Search Results (7,413)

Urban roof segmentation plays a pivotal role in applications such as urban planning, infrastructure management, and renewable energy deployment. This study explores the evolution of deep learning techniques from traditional Convolutional Neural Networks (CNNs) to cutting-edge transformer-based models in the context of roof segmentation from satellite imagery. We highlight the limitations of conventional methods when applied to urban environments, including resolution constraints and the complexity of roof structures. To address these challenges, we evaluate two advanced deep learning models, Mask R-CNN and MaskFormer, which have shown significant promise in accurately segmenting roofs, even in dense urban settings with diverse roof geometries. These models, especially the one based on transformers, offer improved segmentation accuracy by capturing both global and local image features, enhancing their performance in tasks where fine detail and contextual awareness are critical. A case study on Ben Guerir City in Morocco, an urban area experiencing rapid development, serves as the foundation for testing these models. Using high-resolution satellite imagery, the segmentation results offer a deeper understanding of the accuracy and effectiveness of these models, particularly in optimizing urban planning and renewable energy assessments. Quantitative metrics such as Intersection over Union (IoU), precision, recall, and F1-score are used to benchmark model performance. Mask R-CNN achieved a mean IoU of 74.6%, precision of 81.3%, recall of 78.9%, and F1-score of 80.1%, while MaskFormer reached a mean IoU of 79.8%, precision of 85.6%, recall of 82.7%, and F1-score of 84.1% (pixel-level, micro-averaged at IoU = 0.50 on the held-out test set), highlighting the transformative potential of transformer-based architectures for scalable and precise urban imaging. The study also outlines future work in 3D modeling and height estimation, positioning these advancements as critical tools for sustainable urban development. Full article

Computer-Aided Design (CAD) software has long served as a foundation for planning and modeling in Architecture, Engineering, and Construction (AEC). In recent years, the introduction of Augmented Reality (AR) and Virtual Reality (VR) has significantly reshaped the CAD landscape, offering novel interaction paradigms that bridge the gap between digital prototypes and real-world spatial understanding. These technologies have enabled users to engage with 3D architectural content in more immersive and intuitive ways, facilitating improved decision making and communication throughout design workflows. As digital design services grow more complex and span multiple media platforms—from desktop-based modeling to immersive AR/VR environments—evaluating usability and User Experience (UX) becomes increasingly challenging. This paper presents a longitudinal usability and UX study of a multiplatform house design pipeline (i.e., structured workflow for creating, adapting, and delivering house designs so they can be used seamlessly across multiple platforms) comprising a web-based application for initial house creation, a mobile AR tool for contextual exterior visualization, and VR applications that allow full-scale interior exploration and configuration. Together, these components form a unified yet heterogeneous service experience across different devices and modalities. We describe the iterative design and development of this system over three distinct phases (lasting two years), each followed by user studies which evaluated UX and usability and targeted different participant profiles and design maturity levels. The paper outlines our approach to cross-platform UX evaluation, including methods such as the Think-Aloud Protocol (TAP), standardized usability metrics, and structured interviews. The results from the studies provide insight into user preferences, interaction patterns, and system coherence across platforms. From both participant and evaluator perspectives, the iterative methodology contributed to improvements in system usability and a clearer mental model of the design process. The main research question we address is how iterative design and development affects the UX of the heterogeneous service. Our findings highlight important considerations for future research and practice in the design of integrated, multiplatform XR services for AEC, with potential relevance to other domains. Full article

