Search Results (8,153)

As industrial automation evolves towards human-centric, adaptable solutions, collaborative robots must overcome challenges in unstructured, dynamic environments. This paper extends our previous work on developing a digital shadow for industrial robots by introducing a comprehensive framework that bridges the gap between physical systems and their virtual counterparts. The proposed framework advances toward a fully functional digital twin by integrating real-time perception and intuitive human–robot interaction capabilities. The framework is applied to a hospital test lab scenario, where a YuMi robot automates the sorting of microscope slides. The system incorporates a RealSense D435i depth camera for environment perception, Isaac Sim for virtual environment synchronization, and a locally hosted large language model (Mistral 7B) for interpreting user voice commands. These components work together to achieve bi-directional synchronization between the physical and digital environments. The framework was evaluated through 20 test runs under varying conditions. A validation study measured the performance of the perception module, simulation, and language interface, with a 60% overall success rate. Additionally, synchronization accuracy between the simulated and physical robot joint movements reached 98.11%, demonstrating strong alignment between the digital and physical systems. By combining local LLM processing, real-time vision, and robot simulation, the approach enables untrained users to interact with collaborative robots in dynamic settings. The results highlight its potential for improving flexibility and usability in industrial automation. Full article

Background/Objectives: Combination therapies using traditional Chinese medicine and Western drugs have gained attention for their enhanced therapeutic effects and reduced side effects. Toujie Quwen Granules (TQG), known for its antiviral properties, particularly against respiratory viruses, could offer new treatment strategies when combined with antiviral drugs like arbidol, especially for diseases such as Coronavirus disease. This study investigates the synergistic mechanisms between arbidol and components from TQG against the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) main protease (M^pro). Methods: We identified compounds from TQG via existing data. Multi-ligand molecular docking, pharmacokinetic/toxicity screening, and preliminary simulations were performed to assess potential synergistic compounds with arbidol. UPLC-Q-Exactive Orbitrap-MS verified the presence of these compounds. Extended simulations and in vitro assays, including Luciferase and surface plasmon resonance, validated the findings. Results: Five compounds interacted with arbidol in synergy based on docking and preliminary dynamics simulation results. Only Baicalein (HQA004) could be identified in the herbal remedy by untargeted metabolomics, with ideal pharmacokinetic properties, and as a non-toxic compound. Extended simulations revealed that HQA004 enhanced arbidol’s antiviral activity via a “Far” Addition Mechanism #2, with an optimal 2:1 arbidol:HQA004 ratio. The movements of arbidol (diffusion and intramolecular conformational shifts) in the system were significantly reduced by HQA004, which may be the main reason for the synergism that occurred. In vitro experiments confirmed an increased inhibition of M^pro by the combination. Conclusions: HQA004 demonstrated synergistic potential with arbidol in inhibiting M^pro. The development of combination therapies integrating Western and herbal medicine is supported by these findings for effective antiviral treatments. Full article

Background: Histologic chorioamnionitis (HCA) is a placental inflammatory condition characterized by neutrophilic infiltration of the fetal membranes, often occurring without overt clinical signs or symptoms. Risk factors include prolonged labor, premature rupture of membranes (PROM) exceeding 12 h, nulliparity, labor dystocia, and lower socioeconomic status. Although HCA frequently presents as a subclinical condition, its early diagnosis remains challenging. Nevertheless, HCA is associated with an increased risk of maternal and neonatal morbidity, including early-onset neonatal sepsis, cerebral palsy, and long-term neurodevelopmental impairment. We report the case of a 29-year-old primigravida at 40 + 0 weeks of gestation, admitted for decreased fetal movements. Discussion: Cardiotocographic (CTG) monitoring revealed a “zigzag pattern” in the absence of maternal fever, leukocytosis, or tachycardia. Due to the CTG findings suggestive of possible fetal compromise, in addition to reduced fetal movements, an emergency cesarean section was performed. Intraoperative findings included heavily meconium-stained amniotic fluid, then the examination of the placenta confirmed acute HCA with a maternal inflammatory response, without evidence of fetal inflammatory response. Conclusion: This case highlights the crucial role of CTG abnormalities, particularly the “zigzag pattern,” as an early marker of subclinical intrauterine inflammation. Early recognition of such patterns may facilitate timely intervention and improve perinatal outcomes in cases of histologic chorioamnionitis. Full article

