Search Results (5,278)

Using the Suzhou East Station integrated transportation hub as a case study, this paper investigates the train-induced vibration responses and their distribution patterns under various operating conditions of high-speed railway lines, intercity lines, and subway lines. The results show that train speed is the dominant factor: the high-speed railway passage controls floor vibrations in most stories, while line distance also plays a role for some floors. No significant amplification is observed under multi-train convergence; the vibration level is similar to that of the most unfavorable single-train condition. Therefore, only the most unfavorable single-train condition needs to be considered. As vibrations propagate upward through the floors, high-frequency vibrations gradually attenuate while low-frequency vibrations are amplified, leading to an overall amplification of vibrations at the top floors of some buildings. The floor vibration response level decreases as the vertical stiffness of the structural member increases. Cantilevered slabs and mid-span areas are vibration-sensitive zones. For station–city integrated transportation hubs with high-speed railways running underneath, track vibration mitigation measures should be prioritized, such as thickening the track slab. Thin side-wall vibration mitigation pads have a poor vibration reduction effect. When diaphragm walls are rigidly connected to the station and buildings, they amplify the building’s vibration response. Full article

Particle accelerators are complex facilities that collide particles at extreme high speed, aiming to discover new physics. In this context, high-energy calorimeter systems play a crucial role, as they provide the particle energy quantity, which is important information for the potential new discoveries. Therefore, this work evaluates the performance of the commonly used Optimal Filter (OF) method and several Convolutional Neural Network (CNN) architectures in reconstructing the amplitude and phase of simulated signals that represent the response pulses produced by high-energy calorimeters. The comparison is conducted using quantitative metrics—including RMS, MAE, MedAE, and Coefficient of Determination. The results show that different CNN architectures exhibit varying performances depending on the calorimeter cell occupancy rate but generally outperform the typical linear OF method, providing more accurate signal reconstructions. Considering all evaluated occupancy levels (10%, 50%, 80%, and 100%), the CNN-based approaches achieved an average improvement of approximately 79% in amplitude RMS and 62% in amplitude standard deviation when compared to the OF method. For phase estimation, the CNNs achieved improvements of approximately 26% for both RMS and standard deviation metrics. Although the proposed strategy requires a large execution time due to the training process across multiple folds, these findings indicate that CNNs are promising alternatives for calorimeter energy reconstruction, particularly in high-occupancy conditions such as those expected for high-luminosity experiments. Full article

Knowledge Tracing (KT) plays a pivotal role in Intelligent Tutoring Systems (ITS) by dynamically assessing learners’ evolving knowledge states. However, tracking the acquisition of English presents unique challenges. Existing KT models typically employ homogeneous, predefined forgetting mechanisms that fail to capture the highly individualized nature of linguistic memory retention. Furthermore, language assessment data is notoriously noisy, which leads models to overfit superficial performance rather than capturing true underlying linguistic competence. To address these issues, we propose a novel framework to robustly trace English language competence. First, we introduce a Learning-Profile-Driven Adaptive Forgetting mechanism. Unlike methods with shared forgetting rates, our approach constructs a dynamic and strictly causal profile from historical interactions to generate personalized cognitive parameters (e.g., individualized forgetting rates). These parameters synchronously modulate the decay of multi-level knowledge states, enabling the model to accurately capture the heterogeneous memory retention patterns of different learners. Second, we design a Masked Consistency Regularization training paradigm. By applying stochastic masking to historical responses and enforcing predictive consistency, we prevent the model from exploiting localized noise and “shortcut” learning, compelling it to mine robust and invariant language representations. Extensive experiments on real-world educational datasets demonstrate that our proposed framework significantly outperforms state-of-the-art baselines in both prediction accuracy and noise resistance, offering a robust and interpretable solution for personalized language learning. Full article

