Human Gait Analysis Research Papers (original) (raw)

2025, University of Essex

Introduction: Various tools exist to analyse human locomotion, with optical systems being the most widely used due to their high accuracy and reliability. Marker-based motion capture (MBMC) systems, though considered a gold standard, require complex setups with multiple cameras. To overcome these limitations, researchers have explored single-camera, markerless approaches using Human Pose Estimation (HPE), which estimates joint coordinates and body segment orientations from 2D images. While HPE has advanced significantly, its application using single-camera systems for lower-limb analysis in healthcare remains limited.
Methods: One healthy male walked over a 7 (m) walkway at a self-selected speed. Institutional ethics approval was obtained (ID: ETH2425-0307). Full-body kinematics were captured using Theia3D with eight RGB Sony RX0 II cameras (120 Hz), arranged radially 3 (m) from the center at 1.5 (m) height. For 2D analysis, one of the Sony cameras was placed perpendicular to the walkway at 0.8 (m) height. Joint positions (hip, knee, ankle) were extracted per frame using OpenPose, PoseFormerV2, and manual digitization (Kinovea), then used to compute sagittal-plane knee angles for one gait cycle (left leg occluded, right leg visible). Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) were calculated against Theia3D ground truth and compared with published benchmarks.
Results: For the occluded left leg, OpenPose yielded 7.97° RMSE and 6.75° MAE, improving to 5.09° RMSE and 4.47° MAE for the fully visible right leg. PoseFormerV2 performed better, with 6.14° RMSE and 4.79° MAE for the occluded left leg and 4.11° RMSE and 3.61° MAE for the visible right leg. In contrast, Kinovea manual digitization showed significantly higher errors (left/occluded: 25.58° RMSE, 18.80° MAE; right/visible: 26.38° RMSE, 20.05° MAE).
Discussion: RGB single-camera markerless analysis yields clinically valid occluded and visible knee-flexion angles during overground gait. Future work should examine the applicability of these methods in real-world settings across varied speeds and tasks.

2025, Intelligence Science III

Human activity recognition (HAR) plays an important role in every spheres of life as it assists in fitness tracking, health monitoring, elderly care, user authentication and management of smart homes. The assistive applications can be implemented on smartphones and wearable watches which are easily accessible and affordable. Now-a-days use of smart phones is ubiquitous, sensor data of diverse physical activities can be easily collected by in-built motion sensors. Many research works are proposed in this area using machine learning techniques including deep neural networks to develop smartphone based applications for human activity recognition. Our objective is to find an effective method from a variety of machine learning including deep learning models for low cost as well as high accuracy activity recognition. To fulfill the objective, a comparative performance study has been done in this work by simulation experiments on five publicly available bench mark data sets. The simulation results show that deep learning models, especially, 2D CNN and BI GRU can be promising candidates for developing smartphone based applications using motion sensor data.

2025, International Journal of Novel Research and Development, IJNRD,

A situation occurs when the robot intentionally makes the transition from walking to stopping To stop the robot the step length can be adjusted and can be accelerated backwards by lunging forward. Using this strategy results in the Humanoid having to take less steps in order to come to a stop. Humanoid robots movement without lying down in ground is of major importance This thesis focuses on the hip-ankle strategy as a method to maintain balance when subjected to a large disturbance. This strategy is characterised by a large rotation of the hip joint which repositions the Centre of Mass (CoM) with the cognition of Convolutional Neural Network CNN incorporated in the adversarial large learning model.

2025, Sports

This systematic overview aimed to review studies investigating the benefits and risks of judo training in older people, and to explore practical methodological applications (Registration ID: CRD42021274825). Searches of EBSCOhost, ISI-WoS, and Scopus databases, with no time restriction up to December 2022, resulted in 23 records meeting the inclusion criteria. A quality assessment was performed through the following tools: ROBINS-I for 10 experimental studies, NIH for 7 observational studies, and AGREE-II for 6 methodological studies. A serious risk of bias emerged for 70% of the experimental studies, whereas 100% of the observational and 67% of the methodological studies presented a “fair” quality. When involving 1392 participants (63 ± 12 years; females: 47%), the studies investigated novice (n = 13), amateur/intermediate (n = 4), expert (n = 4), and unknown (n = 3) level judoka by means of device-based, self-reported, and visual evaluation measures. Mean training encompassed 2 ± ...

