different techniques,but there is still room for improvement in accuracy due to these covariant factors.This paper proposes an automated model-free framework for human gait recognition in this article.There are a few critical steps in the proposed method.Firstly,optical flow-based motion region esti-mation and dynamic coordinates-based cropping are performed.The second step involves training a fine-tuned pre-trained MobileNetV2 model on both original and optical flow cropped frames;the training has been conducted using static hyperparameters.The third step proposed a fusion technique known as normal distribution serially fusion.In the fourth step,a better optimization algorithm is applied to select the best features,which are then classified using a Bi-Layered neural network.Three publicly available datasets,CASIA A,CASIA B,and CASIA C,were used in the experimental process and obtained average accuracies of 99.6%,91.6%,and 95.02%,respectively.The proposed framework has achieved improved accuracy compared to the other methods.
文摘Human Activity Recognition(HAR)has always been a difficult task to tackle.It is mainly used in security surveillance,human-computer interaction,and health care as an assistive or diagnostic technology in combination with other technologies such as the Internet of Things(IoT).Human Activity Recognition data can be recorded with the help of sensors,images,or smartphones.Recognizing daily routine-based human activities such as walking,standing,sitting,etc.,could be a difficult statistical task to classify into categories and hence 2-dimensional Convolutional Neural Network(2D CNN)MODEL,Long Short Term Memory(LSTM)Model,Bidirectional long short-term memory(Bi-LSTM)are used for the classification.It has been demonstrated that recognizing the daily routine-based on human activities can be extremely accurate,with almost all activities accurately getting recognized over 90%of the time.Furthermore,because all the examples are generated from only 20 s of data,these actions can be recognised fast.Apart from classification,the work extended to verify and investigate the need for wearable sensing devices in individually walking patients with Cerebral Palsy(CP)for the evaluation of chosen Spatio-temporal features based on 3D foot trajectory.Case-control research was conducted with 35 persons with CP ranging in weight from 25 to 65 kg.Optical Motion Capture(OMC)equipment was used as the referral method to assess the functionality and quality of the foot-worn device.The average accuracy±precision for stride length,cadence,and step length was 3.5±4.3,4.1±3.8,and 0.6±2.7 cm respectively.For cadence,stride length,swing,and step length,people with CP had considerably high inter-stride variables.Foot-worn sensing devices made it easier to examine Gait Spatio-temporal data even without a laboratory set up with high accuracy and precision about gait abnormalities in people who have CP during linear walking.
基金Michael C Schubert was funded by the Department of Defense under the Neurosensory and Rehabilitation Research Award Program (Grant award#W81XWH-15-1-0442)Lee Dibble was funded by the Telemedicine and Advanced Technology Research Center(TATRC) through the Army Medical Department Advanced Medical Technology Initiative (AAMTI)Brian J.Loyd was supported in part by the Foundation for Physical Therapy Research New Investigator Fellowship Training Initiative (NIFTI).
文摘Gait speed is a valid measure of both physical function and vestibular health.Vestibular rehabilitation is useful to improve gait speed for patients with vestibular hypofunction,yet there is little data to indicate how changes in gait speed reflect changes in patient-reported health outcomes.We determined the minimal clinically important difference in the gait speed of patients with unilateral vestibular hypofunction,mostly due to deafferentation surgery,as anchored to the Dizziness Handicap Index and the Activities Balance Confidence scale,validated using regression analysis,change difference,receiveroperator characteristic curve,and average change methods.After six weeks of vestibular rehabilitation,a change in gait speed from 0.20 to 0.34 m/s with 95%confidence was required for the patients to perceive a significant reduction in perception of dizziness and improved balance confidence.
基金The authors extend their appreciation to the Deanship of Scientific Research at King Khalid University for funding this work through Large Groups RGP.2/212/1443.
