Search Results (695)

As critical components of wind energy systems, the structural integrity of wind turbine blades is directly tied to the operational safety and economic performance of wind turbines. With blade designs trending toward larger and more flexible structures and operating environments becoming increasingly harsh, maintenance strategies must urgently shift from reactive approaches to predictive maintenance paradigms. From an engineering application perspective, this study conducts a systematic and critical review of non-destructive testing (NDT) and structural health monitoring (SHM) technologies for wind turbine blades. Drawing on the literature published over the past decade, we examine the field applicability, limitations, and engineering challenges of core NDT techniques—including vision-based methods, acoustic approaches, vibration analysis, ultrasound, and infrared thermography. Particular emphasis is placed on the integration of data-driven approaches with engineering practice, evaluating the role of machine learning in fault classification and anomaly diagnosis, as well as the contributions of deep learning to automated defect detection in image and signal data. Moreover, this paper critically discusses the growing use of robotic inspection platforms, such as unmanned aerial vehicles and climbing robots, as multi-sensor carriers enabling rapid and comprehensive blade assessment. By comparatively analyzing detection performance, cost, and automation levels across technologies, we identify key engineering barriers, including environmental noise robustness, signal attenuation within complex blade structures, and the persistent gap between laboratory methods and field deployment. Finally, we outline forward-looking research directions, encompassing multi-modal sensor fusion, edge computing for real-time diagnostics, and the development of standardized SHM systems aimed at supporting full lifecycle blade management. Full article

A large number of architectural drawings have historically existed in paper form or as non-editable raster images, which makes them difficult to directly support information reuse and digital management, while manual CAD reconstruction is time-consuming and inefficient. This paper proposes a hybrid deep learning and rule-based method for architectural drawing vectorization and CAD reconstruction, which automatically converts scanned raster images into editable CAD vector files while preserving geometric structure and scale consistency. The proposed method consists of four modules: axis grid and dimension detection, text recognition and scale recovery, architectural line topology reconstruction, and CAD geometric rectification and reconstruction. The method utilizes object detection and OCR technologies to extract key semantic information from the drawings. By extracting semantic information, the method constructs a line topology structure and applies architectural drawing constraints to parameterize and normalize geometric results, thereby achieving the recognition and vectorization of raster drawings. Experimental results and engineering case studies demonstrate that the proposed method can effectively extract typical architectural elements, and generate directly editable CAD vector drawings. The method achieves favorable geometric accuracy and topological consistency in architectural drawing digitization and automatic CAD reconstruction tasks, providing a technical solution for the automatic vectorization of existing architectural drawings. Full article

This article investigates how intuition operates when its referent is structurally absent or non-objectifiable. While phenomenology has traditionally linked intuition to fulfilment and object-givenness, a growing range of contemporary experiences, such as climate change, future generations, and technologically mediated processes, resist such modes of presentation in principle. Their absence is not contingent but structural. The article argues that phenomenology can nonetheless account for these experiences by articulating a mode of intuition that does not depend on presentable objects, but arises through mediation, temporal articulation, and responsiveness. Drawing on Husserl’s analyses of intuition and temporality, the first part identifies the limits of object-centred accounts of evidence in contexts characterized by mediation and diachronic dispersion. The second part turns to Levinas, whose account of diachrony and responsibility discloses a relation to the future that is ethically binding without being anticipable or reciprocable. The third part elaborates this insight through Waldenfels’s phenomenology of the alien and of responsiveness, showing how experience is structured by pathos, delay, and asymmetry. Here, intuition without objects appears not as a lack of evidence, but as a specific mode of experiential articulation grounded in interruption and answerability. The article concludes by showing how this phenomenological reconstruction clarifies central problems in contemporary climate ethics, particularly those concerning intergenerational responsibility. It suggests that what is often described as a motivational or institutional deficit can also be understood as a failure to recognize a distinctive intuitive relation to the future, i.e., one that binds without presenting and calls for response despite structural absence. In doing so, the notion of intuition without objects contributes to broader reflections on temporality, responsibility, and ethical agency under conditions of deep temporal asymmetry. Full article