2025, Mathématiques méthodiques Tronc Commun scientifique

Cette édition de votre Collection Méthodos, est certes chargée de contenus informatifs et didactiques nécessaires en matière des mathématiques à le Tronc Commun scientifique (2nd en France), mais elle est à même de vous fournir un outil... more

2025

The treatment of the patient with the right Sacroiliac Joint Koch`s. The condition is rare and less documented on the Indian population. The patient had severe pain and postural impairment. It was observed that activities of daily living (ADL) were badly affected. Hence this study is done to assess the effect of mirror therapy in pain management, postural correction, and activities of daily living in the patient with SI joint Koch`s. The patient was diagnosed using MRI, X-ray and hematological assessment. Skin traction and antitubercular treatment along with painkillers were started. The patient is referred to Occupational Therapy Services on 11/10/2017. On clinical evaluation FABER, GEANSLENS and Thomas test found positive. Pain on VAS found 8 i.e. severe pain with Grade 2 of tenderness (tenderness to grimace or flinch to palpation) over right SI joint and posterior aspect of buttock and ADL scoring on Modified Barthel Index is 9 i.e. lowermost indicates disabilities on the first...

2025, Multimedia Tools and Applications

The classification of humanoid locomotion is a troublesome exercise because of nonlinearity associate with gait signals. The classification using the different machine learning technique leads for over fitting and under fitting. To select the optimized feature is a difficult task. The high dimension feature vector requires a high computational cost. The hand craft feature selection machine learning techniques performed poor. We have used the incremental feature selection strategy for feature selection. In this paper we first selected the feature and identify the principle feature then we classify gait data using different machine learning technique (KNN, ANN, SVM, DNN and classifier fusion) and shown the performance comparison. Experimental result on real time datasets propose method is better than previous method as far as humanoid locomotion classification is concerned and the generalization accuracy provided by new feature selection method i.e. incremental feature selection (IFS) with analysis of variance (ANOVA) (Zhang et al.,. During the feature extraction, 17 features were selected from the existing literatures . Using all the features could lead to over fitting, information redundancy and dimension disaster. Thus, a system with optimal features was selected using ANOVA combined with IFA. These selected features were then fed as an input to the ANN, SVM, KNN and DNN model. These individual classifiers were combined to produce classifier fusion model. The 5-fold cross-validation was used to evaluate the performance of the proposed model. Based on the empirical results it may be concluded that classifier fusion provides satisfactory results (92.23 %) compared to other individual classifiers. One-way analysis of variance test, Friedman's test and Kruskal-Wallis test has also been conducted Multimed Tools Appl

2025, Engineering review

A general second-order low-pass OTA-C filter section is analyzed. Voltage noise spectral density and Schoeffler sensitivity are calculated. The design of the filter is performed in two ways, one based on simplicity of calculating filter elements and the other based on optimization. Optimization is done to decrease observed parameters: noise and sensitivity. The analyses results give a filter that gives lower sensitivity and noise. The optimization procedure is done for the fourth-order low-pass filter, as well. It is shown that decreasing one of the two parameters increases the other and a compromise has to be made in designing filter elements.

2025, 2008 International Conference on Intelligent Sensors, Sensor Networks and Information Processing

A new approach to modelling and classification of human gait is proposed. Body movements are obtained using a sensor suit that records inertial signals that are subsequently modelled on a humanoid frame with 23 degrees of freedom (DOF). Measured signals include position, velocity, acceleration, orientation, angular velocity and angular acceleration. Using a range of concurrent features extracted from the sensor signals, a system using induced symbolic classification models, such as decision trees or rule sets, has been used for classification of identity. It is anticipated that this approach will also enable the identification of a variety of gestures. The feasibility of generating the identified behaviours in a humanoid robot will be explored. The approach is described and the characteristics of the algorithm are presented. The results obtained so far are reported and conclusions drawn.

2025

Background: Low back pain (LBP) is a frequent post-natal musculoskeletal condition that is severe enough to interfere with everyday life, resulting in decreased work performance and productivity, increased sick leave, high rates of functional disability, and increased treatment seeking for symptom relief. Objective: The goal of the study was to invesigate how lowering abdominal fat affected postpartum women's LBP. Patients and Methods: The participants in this study were forty obese post-natal women with low back pain, ranging in age from 25 to 35 years old and with a BMI of less than 40 kg/m2. They were divided into two equal groups at random.Group (A) received focused ultrasound cavitation (FUSC) and low caloric diet in addition to performing abdominal strengthening and posterior pelvic tilt exercises and Group (B) performed the same exercises as group (A) for one month. Before and after 4 weeks of treatment, both groups (A&B) were assessed. by using visual analogue scale (VAS...

