Search Results (315)

Foraging behavior in hens is an important indicator of animal welfare. It involves both the search for food and exploration of the environment, which provides necessary enrichment. In addition, it has been inversely linked to damaging behaviors such as severe feather pecking. Conventional studies rely on manual observation to investigate foraging location, duration, timing, and frequency. However, this approach is labor-intensive, time-consuming, and subject to human bias. Our study developed computer vision-based methods to automatically detect foraging hens in a cage-free research environment and compared their performance. A cage-free room was divided into four pens, two larger pens measuring 2.9 m × 2.3 m with 30 hens each and two smaller pens measuring 2.3 m × 1.8 m with 18 hens each. Cameras were positioned vertically, 2.75 m above the floor, recording the videos at 15 frames per second. Out of 4886 images, 70% were used for model training, 20% for validation, and 10% for testing. We trained multiple You Only Look Once (YOLO) object detection models from YOLOv9, YOLOv10, and YOLO11 series for 100 epochs each. All the models achieved precision, recall, and mean average precision at 0.5 intersection over union (mAP@0.5) above 75%. YOLOv9c achieved the highest precision (83.9%), YOLO11x achieved the highest recall (86.7%), and YOLO11m achieved the highest mAP@0.5 (89.5%). These results demonstrate the use of computer vision to automatically detect complex poultry behavior, such as foraging, making it more efficient. Full article

Objectives: Older adults who worry about not being able to stand up from the floor after a fall, reduce their physical activity, which leads to a higher risk of falling. The Backward Chaining Method (BCM) was developed specifically for this population to safely teach and practice the movement sequence required to stand up from the floor. Our aim is to evaluate the effectiveness of using the BCM to teach older adults how to stand up from the floor, and to determine whether this training has an impact on functional mobility, muscle strength, fear of falling, and life-space mobility. Methods: A total of 26 residents of a long-term care facility were randomly allocated to two groups. Residents in the intervention group (IG, n = 13) participated in a seven-week training program to learn how to stand up from the floor with BCM, in addition to the usual care generally offered in long-term care facilities. The participants in the control group (CG, n = 13) received the usual care alone. The primary outcome measure was functional mobility, assessed by the Timed Up and Go test. Secondary outcome measures included functional lower limb strength, grip strength, fear of falling, and life-space mobility. The outcomes were measured at baseline and after the seven-week intervention period. Results: We found no significant between-group differences in functional mobility, lower limb strength and grip strength; however, IG subjects demonstrated significantly lower fear of falling scores, and significantly higher life-space mobility and independent life-space mobility scores compared to CG subjects after the training program. Conclusions: This study demonstrates that the Backward Chaining Method is a feasible, well-tolerated intervention in a long-term care setting and it may have meaningful benefits, particularly in lessening fear of falling and improving life-space mobility and independent life-space mobility when incorporated into the usual physiotherapy interventions. Full article

Introduction: Overactive bladder (OAB) and urinary incontinence (UI) are prevalent, particularly in older adults, and affect quality of life. OAB involves urgency, frequency, nocturia, and urgency incontinence, often linked to involuntary detrusor contractions. Treatment guidelines recommend a stepwise approach, starting with pelvic floor muscle training (PFMT), followed by pharmacological or minimally invasive therapies, such as neuromodulation. However, the combined effects of PFMT and neuromodulation have not been well established. This study aimed to evaluate the impact of combining pelvic floor exercises with neuromodulation versus PFMT with sham neuromodulation or standard physiotherapy after a 12-week intervention in individuals with OAB and UI. Methods/Materials: A double-blind, randomized controlled trial was designed with three groups: PFMT + neuromodulation, PFMT + sham, and conventional physiotherapy (control) in a 1:1:1 ratio. This study followed the CONSORT guidelines and was registered at ClinicalTrials.gov (NCT06783374). The sample size was calculated using GPower^® software, assuming a Cohen’s effect size of 1.04, a power of 0.80, an alpha of 0.05, and a 15% dropout rate, totaling 63 participants (21 per group). Participants attended 24 sessions over 12 weeks (2 sessions per week). The interventions were based on previously validated protocols. Outcomes: The primary outcomes included health-related quality of life, pelvic floor muscle function, pain, adherence, and general health. The secondary outcomes included Incontinence Quality of Life questionnaire, 3-day bladder diary, International Consultation on Incontinence Questionnaire–Urinary Incontinence Short Form, kinesiophobia, and electromyographic data. Full article