文摘Human biometric analysis has gotten much attention due to itswidespread use in different research areas, such as security, surveillance,health, human identification, and classification. Human gait is one of the keyhuman traits that can identify and classify humans based on their age, gender,and ethnicity. Different approaches have been proposed for the estimation ofhuman age based on gait so far. However, challenges are there, for which anefficient, low-cost technique or algorithm is needed. In this paper, we proposea three-dimensional real-time gait-based age detection system using a machinelearning approach. The proposed system consists of training and testingphases. The proposed training phase consists of gait features extraction usingthe Microsoft Kinect (MS Kinect) controller, dataset generation based onjoints’ position, pre-processing of gait features, feature selection by calculatingthe Standard error and Standard deviation of the arithmetic mean and bestmodel selection using R2 and adjusted R2 techniques. T-test and ANOVAtechniques show that nine joints (right shoulder, right elbow, right hand, leftknee, right knee, right ankle, left ankle, left, and right foot) are statisticallysignificant at a 5% level of significance for age estimation. The proposedtesting phase correctly predicts the age of a walking person using the resultsobtained from the training phase. The proposed approach is evaluated on thedata that is experimentally recorded from the user in a real-time scenario.Fifty (50) volunteers of different ages participated in the experimental study.Using the limited features, the proposed method estimates the age with 98.0%accuracy on experimental images acquired in real-time via a classical generallinear regression model.
基金This research was supported by a grant from the Korea Health Technology R&D Project through the Korea Health Industry Development Institute(KHIDI),funded by the Ministry of Health&Welfare,Republic of Korea(grant number:HI21C1831)the Soonchunhyang University Research Fund.
文摘Human personality assessment using gait pattern recognition is one of the most recent and exciting research domains.Gait is a person’s identity that can reflect reliable information about his mood,emotions,and substantial personality traits under scrutiny.This research focuses on recognizing key personality traits,including neuroticism,extraversion,openness to experience,agreeableness,and conscientiousness,in line with the bigfive model of personality.We inferred personality traits based on the gait pattern recognition of individuals utilizing built-in smartphone sensors.For experimentation,we collected a novel dataset of 22 participants using an android application and further segmented it into six data chunks for a critical evaluation.After data pre-processing,we extracted selected features from each data segment and then applied four multiclass machine learning algorithms for training and classifying the dataset corresponding to the users’Big-Five Personality Traits Profiles(BFPT).Experimental results and performance evaluation of the classifiers revealed the efficacy of the proposed scheme for all big-five traits.
基金supported by a grant from the Korea Health Technology R&D Project through the KoreaHealth Industry Development Institute (KHIDI)funded by the Ministry of Health&Welfare,Republic of Korea (grant number:HI21C1831)the Soonchunhyang University Research Fund.
文摘Gait is a biological typical that defines the method by that people walk.Walking is the most significant performance which keeps our day-to-day life and physical condition.Surface electromyography(sEMG)is a weak bioelectric signal that portrays the functional state between the human muscles and nervous system to any extent.Gait classifiers dependent upon sEMG signals are extremely utilized in analysing muscle diseases and as a guide path for recovery treatment.Several approaches are established in the works for gait recognition utilizing conventional and deep learning(DL)approaches.This study designs an Enhanced Artificial Algae Algorithm with Hybrid Deep Learning based Human Gait Classification(EAAA-HDLGR)technique on sEMG signals.The EAAA-HDLGR technique extracts the time domain(TD)and frequency domain(FD)features from the sEMG signals and is fused.In addition,the EAAA-HDLGR technique exploits the hybrid deep learning(HDL)model for gait recognition.At last,an EAAA-based hyperparameter optimizer is applied for the HDL model,which is mainly derived from the quasi-oppositional based learning(QOBL)concept,showing the novelty of the work.A brief classifier outcome of the EAAA-HDLGR technique is examined under diverse aspects,and the results indicate improving the EAAA-HDLGR technique.The results imply that the EAAA-HDLGR technique accomplishes improved results with the inclusion of EAAA on gait recognition.
