Search Results (2,535)

Biometric authentication on smartphones has advanced rapidly in recent years, with face recognition becoming the dominant modality due to its convenience and easy integration with modern mobile hardware. However, despite these developments, smartphone-based facial recognition systems remain vulnerable to a broad spectrum of attacks. This survey provides an updated and comprehensive examination of the evolving attack landscape and corresponding defense mechanisms, incorporating recent advances up to 2025. A key contribution of this work is a structured taxonomy of attack types targeting smartphone facial recognition systems, encompassing (i) 2D and 3D presentation attacks; (ii) digital attacks; and (iii) dynamic attack patterns that exploit acquisition conditions. We analyze how these increasingly realistic and condition-dependent attacks challenge the robustness and generalization capabilities of modern face anti-spoofing (FAS) systems. On the defense side, the paper reviews recent progress in liveness detection, deep-learning- and transformer-based approaches, quality-aware and domain-generalizable models, and emerging unified frameworks capable of handling both physical and digital spoofing. Hardware-assisted methods and multi-modal techniques are also examined, with specific attention to their applicability in mobile environments. Furthermore, we provide a systematic overview of commonly used datasets, evaluation metrics, and cross-domain testing protocols, identifying limitations related to demographic bias, dataset variability, and controlled laboratory conditions. Finally, the survey outlines key research challenges and future directions, including the need for mobile-efficient anti-spoofing models, standardized in-the-wild evaluation protocols, and defenses robust to unseen and AI-generated spoof types. Collectively, this work offers an integrated view of current trends and emerging paradigms in smartphone-based face anti-spoofing, supporting the development of more secure and resilient biometric authentication systems. Full article

With the rapid development of artificial intelligence technology, facial expression recognition (FER) has gained increasingly widespread applications in digital human generation, humanoid robotics, mental health, and human–computer dialogue. Typical FER algorithms based on machine learning have been widely studied over the past few decades, which motivated our survey. In this study, we have surveyed the state of the art in FER across two categories: traditional machine learning-based (ML-based) and deep learning-based (DL-based) approaches. Each category is analyzed based on six subcategories. Then, twelve methods, including four ML-based models and eight DL-based models, are compared to evaluate FER performance across four datasets. The experimental results show that in validation sets, the average accuracy of HOG-SVM is 50.12%, which is the best performance for the four ML-based methods; in contrast, Poster has an average accuracy of 75.98%, which is the best result obtained among the eight DL-based methods. The most difficult expression to recognize is contempt, with recognition accuracies of 10.00% and 40.06% for ML-based and DL-based methods, respectively. The accuracy of the ML-based method for identifying neutral expression is the highest at 35.25%; the DL-based method has the highest accuracy in identifying surprise at 69.56%. From the theoretical analysis and comparative experimental results of existing methods, we can see that FER faces challenges, including inaccurate recognition in complex environments and unbalanced data categories, highlighting several future research directions, especially those involving the latest applications of digital humans and large language models. Full article

In order to reduce the risk of collapse disasters during tunnel construction in mountainous areas and to make full use of the available data, a collapse risk assessment model for highway tunnel construction was established based on the WOA–XGBOOST algorithm. Three major categories of tunnel construction risk, namely engineering geological factors, survey and design factors, and construction management factors, were selected as the first-level indicators, and 14 secondary indicators were further specified as the input variables of the collapse risk assessment model for tunnel construction. The confusion matrix and accuracy metrics were employed to evaluate the training and prediction performance of the risk assessment model on both the training set and the test set. The results show that subjective weights derived from the G1 method were integrated with objective weights generated by the WOA–XGBOOST algorithm. A game-theory-based weight integration strategy was then applied to optimize the combined weights, effectively mitigating the biases inherent in single-method weighting approaches. Risk quantification was systematically conducted using a cloud model, while spatial risk distribution patterns were visualized through graphical cloud-mapping techniques. After completion of model training, the proposed model achieved a high accuracy of over 99% on the training set and around 95% on the held-out test set based on an available dataset of 100 collapse-prone tunnel construction sections. Case-based verification further suggests that, in the studied collapse scenarios, the predicted risk levels are generally consistent with the actual engineering risks, indicating that the model is a promising tool for assisting tunnel construction risk assessment under similar conditions. The research outcomes provide an efficient and reliable approach for assessing risks in tunnel construction, thereby offering a scientific basis for engineering decision-making processes. Full article

