Search Results (7,959)

Bearings are vital to rotating machinery, where undetected faults can cause severe failures. Conventional fault diagnosis methods depend on manual feature engineering and labeled data, struggling with complex industrial conditions. This study introduces an innovative unsupervised framework combining masked self-supervised learning with the Swin Transformer for bearing fault diagnosis. The novel integration leverages masked Auto Encoders to learn robust features from unlabeled vibration signals through reconstruction-based pretraining, while the Swin Transformer’s shifted window attention mechanism enhances efficient capture of fault-related patterns in long-sequence signals. This approach eliminates reliance on labeled data, enabling precise detection of unknown faults. The proposed method achieves 99.53% accuracy on the Paderborn dataset and 100% accuracy on the CWRU dataset significantly, surpassing other unsupervised Auto Encoder-based methods. This method’s innovative design offers high adaptability and substantial potential for predictive maintenance in industrial applications. Full article

This article proposes a pluralistic conceptual framework for fostering creativity in musically gifted students, exploring the complex and non-linear nature of creativity development and manifestation. It aims to address a core research question: what is the intersection between musical giftedness and creativity in education? The proposed framework integrates two prominent theoretical models—the systems theory of creativity and the ‘four C’ model of creativity. Together, these models offer a dynamic and developmental understanding of creative expression, ranging from everyday creativity to potential for eminent achievement, as it manifests in musically gifted learners. The role of the teacher is placed at the heart of the creative developmental process, and the teacher is conceptualised not merely as a knowledge provider but as a central catalyst for creativity. This framework argues that the teacher functions as an environmental mediator shaping classroom climates that support innovation and as a curator of meaningful musical experiences. The article considers how established gifted education strategies, including enrichment, acceleration, and differentiated instruction, can be oriented toward fostering creative musical growth. Implications for research and practice will be discussed. Full article

Remaining useful life (RUL) prediction is a core technology in prognostics and health management (PHM), crucial for ensuring the safe and efficient operation of modern industrial systems. Although deep learning methods have shown potential in RUL prediction, they often face two major challenges: an insufficient generalization ability when distribution gaps exist between training data and real-world application scenarios, and the difficulty of comprehensively capturing complex equipment degradation processes with single-modal data. A key challenge in current research is how to effectively fuse multimodal data and leverage transfer learning to address RUL prediction in small-sample and cross-condition scenarios. This paper proposes an innovative deep multimodal fine-tuning regression (DMFR) framework to address these issues. First, the DMFR framework utilizes a Convolutional Neural Network (CNN) and a Transformer Network to extract distinct modal features, thereby achieving a more comprehensive understanding of data degradation patterns. Second, a fusion layer is employed to seamlessly integrate these multimodal features, extracting fused information to identify latent features, which are subsequently utilized in the predictor. Third, a two-stage training algorithm combining supervised pre-training and fine-tuning is proposed to accomplish transfer alignment from the source domain to the target domain. This paper utilized the Commercial Modular Aero-Propulsion System Simulation (C-MAPSS) turbine engine dataset publicly released by NASA to conduct comparative transfer experiments on various RUL prediction methods. The experimental results demonstrate significant performance improvements across all tasks. Full article

The evaluation of pressure drops across the length of production wells is a crucial task, as it influences both the cost-effective selection of tubing and the development of an efficient production strategy, both of which are vital for maximizing oil recovery while minimizing operational expenses. To address this, our study proposes an innovative hybrid intelligent system designed to predict bottom-hole flowing pressure in vertical multiphase conditions with superior accuracy compared to existing methods using a data set of 150 field measurements amassed from Algerian fields. In this work, the applied hybrid framework is the Adaptive Neuro-Fuzzy Inference System (ANFIS), which integrates artificial neural networks (ANN) with fuzzy logic (FL). The ANFIS model was constructed using a subtractive clustering technique after data filtering, and then its outcomes were evaluated against the most widely utilized correlations and mechanistic models. Graphical inspection and error statistics confirmed that ANFIS consistently outperformed all other approaches in terms of precision, reliability, and effectiveness. For further improvement of the ANFIS performance, a particle swarm optimization (PSO) algorithm is employed to refine the model and optimize the design of the antecedent Gaussian memberships along with the consequent linear coefficient vector. The results achieved by the hybrid ANFIS-PSO model demonstrated greater accuracy in bottom-hole pressure estimation than the conventional hybrid approach. Full article