2025

Robotics has been successfully applied in the design of collaborative robots for assistance to people with motor disabilities. However, man-machine interaction is difficult for those who suffer severe motor disabilities. The aim of this study was to test the feasibility of a low-cost robotic arm control system with an EEG-based brain-computer interface (BCI). The BCI system relays on the Steady State Visually Evoked Potentials (SSVEP) paradigm. A cross-platform application was obtained in C++. This C++ platform, together with the open-source software Openvibe was used to control a Stäubli robot arm model TX60. Communication between Openvibe and the robot was carried out through the Virtual Reality Peripheral Network (VRPN) protocol. EEG signals were acquired with the 8-channel Enobio amplifier from Neuroelectrics. For the processing of the EEG signals, Common Spatial Pattern (CSP) filters and a Linear Discriminant Analysis classifier (LDA) were used. Five healthy subjects tried the BCI. This work allowed the communication and integration of a well-known BCI development platform such as Openvibe with the specific control software of a robot arm such as Stäubli TX60 using the VRPN protocol. It can be concluded from this study that it is possible to control the robotic arm with an SSVEP-based BCI with a reduced number of dry electrodes to facilitate the use of the system.

2025, Effects of Mental Fatigue on Gait Performance and Variability

OBJECTIVES Mental fatigue has been shown to negatively impact physical performance, including motor skills and neuromuscular function. This study aimed to investigate the effects of mental fatigue on gait performance and variability in healthy young male adults. METHODS Eighteen participants walked over-ground at their preferred speed before and after completing a mentally fatiguing Stroop task. Kinematic data were recorded to assess gait variables such as speed, step length, step time, and step width, along with their coefficients of variation (CV). Subjective ratings of mental fatigue were also collected. RESULTS While subjective ratings of mental fatigue significantly increased following the Stroop task, no significant changes were observed in gait performance or CV variables at the group level. However, singlesubject analyses revealed that some participants experienced significant increases or decreases in gait speed, suggesting gait performance responses to mental fatigue are individual-specific. CONCLUSIONS These findings indicate that although mental fatigue increases perceptibly, it may not uniformly affect gait performance in simple walking tasks. Factors such as the duration and intensity of the fatigue-inducing task, individual coping strategies, and the nature of the gait task, particularly the participant's preferred speed, likely influenced these results. Future research should explore more complex gait tasks and varied mental fatigue protocols to better understand this relationship.

2025

INTRODUCTION: Chronic obstructive pulmonary disease (COPD) is the most common disorder affecting 10-15% of adult over the age of 40. COPD is a disorder characterized by the presence of air flow obstruction that is generally progressive may be accompanied by airway hyper reactivity and may partially reversible. COPD patients shows marked decrease in the lung volumes and lung capacities leads to decrease arterial oxygen saturaisation level and over all it affects the aerobic and exercise tolerance capacity of the persons. In initial stage it produces hypoxemia and in later stage hypercapnia will occur. The cornerstone of pulmonary rehabilitation is exercise training based on the premise that altering physiologic process will result in improved outcomes. Intensity and duration are important determinants of the physiologic adaptation that occur in response to exercise. COPD patients are so limited by dyspnea, even at modest level of ventilation that their training is restricted to low i...

2025

The development and progress of modern video imaging technology is not only limited to imaging itself. It has also led to the development of panel display technology with the resolution of electronic devices becoming more and more detailed, with an increasingly wider color gamut and color accuracy becoming higher and higher. Hence the requirement for details of the color image information has increased. However, due to the improper use of image processing technology or a lack of detailed calculation, these often cause the loss of detailed image or color information. The main purpose of this paper is to provide a new algorithm which can repair the gradation of the image when detailed information is lost by calculations; re-patching the missing color information so that the color information of the image can be recovered with as much detail as possible. The experimental results validate that images improved by proposed algorithm are easier with other techniques of image enhancement.

2025

Gait is basically understanding of how a person locomotes from one point to the next. But injurious situations in life, just as the normal aging process predispose one with incapability to tackle the task to walk and move, hence would require support and assistance to compliment the ability to ambulate successfully with variations offered in stability verses mobility. The bottom-line aim of this symbiotic relation is to sire independence in Ambulation.

2025

Lateral shank bar is used by several motion analysis protocols for the definition of the anatomical reference frame of the shank. In addition to critical static alignment, the lateral bar can be affected by relevant motion relative to the underlying bony segment during walking, and this motion can result into a significant error superimposed to the relevant resulting ankle kinematics. The present study quantified the propagation of lateral bar motion to relevant 3D ankle kinematics during walking in normal subjects. Lateral bar motion critically affects particularly ankle internal-external rotation and kinematic values at heel-strike.