Parkinson’s disease (PD) is a progressive neurodegenerative disorder in which early detection remains a major clinical challenge due to heterogeneous motor and non-motor manifestations and the lack of reliable biomarkers. In recent years, machine learning (ML) and deep learning (DL) methods have been increasingly investigated as decision-support tools for PD screening using diverse clinical and behavioral data. This review synthesizes PD detection studies published between 2017 and 2025, systematically analyzing 32 representative works across multiple modalities, including MRI, PET, EEG, REM sleep biomarkers, voice recordings, gait signals, handwriting/drawing tasks, and finger-tapping measurements. Across the reviewed literature, high classification performance is frequently reported, with CNN-based and hybrid DL architectures achieving particularly strong results in imaging and time-series settings, while classical ML approaches such as SVM and ensemble models remain competitive for engineered feature-based datasets. However, the review also reveals major barriers to reliable translation, including small datasets, inconsistent evaluation protocols, limited external validation, and the risk of performance inflation caused by non-subject-independent data splitting. Overall, this review provides a structured and modality-oriented reference of algorithms, datasets, and performance trends, while highlighting key methodological gaps and practical priorities for developing robust and clinically deployable PD detection systems. Full article

Water resources in arid oases are extremely scarce, and the quality of irrigation water and groundwater depth are key factors affecting soil secondary salinization and maintaining high and stable crop yields. This study focuses on the oasis irrigation area of the 38th Regiment in Qiemo County, located in the extremely arid region at the southeastern edge of the Tarim Basin. For the first time, irrigation experiments with different water qualities, ranging from 0.5 to 3.0 g/L, were conducted under varying groundwater depths for multiple crops. Through indoor soil column experiments and numerical simulations of water and salt in the unsaturated zone, the study reveals the water and salt migration patterns in the root zones of watermelon, corn, jujube, and peanuts. It was found that the process of soil water and salt transport exhibits significant differentiation characteristics in the vertical direction, with the surface layer responding most rapidly to changes in moisture and salinity, while the middle and deep layers show certain lag and buffering effects. The study also examined the spatiotemporal distribution trends of soil water and salt under different water quality and quantity irrigation conditions, drawing nonlinear threshold response curves for groundwater depth and determining the optimal groundwater depth under various irrigation conditions. The results indicate: (1) for the four crops under freshwater (0.5 g/L) irrigation and actual irrigation water conditions, soil salinity is safe at groundwater depths of 1–2 m; (2) under slightly saline water (2.0 g/L) irrigation, the safe groundwater depth (GWD) ranges for corn, peanuts, watermelon, and jujube root zones are 3.5–4.2 m, 1.2–3.5 m, ≥2.9 m, and ≥1.6 m, respectively, with crop sensitivity ranking as “corn > peanuts > watermelon > jujube”; and (3) under saline water (3.0 g/L) irrigation, the salinity tolerance thresholds for corn and peanuts root zones are exceeded regardless of shallow or deep groundwater depths, while the upper limits of salinity tolerance thresholds for watermelon and jujube correspond to groundwater depths of 2.9 m and 2.1 m, respectively, with increased groundwater depth making soil salinity increasingly safe. The study proposes a “sensitive-suitable-reinforced” three-zone paradigm and constructs a threshold table for optimal crop layout in arid areas based on the synergistic dual factors of “water quality–water quantity,” providing a theoretical basis for crop layout considering the spatial heterogeneity of groundwater occurrence. This has guiding value for arid oases in addressing the dual stress of water quality deterioration and salinization. Full article