Background/Objectives: International guidelines recommend the combined use of the General Movement Assessment (GMA), Hammersmith Infant Neurological Examination (HINE), and magnetic resonance imaging (MRI) to support early and accurate diagnosis of cerebral palsy (CP). However, their implementation remains inconsistent. This study aimed to map their reported global use and identify associated enablers and barriers. Methods: A scoping review was conducted following JBI and PRISMA-ScR guidelines. Systematic searches were performed in PubMed, Cochrane, PEDro, ProQuest, Web of Science, and Scopus. Eligible studies were charted and thematically analyzed, focusing on tools use and implementation factors at individual, organizational, and system levels. Results: Fourteen articles (seven surveys, seven implementation studies) from seven countries met the inclusion criteria. While awareness of GMA, HINE, and MRI was generally high, routine clinical use was limited—particularly outside structured implementation initiatives. Major barriers emerged at the system level (e.g., limited training access, time constraints, lack of standardized referral pathways) and social level (e.g., unclear leadership and coordination). Conclusions: The limited integration of GMA, HINE, and MRI into routine practice reflects a persistent “know–do” gap in early CP detection. Since implementation is shaped by the dynamic interplay of capability, opportunity, and motivation, bridging this gap demands sustained and equitable action—by addressing system-wide barriers, supporting professional development, and embedding early detection within national care pathways. Full article

Background/Objectives: Deep brain stimulation (DBS) is an effective surgical treatment for Parkinson’s Disease (PD) and other movement disorders. Despite its benefits, DBS explantation occurs in 5.6% of cases, with costs exceeding USD 22,000 per implant. Traditional statistical methods have struggled to identify reliable risk factors for explantation. We hypothesized that supervised machine learning would more effectively capture complex interactions among perioperative factors, enabling the identification of novel risk factors. Methods: The Medical Informatics Operating Room Vitals and Events Repository was queried for patients with DBS, adequate clinical data, and at least two years of follow-up (n = 38). Fisher’s exact test assessed demographic and medical history variables. Data were analyzed using Anaconda Version 2.3.1. with pandas, numpy, sklearn, sklearn-extra, matplotlin. pyplot, and seaborn. Recursive feature elimination with cross-validation (RFECV) optimized factor selection was used. A multivariate logistic regression model was trained and evaluated using precision, recall, F1-score, and area under the curve (AUC). Results: Fisher’s exact test identified chronic pain (p = 0.0108) and tobacco use (p = 0.0026) as risk factors. RFECV selected 24 optimal features. The logistic regression model demonstrated strong performance (precision: 0.89, recall: 0.86, F1-score: 0.86, AUC: 1.0). Significant risk factors included tobacco use (OR: 3.64; CI: 3.60–3.68), primary PD (OR: 2.01; CI: 1.99–2.02), ASA score (OR: 1.91; CI: 1.90–1.92), chronic pain (OR: 1.82; CI: 1.80–1.85), and diabetes (OR: 1.63; CI: 1.62–1.65). Conclusions: Our study suggests that supervised machine learning can identify risk factors for early DBS explantation. Larger studies are needed to validate our findings. Full article

With the rapid development of sports analytics and artificial intelligence, accurate human pose estimation in badminton is becoming increasingly important. However, challenges such as the lack of domain-specific datasets and the complexity of athletes’ movements continue to hinder progress in this area. To address these issues, we propose an enhanced pose estimation framework tailored to badminton players, built upon an improved YOLOv8-Pose architecture. In particular, we introduce an efficient local attention (ELA) mechanism that effectively captures fine-grained spatial dependencies and contextual information, thereby significantly improving the keypoint localization accuracy and overall pose estimation performance. To support this study, we construct a dedicated badminton pose dataset comprising 4000 manually annotated samples, captured using a Microsoft Kinect v2 camera. The raw data undergo careful processing and refinement through a combination of depth-assisted annotation and visual inspection to ensure high-quality ground truth keypoints. Furthermore, we conduct an in-depth comparative analysis of multiple attention modules and their integration strategies within the network, offering generalizable insights to enhance pose estimation models in other sports domains. The experimental results show that the proposed ELA-enhanced YOLOv8-Pose model consistently achieves superior accuracy across multiple evaluation metrics, including the mean squared error (MSE), object keypoint similarity (OKS), and percentage of correct keypoints (PCK), highlighting its effectiveness and potential for broader applications in sports vision tasks. Full article