2025, Deleted Journal

As the population grows rapidly and the standard of living increases, the demand for housing will increase. One way to meet housing needs is to build housing. Housing development must be in accordance with careful planning in determining the investment model to be made in housing development. The initial stages of housing development start from surveying the location, number and type of houses to be built, marketing, to selling to consumers. The housing development process must also be calculated economically with the investment method, to find out whether this housing can be economically profitable or not. Based on the calculation of investment analysis with an investment period of 6 years, the Net Present Value (NPV) is Rp. 33,716,228,908 (NPV>0), the Internal Rate of Return (IRR) is 23,18% (IRR>MARR), Payback Period (PP) in the 3rd year to 11th months is smaller than the 6 year investment period, Benefit Cost Ratio (BCR) is 1.42 (BCR > 1), and Break Event Point (BEP) gets a percentage for type 30/60 of 90% with 132 units, type 36/60 by 69% with 207 units, type 36/72 by 56% with 172 units, and type 48/84 by 48% with 32 units. And from the sensitivity analysis results it is known that housing investment Puri Mahkota Muktiwari will still be feasible if the increase in investment costs is less than 20.15%, the decrease in the occupancy rate is not more than 16.74%, the decrease in the selling price level is not more than 16.7% and the increase in loan interest rates is less of 122.22%.

2025, Archives of Budo

The proliferation of adapted judo programs for people with intellectual disabilities has garnered continuous growth in the number of participants in this activity. As a result of this growing popularity, a number of adapted international judo competitions are now being held. The adaptive judo classification system was established to ensure that Special Needs judo athletes could be appropriately divided into categories to ensure their safety within the context of competition. The purpose of this study is knowledge about the reliability of the recently developed classification system for individuals with intellectual disabilities in adapted judo competitions. The classification system has five levels according to functional criteria. Six raters (experts) evaluated 20 videos of official adapted judo competitions, corresponding to one of the five proposed classification categories. Two methods were used to quantify the degree of inter-rater agreement as to the analysis and classification of the recorded matches. Inter-rater agreement was evaluated using the Intraclass Correlation Coefficient (ICC) and Fleiss-Kappa procedures. Results indicated an excellent degree of inter-rater reliability, showing that the system produces consistent results with different raters. This study represents an important step forward in the classification level of participants in adapted judo competitions for people with intellectual disabilities. Future international adapted judo competitions would benefit from field studies to confirm the reliability of this classification system.

2025, 2012 IEEE Virtual Reality (VR)

This paper describes a sensor-fusion-based wireless walking-inplace (WIP) interaction technique. We devised a new humanwalking detection algorithm that is based on a sensor-fusion using both acceleration and magnetic sensors integrated within a smart phone. Our sensor-fusion approach can be useful for the cases when the detection capability of a single sensor is limited to a certain range of walking speeds, when a system power source is limited, and/or when computation power is limited. The proposed algorithm is versatile enough to handle possible data-loss and random delay in the wireless communication environment, resulting in reduced wireless communication load and computation overhead. The initial study demonstrated that the algorithm can detect dynamic speeds of human walking. The algorithm can be implemented on any mobile device equipped with magnetic and acceleration sensors.

2025

and the United States of America participated in the four day conference programme. In four plenary, fourteen thematic parallel sessions and thirteen poster sessions there were more than 130 oral and 90 poster presentations. An impressive number of 239 articles were printed in the Proceedings Book which contained 1012 pages. Along with the Proceedings Book, a CD with an electronic version of the articles, which allows for browsing by a key word, the authors' name, a title and a country, was also printed and distributed at the Conference. The Scientifi c Committee consisted of 59 members from 16 countries and 3 continents. The Organizing Committee had contacted 50 potential key-note speakers and 42 accepted the invitation and came to the Conference. A total number of 246 scientifi c

2025, Journal of Medical Engineering & Technology

With the rising popularity of activity tracking, there is a desire to not only count the number of steps a person takes, but also identify the type of step (e.g., walking or running) they are taking. For rehabilitation and athletic training, this difference is important to the prescribed regiment. Fourteen healthy adults walked, jogged and ran on a treadmill at three different constant speeds (1.21, 2.01, 2.68 m/s) for 90 s. An inertial measurement unit (IMU) with accelerometer and gyroscope was affixed to their left ankle. Collected acceleration and angular velocity data were partitioned into individual time-normalised strides. These data were used as features in the artificial neural network (ANN) that classified the type of stride. Several ANN models were tested: using only acceleration, only angular velocity and both. Using primarily acceleration data in the trained ANN yielded the best results (>94% correct stride-type identification) after cross-validation. The ANN models were able to accurately classify the gait type of each stride using a single wearable IMU. The accuracy of the method should improve further as more data is added to the ANN training.