This research takes the Suzhou Gardens, a World Cultural Heritage Site, as the object of study and investigates a rapid scheme generation approach for garden restoration and expansion projects, assisting designers in making scientific decisions. Considering the limitations of current garden design, which is inefficient and relies on human experience, this study proposes an intelligent generation framework based on a conditional generative adversarial network (CGAN). In constructing the CGAN model, we determine the spatial characteristics of the Suzhou Gardens and, combined with historical floor plan data, train the network. We then design an optimization strategy for the model training process and finally test and verify the generative space scheme. The research results indicate the following: (1) The CGAN model can effectively capture the key elements of the garden space and generate a planar scheme that conforms to the traditional space with an accuracy rate reaching 91.08%. (2) This model can be applied to projects ranging from 200 to 1000 square meters. The generated results can provide multiple scheme comparisons for update decisions, helping managers to efficiently select the optimal solution. (3) Decision-makers can conduct space utilization analyses and evaluations based on the generated results. In conclusion, this study can help decision-makers to efficiently generate and evaluate the feasibility of different design schemes, providing intelligent support for decision-making in urban renewal plans. Full article

Background: The aim of this review was to analyze training interventions used and their effectiveness in improving pelvic floor muscle function related to urinary continence in postmenopausal women. We then characterized the recommended pelvic floor muscle training programs used in experimental studies based on four training components: frequency, intensity, duration, and type of pelvic floor muscle exercise. Methods: For this purpose, we conducted a literature review of works published up until the end of 2024, available in the Web of Science, PubMed, MEDLINE, and SPORTDiscus with Full Text databases. We used the keywords “pelvic floor muscle”, “training”, and “postmenopausal women”. Initially, we identified 205 articles published between 1997 and 2024. Then, based on specific criteria, we qualified 15 for analysis. Results: Thirteen studies included only PFMT, while three of them combined PFMT with other physical activity. In two studies, training was conducted in the form of a virtual video game using a pressure platform. We have noted that researchers most often use a 1 h pad test, digital palpation, and surface electromyography to assess the function of pelvic floor muscles. In improving pelvic floor muscle function related to urinary incontinence, 14 out of the 15 analyzed studies showed improvement. In only eight of the fifteen articles, researchers characterized all components of the implemented PFMT that enable full replication of the training intervention. In four of the studies, only one of the required components, namely intensity, was missing. The recommended number of training sessions was 2 to 7 per week, on average 3 ± 2 (M ± SD). Training interventions lasted from 2 to 24 weeks, on average 10 ± 6 weeks. Conclusions: Regardless of the chosen form of training intervention, PFMT is an effective method in improving the function of pelvic floor muscles in postmenopausal women. Full article

The ecological region and training system are critical in determining an orchard’s microclimate and, ultimately, the quality and yield of the fruit produced. However, few studies have addressed the effects of their interactions on the commodity properties preferred by consumers, including appearance, flavor, and nutritional components. This study was conducted in distinct ecological regions at the county scale, with two classic cultivation modes (a traditional freestanding system with natural grassing and fruit without bagging and a flat-type trellis system with floor covering and fruit bagging) used for investigation and testing in 2020 and 2024, respectively. Significant differences in internal and external quality attributes were observed between the two groups. A sensory analysis showed that an increase in the soluble solid content and a better fruit appearance were strongly associated with higher purchase intentions. By integrating meteorological parameters, it was also found that temperature and air humidity during the month before harvest were associated with the pear phytochemical and metabolomic profiles. Planting site had a particularly notable effect on quality attributes and sensory experience, with low-latitude-harvested samples under cultivation mode 1 clustering together and showing higher overall scores, while cultivation mode 2 may be more suitable for high-latitude areas. Our results pave the way for making precise recommendations for the selection of suitable planting sites and optimum cultivation modes in Jiangxi Province to achieve high-quality ‘Cuiguan’ pears and fully exploit their planting potential. Full article