In today’s fast-changing digital environment, cyber-physical systems face escalating security challenges due to increasingly sophisticated cyberattacks. Artificial Intelligence (AI) has emerged as a powerful enabler of modern cyberattack detection, offering scalable, accurate, and adaptive solutions to counter dynamic threats. This paper provides a comprehensive review of recent advancements in AI-based cyberattack detection, focusing on Machine Learning (ML), Deep Learning (DL), Reinforcement Learning (RL), Federated Learning (FL), and emerging techniques such as generative AI, neuro-symbolic AI, swarm intelligence, lightweight AI, and quantum Computing. We evaluate the strengths and limitations of these approaches, highlighting their performance on benchmark datasets. The review discusses traditional signature-based Intrusion Detection Systems (IDS) and their limitations against novel attack patterns, contrasted with AI-driven anomaly-based and hybrid detection methods that improve detection rates for unknown and zero-day attacks. Key challenges, including computational costs, data quality, privacy concerns, and model interpretability, are analysed alongside the role of Explainable AI (XAI) in enhancing trust and transparency. The impact of computational resources, dataset representativeness, and evaluation metrics on AI model performance is also explored. Furthermore, we investigate the potential of lightweight AI for resource-constrained environments like IoT and edge devices, and quantum computing’s role in advancing detection efficiency and cryptographic security. The paper also draws attention to future research directions, particularly the development of up-to-date datasets, integration of hybrid quantum–classical models, and optimisation of asynchronous FL protocols to address evolving cybersecurity challenges. This study aims to inspire innovation in AI-driven cyberattack detection, fostering robust, interpretable, and efficient solutions for securing complex digital environments. Full article

Chinese poetry is rich in cultural landscapes, and the cultural spirit in poetry imbues these landscapes with profound meaning and value. Exploring and integrating the cultural landscape resources in poetry offers a novel approach for the planning and development of national cultural parks (NCPs). In this study, the Yangtze River NCP in Hubei Province is chosen as the case study area, owing to its deep historical heritage in poetic literature and its wealth of poetic works. The temporal–spatial evolution and formation mechanisms of cultural landscapes in poetry (CLP) from the Pre-Qin period to the Republic of China period are examined by using the landscape index, ArcGIS spatial analysis methods, Geodetector, and cultural ecology theory. This study contributes to research on CLP in two key ways: (1) The landscape index is used to evaluate the cultural value of CLP and is subsequently incorporated as a weighting factor in spatial analysis. It enables more precise identification of the spatial patterns of CLP and highlight the most iconic and culturally significant landscapes. This supports the optimization and integration of Chinese poetic cultural resources. (2) Drawing on cultural ecology theory, Geodetector is applied to examine the influencing factors and underlying mechanisms shaping the temporal–spatial evolution of CLP. It offers theoretical insights into the formation mechanisms of spatial distribution in other forms of cultural heritage. Overall, this study broadens the perspective on cultural landscapes in Chinese poetry and provides practical guidance for the planning and construction of the Yangtze River NCP in Hubei Province. Full article

The cylindrical submerged linear motor with the primary core used in traditional welded stacked 50ww470 non-silicon steel sheets faces many shortcomings. These include its structure being complex and difficult to manufacture, the process requiring stages such as steel sheet blanking, stacking, and welding, and the iron core exhibiting large magnetic resistance and generating a lot of heat when the motor is working, reducing the motor efficiency. Therefore, an ultrasonic vibration-assisted (UVA) deep drawing process for multilayer sheets was proposed to replace the traditional process. The finite element analysis was carried out on single-layer sheet drawing. Using Abaqus software, we verified that UVA could improve the uniformity of the wall thickness of formed parts, and reduce wall thickness thinning and rebound; the core forming height is so low that there will be a larger rebound after forming. The “split ring” method was used to verify that ultrasonic vibration can suppress the rebound of the formed part. As the bottom of the core was made of six layers of silicon steel sheets, laminated and welded, the feasibility of different solutions was investigated by setting up a UVA deep drawing experimental platform to study single-, double-, three- and six-layer-sheets, and the forming quality and forming forces were analyzed. The final forming process was determined to require two deep-drawing three-layer sheets, and the forming part was successfully manufactured. Full article