Background/Objectives: Access to specialized care for patients with cognitive impairment in remote areas is often limited. Despite the increasing adoption of telemedicine, standardized guidelines have not yet been specified. This study aimed to develop a comprehensive protocol for the specialized neurological, neuropsychological, and neuropsychiatric assessment of patients with cognitive disorders in remote areas through telemedicine. Methods: We analyzed data from (i) a comprehensive literature review of the existing recommendations, reliability studies, and telemedicine models for cognitive disorders, (ii) insights from a three-year experience of a specialized telemedicine outpatient clinic for cognitive movement disorders in Greece, and (iii) suggestions coming from dementia specialists experienced in telemedicine (neurologists, neuropsychologists, psychiatrists) who took part in three focus groups. A critical synthesis of the findings was performed in the end. Results: The final protocol included: technical and organizational requirements (e.g., a high-resolution screen and a camera with zoom, room dimensions adequate for gait assessment, a noise-canceling microphone); medical history; neurological, neuropsychiatric, and neuropsychological assessment adapted to videoconferencing; ethical–legal aspects (e.g., data security, privacy, informed consent); clinician–patient interaction (e.g., empathy, eye contact); diagnostic work-up; linkage to other services (e.g., tele-psychoeducation, caregiver support); and instructions for treatment and follow-up. Conclusions: This protocol is expected to serve as an example of good clinical practice and a source for official telemedicine guidelines for cognitive disorders. Ultimate outcomes include the potential enhanced access to specialized care, minimized financial and logistical costs, and the provision of a standardized, effective model for the remote diagnosis, treatment, and follow-up. This model could be applied not only in Greece, but also in other countries with similar healthcare systems and populations living in remote, difficult-to-access areas. Full article

Electromagnetic articulography is a technique developed for recording three-dimensional movements. It is based on magnetic induction, where small currents are induced in miniature receiver coils acting as motion sensors by means of electromagnetic fields generated by transmitter coils. This technology has been applied in dental research to record mandibular movements during mastication, Posselt’s envelope of motion, and micromovements of dental prostheses. The AG501 electromagnetic articulograph (Carstens Medizinelektronik GmbH, Bovenden, Germany) provides a Head Correction (HC) procedure to eliminate head movement, which requires the reference sensors to be firmly attached to the subject’s head. If the sensors shift during the recordings, it becomes necessary to reposition them and repeat the head correction procedure. The aim of this study was to develop a 3D-printed helmet to securely fix the reference sensors to the head of a subject in the context of performing a series of recordings involving the mastication of 36 foods and the execution of Posselt’s envelope of motion. The number of HCs required was recorded for a group using the helmet and for a control group in which the sensors were attached to the subject’s head using tissue adhesive. A total of 29 recordings were conducted with and without the helmet. Without the helmet 44 HCs were required; on the other hand, with the helmet 36 HCs were required. On average, 1.5 HCs were required per session without the helmet and 1.2 HCs with the helmet, showing a non-significant difference (p < 0.05). A reduction in the number of HCs required per session was observed. However, more than one HC was still needed to complete a session. This could be addressed in future research by designing a series of helmets that adapt to different head sizes. Full article