Background: Stress urinary incontinence (SUI) is frequently underrecognized in late pregnancy, with limited tools for effective risk assessment. This study aimed to evaluate the predictive value of clinical and pelvic floor ultrasound parameters for SUI and construct a validated risk model. Methods: Clinical, obstetric, and pelvic floor ultrasound findings were collected from a total of 521 women in late pregnancy who were enrolled in the study. Based on follow-up results, participants were categorized into SUI and non-SUI groups. Logistic regression analyses were used to identify independent risk factors for SUI, which were incorporated into a nomogram. Results: Four independent predictors were identified: vaginal delivery history (odds ratio [OR] = 2.320), bladder neck funneling (OR = 2.349), bladder neck descent (OR = 1.891), and pubococcygeus muscle contraction strain rate (OR < 0.001). The nomogram achieved an AUC of 0.817 (95% CI: 0.770–0.863) in the training set and 0.761 (95% CI: 0.677–0.845) in the test set. Conclusions: The nomogram based on clinical and pelvic floor ultrasound parameters accurately predicts the risk of SUI during late pregnancy, offering a useful tool for early identification and personalized management. Full article

Robust visual perception and geometric alignment are crucial for intelligent automation in various domains, such as industrial processes and infrastructure monitoring. Accurately aligning structured visual elements, such as floor markings or road-marking templates, is essential for tasks like automated guidance, verification, and condition assessment. However, traditional feature-based methods struggle with templates that feature simple geometries and lack rich textures, making reliable feature matching and alignment difficult, even under controlled conditions. To address this, we propose GeoTemplateKPNet, a novel self-supervised deep-learning framework, built upon Convolutional Neural Networks (CNNs), designed to learn robust, geometrically consistent keypoints specifically in synthetic template images. The model is trained exclusively in a synthetic template dataset by enforcing equivariance to geometric transformations and utilizing self-supervised losses, including inside mask loss, peakiness loss, repulsion loss, and keypoint-driven image reprojection loss, thereby eliminating the need for manual keypoint annotations. We evaluate the method in a synthetic template test set, using metrics such as a keypoint-matching comparison, the Inside Mask Rate (IMR), and the Alignment Reconstruction Error (ARE). The results demonstrate that GeoTemplateKPNet successfully learns to predict meaningful keypoints on template structures, enabling accurate alignment between templates and their transformed counterparts. Ablation studies reveal that the number of keypoints (K) impacts the performance, with K = 3 providing the most suitable balance for the overall alignment accuracy, although the performance varies across different template geometries. GeoTemplateKPNet offers a foundational self-supervised solution for the robust geometric analysis of templates, which is crucial for downstream alignment tasks and applications. Full article

A previously buried paleosol was found on the continental shelf during a study of sea floor scour, nucleated by large artificial reef structures such as vessel hulks, barges, train cars, military vehicles, etc., called “scour nuclei”. It is a relic paleo-land surface of sapling-sized tree stumps, root systems, and fossil animal bone exhumed by scour processes active adjacent to the artificial reef structure. Over the span of five research cruises to the site in 2022–2024, soil samples were taken using hand excavation, PONAR grab samplers, split spoon, hollow tube auger, and a modified Shelby-style push box. High-definition (HD) video was taken using a Remotely Operated Vehicle (ROV) and diver-held cameras. Radiocarbon dating of wood samples returned ages of 42,015–43,417 calibrated years before present (cal yrBP). Pollen studies, together with the recovered macrobotanical remains, support our interpretation of the site as a freshwater forested wetland whose keystone tree species was Taxodium distichum—bald cypress. The paleosol was identified as an Aquult, a sub-order of Ultisols where water tables are at or near the surface year-round. A deep (0.25 m+) argillic horizon comprised the bulk of the preserved soil. Comparable Ultisols found in Georgia wetlands include Typic Paleaquult (Grady and Bayboro series) soils. Full article

