Search Results (121)

Monitoring the health of wind turbine foundations is essential for ensuring their operational safety. This paper presents a cost-effective approach to obtain rotational stiffness of wind turbine foundations by using only acceleration and wind speed data that are part of SCADA data, thus lowering the use of moment and tilt sensors that are currently being used for obtaining foundation stiffness. First, a convolutional neural network model is applied to map acceleration and wind speed data within a moving window to corresponding moment and tilt values. Rotational stiffness of the foundation is then estimated by fitting a line in the moment-tilt plane. The results obtained indicate that such a mapping model can provide stiffness values that are within 7% of ground truth stiffness values on average. Second, the developed mapping model is re-trained by using synthetic acceleration and wind speed data that are generated by an autoencoder generative AI network. The results obtained indicate that although the exact amount of stiffness drop cannot be determined, the drops themselves can be detected. This mapping model can be used not only to lower the cost associated with obtaining foundation rotational stiffness but also to sound an alarm when a foundation starts deteriorating. Full article

This study aimed to evaluate the feasibility of using serious games for the (tele)rehabilitation of children with disabilities affected by the Ukrainian war. Additionally, it provides requirements for technologies that can be used in war-affected areas. Structured interviews and Likert scale assessments were conducted on-site and remotely with patients of the tertiary care facility in Ukraine. All participants used the telerehabilitation platform for motor and cognitive training. Nine serious games were employed, involving trunk tilts, upper limb movements, and head control. By mid-September 2023, 186 positive user experiences were evident, with 89% expressing interest in continued engagement. The platform’s accessibility, affordability, and therapeutic benefits were highlighted. The recommendations from user feedback informed potential enhancements, showcasing the platform’s potential to provide uninterrupted rehabilitation care amid conflict-related challenges. This study suggests that serious games solutions that suit the sociopolitical and economic context offer a promising solution to rehabilitation challenges in conflict zones. The positive user experiences towards using the platform with serious games indicate its potential in emergency healthcare provision. The findings emphasize the role of technology, particularly serious gaming, in mitigating the impact of armed conflicts on children’s well-being, thereby contributing valuable insights to healthcare strategies in conflict-affected regions. Requirements for technologies tailored to the context of challenging settings were defined. Full article

This study aimed to train and validate two artificial neural network (ANN) models, one with four hidden layers and the other with five hidden layers, to predict the daily photovoltaic power output of a 20 Kw photovoltaic power plant with bifacial photovoltaic modules with tilt angle variation from 0° to 90° in two Moroccan cities, Ouarzazate and Oujda. To validate the two proposed models, photovoltaic power data calculated using the System Advisor Model (SAM) software version 2023.12.17 were employed to predict the average daily power of the photovoltaic plant for December, utilizing MATLAB software Version R2020a 9.8, and for the tilt angles corresponding to the latitudes of the two cities studied. The results differ from one model to another according to their mean absolute error (MAE), root mean squared error (RMSE), and coefficient of determination (R²) values. The artificial neural network model with five hidden layers obtained better results with a R² value of 0.99354 for Ouarzazate and 0.99836 for Oujda. These two proposed models are trained using the Levenberg Marquardt (LM) optimizer, which is proven to be the best training procedure. Full article

This paper proposes a drug classification system using convolutional neural network (CNN) training and rotational pill dropping technology. Images of 40 pills for each of 102 types (total 4080 images) were captured, achieving a CNN classification accuracy of 88.8%. The system uses a bowl feeder with optimized operating parameters—voltage, torque, PWM, tilt angle, vibration amplitude (0.2–1.5 mm), and frequency (4–40 Hz)—to ensure stable, sequential pill movement without loss or clumping. Performance tests were conducted at 5 V, 20 rpm, 20% PWM (@40 Hz), and 1.5 mm vibration amplitude. The bowl feeder structure tolerates oblique angles up to 75°, enabling precise pill alignment and classification. The CNN model plays a key role in accurate pill detection and classification. Full article

It has been demonstrated that needle guidance systems can enhance the precision and safety of ultrasound-guided punctures in human medicine. Systems that permit the utilization of commercially available standard needles, instead of those that necessitate the acquisition of costly, proprietary needles, are of particular interest. The objective of this phantom study is to evaluate the reliability and accuracy of magnet-based ultrasound needle guidance systems, which superimpose the position of the needle tip and a predictive trajectory line on the live ultrasound image. We conducted fine-needle aspiration cytology of thyroid nodules. The needles utilized in these procedures are of a slender gauge (21–27G), with lengths ranging from 40 to 80 mm. A dedicated training workstation with integrated software-based analyses of the movement of the needle tip was utilized in 240 standardized phantom punctures (angle: 45°; target depth: 20 mm). No system failures occurred, and the target achieved its aim in all cases. The analysis of the software revealed stable procedural parameters with minor relative deviations from the predefined reference values regarding the distance of needle tip movement (−4.2% to +6.7%), needle tilt (−6.4% to +9.6%), and penetration depth (−7.5% to +4.5%). These deviations appeared to increase with the use of thin needles and, to a lesser extent, long needles. They are attributed to the slight bending of the needle inside the (phantom) tissue. The training workstation we employed is thus suitable for use in educational settings. Nevertheless, in intricate clinical puncture scenarios—for instance, in the case of unfavorable localized small lesions near critical anatomical structures, particularly those involving thin needles—caution is advised, and the system should not be relied upon exclusively. Full article