2025, Ayurline: IJ-RIM

This single case study is done in the treatment of the patient with the right Sacroiliac Joint Koch`s. The condition is rare and less documented on the Indian population. The patient had severe pain and postural impairment. It was observed that activities of daily living (ADL) like an independent transfer (get out of bed and sit on a chair), toilet use (squat and get up), bathing, walking, staircase climbing and dressing independently were badly affected. Hence this study is done to assess the effect of mirror therapy in pain management, postural correction, and activities of daily living in the patient with SI joint Koch`s. The patient was diagnosed using MRI, X-ray and hematological assessment. Skin traction and antitubercular treatment along with painkillers were started. The patient is referred to Occupational Therapy Services on 11/10/2017. On clinical evaluation FABER, GEANSLENS and Thomas test found positive. Hyperlordosis in supine and kyphosis in sitting was observed. Pain on VAS found 8 i.e. severe pain with Grade 2 of tenderness (tenderness to grimace or flinch to palpation) over right SI joint and posterior aspect of buttock and ADL scoring on Modified Barthel Index is 9 i.e. lowermost indicates disabilities on the first day of assessment. He was assessed and mirror therapy was started. The patient showed a reduction in lordosis

2025

Aim. Coactivation of the knee agonist-antagonist muscles plays an important role in knee joint stability in different planes of motion. Fatigue is common after high intensity exercise and may affect on muscle co activation to regulate joint stiffness during unexpected postural perturbations. The aim of the study was to investigate muscle co activation of the knee flexor and extensor muscles in response to sagital (forward-backward) and frontal (medial-lateral) perturbations before and after dynamic fatiguing exercise. Methods. Bipolar surface EMG signals were recorded from 14 healthy men with five pairs of electrodes located on the knee extensor muscles (vastus medialis, rectus femoris, and vastus lateralis) and knee flexor muscles (the medial and lateral heads of the hamstring) of the right leg during sagittal/frontal perturbations. Results. Maximal voluntary contraction force and time to task failure were significantly reduced after fatiguing exercise with respect to baseline (P<0.001). During the postexercise sagittal / frontal perturbations, reflexive activity in knee extensor muscles was significantly lower than baseline (P<0.05). Moreover, a significant reduction in the level of co-activation between the hamstring and quadriceps muscles was observed during sagittal / frontal perturbations (P<0.05), with a greater reduction identified for the frontal perturbation (P<0.05). Conclusion. Fatigue alters muscle co activation around knee joint, particularly when knee is subjected to the frontal perturbation.

2025

Background: Subjects with knee osteoarthritis typically have higher knee adduction moment. Current research efforts are mainly focused on therapeutic procedures that potentially may modify disease progression. This preliminary study was designed as a single blind (examiner) randomized control trial to investigate the impact of conventional physical therapy on pain, and knee joint load in subjects with moderate knee osteoarthritis. Methods: Twelve participants diagnosed with moderate knee OA were randomly assigned into control and intervention groups. Three-dimensional knee kinematic and kinetic data were recorded during the gait before and after 10 sessions of conventional physical therapy. In addition, pain intensity was evaluated by visual analog scale and pain subscale of KOOS questionnaire. The control group did not receive any intervention during the same period. Gait parameters were analyzed within and between groups using nonparametric tests. Results: There was a significant ...

2025

"Background: Knee osteoarthritis (KOA) is one of the most common joint diseases in elderly individuals (1). Various grades of KOA lead to change in gait pattern by different compensatory mechanisms. Spatiotemporal parameters of gait can be influenced by KOA maybe as a strategy to reduce pain and functional adaptation. Most researches are agreed on reduction of gait stride length (2-5) and cadence (6, 7) in KOA patients in comparison to control normal groups. But there is controversy about them. The present study will discuss the effect of KOA severity on gait spatiotemporal parameters. Aim: To determine how KOA severity will affect stride length, walking speed and cadence. Materials and Methods: Thirty four women aged between 40-70 years diagnosed with medial KOA were systematically divided in to three groups of mild, moderate and severe OA and a group of normal subjects. KOA severity was classified according to the (K–L scale) using atlas of the Osteoarthritis Research Society...

2025

"Background: Knee osteoarthritis (KOA) is a major common form of osteoarthritis (1) with higher ratio in women than men (2). Gait alterations are of the most common complications of KOA and may lead to functional dependency and work disability (3). Aim: The purpose of this study is to review the gait differences between osteoarthritic patients and healthy individuals. Materials and Methods: In this study we have searched from April 2012 in Pub Med data base for relevant studies published in two recent decades from 1990 until now. The key words used in this article include "knee osteoarthritis" AND "gait" in combination with "severity" and "knee adduction moment". Abstracts articles that analyzed Kallgren and Lawrence progression in examination of KOA and evaluated the kinetic and kinematic parameters from 3D gait analysis, were eligible for inclusion. Results: More than 100 articles are published about KOA severity and changes of knee add...

2025, MEDWIN Publisher

This study investigates the dynamics of foot placement as a forensic tool for identifying individuals in various scenarios, focusing on the differences between athletes and non-athletes. Analyzing the unique characteristics of foot placement patterns, we examine how factors such as gait, pressure distribution, and stride length vary between these two groups. Collected data from a sample of professional athletes across different sports and a control group of non-athletes. Findings reveal that athletes exhibit distinct foot placement dynamics characterized by more consistent and efficient gait patterns, marked by variations in pressure distribution and stride mechanics. These insights highlight the potential for utilizing foot placement dynamics in forensic contexts to enhance the accuracy of individual identification and scene reconstruction. This study emphasizes the importance of considering physical conditioning and activity levels in forensic analysis.