Defect repair on custom-curved glulam beams is still performed manually because knots are irregular, numerous, and located on elements that cannot pass through linear production lines, limiting the scalability of timber-based architecture. This study presents Woodot, an autonomous mobile robotic platform that combines an omnidirectional rover, a six-dof collaborative arm, and a fine-tuned Segment Anything computer vision pipeline to identify, mill, and plug surface knots on geometrically variable beams. The perception model was trained on a purpose-built micro-dataset and reached an F1 score of 0.69 on independent test images, while the integrated system located defects with a 4.3 mm mean positional error. Full repair cycles averaged 74 s per knot, reducing processing time by more than 60% compared with skilled manual operations, and achieved flush plug placement in 87% of trials. These outcomes demonstrate that a lightweight AI model coupled with mobile manipulation can deliver reliable, shop-floor automation for low-volume, high-variation timber production. By shortening cycle times and lowering worker exposure to repetitive tasks, Woodot offers a viable pathway to enhance the environmental, economic, and social sustainability of digital timber construction. Nevertheless, some limitations remain, such as dependency on stable lighting conditions for optimal vision performance and the need for tool calibration checks. Full article

In structural health monitoring, visual inspection remains vital for detecting damage, especially in concealed elements such as columns and beams. To improve damage localization, many studies have investigated and implemented deep learning into damage detection frameworks. However, the practicality of such models is often limited by their computational demands, and the relative accuracy may suffer if input features lack sensitivity to localized damage. This study introduces an efficient method for estimating damage locations and severity in buildings using a neural network array. A synthetic dataset is first generated from a simplified building model that includes floor flexural behavior and reflects the target dynamics of the structures. A dense, single-layer neural network array is initially trained with full floor accelerations, then pruned iteratively via the Lottery Ticket Hypothesis to retain only the most effective sub-networks. Subsequently, critical event measurements are input into the pruned array to estimate story-wise stiffness reductions. The approach is validated through numerical simulation of a six-story model and further verified via shake table tests on a scaled twin-tower steel-frame building. Results show that the pruned neural network array based on the Lottery Ticket Hypothesis achieves high accuracy in identifying stiffness reductions while significantly reducing computational load and outperforming full-input models in both efficiency and precision. Full article

Background/Objectives: Urinary incontinence (UI) is a frequent and distressing complication after radical prostatectomy (RP). Pelvic floor muscle training (PFMT) is widely recommended as first-line rehabilitation, yet the clinical factors influencing its effectiveness remain incompletely understood. Methods: This prospective cohort study included 182 men undergoing RP who completed a standardized physiotherapy program involving pelvic floor muscle exercises, biofeedback (BFB), and ultrasound-guided training. UI severity was assessed using the 1-h pad test and recorded absorbent product use. Outcomes were evaluated at three time points: one month, three months, and six months post-catheter removal. A multiple linear regression model was used to identify the predictors of continence improvement, defined as the change in pad test result between baseline and six months. Results: Pad test results and absorbent use decreased significantly across all UI severity stages (p < 0.0001). The greatest absolute improvement was observed in patients with severe incontinence at baseline (UI stage 3: mean reduction from 130.8 g to 23.7 g). Regression analysis revealed that only the baseline pad test result was significantly associated with the magnitude of improvement (β = 0.91; 95% CI: 0.85–0.97, p < 0.001; R² = 0.89). Age, BMI, and time to rehabilitation were not significant predictors. Conclusions: Pelvic floor rehabilitation after RP is effective in improving continence, including in patients with severe baseline symptoms. The baseline pad test value emerged as the strongest predictor of rehabilitation response, highlighting the importance of initial assessment. These findings support the use of PFMT in clinical practice and emphasize the need for individualized treatment planning based on baseline UI severity. Full article