Servo-free tilt-rotor UAVs decouple position and attitude control without using servos, which cuts structural weight and removes the travel limits of traditional designs. In many applications—such as aerial platform operations and airborne photogrammetry—large attitude changes are required during hover. Conventional control-allocation schemes tend to distribute thrust unevenly, making actuators prone to saturation. To overcome these challenges, we propose a thrust-balancing control-allocation strategy specifically for passive-hinge tilt-rotor octocopters. The presented method integrates min–max optimization with the force decomposition (FD) algorithm, effectively handling actuator saturation while maintaining low computational complexity. Additionally, an offline-trained neural network is employed to replace the online optimization process, enabling the complete controller to operate on the flight control board without relying on an onboard computer. Simulation and experiment results confirm the effectiveness of the proposed strategy, demonstrating enhanced control performance and its practical feasibility for real-world UAV applications. Full article

Marker-based, IMU-based (6-axis IMU), and smartphone-based (OpenCap) motion capture methods are commonly used for motion analysis. The accuracy and reliability of these methods are crucial for applications in rehabilitation and sports training. This study compares the accuracy and inter-operator reliability of inverse kinematics (IK) solutions obtained from these methods, aiming to assist researchers in selecting the most appropriate system. For most lower limb inverse kinematics during walking motion, the IMU-based method and OpenCap show comparable accuracy to marker-based methods. The IMU-based method demonstrates higher accuracy in knee angle (5.74 ± 0.80 versus 7.36 ± 3.14 deg, with p = 0.020) and ankle angle (7.47 ± 3.91 versus 8.20 ± 3.00 deg, with p = 0.011), while OpenCap shows higher accuracy than IMU in pelvis tilt (5.49 ± 2.22 versus 4.28 ± 1.47 deg, with p = 0.013), hip adduction (6.10 ± 1.35 versus 4.06 ± 0.78 deg, with p = 0.019) and hip rotation (6.09 ± 1.74 versus 4.82 ± 2.30 deg, with p = 0.009). The inter-operator reliability of the marker-based method and the IMU-based method shows no significant differences in most motions except for hip adduction (evaluated by the intraclass correlation coefficient-ICC, 0.910 versus 0.511, with p = 0.016). In conclusion, for measuring lower-limb kinematics, wearable sensors (6-axis IMUs) achieve comparable accuracy and reliability to the gold standard, marker-based motion capture method, with lower equipment requirements and fewer movement constraints during data acquisition. Full article

Background: Foreign body airway obstruction is a sudden emergency that can occur unexpectedly in healthy people, leading to severe consequences if immediate first aid is not provided. Unlike the Heimlich maneuver for adults, the first aid for infant choking is less widely known and more complex, making it difficult to explain verbally. This study aimed to assess the efficiency of using an animated graphics interchange format (GIF) to teach first aid for infant choking due to foreign bodies. Methods: Eighty adults who had not received recent training in choking first aid within the last two years were randomly assigned to either the auditory (n = 40) or audiovisual (n = 40) groups. The participants were asked to perform first aid on an infant manikin under the guidance of a researcher using a smartphone in a separate room. The auditory group received verbal instructions only, while the audiovisual group received animated GIFs on their smartphones along with verbal instructions simultaneously. The entire process was recorded with two cameras, and two emergency physicians reviewed the videos to assess the adequacy of the first aid administered. Results: The “infant position”, “supporting arm posture”, and “head tilt” were more adequate in the audiovisual group. The Instruction Performance scores were higher in the audiovisual group. There was no significant difference in the time required to administer first aid between the two groups. Conclusions: Audiovisual guidance using animated GIFs has been shown to effectively enhance the adequacy of first-aid performance for infant airway obstruction caused by foreign bodies. Full article

