Search Results (467)

The increasing reliance on Medical Internet of Things (MIoT) devices introduces critical cybersecurity vulnerabilities, necessitating advanced, adaptive defense mechanisms. Recent cyber incidents—such as compromised critical care systems, modified therapeutic device outputs, and fraudulent clinical data inputs—demonstrate that these threats now directly impact life-critical aspects of patient security. In this paper, we introduce a machine learning-enabled Cognitive Cyber-Physical System (ML-CCPS), which is designed to identify and respond to cyber threats in MIoT environments through a layered cognitive architecture. The system is constructed on a feedback-looped architecture integrating hybrid feature modeling, physical behavioral analysis, and Extreme Learning Machine (ELM)-based classification to provide adaptive access control, continuous monitoring, and reliable intrusion detection. ML-CCPS is capable of outperforming benchmark classifiers with an acceptable computational cost, as evidenced by its macro F1-score of 97.8% and an AUC of 99.1% when evaluated with the ToN-IoT dataset. Alongside classification accuracy, the framework has demonstrated reliable behaviour under noisy telemetry, maintained strong efficiency in resource-constrained settings, and scaled effectively with larger numbers of connected devices. Comparative evaluations, radar-style synthesis, and ablation studies further validate its effectiveness in real-time MIoT environments and its ability to detect novel attack types with high reliability. Full article

This study presents a next-generation clinical decision-support architecture for Clinical Decision Support Systems (CDSS) focused on emergency triage. By integrating Large Language Models (LLMs), Federated Learning (FL), and low-latency streaming analytics within a modular, privacy-preserving framework, the system addresses key deployment challenges in high-stakes clinical settings. Unlike traditional models, the architecture processes both structured (vitals, labs) and unstructured (clinical notes) data to enable context-aware reasoning with clinically acceptable latency at the point of care. It leverages big data infrastructure for large-scale EHR management and incorporates digital twin concepts for live patient monitoring. Federated training allows institutions to collaboratively improve models without sharing raw data, ensuring compliance with GDPR/HIPAA, and FAIR principles. Privacy is further protected through differential privacy, secure aggregation, and inference isolation. We evaluate the system through two studies: (1) a benchmark of 750+ USMLE-style questions validating the medical reasoning of fine-tuned LLMs; and (2) a real-world case study (n = 132, 75.8% first-pass agreement) using de-identified MIMIC-III data to assess triage accuracy and responsiveness. The system demonstrated clinically acceptable latency and promising alignment with expert judgment on reviewed cases. The infectious disease triage case demonstrates low-latency recognition of sepsis-like presentations in the ED. This work offers a scalable, audit-compliant, and clinician-validated blueprint for CDSS, enabling low-latency triage and extensibility across specialties. Full article

Generative AI (genAI) has emerged as a powerful tool for synthesizing diverse and complex image data, offering new possibilities for scientific imaging applications. This review presents a comprehensive comparative analysis of leading generative architectures, ranging from Variational Autoencoders (VAEs) to Generative Adversarial Networks (GANs) on through to Diffusion Models, in the context of scientific image synthesis. We examine each model’s foundational principles, recent architectural advancements, and practical trade-offs. Our evaluation, conducted on domain-specific datasets including microCT scans of rocks and composite fibers, as well as high-resolution images of plant roots, integrates both quantitative metrics (SSIM, LPIPS, FID, CLIPScore) and expert-driven qualitative assessments. Results show that GANs, particularly StyleGAN, produce images with high perceptual quality and structural coherence. Diffusion-based models for inpainting and image variation, such as DALL-E 2, delivered high realism and semantic alignment but generally struggled in balancing visual fidelity with scientific accuracy. Importantly, our findings reveal limitations of standard quantitative metrics in capturing scientific relevance, underscoring the need for domain-expert validation. We conclude by discussing key challenges such as model interpretability, computational cost, and verification protocols, and discuss future directions where generative AI can drive innovation in data augmentation, simulation, and hypothesis generation in scientific research. Full article