The number of people suffering from urinary incontinence increases every year. Along this trend, the knowledge of society increases regarding the various methods available for treating this ailment. Both patients and researchers are constantly looking for new treatments for urinary incontinence. One of the new solutions is sonofeedback of the pelvic floor muscles, which may help to strengthen them and thus reduce the problem. The aim of this study was to evaluate the effectiveness of sonofeedback and transvaginal electrostimulation in increasing the bioelectrical activity of pelvic floor muscles in postmenopausal women with stress urinary incontinence. Sixty women with stress urinary incontinence were enrolled in the study. The patients were divided into two groups: A, where sonofeedback was used, and B, where electrostimulation of the pelvic floor muscles was performed with biofeedback training. In patients, the resting bioelectrical activity of the pelvic floor muscles was assessed using an electromyograph. The assessment of the resting bioelectrical activity of the pelvic floor muscles was performed before the therapy, after the 5th training, and after the therapy. It was observed that after the end of the therapy, the average bioelectrical potential increased by 1.1 µV compared with the baseline in group A. It can be suggested that the sonofeedback method is comparatively effective in reducing symptoms that are associated with urinary incontinence as an electrostimulation method with biofeedback training. Full article

This article presents a comprehensive analysis of the potential for microgeneration of electrical energy from human physical activity and reviews current commercial and research solutions, including stationary bicycles, treadmills, rowing ergometers, strength equipment, and kinetic floor systems. The physiological foundations of human energy generation are examined, with attention to key factors such as age, gender, fitness level, maximum oxygen uptake, heart rate, and hydration. The study includes mathematical models of energy conversion from metabolic to electrical output, incorporating fatigue as a limiting factor in long-duration performance. Available energy storage technologies (e.g., lithium-ion batteries, supercapacitors, and flywheels) and intelligent energy management systems (EMS) for use in sports facilities and net-zero energy buildings are also reviewed. As part of the study, a conceptual design of a multifunctional training and diagnostic device is proposed to illustrate potential technological directions. This device integrates microgeneration with dynamic physiological monitoring and adaptive load control through power electronic conversion. The paper highlights both the opportunities and limitations of harvesting human-generated energy and outlines future directions for sustainable energy applications in fitness environments. A preliminary economic analysis is also included, showing that while the energy payback alone is limited, the device offers commercial potential when combined with diagnostic and smart fitness services and may contribute to broader building energy efficiency strategies through integration with intelligent energy systems. Full article

Given that aging deterioration significantly influences the structural behavior of reinforced concrete (RC) nuclear power plant (NPP) structures, it is crucial to incorporate changes in the material properties of NPPs for accurate prediction of seismic responses. In this study, machine learning (ML) models for predicting the seismic response of RC NPP structures were developed by considering aging deterioration. The OPR1000 was selected as a representative structure, and its finite element model was generated. A total of 500 artificial ground motions were created for time history analyses, and the analytical results were utilized to establish a database for training and testing ML models. Six ML algorithms, commonly employed in the structural engineering domain, were used to construct the seismic response prediction model. Thirteen intensity measures of artificial earthquakes and four material properties were employed as input parameters for the training database. The floor response spectrum of the example structure was chosen as the output for the database. Four evaluation metrics were implemented as quantitative measures to assess the prediction performance of the ML models. This study used multiple input variables to represent the characteristics of the seismic loads and changes in material properties, thereby increasing the minimum required database size for ML model development. This increase may extend the time and effort required to construct the database. Consequently, this study also explored the possibility of reducing the minimum required database size and the prediction performance through input dimension reduction of the ML model. Numerical results demonstrated that the developed ML model could effectively predict the seismic responses of RC NPP structures, taking into account aging deterioration. Full article