A spatial awareness is a fundamental aspect of dance, reflecting deep philosophical ideas and aesthetic values across different cultures. While existing studies often focus on theatrical or biomechanical analyses, few explore how material cultural artifacts, such as pottery and porcelain figurines, reveal spatial differences in dance. This study addresses this gap by comparing Chinese pottery figurines from the Neolithic to Tang dynasties with Western Meissen porcelain dancers from the 18th century onward, applying a three-dimensional framework of “Movement Scheduling Space—kinetic space—expressive space.” Drawing on Confucian principles of “Harmony between Heaven and Humanity” and Christian notions of transcendence, the research examines how cultural traditions shape the spatial expression in dance. The findings show that Chinese dance emphasizes inward, upper-body movements extending from two-dimensional to one-dimensional space, reflecting a centripetal, earthly orientation. In contrast, Western dance expands from two-dimensional to three-dimensional space, emphasizing outward, lower-body movements symbolizing transcendental aspirations. Additionally, Chinese dance focuses on subtle hand gestures, while Western dance highlights expressive foot movements. By integrating artifact-based analysis with cultural and philosophical interpretation, this study offers a fresh approach to comparative dance philosophy, providing valuable insights for the reinterpretation of traditional aesthetics in modern choreography. Full article

Objectives: This study aims to evaluate the predictability of Clear Aligner Therapy (CAT) in deep bite correction and Spee Curve flattening by comparing final intraoral scans with planned outcomes in ClinCheck. Methods: STL files from pre-treatment, post-treatment (first aligner cycle), and planned final positions of 18 patients (12 females; 6 males; mean age 30.9 ± 12.3 years) were analyzed. The software Medit Link (version 3.4.4) was used to measure overbite as the vertical distance between the incisal edges of the maxillary and mandibular central incisors and the Curve of Spee in both arches by drawing a reference line between the most distal molar and the central incisor on each side, recording the perpendicular distance from the distal cusp. Measurements were repeated on post-treatment and ClinCheck STL files. Data analysis was performed using a Student’s t-test (p = 0.05) to compare the expected and actual measure variations and intraclass correlation coefficient (ICC) to assess aligner predictability. Results: A significant discrepancy was observed in overbite correction (55% achieved), with a significant difference between expected and actual outcomes (p = 0.0001). Moderate differences were noted for the lower Spee Curve (62% achieved), while the upper Spee Curve showed 86% of the expected change. ICC values were moderate for overbite and lower Spee Curve, and good for the upper Spee Curve. Conclusions: ClinCheck overestimates deep bite correction. Upper Curve of Spee flattening is highly predictable, while the lower curve flattening has lower predictability. Full article

The paper presents reflections from four black women academics on their process of creating theatricalised performances about their experiences in higher education. These women are part of the research group Feminist Decoloniality as Care (FemDAC). The performances were presented at various academic conferences by the four women. The making of the performance drew on letter-writing reflections prompted by questions centred on the experiences of black women academics in higher education. The audiences and performers engaged in post-performance discussions about issues and ideas pertinent to them. The process involved addressing issues of academic woundedness and exploring how black women can embody the structural injustices of the academy. What happens when black women academics see patriarchy and white supremacist tendencies in themselves? How do we facilitate decolonial care when the theatre process digs into our wounds? How does the performance give insight into the fractured relationship between black women and their fellow academics? This paper describes a decolonial approach to evoking care practices within the academy, especially drawing on the discourse of the arts for social change. The theatrical performance reflected the deep discomfort of black women academics in caring for and healing themselves amid ongoing academic woundedness. Full article