Background: Minimally invasive surgery (MIS) is an advanced surgical technique that relies on a camera to provide the surgeon with a visual field. When the camera rotates along its longitudinal axis, the horizon of the surgical view tilts, increasing the difficulty of the procedure and the cognitive load on the surgeon. To address this, we proposed training a convolutional neural network (CNN) to detect camera rotation, laying the groundwork for the automatic correction of this issue during MIS procedures. Methods: We collected trans-nasal MIS procedure videos from YouTube and labeled each frame as either “tilted” or “non-tilted”. The dataset consisted of 2116 video frames, with 497 frames labeled as “tilted” and 1619 frames as “non-tilted”. This dataset was randomly divided into three subsets: training (70%), validation (20%), and testing (10%) Results: The ResNet50 was trained on the dataset for 10 epochs, achieving an accuracy of 96.9% at epoch 6 with a validation loss of 0.0242 before validation accuracy began to decrease. On the test set, the model achieved an accuracy of 96% with an average loss of 0.0256. The final F1 score was 0.94, and the Matthews Correlation Coefficient was 0.9168, with no significant bias toward either class. The trained ResNet50 model demonstrated a high success rate in predicting significant camera rotation without favoring the more frequent class in the dataset. Conclusions: The trained CNN accurately detected camera rotation with high precision, establishing a foundation for developing an automatic correction system for camera rotation in MIS procedures. Full article

High-precision surface defect detection in manufacturing often relies on laser triangulation profilometric sensors for detailed surface measurements, providing detailed and accurate surface measurements over a line. Accurate motion between the sensor and workpiece, usually managed by robotic systems, is critical for maintaining optimal distance and orientation. This paper introduces a novel Reinforcement Learning (RL) approach to optimize inspection trajectories for profilometric sensors based on the boustrophedon scanning method. The RL model dynamically adjusts sensor position and tilt to ensure consistent profile distribution and high-quality scanning. We use a simulated environment replicating real-world conditions, including sensor noise and surface irregularities, to plan trajectories offline using CAD models. Key contributions include designing a state space, action space, and reward function tailored for profilometric sensor inspection. The Proximal Policy Optimization (PPO) algorithm trains the RL agent to optimize these trajectories effectively. Validation involves testing the model on various parts in simulation and performing real-world inspection with a UR3e robotic arm, demonstrating the approach’s practicality and effectiveness. Full article

Elite football players face increasing physical and tactical demands due to rising match schedules emphasizing the need for effective load monitoring strategies to optimize performance and reduce injury risk. This study integrates fitness and fatigue indices derived from a machine learning approach to develop a performance score based on Banister’s fitness–fatigue model. Data were collected over two seasons (2022/23 and 2023/24) from 23 elite players of an Italian professional team. Fitness was assessed via heart rate collected during small-sided games, while fatigue was evaluated through PlayerLoad recorded during training sessions; both were normalized using z-scores. Match outcomes, including physical (e.g., total distance, high-sprint distance) and tactical metrics (e.g., field tilt, territorial domination), were analyzed in relation to performance conditions (optimal, intermediate, poor). Results revealed that players in the optimal performance condition exhibited significantly higher second-half physical outputs, including total distance (z-TD_2ndHalf: p < 0.05, ES = 0.29) and distance covered at >14.4 km/h (z-D14.4_2ndHalf: p < 0.01, ES = 0.52), alongside improved match tactical parameters as territorial domination (%TDO_2ndHalf: p < 0.01, r = 0.431). This study underscores the utility of invisible monitoring in football, providing actionable insights for weekly training periodization. This research establishes a foundation for integrating data-driven strategies to enhance physical and tactical performance in professional football. Full article

Background: Aging is associated with a decline in both motor and sensory functions that destabilizes posture, increasing the risk of falls. Dynamic standing balance is strongly linked to fall risk in older adults. Sensory information from the soles and trunk is essential for balance control. Few studies have demonstrated the efficacy of targeted sensory training on balance improvement. Objectives: To assess vibratory sensation function in the trunk and sole using a vibration device and evaluate the effects of trunk and sole tactile sensation training on dynamic standing balance performance in older adults. Methods: In this randomized controlled trial, eighteen older adults were randomly assigned to three groups: control (n = 8, mean age 66.6 ± 3.4), trunk training (n = 5, mean age 71.0 ± 1.9), and sole training (n = 5, mean age 66.4 ± 3.6). The training lasted for 10 weeks, utilizing vibratory stimulation at 128 Hz through tuning forks for 15 min during each session, conducted three times a week. The primary outcomes were vibratory sensitivity, assessed with a belt-fitted device on the trunk and a plate equipped with vibrators on the soles, and dynamic balance, evaluated through force plate testing that measured limits of stability (LoS) in multiple directions. Results: Correct response rates for trunk vibratory stimulation significantly improved in the trunk training group (p < 0.05). The rate of two-stimuli discrimination improved in both training groups. Significant advancements in balance metrics were observed in the trunk and sole training groups when compared to the control group, especially regarding anterior–posterior tilts (p < 0.05). A positive correlation was identified between two-point vibratory discrimination and LoS test performance. Conclusions: Sensory training of the trunk and sole enhances balance performance in older adults, suggesting potential benefits for fall prevention. Future studies should assess long-term effects and explore optimal training duration with larger sample sizes. Full article