Background/Objectives: Community-based drug rehabilitation is a key component of public health strategies in China, with anti-drug social workers playing a frontline role in relapse prevention, social reintegration, and long-term recovery. However, the sustainability and effectiveness of this workforce remain uncertain due to complex organisational and structural conditions. This study aims to examine the professional roles, work-related challenges, and coping strategies of anti-drug social workers within community-based rehabilitation systems. Methods: A systematic review was conducted in accordance with PRISMA 2020 guidelines and was registered in PROSPERO (Registration ID: 1381833). The literature published between 2009 and 2025 was identified through Google Scholar, PubMed, Web of Science, and the Electronic Library. A total of 35 Chinese and English-language studies met the inclusion criteria and were analysed to synthesise evidence on social work practice in drug rehabilitation contexts. Results: The findings identify three core professional roles: information provider, resource linker, and relationship repairer. These roles highlight the multifaceted contribution of social workers in bridging institutional systems and client needs. However, their effectiveness is constrained by fragmented governance structures, role conflict, professional identity ambiguity, administrative burden, limited training, and sustained emotional labour. These conditions contribute to occupational stress, burnout risk, and workforce instability, which weaken service continuity and client-centred care. Conclusions: Strengthening community-based drug rehabilitation requires addressing workforce and system-level constraints. Clearer role definition, targeted interdisciplinary training, reduced administrative demands, and structured organisational support are essential to enhance professional capacity, improve service delivery, and support long-term recovery outcomes. Full article

A common limitation of existing multi-AGV cooperative systems is their reliance on the obstacle-agnostic Manhattan distance as the basis for reward signals. This causes agents to receive misleading feedback, engage in excessive futile exploration, and ultimately achieve poor training quality. To address this, we introduce an A*-distance guidance mechanism for multi-agent reinforcement learning (MARL) path planning, built on the precise path distance computed via the A* algorithm (A*-distance). Within the QMIX framework, we incorporate an A*-distance-based guiding function into the action selection mechanism. This function evaluates candidate actions by quantifying their immediate effect on the A*-distance, providing positive incentives for actions that bring the agent closer to the goal and applying negative penalties for those that lead it farther away. This effectively biases exploration towards actions that genuinely shorten the obstacle-aware path to the goal, suppresses ineffective exploration, and accelerates policy convergence. Experiments in four warehouse environments (simple obstacles, complex obstacles, large-scale, and congested) show that, compared with standard QMIX, the proposed method achieves higher global average reward and faster convergence. The advantage grows as environment scale and obstacle density increase. In the large-scale and congested environments, standard QMIX and the other MARL baselines fail to solve the task, whereas the proposed method still succeeds. It is the only learning-based method to solve these hardest tasks while keeping path length close to that of dedicated search-based solvers. Ablation experiments further show that the A*-distance-guided action selection is the primary contributor to these gains, while the A*-distance reward plays a supporting role. Full article

Soil organic carbon (SOC) plays a critical role in climate regulation, soil fertility, and ecosystem resilience, making its accurate spatial quantification essential for sustainable land management and greenhouse gas (GHG) reporting. However, mapping SOC in heterogeneous agroforestry systems remains challenging due to vegetation cover and landscape complexity. In this study, we develop and evaluate a hybrid bare soil modelling- Digital Soil Mapping supported by ML framework to generate high-resolution soil properties predictions in Mediterranean agroforestry systems (Extremadura, Spain). A dual modelling approach was implemented, combining (i) Bare Soil modelling using Sentinel-2 multi-temporal reflectance composites and (ii) Digital Soil Mapping (DSM) supported by environmental covariates (climate, terrain, vegetation) following the SCORPAN framework. Machine learning models, namely Quantile Regression Forests (QRF) and Extreme Gradient Boosting (XGBoost), were applied and optimised using automated hyperparameter tuning (FLAML). A total of 107 LUCAS topsoil samples and 36 complementary points from the Forest ICP Level I were used for calibration and validation, with a 70/30 train–test split. Results show that Sentinel-2-based modelling can effectively capture SOC spatial variability in bare soil conditions, while DSM improves predictions in vegetated areas. Model performance reached R² values up to 0.76 (QRF, pH) and RMSE as low as 0.03 (XGBoost, N), with uncertainty quantified using the Prediction Interval Ratio (PIR) and performance further supported by RPIQ values up to 3.15. However, prediction accuracy remains sensitive to vegetation structure and sample density. The proposed framework provides a scalable and uncertainty-aware approach for SOC mapping, supporting Tier-3 GHG inventories and emerging Monitoring, Reporting, and Verification (MRV) systems. The results highlight the importance of integrating multi-source datasets and hybrid modelling strategies for reliable SOC estimation in complex landscapes. Full article