The use of Reclaimed Asphalt Pavement (RAP) in asphalt mixtures offers environmental and economic advantages by reducing reliance on virgin aggregates and minimizing construction waste. However, the aged binder in RAP increases mixture stiffness, which can compromise fatigue resistance. This systematic review evaluates the influence of RAP content on fatigue performance compared to conventional mixtures, with a focus on the Indirect Tensile Test (IDT) as the primary assessment method. Following the parameters of Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, five studies published between 2014 and 2024 were identified through searches in Web of Science, ScienceDirect, ASCE, and Scopus. Study quality was assessed using the Cochrane Risk of Bias tool. The results indicate that although RAP enhances rutting resistance, higher contents (>30%) often lead to reduced fatigue performance due to binder hardening and reduced mixture flexibility. The incorporation of rejuvenators—such as heavy paraffinic extracts—and modifiers, including high-modulus agents, polymers, and epoxy binders, can partially restore aged binder properties and improve performance. Sustainable innovations, such as lignin-based industrial by-products and warm-mix asphalt technologies, show promise in balancing mechanical performance with reduced environmental impact. Variability in material sources, modification strategies, and test protocols limits direct comparability among studies, underscoring the need for standardized evaluation frameworks. Overall, this review highlights that optimizing RAP content and selecting effective rejuvenation or modification strategies are essential for achieving durable, cost-effective, and environmentally responsible asphalt pavements. Future research should integrate advanced laboratory methods with performance-based design to enable high RAP utilization without compromising fatigue resistance. Full article

Cross-category innovation in digital platform ecosystems is increasingly pivotal for competitive reconfiguration, and the value it generates for users primarily stems from the benefits of network effects. By extending the spatial competition framework of the Hotelling model through a four-stage sequential game comprising category competition, we formalize the strategic mechanism for expanding network effects governing benchmark competition and category dynamics. The cross-category innovation strategy proposed in this paper offers valuable insights in three key areas: investment in core technological advantages, reconstruction of user cognitive boundaries, and strengthening ecological dependency within the ecosystem. By transcending the limitations in the explanatory power of traditional management theories for cross-organizational boundary issues, this study integrates digital contexts into its analytical framework, thus providing a novel perspective for understanding the dynamic processes of cross-category innovation in digital platform ecosystems. Full article

The rapid evolution of the metaverse is driving the development of new digital design tools that integrate Computer-Aided Design (CAD) and Building Information Modeling (BIM) technologies. Core technologies such as Virtual Reality (VR), Augmented Reality (AR), and Mixed Reality (MR) are increasingly combined with BIM to enhance collaboration and innovation in design and construction workflows. However, current BIM–VR integration often remains limited to isolated tasks, lacking persistent, multi-user environments that support continuous project collaboration. This study proposes a BIM-based Virtual World (VW) framework that addresses these limitations by creating an immersive, real-time collaborative platform for the Architecture, Engineering, and Construction (AEC) industry. The system enables multi-user access to BIM data through avatars, supports direct interaction with 3D models and associated metadata, and maintains a persistent virtual environment that evolves alongside project development. Key functionalities include interactive design controls, real-time decision-making support, and integrated training capabilities. A prototype was developed using Unreal Engine and supporting technologies to validate the approach. The results demonstrate improved interdisciplinary collaboration, reduced information loss during design iteration, and enhanced stakeholder engagement. This research highlights the potential of BIM-based Virtual Worlds to transform AEC collaboration by fostering an open, scalable ecosystem that bridges immersive environments with data-driven design and construction processes. Full article

Aiming at the problems of detail blurring and structural distortion caused by speckle noise, additive white noise and hybrid noise interference in synthetic aperture radar (SAR) images, this paper proposes a Dynamic Adaptive Transformer Network (DAT-Net) integrating a dynamic gated attention module and a frequency-domain multi-expert enhancement module for SAR image denoising. The proposed model leverages a multi-scale encoder–decoder framework, combining local convolutional feature extraction with global self-attention mechanisms to transcend the limitations of conventional approaches restricted to single noise types, thereby achieving adaptive suppression of multi-source noise contamination. Key innovations comprise the following: (1) A Dynamic Gated Attention Module (DGAM) employing dual-path feature embedding and dynamic thresholding mechanisms to precisely characterize noise spatial heterogeneity; (2) A Frequency-domain Multi-Expert Enhancement (FMEE) Module utilizing Fourier decomposition and expert network ensembles for collaborative optimization of high-frequency and low-frequency components; (3) Lightweight Multi-scale Convolution Blocks (MCB) enhancing cross-scale feature fusion capabilities. Experimental results demonstrate that DAT-Net achieves quantifiable performance enhancement in both simulated and real SAR environments. Compared with other denoising algorithms, the proposed methodology exhibits superior noise suppression across diverse noise scenarios while preserving intrinsic textural features. Full article