2025, IEEE ACCESS

The complexity of diagnosing and treating gait-related diseases necessitates the existence of a domain ontology that can support intelligent decision-making by gait experts and medical personnel. This study describes the development of a domain ontology for gait analysis and decision support on gait-related diseases. The process for developing the ontology followed a custom ontology development process that is based on the hybridisation of the Ontology 101 (OD-101) development methodology and Methontology,
ensuring a systematic and replicable construction of the ontology. The design of the Gait Analysis Domain Ontology (GADO) embraced thirteen dimensions, making it the most comprehensive domain ontology for gait analysis compared to previous efforts. The GADO was created using the Protégé ontology editor and was evaluated by using ontology verification and validation procedures. Ontology verification was conducted by using the Framework for Ontology Conformance Analysis (FOCA) to assess domain task fit through competency questions and content richness of the ontology. The results demonstrated GADO’s suitability in representing the domain effectively. Ontology validation involved checking the structural and logical consistency of the ontology by using reasoners such as HermiT and Pellet and employing Description Logic and SPARQL queries to assess the ontology’s ability to respond to domain-specific queries accurately. The validation process confirmed the GADO’s effectiveness in facilitating the retrieval of relevant information. Thus, the GADO is positioned to enhance clinical decision support for gait-related diseases, thereby advancing the applications of ontology-enabled decision support systems.

2025, 2006 Fourth International Conference on Intelligent Sensing and Information Processing

Biological motion has successfully been used for analysis of a person's mood and other psychological traits. Efforts are made to use human gait as a non-invasive mode of biometric. In this reported work, we try to study the effectiveness of biological gait motion of people as a cue to biometric based person recognition. The data is 3D in nature and, hence, has more information with itself than the cues obtained from videobased gait patterns. The high accuracies of person recognition, using a simple linear model of data representation and simple neighborhood based classfiers, suggest that it is the nature of the data which is more important than the recognition scheme employed.

2024, Bulletin of Electrical Engineering and Informatics

Medical images are comprised of sensor measurements which help detect the
characteristics of diseases. Computer-based analysis results in the early
detection of diseases and suitable medications. Human activity recognition
(HAR) is highly useful in applications related to medical care, fitness
tracking, and patient data archiving. There are two kinds of data fed into the
HAR system which are, image data and time series data of physical
movements through accelerometers and gyroscopes present in smart devices.
This study introduced crayfish optimization algorithm with long short term
memory (COA-LSTM). The raw data is obtained from three datasets
namely, WISDM, UCI-HAR, and PAMAP2 datasets; then, pre-processing
helps in removal of unwanted information. The features from pre-processed
data are reduced using principal component analysis and linear discriminant
analysis (PCA-LDA). Finally, classification is performed using COA-LSTM
where, the hyperparameters are fine-tuned with the help of COA. The
suggested method achieves a classification accuracy of 98.23% for UCIHAR dataset, whereas the existing techniques like convolutional neural
network (CNN), multi-branch CNN-bidirectional LSTM, CNN with gated
recurrent unit (GRU), ST-deep HAR, and Ensem-HAR obtain a
classification accuracy of 91.98%, 96.37%, 96.20%, 97.7%, and 95.05%,
respectively.

2024, Journal of Learning Theory and Methodology

Background. Backpacks are commonly used by students to carry their school items. However, increasing backpack loads can lead to negative effects on health and posture, particularly through changes in gait dynamics. Peak forces are a... more

2024

Over a few decades, there is a steady accretion of life expectancy in many countries. Significant advances in modern healthcare technologies, medicines and overall health care awareness gave many to lead a prolonged healthy life. Over the past few years, there has been a huge demand for unobtrusive health monitoring systems from both medical professionals and the general populace to use these technologies for understanding the general health well being in order to improve life longevity. However, most of the available technologies for health monitoring are difficult for the general populace to access and most of the developed health monitoring systems are either deployed in a controlled environment or in healthcare facilities, thus severely limiting the ease of access to many, especially the elderly people. For effective health management of elderly people, evidence-based decision making, continuously monitoring the health status of the elderly demographic is paramount. In order to address these issues, we developed an innovative smart IoT based outdoor health monitoring system. The proposed system collects information about the mobility, posture, and overall gait of the person in an easy to access public outdoor setting such as parks, supermarkets etc. It is quite evident from multiple studies, that analysing the gait can be a useful tool in early detection of the declining health of individuals, as mobility is a key factor in any individual's well being. Also, detecting gait disorders earlier will allow for functional relief to the health care system with the possibility of reducing the number and severity of gait disorders through early intervention.