This study introduces a novel, automated image-to-BIM (Building Information Modeling) workflow designed to generate semantically rich and geometrically useful BIM models directly from RGB images. Conventional scan-to-BIM often relies on specialized, costly, and time-intensive equipment, specifically if LiDAR is used to generate point clouds (PCs). Typical workflows are followed by a separate post-processing step for semantic segmentation recently performed by deep learning models on the generated PCs. Instead, the proposed method integrates vision language object detection (YOLOv8x-World v2) and vision based segmentation (SAM 2.1) with Neural Radiance Fields (NeRF) 3D reconstruction to generate segmented, color-labeled PCs directly from images. The key novelty lies in bypassing post-processing on PCs by embedding semantic information at the pixel level in images, preserving it through reconstruction, and encoding it into the resulting color labeled PC, which allows building elements to be directly identified and geometrically extracted based on color labels. Extracted geometry is serialized into a JSON format and imported into Revit to automate BIM creation for walls, windows, and doors. Experimental validation on BIM models generated from Unmanned Aerial Vehicle (UAV)-based exterior datasets and standard camera-based interior datasets demonstrated high accuracy in detecting windows and doors. Spatial evaluations yielded up to 0.994 precision and 0.992 Intersection over Union (IoU). NeRF and Gaussian Splatting models, Nerfacto, Instant-NGP, and Splatfacto, were assessed. Nerfacto produced the most structured PCs suitable for geometry extraction and Splatfacto achieved the highest image reconstruction quality. The proposed method removes dependency on terrestrial surveying tools and separate segmentation processes on PCs. It provides a low-cost and scalable solution for generating BIM models in aging or undocumented buildings and supports practical applications such as renovation, digital twin, and facility management. Full article

The Internet of Things (IoT) has established an exceptional ecosystem of interconnected devices where a vast multitude of heterogeneous devices can communicate, collect, and share data for enhanced decision-making processes. To effectively analyze this immense volume of data, researchers have deployed advanced machine learning algorithms and deep neural networks. However, these approaches typically rely on centralized data storage for training, which raises significant privacy concerns. Federated Learning (FL) addresses this issue by allowing devices to train local models on their own data and share only model updates. Despite this advantage, FL remains vulnerable to several security threats, including model poisoning, data manipulation, and Byzantine attacks. Therefore, robust and scalable authentication mechanisms are essential to ensure secure participation in FL environments. This study provides a comprehensive survey of authentication in FL. We examine the authentication process, discuss the associated key challenges, and analyze architectural considerations relevant to securing FL deployments. Existing authentication schemes are reviewed and evaluated in terms of their effectiveness, limitations, and practicality. To provide deeper insight, we classify these schemes along two dimensions as follows: their underlying enabling technologies, such as blockchain, cryptography, and AI-based methods, and the system contexts in which FL operates. Furthermore, we analyze the datasets and experimental environments used in current research, identify open research challenges, and highlight future research directions. To the best of our knowledge, this study presents the first structured and comprehensive analysis of authentication mechanisms in FL, offering a foundational reference for advancing secure and trustworthy federated learning systems. Full article

Tidal inundation is a key factor determining the structure and function of estuarine salt marsh ecosystems. However, due to the influence of microtopography (small-scale topographic variations), the fine-scale spatial variations in tidal inundation have not been fully studied. To fill this research gap, this study focuses on the Luanhe Estuary—a region highly sensitive to topographic changes—and explores in depth the physical mechanisms regulating tidal inundation in this area. The study integrates long-term data from the Sentinel-1 Synthetic Aperture Radar (SAR) and Sentinel-2 Multispectral Instrument (MSI), spanning the period from 2016 to 2025, to construct a high-resolution time series dataset of Apparent Inundation Frequency (AIF). Subsequently, this dataset is correlated with a high-precision microtopographic Digital Elevation Model (DEM) obtained through Unmanned Aerial Vehicle (UAV) surveys. The analysis reveals a strong nonlinear relationship between AIF and topographic elevation, which is best described by an exponential decay model (R² = 0.903). The results show that the average inundation probability in the study area has shown a fluctuating but overall upward trend, increasing from 16.74% in 2016 to 29.02% in 2025 (peaking at 31.39% in 2024). Quantitative modeling confirms that microtopography is the primary controlling factor for fine-scale variations in tidal inundation levels. The integrated research approach proposed in this study provides a reliable framework for coastal vulnerability assessment. Against the backdrop of increasingly severe impacts from climate change and human activities, the high-resolution quantitative data generated by this study provides scientific support for formulating disaster mitigation and geomorphological management strategies. Full article