Background: Medication errors remain a major threat to patient safety in acute care settings worldwide and are associated with preventable morbidity, mortality, and increased healthcare costs. Nurses play a critical role in identifying, intercepting, and preventing medication-related harm. However, limited qualitative evidence has explored nurses’ perspectives on medication safety within the Saudi Arabian healthcare context. This study explored nurses’ experiences of medication safety, perceived systemic challenges, and strategies for error prevention in Saudi hospitals. Methods: A qualitative descriptive design was employed. Fourteen (n = 14) nurses from two major referral hospitals in Saudi Arabia participated in semi-structured face-to-face interviews. Interviews were audio-recorded, transcribed verbatim, and analyzed using Braun and Clarke’s six-phase thematic analysis framework. Results: Five overarching themes were identified: (1) Communication gaps; (2) Medication processes; (3) Technology and safety; (4) Workload and staffing; and (5) Staff competence. Participants described how communication failures, staffing pressures, workflow interruptions, and documentation ambiguities compromised medication safety. While barcode systems and EHRs were perceived as valuable safeguards, participants emphasized that their effectiveness depended on staff vigilance, adequate training, and supportive workplace cultures. Conclusions: Medication safety is a dynamic socio-technical process shaped by communication, competence, staffing capacity, and human interaction with technology. Improving safety requires integrated organizational strategies that combine workforce investment, structured communication practices, continuous professional education, and non-punitive incident reporting cultures. These findings provide practical insights for healthcare leaders seeking to strengthen medication safety systems in Saudi Arabia and comparable settings. Full article

Background/Objectives: Postoperative monitoring of microvascular free flaps is critical for early detection of vascular complications and flap survival. Nurses play a central role in this process; however, qualitative evidence on their experiences and challenges remains limited. This study explored nurses’ experiences in free tissue flap care to identify clinical practices, challenges, and improvement needs. Methods: A phenomenological qualitative design was used. Data were collected through semi-structured interviews with nine nurses experienced in free tissue flap care, recruited via purposive and snowball sampling. Interviews were conducted online and lasted 30–45 min. Data were analyzed using content analysis with MAXQDA 2025. Inter-researcher reliability was 97%. Results: The findings were categorized into four main themes and seventeen subthemes: (1) clinical monitoring and evaluation in the care process, (2) challenges and difficulties, (3) emotional and professional reflections, and (4) suggestions for improving care. Nurses reported that flap care requires intensive monitoring, rapid decision-making, and close collaboration with physicians, especially within the first 24–48 h. Monitoring was largely based on observation and experience due to the lack of standardized protocols. Major challenges included high workload, frequent assessments, and donor site management. Emotional burden, stress, and responsibility were also prominent. Conclusions: Free flap care is a complex and demanding process for nurses. The lack of standardized monitoring tools and protocols is a key gap. Developing structured tools, improving training, and strengthening multidisciplinary collaboration may enhance patient safety and care quality. Full article

The early and accurate detection of lung cancer (LC) is one of the primary challenges in the clinical diagnostics process, which plays a vital role in the treatment of the disease. Although various deep learning (DL) techniques have been presented, the existing DL methods are mainly focused on single-modal images, either computed tomography (CT) or histopathological images, which are associated with poor generalization, diversity, and applicability. To mitigate the existing issues, the present work aims to develop a modality-independent ensemble DL framework that is independently evaluated on CT and histopathological image datasets for LC classification. In this work, the proposed framework was developed using the Beta Normalization Aggregation (BNA) technique, where the performance of three state-of-the-art pre-trained convolutional neural network (CNN) architectures was compared on two distinct imaging modalities images. Based on the comparative analysis of the performance metrics, Xception, DenseNet121, and MobileNetV2, are chosen to develop the Ensemble model. Predictions generated by the selected CNN models are aggregated using the proposed BNA strategy to improve classification robustness, which improves the confidence of the prediction results and discriminative capabilities. The experiments using public data sets have confirmed the excellent performance of the model. On the CT dataset, the proposed BNA Ensemble achieved a testing accuracy of 97.45%, with a precision of 97.88%, recall of 97.45%, F1-score of 97.45%, and an AUC of 0.9986. On the histopathological dataset, the framework achieved an accuracy of 99.80%, with precision, recall, and F1-score all reaching 99.80%, and an AUC of 1.0000. These results demonstrate the effectiveness, robustness, and generalizability of the proposed BNA framework. The analysis of the results using t-SNE plots, confusion matrices, ROC curves, and confidence distributions provided additional insights into feature separability, classification performance, and prediction confidence of the proposed framework. Full article