Introduction: Vasovagal syncope is a prevalent condition marked by transient loss of consciousness due to abrupt decreases in systemic blood pressure and/or heart rate. Despite its clinical impact, the underlying haemodynamic mechanisms remain poorly defined, and data on age-related differences are limited and sometimes contradictory. Objectives: This study aimed to characterise haemodynamic adaptation patterns during a head-up tilt (HUT) test in adult (≥18 years) and paediatric (<18 years) patients with recurrent reflex syncope, compared with healthy adult controls. We sought to identify distinct temporal haemodynamic signatures and clarify potential age-related differences in syncope mechanisms. Methods: In this prospective observational study, participants underwent continuous beat-to-beat monitoring of cardiac output (CO), stroke volume (SV), heart rate (HR), and total peripheral resistance (TPR) during HUT. Linear mixed-effects models were used to examine time-by-group interactions, and post-hoc analyses were adjusted for multiple comparisons. Effect sizes and confidence intervals (CIs) were reported to quantify the magnitude of differences. Results: A total of 187 fainters (paediatric n = 81, adult n = 106) and 108 non-fainters (including 30 healthy controls) were studied. Compared to adult fainters, paediatric fainters showed a 24% larger decline in CO from baseline (mean difference of 1.1 L/min [95% CI: 0.5–1.7], p = 0.003) and a 15–20 bpm higher peak HR (p = 0.001) during presyncope. Both subgroups experienced significant drops in TPR, which were more pronounced in paediatric fainters (effect size = 0.27, 95% CI: 0.12–0.42). Non-fainters (including controls) maintained relatively stable haemodynamics, with no significant decrease in CO or TPR (p > 0.05). Age-related comparisons indicated a heavier reliance on HR modulation in paediatric fainters, leading to an earlier transition from compensated to pre-syncopal states. Conclusions: These findings demonstrate that paediatric fainters exhibit more abrupt decreases in CO and TPR than adults, alongside higher HR responses during orthostatic stress. Targeted interventions that address this heightened chronotropic dependency—such as tilt-training protocols or strategies to improve venous return—may be particularly beneficial in younger patients. An age-specific approach to diagnosis and management could improve risk stratification, minimise recurrent episodes, and enhance patient outcomes. Full article

Accurate image registration is essential for various remote sensing applications, particularly in multi-temporal image analysis. This paper introduces DVF-NET, a novel deep learning-based framework for dual-temporal remote sensing image registration. DVF-NET integrates two displacement vector fields to address nonlinear distortions caused by significant variations between images, enabling more precise image alignment. A key innovation of this method is the incorporation of a Structural Attention Module (SAT), which enhances the model’s ability to focus on structural features, improving the feature extraction process. Additionally, we propose a novel loss function design that combines multiple similarity metrics, ensuring more comprehensive supervision during training. Experimental results on various remote sensing datasets indicate that the proposed DVF-NET outperforms the existing methods in both accuracy and robustness, particularly when handling images with substantial geometric distortions such as tilted buildings. The results validate the effectiveness of our approach and highlight its potential for various remote sensing tasks, including change detection, land cover classification, and environmental monitoring. DVF-NET provides a promising direction for the advancement of remote sensing image registration techniques, offering both high precision and robustness in complex real-world scenarios. Full article

Background: Orthostatic hypotension can occur during acute spinal cord injury (SCI) and subsequently persist. We investigated whether a gait rehabilitation robot combined with functional electrical stimulation (FES) stabilizes hemodynamics during orthostatic stress in SCI. Methods: Six intermediate-phase SCI patients (five males and one female; mean age: 49.5 years; four with quadriplegia and two with paraplegia) participated. The participants underwent robotic training (RT), with a gait rehabilitation robot combined with FES, and tilt table training (TT). Hemodynamics were monitored using a laser Doppler flowmeter for the earlobe blood flow (EBF) and non-invasive blood pressure measurements. The EBF over time and the resting and exercise blood pressures were compared between each session. Adverse events were also evaluated. Results: The EBF change decreased in TT but increased in RT at the 0.5-min slope (p = 0.03). Similarly, the pulse rate change increased in TT but decreased in RT at the 1-min slope (p = 0.03). Systolic and mean blood pressures were slightly higher in RT than in TT but not significantly (p = 0.35; 0.40). No adverse events occurred in RT, but two TT sessions were incomplete due to dizziness. Conclusions: RT with FES can reduce symptoms during orthostatic stress in intermediate-phase SCI. Future studies require a larger number of cases to generalize this study. Full article