The highly heterogeneous and irregular morphology of liver tumors presents considerable challenges for automated segmentation. To better capture complex tumor structures, this study proposes a liver tumor segmentation framework based on multi-scale deformable feature fusion and global context modeling. The method incorporates three key innovations: (1) a Deformable Large Kernel Attention (D-LKA) mechanism in the encoder to enhance adaptability to irregular tumor features, combining a large receptive field with deformable sensitivity to precisely extract tumor boundaries; (2) a Context Extraction (CE) module in the bottleneck layer to strengthen global semantic modeling and compensate for limited capacity in capturing contextual dependencies; and (3) a Dual Cross Attention (DCA) mechanism to replace traditional skip connections, enabling deep cross-scale and cross-semantic feature fusion, thereby improving feature consistency and expressiveness during decoding. The proposed framework was trained and validated on a combined LiTS and MSD Task08 dataset and further evaluated on the independent 3D-IRCADb01 dataset. Experimental results show that it surpasses several state-of-the-art segmentation models in Intersection over Union (IoU) and other metrics, achieving superior segmentation accuracy and generalization performance. Feature visualizations at both encoding and decoding stages provide intuitive insights into the model’s internal processing of tumor recognition and boundary delineation, enhancing interpretability and clinical reliability. Overall, this approach presents a novel and practical solution for robust liver tumor segmentation, demonstrating strong potential for clinical application and real-world deployment. Full article

Emotion recognition remains a challenging task in human–computer interaction. With advancements in multimodal computing, multimodal emotion recognition has become increasingly important and significant. To address the existing limitations in multimodal fusion efficiency, emotional–semantic association mining, and long-range context modeling, we propose an innovative graph neural network (GNN)-based framework. Our methodology integrates three key components: (1) a hierarchical sequential fusion (HSF) multimodal integration approach, (2) a sentiment–emotion enhanced joint learning framework, and (3) a context-similarity dual-layer graph architecture (CS-BiGraph). The experimental results demonstrate that our method achieves 69.1% accuracy on the IEMOCAP dataset, establishing a new state-of-the-art performance. For future work, we will explore robust extensions of our framework under real-world scenarios with higher noise levels and investigate the integration of emerging modalities for broader applicability. Full article

The 4E Cognition paradigm offers a novel theoretical framework for understanding how acoustic environments influence cognitive processes in university learning spaces. This research integrates objective characterization of environmental parameters with comprehensive subjective evaluation of student experience to explore how aural conditions relate to cognitive processes and physiological stress responses in university learning environments. The study recruited 126 university students from the Engineering Faculty of “G. D’Annunzio” University, with final analysis including 66 valid responses from 28 participants in the acoustically treated classroom and 38 from the control condition. The results revealed modest associations between environmental conditions and cognitive performance measures, with small to moderate effect sizes (Cohen’s d ranging from 0.02 to 0.31). While acoustic treatment produced measurable improvements in speech intelligibility and acoustic quality ratings, differences in cognitive load and allostatic load indices were minimal between conditions. These findings provide preliminary empirical insights for applying the 4E Cognition framework to educational settings, suggesting that acoustic interventions may require extended exposure periods or more intensive treatments to produce substantial physiological and cognitive effects. This work contributes to the emerging field of cognitive architecture by introducing an innovative theoretical approach that reconceptualizes acoustic environments as potential cognitive extensions rather than mere background conditions. The findings offer initial evidence-based insights for integrating environmental considerations into educational facility design, while highlighting the need for longitudinal studies to fully understand how acoustic environments function as cognitive scaffolding in learning contexts. Full article

With globalization and technology advancement, traditional teaching models are facing challenges due to the diverse needs of modern learners. It is necessary to enhance learner engagement and motivation, and incorporating Internet of Things (IoT)-assisted teaching tools has become a major concern for educators. However, the time it takes to develop new teaching tools and integrate IoT technology must be shortened by combining educational content with game mechanics seamlessly. Therefore, we developed a gamified teaching model by incorporating IoT technology. We used the “System, Indicators, Criteria” framework to develop a three-tiered board game evaluation and development model. Based on this framework, a teaching tool was designed to provide personalized learning experiences with IoT technology. The tool provides abstract knowledge, fosters interaction and collaboration among learners, and thus enhances engagement. To ensure a rigorous design and evaluation process, we employed quality function deployment (QFD), analytic hierarchy process (AHP), and fuzzy comprehensive evaluation (FCE). The developed model facilitates the integration of IoT technology with innovative design concepts and enhances the application value of teaching tools in education. The model also enhances intelligence, interactivity, and creativity for traditional education to revitalize learning experiences. Full article

