Search Results (248)

With the accelerated digital transformation of the power industry, critical infrastructures such as power grids are increasingly migrating to cloud-native architectures, leading to unprecedented growth in service scale and complexity. Traditional operation and maintenance (O&M) methods struggle to meet the demands for real-time monitoring, accuracy, and scalability in such environments. This paper proposes a novel service performance anomaly detection system based on large language models (LLMs) and multi-agent systems (MAS). By integrating the semantic understanding capabilities of LLMs with the distributed collaboration advantages of MAS, we construct a high-precision and robust anomaly detection framework. The system adopts a hierarchical architecture, where lower-layer agents are responsible for tasks such as log parsing and metric monitoring, while an upper-layer coordinating agent performs multimodal feature fusion and global anomaly decision-making. Additionally, the LLM enhances the semantic analysis and causal reasoning capabilities for logs. Experiments conducted on real-world data from the State Grid Corporation of China, covering 1289 service combinations, demonstrate that our proposed system significantly outperforms traditional methods in terms of the F1-score across four platforms, including customer services and grid resources (achieving up to a 10.3% improvement). Notably, the system excels in composite anomaly detection and root cause analysis. This study provides an industrial-grade, scalable, and interpretable solution for intelligent power grid O&M, offering a valuable reference for the practical implementation of AIOps in critical infrastructures. Evaluated on real-world data from the State Grid Corporation of China (SGCC), our system achieves a maximum F1-score of 88.78%, with a precision of 92.16% and recall of 85.63%, outperforming five baseline methods. Full article

This paper examines how artificial intelligence (AI) can be strategically deployed to enhance urban planning and environmental livability in Riyadh by generating data-driven, people-centric design interventions. Unlike previous studies that concentrate primarily on visualization, this research proposes an integrative appraisal framework that combines AI-generated design with site-specific environmental data and native vegetation typologies. This study was conducted across key jurisdictional areas including the Northern Ring Road, King Abdullah Road, Al Rabwa, Al-Malaz, Al-Suwaidi, Al-Batha, and King Fahd Road. Using AI tools, urban scenarios were developed to incorporate expanded pedestrian pathways (up to 3.5 m), dedicated bicycle lanes (up to 3.0 m), and ecologically adaptive green buffer zones featuring native drought-resistant species such as Date Palm, Acacia, and Sidr. The quantitative analysis of post-intervention outcomes revealed surface temperature reductions of 3.2–4.5 °C and significant improvements in urban esthetics, walkability, and perceived safety—measured on a five-point Likert scale with 80–100% increases in user satisfaction. Species selection was validated for ecological adaptability, minimal maintenance needs, and compatibility with Riyadh’s sandy soils. This study directly supports the Kingdom of Saudi Arabia’s Vision 2030 by demonstrating how emerging technologies like AI can drive smart, sustainable urban transformation. It aligns with Vision 2030’s urban development goals under the Quality-of-Life Program and environmental sustainability pillar, promoting healthier, more connected cities with elevated livability standards. The research not only delivers practical design recommendations for planners seeking to embed sustainability and digital innovation in Saudi urbanism but also addresses real-world constraints such as budgetary limitations and infrastructure integration. Full article

Generation Z (Gen Z; born 1997–2012) is reshaping global tourism through digital fluency, ethical awareness, and a desire for authentic, sustainable travel experiences. This study surveys 413 Gen Z travelers across France, Portugal, Romania, and the USA to map their booking behaviors, information sources, transport modes, accommodations, dining practices, and leisure activities. The findings reveal a strong preference for independent online bookings and social-media-influenced destination choices (Instagram, TikTok), with air and car travel being used for long-distance journeys and walking/public transit being used for local journeys. Accommodation spans commercial hotels and private rentals, while informal, local dining and nature- or culture-centered leisure prevail. Chi-square tests were performed to identify differences between countries. To reveal distinct traveler segments and their country’s modulations towards sustainability, a hierarchical cluster analysis was performed. The results uncover four segments: “Tech-Active, Nature-Oriented Minimalists” (32.3% in France); “Moderate Digital Planners” (most frequent across all countries, particularly dominant among Romanian respondents); “Disengaged and Indecisive Travelers” (overrepresented in the USA); and “Culturally Inclined, Selective Sustainability Seekers” (>30% in France/Portugal). Although sustainability is widely valued, only some segments of the studied population consistently act on these values. The results suggest that engaging Gen Z requires targeted, value-driven digital strategies that align platform design with the cohort’s diverse sustainability commitments. Full article