Quiet drivetrains have become a central requirement in modern electric vehicles, where the absence of engine masking makes even subtle gear tones clearly audible. As a result, manufacturers are looking for more reliable ways to understand how design choices, manufacturing variability, and operating conditions shape gear noise and vibration. Digital Twin (DT) approaches—linking high-fidelity models with measured data throughout the product lifecycle—offer a potential route to achieve this, but their use in gear NVH is still emerging. This review examines recent work from the past decade on DT concepts applied to gears and drivetrain NVH, drawing together advances in simulation, metrology, sensing, and data exchange standards. The survey shows that several building blocks of an NVH-oriented twin already exist, yet they are rarely combined into an end-to-end workflow. Clear gaps remain. Current models still struggle with high-frequency behavior. Real-time operation is also limited. Manufacturing and test data are often disconnected from simulations. Validation practices lack consistent NVH metrics. Hybrid and surrogate modeling methods are used only to a limited extent. The sustainability benefits of reducing prototypes are rarely quantified. These gaps define the research directions needed to make DTs a practical tool for future gear NVH development. A research Gap Map is presented, categorizing these gaps and their impact. For each gap, we propose actionable future directions—from multiscale “hybrid twins” that merge test data with simulations, to benchmark datasets and standards for DT NVH validation. Closing these gaps will enable more reliable gear DTs that reduce development costs, improve acoustic quality, and support sustainable, data-driven NVH optimization. Full article

This study examines the perceived mental health of Ukrainian female forced migrants in Ireland through the lens of the socio-ecological model (SEM). Using binomial logistic regression on a 2023 online survey dataset (N = 656), it explores multi-level predictors across individual, relationship, community, and societal domains. Results indicate that individual-level factors explain the largest proportion of variance in perceived mental health (Nagelkerke R² = 0.399). Employment status, self-rated physical health, and coping strategies were key determinants: part-time employment and good physical health were associated with higher odds of good perceived mental health. In contrast, avoidant coping and worsening health were associated with poorer outcomes. Relationship-level factors (R² = 0.194) also contributed significantly; lack of social support and deteriorating family or friendship ties were linked to poorer mental health, whereas participation in refugee meetings was strongly protective. Community-level factors (R² = 0.123) revealed that unstable housing, living with strangers, and declining neighbourhood relationships were associated with reduced mental well-being. At the societal level (R² = 0.168), insufficient access to psychological support and excessive exposure to Ukrainian news were associated with poorer outcomes, while moderate news engagement was protective. The findings highlight the multifaceted nature of refugees’ perceived mental health, emphasising the interdependence of personal resilience, social connectedness, and systemic support. Full article

We present an integrated methodology for three-dimensional inversion of large-scale airborne electromagnetic (AEM) and magnetic survey data that simultaneously recovers electrical conductivity, chargeability, and both induced and remanent magnetizations. A central feature of the AEM component is the explicit incorporation of induced polarization (IP) effects. Neglecting IP responses can lead to biased conductivity models, particularly in mineralized systems where disseminated sulfides contribute strongly to chargeability. Using the Generalized Effective-Medium Theory of Induced Polarization (GEMTIP), the inversion produces physically consistent 3D distributions of conductivity and chargeability. To enhance magnetic interpretation, we also implement a vector magnetic inversion that resolves both induced and remanent magnetization from Total Magnetic Intensity (TMI) data, enabling geologically realistic magnetization models in terranes with significant remanence. This integrated workflow was applied to airborne AEM and TMI datasets collected over the Asankrangwa Gold Belt in central Ghana. The inversion results delineate a key exploration target defined by coincident magnetic low and elevated chargeability, interpreted as sulfide-rich gold mineralization and subsequently confirmed by drilling. These results demonstrate that jointly accounting for IP and remanent magnetization in 3D inversion substantially improves subsurface characterization and provides a powerful tool for mineral exploration in structurally and lithologically complex environments. Full article