Background and Objectives: Water polo (WP) is a high-intensity, intermittent aquatic team sport that has been extensively investigated within sports science. While contemporary literature has examined the body composition and morphological characteristics of elite and international WP players, this study aimed to define the general body composition profile of world-class WP players and determine position-specific differences. Methods: The study involved 72 national team players from Serbia, Croatia, Greece, and Italy who participated in the Olympic Games, World Championships, or European Championships. Participants’ body composition was measured using the InBody 720 multichannel bioimpedance method. Ten different variables were examined to assess body structure regarding contractile and ballast components. Results: MANOVA revealed statistically significant differences in body composition across playing positions (Wilks’ lambda = 0.239, p < 0.000, η²_p = 0.402). The variables that had the greatest impact on the difference were: body mass, body fat and body mass index with the 47.0, 44.4, and 43.7% of explained total variance of the impact on the differences (p = 0.000), respectively. Conclusions: world-class WP players assigned to different playing positions differ significantly in body composition. These positional profiles should be considered in talent identification, selection procedures, training, and nutritional strategies to optimize performance models, considering the future evolution of the game at the highest competitive level. Coaches could use this information to initially select players for different specific positions based on anthropometric and body composition criteria. Full article

Web service classification plays an important role in software reuse, service discovery, and automatic metadata organization. Although recent deep learning approaches have improved classification performance by using service names and natural-language descriptions, most existing methods still operate as black-box models and offer limited insight into how different metadata sources influence classification decisions. This lack of transparency reduces their practical usefulness for developers who need to verify predicted categories, analyze incorrect classifications, and improve service metadata quality. A well-trained interpretable model can not only help developers choose more appropriate and reliable categories for each web service, but also help write a more reasonable service name and description. In this paper, we present xServeNet, an explainability-oriented extension of ServeNet for transparent web service classification. xServeNet preserves the BERT-based representation and CNN–BiLSTM feature extractor of ServeNet and introduces (i) an instance-wise dynamic source-fusion mechanism that adaptively combines service-name and service-description features according to their semantic contribution, and (ii) model-internal importance indicators at both the source and word levels that support inspection of classification decisions without introducing additional trainable parameters. We benchmark xServeNet against eleven machine learning baselines on two real-world ProgrammableWeb datasets of 10,943 and 14,086 services covering 50 categories. xServeNet reaches 71.08% Top-1/91.35% Top-5 accuracy on the original dataset and 74.10% Top-1/92.95% Top-5 accuracy on the updated dataset, consistently improving Top-1 accuracy over ServeNet while remaining competitive on Top-5, and achieving the lowest per-category Top-5 standard deviation among all twelve compared methods. In practice, the importance indicators support three concrete activities at the service registry: helping developers verify predicted categories at registration time, iterating on description wording when the predicted category looks wrong, and supporting registry curators in flagging likely mislabelled services for review. Full article

Background: Myocardial scar segmentation from late gadolinium enhancement (LGE) cardiac magnetic resonance (CMR) images plays an important role in cardiac disease assessment and prognosis evaluation. However, accurate scar annotation is labor-intensive and requires substantial clinical expertise because scar regions are typically small, irregularly shaped, and characterized by ambiguous boundaries. Although scribble supervision provides a more practical alternative to dense annotation by substantially reducing labeling costs, the extreme sparsity of scribbles and the high similarity between scar tissue and surrounding myocardium make accurate weakly supervised segmentation challenging. Methods: To address these challenges, we propose SSMSNet, a novel scribble-supervised framework for myocardial scar segmentation. Specifically, a weakly supervised anatomical segmentation network is first employed to provide reliable myocardial structural priors and suppress irrelevant background interference. Subsequently, a local distance prior map is dynamically generated from scribble annotations, and a corresponding loss is introduced to enhance structural awareness and improve training stability. Meanwhile, by leveraging the spatial correlation between the myocardium and scar regions, teacher–student consistency supervision progressively recovers more complete scar structures from sparse annotations. Furthermore, a detail-aware feature enhancement module strengthens low-level representations through contextual interactions and attention mechanisms, improving the perception of scars with ambiguous boundaries. Results: Extensive experiments conducted on two public cardiac pathology datasets demonstrate that the proposed framework consistently outperforms state-of-the-art scribble-supervised methods and achieves competitive performance compared with fully supervised methods. Conclusions: The proposed SSMSNet effectively alleviates the limitations imposed by scribble annotations by integrating anatomical guidance, local distance priors, and consistency learning. These findings suggest that the framework provides an effective and annotation-efficient solution for myocardial scar segmentation in LGE CMR images. Full article