Under the background of global green sustainable development and the urgent need to understand complex regional innovation systems, it is crucial to scientifically assess China’s Tourism Green Innovation Efficiency (TGIE) as a dynamic networked system and reveal its system-level evolution driving mechanism. This article presents the construction of the TGIE evaluation indicator system, measures the inter-provincial TGIE in China in 2011–2023 based on the three-stage super-efficiency SBM-DEA model, analyzes the spatial correlation network characteristics of TGIE by using the motif analysis method and the social network analysis method, and explores the evolutionary driving mechanism by using the time-exponential random graph model (TERGM). The study shows the following: (1) The TGIE of China exhibits a regional distribution pattern characterized by “high in the east and low in the west.” The efficiency of the eastern coastal region is significantly higher than that of the central and western regions, and the overall efficiency shows a fluctuating upward trend. (2) The local structure of China’s TGIE network is dominated by the chain structure, and the partially closed structure is gradually enhanced. It indicates that the bridge role of intermediary nodes in the cross-regional flow of innovation resources is becoming more and more significant. (3) The overall network evolves from a single center to a polycentric collaboration model. High-efficiency regions attract low-efficiency regions to collaborate through high connectivity, and intermediary nodes play a key role in connecting high- and low-efficiency regions. (4) The evolution of China’s TGIE network is driven by both exogenous and endogenous dynamics, showing significant path dependence and path creation characteristics. This study enhances the theoretical framework of complex systems in tourism innovation and offers theoretical support and policy insights for optimizing the network structure of China’s TGIE as a complex adaptive system and maximizing regional cooperation networks. Full article

With the rapid development of urban underground rail transit, its enclosed and densely populated environment significantly increases fire risks, posing serious threats to personnel safety and operational stability. Based on the WSR methodology and 4M theory, this study identifies fire-related factors from the physical, operational, and human dimensions. And refine indicators at the four levels of personnel, equipment and facilities, environment, and management to establish a resilience assessment system for urban underground rail transit fires. The results detailed display the application of Cross-Influence Analysis (CIA) and analytic network process (ANP) methods in fire resilience evaluation, including theoretical framework construction, computational procedures, and result analysis. A comprehensive assessment system is developed, comprising 14 secondary indicators under four primary criteria: resistance capacity, adaptation capacity, absorption capacity, and resilience capacity. And then, the CIA and ANP methods were employed to quantify inter-indicator relationships and weights through 15 expert evaluations and 52 judgment matrices, facilitating disaster-adaptive strategy formulation. Finally, an empirical analysis of Xi’an Metro Line 1 reveals that resistance capacity and resilience capacity are critical to fire resilience, with fire cause investigation and post-incident review exhibiting the highest weights. Meanwhile, resilience enhancement strategies are proposed, including optimized monitoring equipment deployment, strengthened emergency drills, and improved personnel training. The paper innovatively integrates WSR methodology and 4M theory to establish a comprehensive, representative metro fire resilience assessment system with CIA-ANP quantification. This study provides novel methodological support for fire safety assessment in urban underground rail transit systems, offering significant theoretical and practical value. Full article

During the last decade, artificial intelligence (AI) has enabled key technological innovations within the modern dementia and frailty healthcare and prevention landscape. This has boosted the impact of technology in the clinical setting, enabling earlier diagnosis with improved specificity and sensitivity, leading to accurate and time-efficient support that has driven the development of preventative interventions minimizing the risk and rate of progression. Background/Objectives: The rapid ageing of the European population places a substantial strain on the current healthcare system and imposes several challenges. COMFORTage is the joint effort of medical experts (i.e., neurologists, psychiatrists, neuropsychologists, nurses, and memory clinics), social scientists and humanists, technical experts (i.e., data scientists, AI experts, and robotic experts), digital innovation hubs (DIHs), and living labs (LLs) to establish a pan-European framework for community-based, integrated, and people-centric prevention, monitoring, and progression-managing solutions for dementia and frailty. Its main goal is to introduce an integrated and digitally enabled framework that will facilitate the provision of personalized and integrated care prevention and intervention strategies on dementia and frailty, by piloting novel technologies and producing quantified evidence on the impact to individuals’ wellbeing and quality of life. Methods: A robust and comprehensive design approach adopted through this framework provides the guidelines, tools, and methodologies necessary to empower stakeholders by enhancing their health and digital literacy. The integration of the initial information from 13 pilots across 8 European countries demonstrates the scalability and adaptability of this approach across diverse healthcare systems. Through a systematic analysis, it aims to streamline healthcare processes, reduce health inequalities in modern communities, and foster healthy and active ageing by leveraging evidence-based insights and real-world implementations across multiple regions. Results: Emerging technologies are integrated with societal and clinical innovations, as well as with advanced and evidence-based care models, toward the introduction of a comprehensive global coordination framework that: (a) improves individuals’ adherence to risk mitigation and prevention strategies; (b) delivers targeted and personalized recommendations; (c) supports societal, lifestyle, and behavioral changes; (d) empowers individuals toward their health and digital literacy; and (e) fosters inclusiveness and promotes equality of access to health and care services. Conclusions: The proposed framework is designed to enable earlier diagnosis and improved prognosis coupled with personalized prevention interventions. It capitalizes on the integration of technical, clinical, and social innovations and is deployed in 13 real-world pilots to empirically assess its potential impact, ensuring robust validation across diverse healthcare settings. Full article