This paper focuses on the efficient fine-tuning of large language models within the federated learning framework. To address the performance bottlenecks caused by multi-source heterogeneity and structural inconsistency, a structure-aware federated fine-tuning method is proposed. The method incorporates a graph representation module (GRM) to model internal structural relationships within text and employs a segmentation mechanism (SM) to reconstruct and align semantic structures across inputs, thereby enhancing structural robustness and generalization under non-IID (non-Independent and Identically Distributed) settings. During training, the method ensures data locality and integrates structural pruning with gradient encryption (SPGE) strategies to balance privacy preservation and communication efficiency. Compared with representative federated fine-tuning baselines such as FedNLP and FedPrompt, the proposed method achieves consistent accuracy and F1-score improvements across multiple tasks. To evaluate the effectiveness of the proposed method, extensive comparative experiments are conducted across tasks of text classification, named entity recognition, and question answering, using multiple datasets with diverse structures and heterogeneity levels. Experimental results show that the proposed approach significantly outperforms existing federated fine-tuning strategies on most tasks, achieving higher performance while preserving privacy, and demonstrating strong practical applicability and generalization potential. Full article

Background: Acute appendicitis is the most common surgical emergency in children, yet timely and accurate diagnosis remains challenging due to nonspecific clinical presentations and limitations of imaging and blood tests. Saliva has emerged as a promising diagnostic medium because it is non-invasive, painless, inexpensive, and highly acceptable for pediatric patients. Salivary biomarkers may provide rapid and child-friendly adjuncts to existing diagnostic pathways. Methods: A systematic literature search was performed in Ovid/MEDLINE, Scopus, Web of Science, and the Cochrane Library to identify studies assessing salivary biomarkers in pediatric appendicitis. Eligible studies included children with suspected or confirmed appendicitis and evaluated the diagnostic accuracy of salivary markers compared to clinical, laboratory, or imaging standards. Results: To date, only three salivary biomarkers have been investigated. Leucine-rich α-2-glycoprotein 1 (LRG1) demonstrated high specificity of 100% but low sensitivity of 35–36%, with diagnostic accuracy ranging from AUC 0.77 to 0.85. C-reactive protein (CRP) showed excellent diagnostic performance with sensitivity of 91.3% and specificity of 95.4% (AUC 0.97), and strong correlation with serum CRP (ρ = 0.96). Irisin showed sensitivity of 90% and specificity of 60% with estimated AUC around 0.75, suggesting potential as an adjunct marker but limited as a standalone test. Conclusions: Salivary biomarkers in pediatric appendicitis are promising but remain underexplored, with evidence limited to small, single-center studies totalling fewer than 300 patients. Their advantages include feasibility, tolerability, and suitability for integration into point-of-care testing. Future research should focus on multicenter validation, development of multi-marker salivary panels, and application of biosensor technologies. With further evidence, salivary diagnostics could complement existing strategies and improve the accuracy and child-friendliness of appendicitis care. Full article

Selecting an appropriate Multi-Criteria Decision-Making (MCDM) algorithm for optimizing marine diesel engine operation presents a complex challenge due to the diversity in mathematical formulations, normalization schemes, and trade-off resolutions across methods. This study systematically evaluates fourteen MCDM algorithms, which are grouped into five primary methodological categories: Scoring-Based, Distance-Based, Pairwise Comparison, Outranking, and Hybrid/Intelligent System-Based methods. The goal is to identify the most suitable algorithm for real-time performance optimization of two stroke marine diesel engines. Using Diesel-RK software, calibrated for marine diesel applications, simulations were performed on a variant of the MAN-B&W-S60-MC-C8-8 engine. A refined five-dimensional parameter space was constructed by systematically varying five key control variables: Start of Injection (SOI), Dwell Time, Fuel Mass Fraction, Fuel Rail Pressure, and Exhaust Valve Timing. A subset of 4454 high-potential alternatives was systematically evaluated according to three equally important criteria: Specific Fuel Consumption (SFC), Nitrogen Oxides (NO_x), and Particulate Matter (PM). The MCDM algorithms were evaluated based on ranking consistency and stability. Among them, Proximity Indexed Value (PIV), Integrated Simple Weighted Sum Product (WISP), and TriMetric Fusion (TMF) emerged as the most stable and consistently aligned with the overall consensus. These methods reliably identified optimal engine control strategies with minimal sensitivity to normalization, making them the most suitable candidates for integration into automated marine engine decision-support systems. The results underscore the importance of algorithm selection and provide a rigorous basis for establishing MCDM in emission-constrained maritime environments. This study is the first comprehensive, simulation-based evaluation of fourteen MCDM algorithms applied specifically to the optimization of two stroke marine diesel engines using Diesel-RK software. Full article

