Discrimination of the Lame Limb in Horses Using a Machine Learning Method (Support Vector Machine) Based on Asymmetry Indices Measured by the EQUISYM System

Sensors, Journal Year: 2025, Volume and Issue: 25(4), P. 1095 - 1095

Published: Feb. 12, 2025

Lameness detection in horses is a critical challenge equine veterinary practice, particularly when symptoms are mild. This study aimed to develop predictive system using support vector machine (SVM) identify the affected limb trotting straight line. The analyzed data from inertial measurement units (IMUs) placed on horse's head, withers, and pelvis, variables such as vertical displacement retraction angles. A total of 287 were included, with 256 showing single-limb lameness 31 classified sound. model achieved an overall accuracy 86%, highest success rates identifying right left forelimb lameness. However, there challenges sound horses, 54.8% rate, misclassification between hindlimb occurred some cases. highlighted importance specific variables, head withers displacement, for accurate classification. Future research should focus refining model, exploring deep learning methods, reducing number sensors required, goal integrating these systems into equestrian equipment early locomotor issues.

Language: Английский

---

Effects of Experimentally Induced Lower Limb Muscle Fatigue on Healthy Adults’ Gait: A Systematic Review

Bioengineering, Journal Year: 2025, Volume and Issue: 12(3), P. 225 - 225

Published: Feb. 22, 2025

Lower limb fatigue reduces muscle strength, alters joint biomechanics, affects gait, and increases injury risk. In addition, it is of great clinical significance to explore local or weakness caused by understand its compensatory effect on the ipsilateral contralateral joints. We systematically searched multiple databases, including five using key terms such as “Muscle Fatigue” “Gait”. Only studies that experimentally induced through sustained activities in healthy adults were included. This review examined 11 exploring effects lower gait biomechanics. The findings indicated significantly influenced spatiotemporal parameters, angles, moments. Most reviewed reported an increase step width a decrease knee moments following fatigue. Additionally, activation levels tended decline. summary, mechanisms can lead new walking strategies, increasing enhancing strength muscles adjacent These adjustments impact dynamic balance differently: wider steps may enhance medial–lateral stability, while reduced could higher heel contact velocity longer slip distances. Although these changes might influence balance, strategies help mitigate overall fall Future should use appropriate protocols, moderate severe interventions with isokinetic dynamometry.

Language: Английский

---

Test-Retest Reliability and Minimal Detectable Changes for Wearable Sensor-Derived Gait Stability, Symmetry, and Smoothness in Individuals with Severe Traumatic Brain Injury

Sensors, Journal Year: 2025, Volume and Issue: 25(6), P. 1764 - 1764

Published: March 12, 2025

Severe traumatic brain injury (sTBI) often results in significant impairments gait stability, symmetry, and smoothness. Inertial measurement units (IMUs) have emerged as powerful tools to quantify these aspects of gait, but their clinometric properties sTBI populations remain underexplored. This study aimed assess the test-retest reliability minimal detectable change (MDC) three IMU-derived indices—normalized Root Mean Square (nRMS), improved Harmonic Ratio (iHR), Log Dimensionless Jerk (LDLJ)—during a 10 m walking test for survivors. Forty-nine participants with completed test, IMUs placed on key body segments capture accelerations angular velocities. Test-retest analyses revealed moderate excellent nRMS iHR anteroposterior (ICC: 0.78–0.95 0.94, respectively) craniocaudal directions 0.95), small MDC values, supporting clinical applicability (MDC: 0.04–0.3). However, mediolateral direction exhibited greater variability 0.80; MDC: 9.74), highlighting potential sensitivity challenges. LDLJ metrics showed 0.57–0.77) higher values (0.55–0.75), suggesting need further validation. These findings underscore specific indices detecting meaningful changes survivors, paving way refined assessments monitoring rehabilitation process Future research should explore indices’ responsiveness interventions correlation functional outcomes.

Language: Английский

---

Wearable Online Freezing of Gait Detection and Cueing System

Bioengineering, Journal Year: 2024, Volume and Issue: 11(10), P. 1048 - 1048

Published: Oct. 20, 2024

This paper presents a real-time wearable system designed to assist Parkinson's disease patients experiencing freezing of gait episodes. The utilizes advanced machine learning models, including convolutional and recurrent neural networks, enhanced with past sample data preprocessing achieve high accuracy, efficiency, robustness. By continuously monitoring patterns, the provides timely interventions, improving mobility reducing impact explores implementation CNN+RNN+PS model on microcontroller-based device. device operates at processing rate 40 Hz is deployed in practical settings provide 'on demand' vibratory stimulation patients. examines system's ability operate minimal latency, achieving an average detection delay just 261 milliseconds accuracy 95.1%. While received on-demand stimulation, effectiveness was assessed by decreasing duration episodes 45%. These preliminarily results underscore potential personalized, feedback systems enhancing quality life rehabilitation outcomes for movement disorders.

Language: Английский

---

A kinematic dataset of locomotion with gait and sit-to-stand movements of young adults

Scientific Data, Journal Year: 2024, Volume and Issue: 11(1)

Published: Nov. 9, 2024

Kinematic data is a valuable source of movement information that provides insights into the health status, mental state, and motor skills individuals. Additionally, kinematic can serve as biometric data, enabling identification personal characteristics such height, weight, sex. In CeTI-Locomotion, four types walking tasks 5 times sit-to-stand test (5RSTST) were recorded from 50 young adults wearing motion capture (mocap) suits equipped with Inertia-Measurement-Units (IMU). Our dataset unique in it allows study both intra- inter-participant variability high quality for different tasks. Along raw we provide code phase segmentation processed which has been segmented total 4672 individual repetitions. To validate conducted visual inspection well machine-learning based identity action recognition tests, achieving 97% 84% accuracy, respectively. The normative reference gait movements healthy training recognition.

Language: Английский

---

AI-Aided Gait Analysis with a Wearable Device Featuring a Hydrogel Sensor

Sensors, Journal Year: 2024, Volume and Issue: 24(22), P. 7370 - 7370

Published: Nov. 19, 2024

Wearable devices have revolutionized real-time health monitoring, yet challenges persist in enhancing their flexibility, weight, and accuracy. This paper presents the development of a wearable device employing conductive polyacrylamide-lithium chloride-MXene (PLM) hydrogel sensor, an electronic circuit, artificial intelligence (AI) for gait monitoring. The PLM sensor includes tribo-negative polydimethylsiloxane (PDMS) tribo-positive polyurethane (PU) layers, exhibiting extraordinary stretchability (317% strain) durability (1000 cycles) while consistently delivering stable electrical signals. weighs just 23 g is strategically affixed to knee brace, harnessing mechanical energy generated during motion which converted into These signals are digitized then analyzed using one-dimensional (1D) convolutional neural network (CNN), achieving impressive accuracy 100% classification four distinct patterns: standing, walking, jogging, running. demonstrates potential lightweight energy-efficient sensing combined with AI analysis advanced biomechanical monitoring sports healthcare applications.

Language: Английский

---