The rising demand for real-time perception in aerial platforms has intensified the need for lightweight, hardware-efficient object detectors capable of reliable onboard operation. This survey provides a focused examination of real-time aerial object detection, emphasizing algorithms designed for edge devices and UAV onboard processors, where computation, memory, and power resources are severely constrained. We first review the major aerial and remote-sensing datasets and analyze the unique challenges they introduce, such as small objects, fine-grained variation, multiscale variation, and complex backgrounds, which directly shape detector design. Recent studies addressing these challenges are then grouped, covering advances in lightweight backbones, fine-grained feature representation, multi-scale fusion, and optimized Transformer modules adapted for embedded environments. The review further highlights hardware-aware optimization techniques, including quantization, pruning, and TensorRT acceleration, as well as emerging trends in automated NAS tailored to UAV constraints. We discuss the adaptation of large pretrained models, such as CLIP-based embeddings and compressed Transformers, to meet onboard real-time requirements. By unifying architectural strategies, model compression, and deployment-level optimization, this survey offers a comprehensive perspective on designing next-generation detectors that achieve both high accuracy and true real-time performance in aerial applications. Full article

The exponential growth of candidate data from large-scale radio pulsar surveys has created a pressing need for efficient and accurate classification methods. This paper presents a novel hybrid pulsar candidate recognition algorithm that integrates diagnostic plot images and structured numerical features using a multi-scale DenseNet framework. The proposed model combines convolutional neural networks (CNNs) for extracting spatial patterns from pulsar diagnostic plots and feedforward neural networks (FNNs) for processing scalar features such as SNR, DM, and pulse width. By fusing these multimodal representations, the model achieves superior classification performance, particularly in class-imbalanced settings standard to pulsar survey data. Evaluated on a synthesized dataset constructed from FAST and HTRU survey characteristics, the model demonstrates robust performance, achieving an F1-score of 0.904 and AUC-ROC of 0.978. Extensive ablation and cross-validation analyses confirm the contribution of each data modality and the model’s generalizability. Furthermore, the system maintains low inference latency (4.2 ms per candidate) and a compact architecture (~2.3 million parameters), indicating potential for real-time deployment once validated on real observational datasets. The proposed approach offers a scalable and interpretable multimodal framework for automated pulsar classification and provides a foundation for future validation and potential integration into observatories such as FAST and the Square Kilometre Array (SKA). Full article

Folk festivals and other intangible cultural heritage have received widespread attention, and their socio-cultural value can be used to promote tourism, strengthen local identity, and build city brands. However, it remains unclear how these intangible cultural heritage festivals transform their multi-dimensional and multi-configuration material characteristics into economic benefits and image enhancement. This study proposes a practical decision-making framework aimed at understanding how different festival design and governance strategies can work synergistically under different cultural conditions. Based primarily on a literature review and expert questionnaire survey, this study identified six stable materialized practice modules: productization, spatialization, experientialization, digitalization, branding/communication, and co-creation governance. At the same time, this framework also incorporates two other conditional intervention properties: classicism and novelty. The interactions between these modules shape people’s understanding of intangible cultural heritage festivals. Subsequently, this study used a multimodal national dataset that included official statistics, industry reports, e-commerce and social media data, questionnaires, and expert ratings to construct module scores and cultural attributes for 167 festival case studies. Through rough set analysis (RSA), this study simplifies the attributes and extracts clear “if-then” rules, establishing a configurational causal relationship between module configuration and classic/novel conditions to form high economic benefits and enhance local image. The findings of this study reveal a robust core built around spatialization, digitalization, and co-creative governance, with brand promotion/communication yielding benefits depending on the specific context. This further confirms that classicism reinforces the legitimacy and effectiveness of rituals/spaces and governance pathways, while novelty amplifies the impact of digitalization and immersive interaction. In summary, this study constructs an integrated and easy-to-understand process that links indicators, weights, and rules, and provides operational support for screening schemes and resource allocation in festival event combinations and venue brand governance. Full article