Background/Objectives: Breast cancer (BC) is the most commonly diagnosed cancer in women and the leading cause of cancer-related deaths globally. Molecular subtyping is crucial for prognosis and treatment planning, with immunohistochemistry (IHC) being the most commonly used method. However, IHC has limitations, including observer variability, a lack of standardization, and a lack of reproducibility. Gene expression profiling is considered the ground truth for molecular subtyping; unfortunately, this is expensive and inaccessible to many institutions. This study investigates the potential of an artificial intelligence (AI) model to predict BC molecular subtypes directly from hematoxylin and eosin (H&E)-stained whole-slide images (WSIs). Methods: A pretrained deep learning framework based on multiple-instance learning (MIL) was validated on the Stavanger Breast Cancer (SBC) dataset, consisting of 538 BC cases. Three classification tasks were assessed, including two-class [triple negative BC (TNBC) vs. non-TNBC], three-class (luminal vs. HER2-positive vs. TNBC), and four-class (luminal A vs. luminal B vs. HER2-positive vs. TNBC) groups. Performance metrics were used for the evaluation of the AI model. Results: The AI model demonstrated strong performance in distinguishing TNBC from non-TNBC (AUC = 0.823, accuracy = 0.833, F1-score = 0.824). However, performance declined with an increasing number of classes. Conclusions: The study highlights the potential of AI in BC molecular subtyping from H&E WSIs, offering an easily applicable and standardized method to IHC. Future improvements should focus on optimizing multi-class classification and validating AI-based methods against gene expression analyses for enhanced clinical applicability. Full article

Background/Objectives: Polygonatum sibiricum (PS), possessing both medicinal and edible dual functions, boasts a long history of application in Chinese traditional practices. As a component of its effectiveness, Polygonatum sibiricum polysaccharides (PSPs) have been reported to exert neuroprotective effects. However, the protective effects of PS on the cognitive deficits induced by simulated weightlessness remain unclear. This study evaluated the therapeutic potential of PSPs to counteract the cognitive deficits induced by simulated weightlessness using the Hindlimb Unloading (HU) method. Methods: Mice were subjected to HU to establish cognitive impairment, and PSP was administered for four weeks. The Morris water maze test (MWMT) and passive avoidance test (PAT) were used to evaluate the cognitive abilities of mice, followed by an analysis of molecular mechanisms. Results: PSP treatment increased learning and memory in mice. PSP treatment partially restored gut microbial diversity and composition towards beneficial taxa, including Lactobacillus and Firmicutes, while inhibiting proinflammatory genera, including Alistipes and Proteus. At the same time, PSP upregulated Claudin-5 and Zonula Occludens-1 (ZO-1) levels in the colon, suggesting improved intestinal barrier integrity, and decreased neuroinflammatory response by inhibiting NLRP3 inflammasome activation and NF-κB phosphorylation in the hippocampus. It also modulated neurotransmitter homeostasis along the microbiota–gut–brain (MGB) axis by increasing the levels of gamma-aminobutyric acid (GABA) and serotonin (5-HT) while reducing the levels of excitotoxic metabolites, including Glutamate (Glu) and 3-hydroxykynurenine (3-HK). Conclusions: These results indicate that PSP may have beneficial effects on HU-induced cognitive impairment by regulating gut microbiota, enhancing barrier function, suppressing neuroimmune signaling, and restoring neurotransmitter balance. Full article