The research was initiated by the Plečnik House gallery (Ljubljana, Slovenia) and focuses on the 3D architectural reconstruction of the unrealised monument of the Czech military leader Jan Žižka, designed by the Slovenian architect Jože Plečnik. In addition, the experience with the 3D reconstructed monument in the exhibition “Plečnik and the Sacred” was analysed. Using the available references and interpretative approaches, a digital and 3D-printed reconstruction was created that retains Plečnik’s architectural style. The experimental phase included a detailed interpretation of the studied references, 3D modelling, 3D printing, exhibition and experience analysis. The dimensions of the finished 3D-printed model are 52.80 × 55.21 × 44.60 cm. It was produced using stereolithography (SLA) for figurative elements and fused deposition modelling (FDM) for architectural components. The reconstruction was evaluated using participant testing, including semantic differential analysis, comparative studies, and knowledge-based questionnaires. The results showed that architectural elements were reconstructed with an average similarity score of 1.97 out of 5. Statues followed with a score of 1.81, and props, though detailed, met audience expectations, scoring 1.61. Clothing received the lowest score of 1.40. This research emphasises the importance of a hypothetical digital 3D reconstruction of never constructed monument for broader understanding of Plečnik’s legacy. Full article

The modern Chinese architectural heritage combines sturdy Western materials with delicate Chinese styling, mainly adopting brick-timber structural systems that are highly vulnerable to fire damage. The study assesses the fire spread characteristics of the First Faculty House, a 20th-century architectural heritage located at a university in China. The assessment is carried out by analyzing building materials, structural configuration, and fire load. By using FDS (Fire Dynamics Simulator (PyroSim version 2022)) and SketchUp software (version 2023) for architectural reconstruction and fire spread simulation, explores preventive measures to reduce fire risks. The result show that the total fire load of the building amounts to 1,976,246 MJ. After ignition, flashover occurs at 700 s, accompanied by a sharp increase in the heat release rate (HRR). The peak ceiling temperature reaches 750 °C. The roof trusses have critical structural weaknesses when approaching flashover conditions, indicating a high potential for collapse. Three targeted fire protection strategies are proposed in line with the heritage conservation principle of minimal visual and functional intervention: fire sprinkler systems, fire retardant coating, and fire barrier. Simulations of different strategies demonstrate their effectiveness in mitigating fire spread in elongated architectural heritages with enclosed ceiling-level ignition points. The efficacy hierarchy follows: fire sprinkler system > fire retardant coating > fire barrier. Additionally, because of chimney effect, for fire sources located above the ceiling and other hidden locations need to be warned in a timely manner to prevent the thermal plume from invading other sides of the ceiling through the access hole. This research can serve as a reference framework for other Modern Chinese Architectural Heritage to develop appropriate fire mitigation strategies and to provide a methodology for sustainable development of the Chinese architectural heritage. Full article

This paper investigates the cultural landscapes established by nineteenth-century German immigrants in South Australia and the southern Riverina of New South Wales, with particular attention to settlement patterns, architectural traditions and toponymic transformation. German immigration to Australia, though numerically modest compared to the Americas, significantly shaped local communities, especially due to religious cohesion among Lutheran migrants. These settlers established distinct, enduring rural enclaves characterized by linguistic, religious and architectural continuity. The paper examines three manifestations of these cultural landscapes. A rich toponymic landscape was created by imposing on natural landscape features and newly founded settlements the names of the communities from which the German settlers originated. It discusses the erosion of German toponyms under wartime nationalist pressures, the subsequent partial reinstatement and the implications for cultural memory. The study traces the second manifestation of a cultural landscapes in the form of nucleated villages such as Hahndorf, Bethanien and Lobethal, which often followed the Hufendorf or Straßendorf layout, integrating Silesian land-use principles into the Australian context. Intensification of land use through housing subdivisions in two communities as well as agricultural intensification through broad acre farming has led to the fragmentation (town) and obliteration (rural) of the uniquely German form of land use. The final focus is the material expression of cultural identity through architecture, particularly the use of traditional Fachwerk (half-timbered) construction and adaptations such as pug-and-pine walling suited to local materials and climate. The paper examines domestic forms, including the distinctive black kitchen, and highlights how environmental and functional adaptation reshaped German building traditions in the antipodes. Despite a conservation movement and despite considerable documentation research in the late twentieth century, the paper shows that most German rural structures remain unlisted and vulnerable. Heritage neglect, rural depopulation, economic rationalization, lack of commercial relevance and local government policy have accelerated the decline of many of these vernacular buildings. The study concludes by problematizing the sustainability of conserving German Australian rural heritage in the face of regulatory, economic and demographic pressures. With its layering of intangible (toponymic), structural (buildings) and land use (cadastral) features, the examination of the cultural landscape established by nineteenth-century German immigrants adds to the body of literature on immigrant communities, settler colonialism and landscape research. Full article