Background/Objectives: Australian terrestrial mammals that fall within the critical weight range (35 g–5.5 kg) have experienced large population declines due to a combination of habitat loss and modification, and the introduction of non-native cats, dogs, and foxes. Because running speed typically increases with body size, predators are usually faster but less agile than their prey due to the biomechanical trade-offs between speed and agility. Quantifying the maximum locomotor capacities of Australian mammals in the critical weight range, and the magnitude of the trade-off between speed and agility, can aid in estimating species’ vulnerability to predation. Methods: To do this, we quantified the trade-off between speed and agility in both males and females (n = 36) of a critical weight range species, the northern brown bandicoot (Isoodon macrourus), and determined if there was an influence of morphology on locomotor performance. Results: When turning, individuals who had higher turn approach speeds, and higher within-turn speeds, had greater turning radii and lower angular velocities, meaning a decrease in overall maneuverability. Females were more agile and exhibited greater turning speeds at similar turning radii than males. For both sexes, individuals with longer relative hind digits had relatively faster sprint speeds, while those with longer forearms had relatively smaller turning radii and higher agility. Conclusions: Due to the constrained limb morphology of the bandicoot species, these findings could translate across this group to provide a better understanding of their escape performance and risk of predation. Full article

Modern database systems require autonomous CPU scheduling frameworks that dynamically optimize resource allocation across heterogeneous workloads while maintaining strict performance guarantees. We present a novel hierarchical deep reinforcement learning framework augmented with graph neural networks to address CPU scheduling challenges in mixed database environments comprising Online Transaction Processing (OLTP), Online Analytical Processing (OLAP), vector processing, and background maintenance workloads. Our approach introduces three key innovations: first, a symmetric two-tier control architecture where a meta-controller allocates CPU budgets across workload categories using policy gradient methods while specialized sub-controllers optimize process-level resource allocation through continuous action spaces; second, graph neural network-based dependency modeling that captures complex inter-process relationships and communication patterns while preserving inherent symmetries in database architectures; and third, meta-learning integration with curiosity-driven exploration enabling rapid adaptation to previously unseen workload patterns without extensive retraining. The framework incorporates a multi-objective reward function balancing Service Level Objective (SLO) adherence, resource efficiency, symmetric fairness metrics, and system stability. Experimental evaluation through high-fidelity digital twin simulation and production deployment demonstrates substantial performance improvements: 43.5% reduction in p99 latency violations for OLTP workloads and 27.6% improvement in overall CPU utilization, with successful scaling to 10,000 concurrent processes maintaining sub-3% scheduling overhead. This work represents a significant advancement toward truly autonomous database resource management, establishing a foundation for next-generation self-optimizing database systems with implications extending to broader orchestration challenges in cloud-native architectures. Full article

With the rise of live-streaming services on e-commerce platforms, AI-powered virtual idols have demonstrated tremendous application potential and thus possess high commercial value. From the perspective of psychological distance, this study adopts the Stimulus–Organism–Response (S–O–R) theoretical framework to construct a research model of “AI-powered virtual idols–psychological distance–impulsive buying intention”. The model aims to explore how AI-powered virtual idols promote digital natives’ impulsive buying intention in the context of e-commerce live streaming. Furthermore, this study examines the moderating effect of technology readiness on the relationship between AI-powered virtual idols and psychological distance. The findings reveal that the level of intelligence of AI-powered virtual idols—including interactivity, anthropomorphism, homogeneity, and reputation—enhances digital natives’ impulsive buying intention by reducing psychological distance. For digital natives with lower technology readiness, the effect of AI-powered virtual idols in narrowing psychological distance is more pronounced. These findings enrich AI-driven consumer behavior models from a theoretical perspective and offer theoretical support and practical insights for developing AI-empowered digital marketing strategies tailored to the psychological traits and technological adaptability of digital natives. Full article

In the era of digital healthcare, electronic health records generate vast amounts of data, much of which is unstructured, and therefore, not in a usable format for conventional machine learning and artificial intelligence applications. This study investigates how to extract meaningful insights from unstructured radiology reports written in Finnish, a minority language, using machine learning techniques for text analysis. With this approach, unstructured information could be transformed into a structured format. The results of this research show that relevant information can be effectively extracted from Finnish medical reports using classification algorithms with default parameter values. For the detection of breast tumour mentions from medical texts, classifiers achieved high accuracy, almost 90%. Detection of metastasis mentions, however, proved more challenging, with the best-performing models Support Vector Machine (SVM) and logistic regression achieving an F1-score of 81%. The lower performance in metastasis detection is likely due to the more complex problem, ambiguous labeling, and the smaller dataset size. The results of classical classifiers were also compared with FinBERT, a domain-adapted Finnish BERT model. However, classical classifiers outperformed FinBERT. This highlights the challenge of medical language processing when working with minority languages. Moreover, it was noted that parameter tuning based on translated English reports did not significantly improve the detection rates, likely due to linguistic differences between the datasets. This larger translated dataset used for tuning comes from a different clinical domain and employs noticeably simpler, less nuanced language than the Finnish breast cancer reports, which are written by native Finnish-speaking medical experts. This underscores the need for localised datasets and models, particularly for minority languages with unique grammatical structures. Full article