Artificial intelligence (AI) has become central to the evolution of learning analytics (LA), transforming how higher-education institutions capture and interpret student engagement data. This narrative review synthesises research published between 2015 and 2025 to examine how AI-driven analytics link learner engagement to measurable academic outcomes, with emphasis on the South-African higher-education context. Drawing on global reviews of AI in education and emerging governance frameworks, the study highlights the shift from traditional dashboards toward deep-learning and transformer-based systems that integrate behavioural, cognitive, and affective indicators. Ethical and policy challenges, particularly around data privacy, transparency, and institutional capacity, remain significant. Grounded in UNESCO and OECD guidance and South Africa’s Protection of Personal Information Act, the review outlines a governance-driven approach for equitable and transparent adoption of AI-enhanced learning analytics. It identifies key challenges, data fragmentation, algorithmic opacity, and limited contextual adaptation, and translates them into practical recommendations for policy, capacity building, and future research. The findings underscore that sustainable AI adoption requires human-centred ethics, robust data governance, and context-sensitive innovation to achieve inclusive and data-driven higher education. Full article

Bridges are a crucial part of infrastructure, but many are in urgent need of maintenance. Digital methods like Building Information Modeling (BIM) and Digital Twinning can support this process but depend on digital models that are often missing for existing structures. Automating the reconstruction of these models from existing documentation, such as construction drawings, is essential to accelerate digital adoption. Addressing a key step in the reconstruction process, this paper presents an end-to-end pipeline for extracting bridge cross-sections from drawings. First, the YOLOv8 network locates and classifies the cross-sections within the drawing. The results are then processed by the segmentation model Segment Anything Model (SAM), which generates pixel-wise masks without requiring task-specific training data. This eliminates the need for manual mask annotation and enables straightforward adaptation to different cross-section types, making the approach broadly applicable in practice. Finally, a global optimization algorithm fits parametric templates to the masks, minimizing a custom loss function to extract geometric parameters. The pipeline is evaluated on 33 real-world drawings and achieves a median parameter deviation of −2.2 cm and 2.4 cm, with an average standard deviation of 35.4 cm. Full article

The crown conveys a rich tapestry of history and deep cultural resonances among the Yoruba people of South-western Nigeria, beyond its representation as an emblem of leadership, royalty, and nobility. This article explores layers of the meaning of crown in the Yoruba personal naming system. It relies on an ethnopragmatic theory to analyse the cultural significance and symbolic impact of crown-related names among the Yoruba. Drawing on a qualitative research approach using participant observation and semi-structured interviews with 25 participants who were purposively sampled in Ikeja, Lagos State, we argue that crown-related names are not mere identifiers or person reference labels, but they provide cultural insights and reflections on the foundation of authority and continuity, and carry the aspirational principles of the Yoruba traditional structure. The names symbolise personal journey; reinforce the hierarchical structure of the Yoruba society; and highlight the people’s deep connection to their ancestral lineage. This study concludes that crown-related names encapsulate the values, beliefs, and social structures of the Yoruba society, serving as enduring markers of dynastic identity and cultural values. In this way, crown-related names represent badges of honour that validate their bearers’ self-worth and dignity. Full article

In the process of ore drawing using a caving method under interburden conditions, the key to controlling ore dilution lies in the accurate prediction of boundary particle migration trajectories. To address the challenges of high computational costs and complex modeling in traditional numerical simulations, this study designs a dataset construction method. After calibrating parameters using the angle of repose, ore-drawing numerical simulation datasets with interburden (post-defined and pre-defined models) are established. Building upon this foundation, an improved Transformer model is proposed. The model enhances spatiotemporal representation through multi-layer feature fusion embedding, strengthens long-range dependency capture via a reinforced spatiotemporal attention backbone, improves local dynamic modeling capability through optimized decoding at the output stage, and integrates transfer learning to achieve continuous prediction of particle migration. Validation results demonstrate that the model accurately predicts the spatial distribution patterns and collective motion trends of particles, with prediction errors at critical nodes confined to within a single stage and an average estimation error of approximately 4% in interburden regions. The proposed approach effectively overcomes the timeliness bottleneck of traditional interburden ore-drawing simulations, enabling rapid and accurate prediction of boundary particle migration under interburden conditions. Full article