2024, Journal of physical therapy science

This study was carried out to determine the effect of an exercise program on pelvic pain and posture associated with endometriosis. [Subjects and Methods] This study was designed as repeated measures design that compared one group of 20 patients (age range 26-32 years) diagnosed by laparoscope as having mild or moderate endometriosis before, after 4 weeks, and after 8 weeks of exercise program. The exercise program parameters were based on the American College of Obstetricians and Gynecologists guidelines for exercise suitable for sedentary women. To assess the intensity of endometriosis pain, a present pain intensity scale was used. On the other hand, a raster stereography system was used to assess the posture. [Results] After 8 weeks of performing the exercise regimen, there was a statistically significant decrease in the patients' pain intensity and thoracic kyphosis angle program in compared with pre treatment. [Conclusion] Ultimately it was proven that eight weeks of an exercise program is very effective in decreasing pain and postural abnormalities associated with endometriosis.

2024

Background: Lumbar spinal stenosis is a growing concern with clinical features capable of resulting into highly disabling conditions. Most patients choose to opt for conservative care as opposed to seeking surgical solutions. However, it is unclear from the literature which of the conservative treatments when apply singly or in combination might work best. Aims of the study: The objective of this study was to investigate the effects of acupuncture, core stability exercise, and single knee to chest stretch and treadmill walk exercises on pain severity, time of first onset of pain (TFS), functional limitation due to pain, and functional mobility in a patient with low back pain with lumbar spinal stenosis. Methods: This is a single case report on a 70-year-old patient with clinical features and radiological diagnosis of lumbar spinal stenosis. The main findings from assessments were; lower back and right leg pain, impaired mobility and impaired ability to do functional Activity of Dail...

2024, International Journal of Kinesiology & Sports Science

Background: Backpacks are vital for students, offering stability by being close to the body's center of gravity. However, increased weight demands more energy and can lead to negative effects like altered gait, fatigue, and a higher risk... more

2024, Journal of Medical and Scientific Research

Background: Foot biomechanics undergo age related changes and visual input may be important for postural stability and stance dynamics. This study aimed to investigate how age-related alterations in foot biomechanics and visual input interact to influence postural stability and stance dynamics in children aged 6 to 19 years. Materials and methods: Prospective observational study was conducted after getting permission from Institutional Ethics Committee. Informed consent was obtained before collecting data. OHM3000 used for collecting data. Data was collected for bipedal stance test, stabilometry test with eyes open and eyes closed, and dynamic stance test during walking with predefined protocol. Result: Statistically significant difference in maximum pressure, average pressure, foot area and foot length are exhibited in both feet with higher values in adolescents as compared to pre-adolescents. Maximum lateral deviation was significantly less in adolescent with eyes open toward right feet as compare to preadolescents and the difference was lost with eyes closed. Maximum pressure, average pressure, foot contact area and forefoot maximum pressure in both feet were statistical significance conclusion: Increased maximum pressure, average pressure, foot area and foot length indicating physical growth and higher load-bearing capacities in adolescents. Weight distribution over the forefoot and hindfoot remained consistent across age groups even if significant changes shown in foot size and pressure. Visual input significantly improved postural stability in both groups. Adolescents show better postural stability probably due to foot maturation. During walking, adolescents showed increased maximum and average pressures, especially in forefoot.

2024, Journal of Modern Rehabilitation (JMR)

Introduction: Myofascial pain syndrome is a common musculoskeletal injury, especially among athletes, typically treated with symptomatic invasive and non-invasive methods. This study compares the effects of massage guns and radial extracorporeal shock wave therapies on myofascial pain syndrome symptoms in amateur athletes.
Materials and Methods: In this clinical trial, 45 amateur athletes (18-30 years old) were recruited, who were randomly assigned to 15-member groups of shock wave, massage gun, and control (routine treatment included electrotherapy and stretching, which was applied on three groups). After initial evaluations of the pain intensity, pain pressure threshold (PPT), isometric muscle strength, and range of motion (ROM), the patients received single-session treatment and were immediately reassessed.
Results: The results showed pain relief and improved PPT following shock wave plus routine treatment (P=0.03). The control group had less pain, while pain intensity and PPT did not change. The variables were not significantly different between the groups (P=0.12). Shock wave along with routine treatment increased plantar flexion ROM (P=0.00), unlike the massage gun. Additionally, dorsiflexion ROM (P=0.63) and maximal isometric gastrocnemius muscle strength (P=0.95) remained unchanged in all groups.
Conclusion: One session of massage gun therapy immediately reduced gastrocnemius muscle pain, while it failed to change PPT, maximal isometric gastrocnemius muscle strength, or dorsiflexion and plantar flexion ROM. However, shock wave therapy immediately increased plantar flexion ROM and PPT, and reduced pain intensity. These modalities led to limited changes, suggesting the need for repeated sessions and supplementary treatments.