Studies that have examined /s/ weakening as a social practice have found that L1 Spanish speakers perceive this cue as an indicator of lower status, region of origin, and greater friendliness, and even L2 Spanish learners have been found to associate /s/ weakening with lower status. The question remains, however, whether L2 learners who use /s/ weakening are perceived as having these same social attributes or whether their nonnative status interrupts said assessment. The present study examines the attitudes of 30 beginning and intermediate-level L2 learners of Spanish towards L1 and L2 speech that was digitally modified to contain /s/ deletion in coda positions, a regionally and stylistically variable sociophonetic cue in Spanish that is often not adopted by L2 learners. Participants rated the speech samples on Likert scales of perceived status, solidarity, and nativeness. Results revealed that learners rated L1 speech with /s/ deletion significantly lower for status and L2 speech with /s/ deletion significantly higher for nativeness. Full article

A persistent challenge in digital asset management is the lack of standardized models for integrating health assessment—such as the Asset Health Index (AHI)—into Digital Twins, limiting their extended implementation beyond individual projects. Asset managers in the energy sector face challenges of digitalization such as digital environment selection, employed digital modules (absence of an architecture guide) and their interconnection, sources of data, and how to automate the assessment and provide the results in a friendly decision support system. Thus, for energy systems, the integration of Asset Assessment in virtual replicas by Digital Twins is a complete way of asset management by enabling real-time monitoring, predictive maintenance, and lifecycle optimization. Another challenge in this context is how to compound in a structured assessment of asset condition, where the Asset Health Index (AHI) plays a critical role by consolidating heterogeneous data into a single, actionable indicator easy to interpret as a level of risk. This paper tries to serve as a guide against these digital and structured assessments to integrate AHI methodologies into Digital Twins for energy converters. First, the proposed AHI methodology is introduced, and after a structured data model specifically designed, orientated to a basic and economic cloud implementation architecture. This model has been developed fulfilling standardized practices of asset digitalization as the Reference Architecture Model for Industry 4.0 (RAMI 4.0), organizing asset-related information into interoperable domains including physical hierarchy, operational monitoring, reliability assessment, and risk-based decision-making. A Unified Modeling Language (UML) class diagram formalizes the data model for cloud Digital Twin implementation, which is deployed on Microsoft Azure Architecture using native Internet of Things (IoT) and analytics services to enable automated and real-time AHI calculation. This design and development has been realized from a scalable point of view and for future integration of Machine-Learning improvements. The proposed approach is validated through a case study involving three high-capacity converters in distinct operating environments, showing the model’s effective assistance in anticipating failures, optimizing maintenance strategies, and improving asset resilience. In the case study, AHI-based monitoring reduced unplanned failures by 43% and improved maintenance planning accuracy by over 30%. Full article

Generative artificial intelligence (genAI) shows promising results in clinical practice. This study compared a GPT-4-turbo virtual assistant with physicians from Italy, France, Spain, and Portugal on medical knowledge derived from national exams while analysing knowledge retention over time and domain-specific performance. Via a digital platform, 17,144 physicians provided 221,574 answers to 600 exam questions between December 2022 and February 2024. Physicians were stratified by years since graduation and specialty, and the assistant answered the same questions in each native language. Differences in proportions of correct answers were tested with binomial logistic regression (odds ratios, 95% CI) or Fisher’s exact test (α = 0.05). The assistant outperformed physicians in all countries (72–96% vs. 46–62%; logistic regression, p < 0.001). Physicians also trailed the assistant across most knowledge domains (p < 0.001), except paediatrics (45% vs. 52%; Fisher, p = 0.60). Accuracy declined with seniority, falling 4–10% between the youngest and oldest cohorts (logistic regression, p < 0.001). Overall, genAI exceeds practising doctors on broad medical knowledge and may help counter knowledge attrition, though paediatrics remains a domain requiring targeted refinement. Full article