Recent advancements in Vision-Language Models (VLMs) have enabled robotic systems to leverage model-based understanding and reasoning over visual and linguistic inputs, offering a promising approach for interpreting user intent in human–robot interaction (HRI). In particular, deictic expressions commonly used in object handovers, such as “take this” and “give me that”, cannot be fully interpreted through language alone and require a comprehensive understanding of the speaker’s perspective and the environment. This study proposes a prompt-driven vision-language framework for deictic interpretation in human–robot handover. The system integrates a pre-trained VLM with a hierarchical prompt that decomposes reasoning into intent classification, spatio-temporal grounding, and output self-validation, enabling accurate identification of target objects and goal locations without model fine-tuning. Experimental results demonstrate 100% command interpretation accuracy across multiple interaction scenarios, including pick-and-place tasks, robot-to-human and human-to-robot handovers, and temporal deictic commands. Notably, the system operates under a prompt–command language mismatch, accurately interpreting Korean commands while being guided by English-based prompts. Analysis across progressive system configurations further demonstrates that structured prompting plays a critical role in reasoning performance. These results highlight the effectiveness of a prompt-driven approach for deictic interpretation and spatio-temporal grounding, providing a practical training-free framework for HRI. Full article

The rapid growth of web-based services has intensified the need for reliable mechanisms to distinguish malicious Uniform Resource Locators (URLs) from legitimate ones. Phishing campaigns, malware distribution networks, and defacement operations increasingly rely on deceptive web addresses to compromise unsuspecting users and critical infrastructure. Accurate URL classification plays a critical role in mitigating phishing attacks, malware distribution, and other cyber threats. This study presents a machine learning framework for detecting malicious URLs in cybersecurity applications. This study presents a comprehensive empirical evaluation of multiple machine learning and deep learning approaches for URL classification under two experimental settings: training with the complete feature set and training with a reduced subset obtained through Particle Swarm Optimization (PSO). The framework incorporates advanced feature engineering techniques that capture domain-specific characteristics of malicious URLs. Seventeen classifiers, encompassing traditional ensemble methods, neural architectures, and hybrid stacking configurations, were evaluated on a publicly available dataset of 651,191 URL samples retrieved from Kaggle. The PSO reduced the original ten-feature space to seven discriminative features, representing a 30% dimensionality reduction. Experimental results demonstrate that all-feature models consistently outperformed their PSO-reduced counterparts, with Random Forest achieving the highest classification accuracy of 91.90% and an F1-score of 0.9165. The findings offer empirical grounding for the design of computationally efficient URL threat detection systems and provide actionable directions for future research in adversarial machine learning and real-time cybersecurity pipelines. Full article

Ionosphere status plays an important role in satellite communication and navigation systems. In this study, we developed an ANN model to predict the ionosphere status regarding the signal-to-noise ratio at non-line-of-sight, near-vertical incidence (NLOS-NVIS) at frequencies within the HF band. The channel sounding was performed by using two software-defined radios placed at a distance of 29 km apart. The databases regarding signal-to-noise ratio (SNR) data were collected for three ham radio bands: 30 m (10.140203 MHz), 40 m (7.040101 MHz) and 80 m (3.570101 MHz). Subsequently, each database was split into a 70% training set and a 30% testing set. In this configuration, the input vectors were represented by the exact time of day (hour and minute) at which the SNR value was predicted, which functioned as an output variable. Also, three error figures were used as indicators for predicting capability and comparing our ANN with other models. Full article