2024, Lower Extremity Review

Postural and gait impairments, including toe walking, are extremely prevalent among individuals with Intellectual Disability and those who have ASD or are on the spectrum. Why this occurs in this population is not fully known. What we do know is that the tendency to hold a particular body position in an abnormal way causes stress on the joints, muscles and vertebrae column. It appears that many individuals with ASD have a limited repertoire of movement combined with sensory processing issues and therefore they are less likely to change from an unnatural position into a better posture. Change in posture occurs when the body gives a sensory signal of discomfort. It is obvious that a long duration of staying in an abnormal posture may cause body distortions, soft tissue changes, weakness, and pain. Eventually, this may lead to a reduction in ability or motivation to participate in functional daily activities.

2024, Journal of Medical Sciences

Objective: To determine the effect of myofascial trigger point release of the plantar fascia and calf muscles in patients with plantar fasciitis for pain management. Material and Methods: It was Quasi experimental study on 42 diagnosed plantar fasciitis patients (13 male and 29 female) with age more than 20 years. It was conducted in Private Physiotherapy clinic in Gujrat, Pakistan,from December 2016 to May 2017.. The patients were given 03 sessions per week of myofascial trigger point release of calf muscles and the plantar fascia for 4 weeks. Plantar fasciitis pain scale questionnaire was used to measure the results of pre and post intervention. The paired T-test was used to determine the significance of treatment. Results: The mean age for diagnosed planter fasciitis patients was 31.40±7.46. The intensity of pain significantly reduced after the treatment in walking (2.35±0.79 vs. 1.35±0.65, p=0.0001). The intensity of pain during standing on bare foot was also improved (1.23 ±1.0...

2024, Sensors

This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY

2024, Computer Science & Information Technology ( CS & IT )

Human gait reveals feelings, intentions and identity which is perceived by most human beings. To understand this perceptual ability, Swedish psychologist Gunnar Johansson (1973), devised a technique known as PL (Point Light) animation of biological motion. In his work, the activity of a human is portrayed by the relative motions of a small number of markers positioned on the head and the joints of the body. This paper explores the basic concept of PL animation along with machine vision and machine learning techniques to analyze and classify gait patterns. Basically, frames of each video are background subtracted, the silhouette noise found were salt noise and noise connected in large blobs which are detected and removed based on morphological operations and area of connected components respectively. Image is then segmented and body points such as hand, knee, foot, neck, head, waist along with the speed, height, width, area of person are determined by an algorithm. We then fit sticks connecting pairs of points. The magnitude and direction of these stick along with other features forming a 24-dimensional feature vector for each frame of a video are classified using SVM Modelling using LIBSVM Toolkit. The maximum recognition accuracy found during testing by cross validation with parameters of LIBSVM was 93.5 %.

2024, International Journal of Advanced Research (IJAR)

The purpose of the study is to evaluate the efficacy of Dynamic taping in conjunction with conventional physiotherapy compared to conventional physiotherapy alone for tennis elbow. Objectives: To evaluate pain intensity at rest, during... more

2024

2024, Smartek

This research was done at project of Taman Sidorejo estate Kecamatan Krian Kabupaten Sidoarjo. It used Competitor analysis, Finance analysis, Break-even Point analysis, and Sensitivity analysis. Result of Competitor analysis show... more

2024

The mechanism of running can be modelled as a simple spring-mass system bouncing on the ground, with a single spring representing the runner’s leg and a point mass equivalent to body mass. When the conditions of running are modified, for example by changing surface stiffness [1] or running barefoot compared to shod [2], it has been shown that runners adjusted their leg stiffness. We applied an unexpected dorsoflexion to the ankle just before the foot contact during running. We observed some immediate biomechanical adjustments, including a decreased leg stiffness and a decreased and delayed foot-slap (unpublished results). We are now interested in quantifying the long-lasting effect of the perturbation: Is the next step still affected by?

2024

Publication in the conference proceedings of EUSIPCO, Poznan, Poland, 2007

2024, 2008 19th International Conference on Pattern Recognition

Gait is an emerging biometric showing promise in its use. Most research focusses on fronto-parallel (FP) gait where people walk across a camera. In this paper, we present an original analysis, presenting the case for the use of frontonormal (FN) gait where motion is towards a camera. In FN gait, the image projected on a camera sensor will get larger, in a looming effect. This affects the data in a nonlinear and non stationary way, which will further complicate analysis of movement. By catering for this effect, we present new insights into perspective motion compensation for FN gait. Using an existing database which uses coloured markers, we compare two methods of compensation for looming. Initial examination of the resulting data shows a significant result, that fundamentally different approaches may be used for time series analyses on the a set of FN gait data. This opens up new avenues for biometric research in gait recognition.