This study investigated Generation Z’s repurchase intention in social commerce environments by integrating three theoretical frameworks: the unified theory of acceptance and use of technology, signaling theory, and herding behavior. The research addressed critical gaps in understanding continued engagement behaviors of digitally native consumers in socially embedded commerce platforms. Data were collected from 542 Generation Z consumers using a structured questionnaire, and relationships were tested using partial least squares structural equation modeling. Results demonstrated that all UTAUT factors significantly influenced repurchase intention. Return policy leniency, as a quality signal, positively impacted repurchase intention both directly and indirectly through enhanced online trust. Fear of missing out demonstrated significant direct effects on repurchase intention and operated indirectly through imitative behaviors. This research advances the theoretical understanding of Generation Z’s continued engagement with social commerce by validating an integrated framework that simultaneously accounts for technological, informational, and social-psychological dimensions. The findings provide practical guidance for social commerce platforms seeking to enhance Generation Z’s loyalty through balanced strategies addressing functional performance, trust-building signals, and social validation mechanisms. Full article

Digital twins (DTs) will revolutionize network autonomy. Recent studies have promoted the idea of a DT-native 6G network, deeply integrating DTs into mobile network architectures to improve the timeliness of physical–digital synchronization and network optimizations. However, DTs have mainly acted just as a tool for network autonomy, leading to a gap regarding the ultimate goal of network self-evolution. This paper analyzes future directions concerning DT-native networks. Specifically, the proposed architecture introduces a key concept called “future shots” that gives accurate network predictions under different time scales of self-evolution strategies for various network elements. To realize the future shots, we propose a long-term hierarchical convolutional graph attention model for cost-effective network predictions, a conditional hierarchical graph neural network for strategy generation, and methods for efficient small-to-large-scale interactions. The architecture is expected to facilitate high-level network autonomy for 6G networks. Full article

This study investigated how the front-page designs of digital newspapers differ based on institutional origin—comparing platforms that were born-digital with those that have transitioned from print—focusing specifically on their appeal to Generation Z audiences. Grounded in Media Richness Theory, this research employed a mixed-methods approach that combined a quantitative visual content analysis with qualitative semi-structured interviews. In the quantitative phase, the front pages of ten Saudi digital newspapers (five digital-native and five digital-migrant) were systematically analyzed to identify differences in their layouts, typography, multimedia usage, and interactivity. The qualitative phase then explored Generation Z users’ perceptions of the design clarity, visual engagement, and interactive affordances, as well as their suggestions for improving interface usability. The results indicate that digital-native newspapers more closely adhere to contemporary digital design standards and demonstrate significantly higher levels of media richness. This study contributes to digital journalism scholarship by offering both theoretical insights into interface-centered richness and practical design recommendations for enhancing user experience and engagement among younger audiences. Full article

Historic Cairo, recognized as a UNESCO World Heritage Site in 1979, is renowned for its rich Islamic architecture, including sabils, which have played a crucial role in the urban fabric of this arid region. This study focuses on the oldest surviving Ottoman sabil in Cairo—the Sabil and Kutab of Khusru Pasha—as a case study for digital heritage preservation using advanced documentation technologies. We propose a flexible, dynamic documentation workflow based on the heritage digital twin (HDT) framework, which integrates both physical and digital-native processes. Through a hybrid methodology that combines 3D laser scanning, photogrammetry, and building information modeling (BIM), this study aims to transition from static heritage record-keeping to an interactive, semantically structured digital representation. This approach enhances the efficiency and accuracy of documentation, supports long-term conservation, and facilitates immersive public engagement. Quantitative data, including scan resolution and processing time, are used to assess the effectiveness of the adopted workflow. The digital twin created from this case study offers a replicable model for safeguarding similar mid-scale heritage assets across Islamic Cairo. Furthermore, integrating HDTs into virtual tourism frameworks creates new possibilities for cultural accessibility, education, and sustainable tourism development. By illustrating how historical buildings like the Khusru Pasha Sabil can be virtually preserved, monitored, and promoted, this study highlights the transformative potential of digital twin technology in heritage conservation. It contributes to the evolving discourse on smart documentation and management strategies, aligning with global sustainability goals and digital heritage preservation initiatives. Full article

Virtual Reality (VR) painting, an emerging form of artistic expression under 5G technology, showcases a broader range of expressive styles and dynamic visual effects compared to traditional computer graphics. The creative process in VR painting enhances spatial depth, exhibiting different spatial abilities and necessitating more physical movements, including hand controllers and foot movements in the virtual space. Furthermore, VR painting in art therapy encourages users to engage in physical activities, contributing to better emotional expression. This study involved digital-native users in VR painting, using Meta Quest 2 to operate Open Brush for their creations. Through observational methods, we examined user operational behaviors and conducted semi-structured interviews post-experiment to explore their painting performance and usage behaviors in the virtual environment. The results of this study indicate that VR painting enhances the sense of space and dynamic expression in creative work and improves users’ emotional and physical engagement, providing new avenues for artistic expression. These findings contribute to improving the usability and application value of VR paintings. Full article