Background/Objectives: Repetitive behaviors such as hand flapping, body rocking, and head shaking characterize Autism Spectrum Disorder (ASD) while functioning as early signs of neurodevelopmental variations. Traditional diagnostic procedures require extensive manual observation, which takes significant time, produces subjective results, and remains unavailable to many regions. The research introduces a real-time system for the detection of ASD-typical behaviors by analyzing body movements through the You Only Look Once (YOLOv11) deep learning model. Methods: The system’s multi-layered design integrates monitoring, network, cloud, and typical ASD behavior detection layers to facilitate real-time video acquisition, wireless data transfer, and cloud analysis along with ASD-typical behavior classification. We gathered and annotated our own dataset comprising 72 videos, yielding a total of 13,640 images representing four behavior classes that include hand flapping, body rocking, head shaking, and non_autistic. Results: YOLOv11 demonstrates superior performance compared to baseline models like the sub-sampling (CNN) (MobileNet-SSD) and Long Short-Term Memory (LSTM) by achieving 99% accuracy along with 96% precision and 97% in recall and the F1-score. Conclusions: The results indicate that our system provides a scalable solution for real-time ASD screening, which might help clinicians, educators, and caregivers with early intervention, as well as ongoing behavioral monitoring. Full article

Research on semantic segmentation for remote sensing road scenes advanced significantly, driven by autonomous driving technology. However, motion blur from camera or subject movements hampers segmentation performance. To address this issue, we propose a knowledge distillation-based semantic segmentation network (KDS-Net) that is robust to motion blur, eliminating the need for image restoration networks. KDS-Net leverages innovative knowledge distillation techniques and edge-enhanced segmentation loss to refine edge regions and improve segmentation precision across various receptive fields. To enhance the interpretability of segmentation quality under motion blur, we incorporate fractal dimension estimation to quantify the geometric complexity of class-specific regions, allowing for a structural assessment of predictions generated by the proposed knowledge distillation framework for autonomous driving. Experiments on well-known motion-blurred remote sensing road scene datasets (CamVid and KITTI) demonstrate mean IoU scores of 72.42% and 59.29%, respectively, surpassing state-of-the-art methods. Additionally, the lightweight KDS-Net (21.44 M parameters) enables real-time edge computing, mitigating data privacy concerns and communication overheads in internet of vehicles scenarios. Full article

Critical components in support structures for wind turbines, flange joints, are fundamental to ensure the structural integrity of mechanical assemblies under varying operational conditions. This paper investigates the structural performance of L-type flange joints, focusing on the influence of bolt grades and bolt pretension through a finite element analysis (FEA) study of its key performance indicators, including stress distribution, deformation, and force–displacement behaviors. This paper studies two high-strength bolt grades, Grade 10.9 and Grade 12.9, and two main steps—first, bolt pretension and, second, external loading (tower shell tensile load)—to investigate the influence on joint reliability and safety margins. The novelty of this study lies in its specific focus on static axial loading conditions, unlike the existing literature that emphasizes fatigue or dynamic loads. Results show that the specimen carrying a higher bolt grade (12.9) has 18% more ultimate load carrying capacity than the specimen with a lower bolt grade (10.9). Increased pretension increases the stability of the joint and reduces the micro-movements between A and B (on model specimen), but could result in material fatigue if over-pretensioned. Comparative analysis of the different bolt grades has provided practical guidance on material selection and bolt pretension in L-type flange joints for wind turbine support structures. The findings of this work offer insights into the proper design of robust flange connections for high-demand applications by highlighting a balance among material properties, bolt pretension, and operational conditions, while also proposing optimized pretension and material recommendations validated against classical analytical models. Full article

Background/Objectives: Accurately predicting the arrival position of a moving target is essential in sports and daily life. While predictive saccades are known to enhance performance, the neural mechanisms underlying the timing of these strategies remain unclear. This study investigated how the timing of saccadic strategies—executed early versus late—affects cortical activity patterns, as measured by electroencephalography (EEG). Methods: Sixteen participants performed a task requiring them to predict the arrival position and timing of a parabolically moving target that became occluded midway through its trajectory. Based on eye movement behavior, participants were classified into an Early Saccade Strategy Group (SSG) or a Late SSG. EEG signals were analyzed in the low beta band (13–15 Hz) using the Hilbert transform. Group differences in eye movements and EEG activity were statistically assessed. Results: No significant group differences were observed in final position or response timing errors. However, time-series analysis showed that the Early SSG achieved earlier and more accurate eye positioning. EEG results revealed greater low beta activity in the Early SSG at electrode sites FC6 and P8, corresponding to the frontal eye field (FEF) and middle temporal (MT) visual area, respectively. Conclusions: Early execution of predictive saccades was associated with enhanced cortical activity in visuomotor and motion-sensitive regions. These findings suggest that early engagement of saccadic strategies supports more efficient visuospatial processing, with potential applications in dynamic physical tasks and digitally mediated performance domains such as eSports. Full article