Background: Using natural substances for cancer therapy has attracted considerable interest due to their safety and reduced systemic toxicity. Nigella sativa (NS) oil, a traditional natural oil rich in bioactive compounds, possesses significant therapeutic potential. Brucine (BR), an alkaloid, exhibits potent cytotoxicity against various cancer cell lines; however, its poor selectivity and high systemic toxicity limit its clinical application. Objective: To overcome these challenges, this study aimed to enhance drug delivery and improve therapeutic efficacy. Method: A PEGylated nanoemulsion (NE) incorporating NS and BR was developed and characterized for particle size, size distribution, zeta potential, viscosity, and drug content. The in vitro release of BR was evaluated both with and without serum incubation. A quantitative amount of serum protein associated with the surface of the NE was estimated, and a hemolytic safety assay was carried out. Finally, an in vitro cytotoxicity study was conducted, and the in vivo anti-tumor effect of the developed PEGylated BR-loaded NE was evaluated and compared with its naked counterpart. Result: The developed PEGylated BR-loaded NE possessed favorable characteristics as a nanocarrier for parenteral administration, with a particle size of 188.5 nm, a zeta potential of −1.61, a viscosity of 3.4 cP, and 99% drug content uniformity. It released up to 60.4% of BR over 12 h, while only 18.4 µg/µmol of the total lipids were adsorbed on the surface of the formulation, compared with 54.5 µg/µmol for the naked counterpart. The PEGylated NE was safe, inducing less than 5% of hemolysis, and displayed substantial inhibition of MDA cell growth. Conclusions: The PEGylated NE achieved a significant reduction in tumor volume, suggesting that PEGylated NE may serve as a promising platform for enhancing anti-tumor activity. Full article

Monitoring brain activity through electroencephalography (EEG) has led to significant advancements in the study of brain microstates and their relationship with cognitive processes, such as memory. Methods: A systematic literature review was conducted following the PRISMA methodology, with the aim of identifying and analyzing potential biomarkers of memory functions derived from EEG microstate analysis. Searches were performed in five major databases (PubMed, Scopus, Web of Science, Springer, and institutional registers), covering studies published between 2019 and 2024. The initial search retrieved 179 records; after removing duplicates and ineligible works, 18 full-text articles were evaluated. Finally, 10 original studies met the inclusion criteria. Although primarily focused on other pathologies or baseline conditions, these studies reported relevant findings related to memory processes. This allowed for an exploratory synthesis of the potential role of EEG microstates as indirect biomarkers of memory. Results: The findings revealed that microstates, particularly microstates C and D, show significant alterations in their duration, coverage, and occurrence in various pathologies, such as Alzheimer’s disease, schizophrenia, and attention disorders, highlighting their potential as noninvasive biomarkers. Conclusions: Although methodological variability across studies represents a limitation, this review provides a solid foundation for future research aimed at standardizing the use of EEG microstates in clinical applications, improving diagnostic accuracy in memory-related diseases. Overall, EEG microstates hold great promise in both neuroscientific research and clinical practice. Full article