This paper presents a comprehensive review of motion capture (MoCap) data recovery techniques, with a particular focus on the suitability of artificial intelligence (AI) for addressing missing or corrupted motion data. Existing approaches are classified into three categories: non-data-driven, data-driven (AI-based), and hybrid methods. Within the AI domain, frameworks such as generative adversarial networks (GANs), transformers, and graph neural networks (GNNs) demonstrate strong capabilities in modeling complex spatial–temporal dependencies and achieving accurate motion reconstruction. Compared with traditional methods, AI techniques offer greater adaptability and precision, though they remain limited by high computational costs and dependence on large, high-quality datasets. Hybrid approaches that combine AI models with physics-based or statistical algorithms provide a balance between efficiency, interpretability, and robustness. The review also examines benchmark datasets, including CMU MoCap and Human3.6M, while highlighting the growing role of synthetic and augmented data in improving AI model generalization. Despite notable progress, the absence of standardized evaluation protocols and diverse real-world datasets continues to hinder generalization. Emerging trends point toward real-time AI-driven recovery, multimodal data fusion, and unified performance benchmarks. By integrating traditional, AI-based, and hybrid approaches into a coherent taxonomy, this review provides a unique contribution to the literature. Unlike prior surveys focused on prediction, denoising, pose estimation, or generative modeling, it treats MoCap recovery as a standalone problem. It further synthesizes comparative insights across datasets, evaluation metrics, movement representations, and common failure cases, offering a comprehensive foundation for advancing MoCap recovery research. Full article

Ancient walled cities represent key material evidence for early state formation and human–environment interaction on the northeastern Tibetan Plateau. However, traditional field surveys are often constrained by the vastness and complexity of the plateau environment. This study proposes an improved deep learning framework, AC-YOLOv11, to achieve automated detection of ancient city remains in the Qinghai Lake Basin using 0.8 m GF-2 satellite imagery. By integrating a dual-path attention residual network (AC-SENet) with multi-scale feature fusion, the model enhances sensitivity to faint geomorphic and structural features under conditions of erosion, vegetation cover, and modern disturbance. Training on the newly constructed Qinghai Lake Ancient City Dataset (QHACD) yielded a mean average precision (mAP@0.5) of 82.3% and F1-score of 94.2%. Model application across 7000 km² identified 309 potential sites, of which 74 were verified as highly probable ancient cities, and field investigations confirmed 3 new sites with typical rammed-earth characteristics. Spatial analysis combining digital elevation models and hydrological data shows that 75.7% of all ancient cities are located within 10 km of major rivers or the lake shoreline, primarily between 3500 and 4000 m a.s.l. These results reveal a clear coupling between settlement distribution and environmental constraints in the high-altitude arid zone. The AC-YOLOv11 model demonstrates strong potential for large-scale archaeological prospection and offers a methodological reference for automated heritage mapping on the Qinghai–Tibet Plateau. Full article

Historical cropland cover change reconstruction is essential for understanding long-term agricultural reclamation dynamics, particularly for modeling carbon and nitrogen cycles and assessing their climatic impacts. Such reconstructions also provide critical regional benchmarks for improving global land-use datasets. In this study, we integrated historical documents and land survey records spanning the Heian period (794–1185 CE) to the present with modern remote sensing data to develop a spatially explicit methodology for reconstructing Japan’s cropland extent over the past millennium. Our analysis revealed four distinct phases of cropland area change, (1) slow expansion (800–1338 CE), (2) gradual decline (1338–1598 CE), (3) rapid growth (1598–1940 CE), and (4) sharp contraction (1940–2000 CE), with significant regional variations. Spatially, cropland progressively expanded from the core Kansai and Kantō regions toward the southwestern and northeastern frontiers. Cropland cover changes in Japan over the past millennium were driven by a combination of socio-political factors—such as technological innovations in agriculture, feudal conflicts, demographic shifts, agricultural industrialization, and urbanization—as well as natural conditions, including topography, climate, and soil texture. Validation against year-2000 remote sensing data demonstrated high accuracy, with 69.12% of grid cells showing ≤20% absolute difference and only 0.15% exceeding ±80% deviation. Full article