This paper provides a comparative study of unsupervised Deep Learning (DL) methods for anomaly detection in Flight Data Monitoring (FDM). The paper applies Long Short-Term Memory (LSTM), Gated Recurrent Units (GRUs), Convolutional Neural Network (CNN), classic Transformer architecture, and LSTM combined with a self-attention mechanism to real-world flight data and compares the results to the current state-of-the-art flight data analysis techniques applied in the industry. The paper finds that LSTM, when integrated with a self-attention mechanism, offers notable benefits over other deep learning methods as it effectively handles lengthy time series like those present in flight data, establishes a generalized model applicable across various airports and facilitates the detection of trends across the entire fleet. The results were validated by industrial experts. The paper additionally investigates a range of methods for feeding flight data (lengthy time series) to a neural network. The innovation of this paper involves utilizing Transformer architecture and LSTM with self-attention mechanism for the first time in the realm of aviation data, exploring the optimal method for inputting flight data into a model and evaluating all deep learning techniques for anomaly detection against the ground truth determined by human experts. The paper puts forth a compelling case for shifting from the existing method, which relies on examining events through threshold exceedances, to a deep learning-based approach that offers a more proactive style of data analysis. This not only enhances the generalization of the FDM process but also has the potential to improve air transport safety and optimize aviation operations. Full article

The spatial genes of rural settlements show a lot of different traditional settlement traits, which makes them a great starting point for studying rural spatial morphology. However, qualitative and macro-regional statistical indicators are usually used to find and extract rural settlement spatial genes. Taking Yubei Village in the Nanxi River Basin as an example, this study combined remote sensing images, real-time drone mapping, GIS (geographic information system), and space syntax, extracted 12 key indicators from five dimensions (landform and water features (environment), boundary morphology, spatial structure, street scale, and building scale), and quantitatively “decoded” the spatial genes of the settlement. The results showed that (1) the settlement is a “three mountains and one water” pattern, with cultivated land accounting for 37.4% and forest land accounting for 34.3% of the area within the 500 m buffer zone, while the landscape spatial diversity index (LSDI) is 0.708. (2) The boundary morphology is compact and agglomerated, and locally complex but overall orderly, with an aspect ratio of 1.04, a comprehensive morphological index of 1.53, and a comprehensive fractal dimension of 1.31. (3) The settlement is a “clan core–radial lane” network: the global integration degree of the axis to the holy hall is the highest (0.707), and the local integration degree R3 peak of the six-room ancestral hall reaches 2.255. Most lane widths are concentrated between 1.2 and 2.8 m, and the eaves are mostly higher than 4 m, forming a typical “narrow lanes and high houses” water town streetscape. (4) The architectural style is a combination of black bricks and gray tiles, gable roofs and horsehead walls, and “I”-shaped planes (63.95%). This study ultimately constructed a settlement space gene map and digital library, providing a replicable quantitative process for the diagnosis of Jiangnan water town settlements and heritage protection planning. Full article