Background/Objective: Sleep is a vital determinant of human health, where both its quantity and quality directly impact physical and mental well-being. Thermoregulation plays a pivotal role in sleep quality, as the body’s ability to regulate temperature varies across different sleep stages. This study examines the effects of a novel real-time temperature adjustment (RTA) mattress, which dynamically modulates temperature to align with sleep stage transitions, compared to constant temperature control (CTC). Through polysomnographic (PSG) assessments, this study evaluates how adaptive thermal regulation influences sleep architecture, aiming to identify its potential for optimizing restorative sleep. Methods: A prospective longitudinal cohort study involving 25 participants (13 males and 12 females; mean age: 39.7 years) evaluated sleep quality across three conditions: natural sleep (Control), CTC (33 °C constant mattress temperature), and RTA (temperature dynamically adjusted: 30 °C during REM sleep; 33 °C during non-REM sleep). Each participant completed three polysomnography (PSG) sessions. Sleep metrics, including total sleep time (TST), sleep efficiency, wake after sleep onset (WASO), and sleep stage percentages, were assessed. Repeated-measures ANOVA and post hoc analyses were performed. Results: RTA significantly improved sleep quality metrics compared to Control and CTC. TST increased from 356.2 min (Control) to 383.2 min (RTA, p = 0.030), with sleep efficiency rising from 82.8% to 87.3% (p = 0.030). WASO decreased from 58.2 min (Control) and 64.6 min (CTC) to 49.0 min (RTA, p = 0.067). REM latency was notably reduced under RTA (110.4 min) compared to Control (141.8 min, p = 0.002). The REM sleep percentage increased under RTA (20.8%, p = 0.006), with significant subgroup-specific enhancements in males (p = 0.010). Females showed significant increases in deep sleep percentage under RTA (12.3%, p = 0.011). Conclusions: Adaptive thermal regulation enhances sleep quality by aligning mattress temperature with physiological needs during different sleep stages. These findings highlight the potential of RTA as a non-invasive intervention to optimize restorative sleep and promote overall well-being. Further research could explore long-term health benefits and broader applications. Full article

Many individuals suffer from sleep disorders associated with chronic pain, neuroendocrine diseases, and primary sleep disorders. Although cervical manual therapy (CMT) is frequently presumed to enhance sleep quality in clinical settings, evidence regarding its effects on sleep remains inconclusive. We aimed to evaluate the therapeutic effect of CMT and clinical patterns, providing novel insights into its applicability for sleep disorders and further mechanism studies. Methods: A comprehensive literature survey was conducted by using 6 databases through February 2025, to identify randomized controlled trials (RCTs) assessing the effect of CMT on sleep quality as clinical outcome, regardless of primary diseases. Results: Among 1220 initial studies, a total of 10 RCTs involving 552 participants were included. All included RCTs assessed sleep quality using patient-reported outcome measures, while only one study utilized objective assessment via polysomnography. Among them, seven RCTs (70.0%) reported significant improvements in sleep quality that were not dependent on alleviating the primary diseases, with notable enhancements in subjective sleep depth and efficiency rather than sleep duration or latency. Sleep benefits were pronounced in primary sleep disorders, such as obstructive sleep apnea and bruxism, and in sleep disturbances secondary to other conditions, with limited effects in fibromyalgia (FM). Conclusions: With the dysregulated hypothalamic–pituitary–adrenal axis and aberrant serotonergic activity in FM, in this review, we formed a hypothesis and explored the potential effects of CMT on sleep-related serotonergic activity and HPA axis regulation. This scoping review underscores the need for further research to clarify the neuroendocrinological mechanisms underlying CMT’s role in sleep modulation and its potential applications in sleep-related disorders. Full article

Accurate mapping of small water structures and streambeds is essential for hydrological modeling, erosion control, and landscape management. While traditional geodetic methods such as GNSS and total stations provide high precision, they are time-consuming and require specialized equipment. Recent advances in mobile technology, particularly smartphones equipped with LiDAR sensors, offer a potential alternative for rapid and cost-effective field data collection. This study assesses the accuracy of the iPhone 14 Pro’s built-in LiDAR sensor for mapping streambeds and retention structures in challenging terrain. The test site was the Dílský stream in the Oslavany cadastral area, characterized by steep slopes, rocky surfaces, and dense vegetation. The stream channel and water structures were first surveyed using GNSS and a total station and subsequently re-measured with the iPhone. Several scanning workflows were tested to evaluate field applicability. Results show that the iPhone LiDAR sensor can capture landscape features with useful accuracy when supported by reference points spaced every 20 m, achieving a vertical RMSE of 0.16 m. Retention structures were mapped with an average positional error of 7%, with deviations of up to 0.20 m in complex or vegetated areas. The findings highlight the potential of smartphone LiDAR for rapid, small-scale mapping, while acknowledging its limitations in rugged environments. Full article