Biomimetic design for engineering applications may suggest the optimal performance of engineering devices. In this work the passive/pure pitching characteristics of a hydrofoil are investigated experimentally with and without a pair of biomimetic fin strips placed symmetrically on the two sides of the foil leading edge. The work is performed in a recirculating water channel at low Reynolds numbers (Re) with a range of 1300 ≤ Re ≤ 3200. Using high-speed videography and Particle Image Velocimetry (PIV), the pitching characteristics and wakes are visualized. Passive pitching characteristics, i.e., the pitching amplitude and pitching frequency of the hydrofoils, are investigated based on their trailing edge movement. Significant improvement in both pitching frequency and amplitudes are observed for the foil with fin strips compared to the baseline simple foil. Comparing the pitching characteristics of the two foils, it is observed that the hydrofoil with biomimetic fin strips exhibits 25% and 21% higher pitching amplitude and pitching frequency, respectively, compared to that of the baseline at comparable Reynolds numbers. The initiation of pitching for the finned foil is also observed at comparatively low Reynolds numbers. The wake is also studied using time mean and fluctuating velocity profiles obtained using PIV. Full article

The present research is related to the application of artificial intelligence (AI) approaches for classifying surface textures, specifically regular reliefs patterns formed by ball burnishing operations. A two-stage methodology is employed, starting with the creation of regular reliefs (RRs) on test parts by ball burnishing, followed by 3D topography scanning with Alicona device and data preprocessing with Gwyddion, and Blender software, where the acquired 3D topographies are converted into a set of 2D images, using various virtual camera movements and lighting to simulate the symmetrical fluctuations around the tool-path of the real camera. Four pre-trained convolutional neural networks (DenseNet121, EfficientNetB0, MobileNetV2, and VGG16) are used as a base for transfer learning and tested for their generalization performance on different combinations of synthetic and real image datasets. The models were evaluated by using confusion matrices and four additional metrics. The results show that the pretrained VGG16 model generalizes the best regular reliefs textures (96%), in comparison with the other models, if it is subjected to transfer learning via feature extraction, using mixed dataset, which consist of 34,037 images in following proportions: non-textured synthetic (87%), textured synthetic (8%), and real captured (5%) images of such a regular relief. Full article

For the airfoil in freestream, the pressure difference between the upper and lower surfaces and the variations in pressure gradients are significant at its leading edge area. Under reasonable deflections, the active leading edge can effectively change airfoil aerodynamic loads, which helps to improve the rotor aerodynamic performance. In this paper, a modeling method for an airfoil with an active leading edge was developed to calculate its aerodynamic loads. The pitch motion of the rotor blade and the leading edge deflections were taken into account. Firstly, simulations of steady and unsteady flow for the airfoil with an active leading edge were conducted under different boundary conditions and with different leading edge deflection movement. Secondly, the rational function approximation (RFA) was employed to establish the relationship between aerodynamic loads and airfoil/active leading edge deflections. Then, coefficient matrices of the RFA approach were identified based on a limited number of high-fidelity computational fluid dynamics (CFD) results. Finally, an aerodynamic model of the airfoil with an active leading edge was developed, and its accuracy was validated by comparing it to the high-fidelity CFD results. Comparative results reveal that the developed model can calculate the aerodynamic loads of an airfoil with an active leading edge accurately and efficiently when applied appropriately. The modeling method can be used in aerodynamic load calculations and the aeroelastic coupling analysis of a rotor with active control devices. Full article