Throughout history, communities have struggled to build homes in places actively hostile to their presence, a challenge long faced by African descendants in the American diaspora. In cities across the U.S., including Washington, D.C., efforts have often been made to erase Black cultural identity. D.C., once a hub of Black culture, saw its urban fabric devastated during the 1968 riots following Dr. Martin Luther King Jr.’s assassination. Since then, redevelopment has been slow and, more recently, marked by gentrification, which has further displaced Black communities. Amid this context, Black architects such as Michael Marshall, FAIA, and Sean Pichon, AIA, have emerged as visionary leaders. Their work exemplifies Value-Inclusive Design and aligns with Roberto Verganti’s Design-Driven Innovation by embedding cultural relevance and community needs into development projects. These architects propose an intentional approach that centers Black identity and brings culturally meaningful businesses into urban redevelopment, shifting the paradigm of design practice in D.C. This collective case study (methodology) argues that their work represents a distinct architectural style, Black Modernism, characterized by cultural preservation, community engagement, and spatial justice. This research examines two central questions: Where does Black Modernism begin, and where does it end? How does it fit within and expand beyond the broader American Modernist architectural movement? It explores the consequences of the destruction of Black communities, the lived experiences of Black architects, and how those experiences are reflected in their designs. Additionally, the research suggests that the work of Black architects aligns with heutagogical pedagogy, which views community stakeholders not just as beneficiaries, but as educators and knowledge-holders in architectural preservation. Findings reveal that Black Modernism, therefore, is not only a design style but a method of reclaiming identity, telling untold histories, and building more inclusive cities. Full article

This research aims to explore the role of architecture in creating an identifiable brand for Amman. It seeks to put forward a vision through which Amman’s city can formulate a clear model for implementing a successful branding strategy. In doing so, this research studies the concepts associated with the ideas of branding, city image and identity, and the extent to which such ideas are to be implemented in Amman. The study adopted an inductive approach using in-depth, semi-structured interviews with 35 experts with central roles in stating the city’s key values that best reflect the city’s identity. A thematic analysis was conducted in line with theoretical aspects, including the city’s message, strategies for formulating the brand, and communication via architecture. The image of Amman shows an obvious distinction between its historical character and modern global styles as it suffers from disorder within its architectural landscape. Amman needs to rethink its identity in order to create a new brand that keeps pace with time without losing the originality of the place. This calls for re-evaluating the role of the iconic buildings and their associations with the surroundings, enabling them to become of significant presence, both symbolically and operationally, in expressing the city’s personality and promoting its message. Full article

Sports stadiums significantly influence urban morphology; however, empirical quantification of these effects remains limited. This study quantitatively examines the spatiotemporal relationship between sports architecture and urban functional evolution using Jiangwan Stadium in Shanghai—China’s first Western-style sports facility—as a case study. Employing Point of Interest (POI) data, ArcGIS spatial analyses, chi-square tests, and linear regression-based predictive modeling, we illustrate how the stadium has catalyzed urban regeneration and functional diversification over nearly a century. Our findings demonstrate a transition from sparse distributions to concentrated commercial and service clusters within a 1000 m radius around the stadium, notably in food and beverage, shopping, finance, insurance, and transportation sectors, significantly boosting local economic vitality. The area achieved peak functional diversity in 2016, showcasing a balanced integration of residential, commercial, and service activities. This research provides actionable insights for urban planners and policymakers on leveraging sports facilities to foster sustainable urban regeneration. Full article