This study explores the application of generative artificial intelligence (AI) in financial risk forecasting, aiming to assess its potential in enhancing both the accuracy and interpretability of predictive models. Traditional methods often struggle with the complexity and nonlinearity of financial data, whereas generative AI—such as large language models and generative adversarial networks (GANs)—offers novel solutions to these challenges. The study begins with a comprehensive review of current research on generative AI in financial risk prediction, with a focus on its roles in data augmentation and feature extraction. It then investigates techniques such as Generative Adversarial Explanation (GAX) to evaluate their effectiveness in improving model interpretability. Case studies demonstrate the practical value of generative AI in real-world financial forecasting and quantify its contribution to predictive accuracy. Furthermore, the study identifies key challenges—including data quality, model training costs, and regulatory compliance—and proposes corresponding mitigation strategies. The findings suggest that generative AI can significantly improve the accuracy and interpretability of financial risk models, though its adoption must be carefully managed to address associated risks. This study offers insights and guidance for future research in applying generative AI to financial risk forecasting. Full article

As global industry enters the digital era, automation is becoming increasingly pervasive. Due to their superior efficiency and reliability, Permanent Magnet Synchronous Motors (PMSMs) are playing an increasingly prominent role in industrial applications. Sliding Mode Control (SMC) has emerged as a modern control strategy that is widely employed not only in PMSM drive systems, but also across broader power and industrial control domains. This technique effectively mitigates key challenges associated with PMSMs, such as nonlinear behavior and susceptibility to external disturbances, thereby enhancing the precision of speed and torque regulation. This paper provides a thorough review and evaluation of recent advancements in SMC as applied to PMSM control. It outlines the fundamentals of SMC, explores various SMC-based strategies, and introduces integrated approaches that combine SMC with optimization algorithms. Furthermore, it compares these methods, identifying their respective strengths and limitations. This paper concludes by discussing current trends and potential future developments in the application of SMC for PMSM systems. Full article

The conceptual design phase in architecture establishes the foundation for subsequent design decisions and influences up to 80% of a building’s lifecycle environmental impact. While Building Information Modeling (BIM) demonstrates transformative potential for sustainable design, its application during conceptual design remains constrained by perceived technical complexity and limited support for abstract thinking. This research examines how BIM tools can facilitate conceptual design through diagrammatic reasoning, thereby bridging technical capabilities with creative exploration. A mixed-methods approach was employed to develop and validate a Diagrammatic BIM (D-BIM) framework. It integrates diagrammatic reasoning, parametric modeling, and performance evaluation within BIM environments. The framework defines three core relationships—dissection, articulation, and actualization—which enable transitions from abstract concepts to detailed architectural forms in Revit’s modeling environments. Using Richard Meier’s architectural language as a structured test case, a 14-week quasi-experimental study with 19 third-year architecture students assessed the framework’s effectiveness through pre- and post-surveys, observations, and artifact analysis. Statistical analysis revealed significant improvements (p < 0.05) with moderate to large effect sizes across all measures, including systematic design thinking, diagram utilization, and academic self-efficacy. Students demonstrated enhanced design iteration, abstraction-to-realization transitions, and performance-informed decision-making through quantitative and qualitative assessments during early design stages. However, the study’s limitations include a small, single-institution sample, the absence of a control group, a focus on a single architectural language, and the exploratory integration of environmental analysis tools. Findings indicate that the framework repositions BIM as a cognitive design environment that supports creative ideation while integrating structured design logic and performance analysis. The study advances Education for Sustainable Development (ESD) by embedding critical, systems-based, and problem-solving competencies, demonstrating BIM’s role in sustainability-focused early design. This research provides preliminary evidence that conceptual design and BIM are compatible when supported with diagrammatic reasoning, offering a foundation for integrating competency-based digital pedagogy that bridges creative and technical dimensions of architectural design. Full article