Indoor radon constitutes a public health issue in various regions across the United States as the second leading cause of lung cancer following tobacco smoke. The U.S. Environmental Protection Agency advises radon mitigation interventions for residential buildings with indoor radon concentrations exceeding the threshold level of 4 pCi/L. Despite considerable research assessing the technical effectiveness of radon mitigation systems, there remains a gap in understanding their broader influence on occupant behavior and preferences in residential design. This study aims to investigate the impact of residing in radon-mitigated homes within the Commonwealth of Kentucky—an area known for elevated radon concentrations—on occupants’ preferences regarding healthy home design attributes. The objectives of this research are twofold: firstly to determine if living in radon-mitigated homes enhances occupant awareness and consequently influences their preferences toward health-related home attributes and secondly to quantitatively evaluate and compare the relative significance homeowners assign to health-related attributes such as indoor air quality, thermal comfort, and water quality relative to conventional attributes including home size, architectural style, and neighborhood quality. The overarching purpose is to explore the potential role radon mitigation initiatives may play in motivating occupants towards healthier home construction and renovation practices. Using choice-based conjoint (CBC) analysis, this paper compares preferences reported by homeowners from radon-mitigated homes against those from non-mitigated homes. While the findings suggest a relationship between radon mitigation and increased preference for indoor air quality, the cross-sectional design limits causal interpretation, and the possibility of reverse causation—where health-conscious individuals are more likely to seek mitigation—must be considered. The results provide novel insights into how radon mitigation efforts might effectively influence occupant priorities towards integrating healthier design elements in residential environments. Full article

This research addresses the optimization and deployment of convolutional neural networks for eyeglasses detection on low-power edge devices. Multiple convolutional neural network architectures were trained and evaluated using the FFHQ dataset, which contains annotated eyeglasses in the context of faces with diverse facial features and eyewear styles. Several post-training quantization techniques, including Float16, dynamic range, and full integer quantization, were applied to reduce model size and computational demand while preserving detection accuracy. The impact of model architecture and quantization methods on detection accuracy and inference latency was systematically evaluated. The optimized models were deployed and benchmarked on Raspberry Pi 5 and NVIDIA Jetson Orin Nano platforms. Experimental results show that full integer quantization reduces model size by up to 75% while maintaining competitive detection accuracy. Among the evaluated models, MobileNet architectures achieved the most favorable balance between inference speed and accuracy, demonstrating their suitability for real-time eyeglasses detection in resource-constrained environments. These findings enable efficient on-device eyeglasses detection, supporting applications such as virtual try-ons and IoT-based facial analysis systems. Full article

Processing ancient text images presents significant challenges due to severe visual degradation, missing glyph structures, and various types of noise caused by aging. These issues are particularly prominent in Chinese historical documents and stone inscriptions, where diverse writing styles, multi-angle capturing, uneven lighting, and low contrast further hinder the performance of traditional OCR techniques. In this paper, we propose a unified neural framework, UniText, for the detection, recognition, and glyph restoration of Chinese characters in images of historical documents and inscriptions. UniText operates at the character level and processes full-page inputs, making it robust to multi-scale, multi-oriented, and noise-corrupted text. The model adopts a multi-task architecture that integrates spatial localization, semantic recognition, and visual restoration through stroke-aware supervision and multi-scale feature aggregation. Experimental results on our curated dataset of ancient Chinese texts demonstrate that UniText achieves a competitive performance in detection and recognition while producing visually faithful restorations under challenging conditions. This work provides a technically scalable and generalizable framework for image-based document analysis, with potential applications in historical document processing, digital archiving, and broader tasks in text image understanding. Full article

The stylistic emulation of historical building facades presents significant challenges for artificial intelligence (AI), particularly for complex and data-scarce styles like Krakow’s Eclecticism. This study aims to develop a methodological framework for a “typological transcoding” of style that moves beyond mere visual mimicry, which is crucial for heritage preservation and urban renewal. The proposed methodology integrates architectural typology with Low-Rank Adaptation (LoRA) for fine-tuning a Stable Diffusion (SD) model. This process involves a typology-guided preparation of a curated dataset (150 images) and precise control of training parameters. The resulting typologically guided LoRA-tuned model demonstrates significant performance improvements over baseline models. Quantitative analysis shows a 24.6% improvement in Fréchet Inception Distance (FID) and a 7.0% improvement in Learned Perceptual Image Patch Similarity (LPIPS). Furthermore, qualitative evaluations by 68 experts confirm superior realism and stylistic accuracy. The findings indicate that this synergy enables data-efficient, typology-grounded stylistic emulation, highlighting AI’s potential as a creative partner for nuanced reinterpretation. However, achieving deeper semantic understanding and robust 3D inference remains an ongoing challenge. Full article