Search Results (5,883)

Automatic Speaker Verification (ASV) systems are increasingly employed to secure access to services and facilities. However, recent advances in speech deepfake generation pose serious threats to their reliability. Modern speech synthesis models can convincingly imitate a target speaker’s voice and generate realistic synthetic audio, potentially enabling unauthorized access through ASV systems. To counter these threats, forensic detectors have been developed to distinguish between real and fake speech. Although these models achieve strong performance, their deep learning nature makes them susceptible to adversarial attacks, i.e., carefully crafted, imperceptible perturbations in the audio signal that make the model unable to classify correctly. In this paper, we explore adversarial attacks targeting speech deepfake detectors. Specifically, we analyze the effectiveness of Basic Iterative Method (BIM) attacks applied in both time and frequency domains under white- and black-box conditions. Additionally, we propose an ensemble-based attack strategy designed to simultaneously target multiple detection models. This approach generates adversarial examples with balanced effectiveness across the ensemble, enhancing transferability to unseen models. Our experimental results show that, although crafting universally transferable attacks remains challenging, it is possible to fool state-of-the-art detectors using minimal, imperceptible perturbations, highlighting the need for more robust defenses in speech deepfake detection. Full article

Chinese Optical Character Recognition (OCR) technology is essential for digital transformation in Chinese regions, enabling automated document processing across various applications. However, Chinese OCR systems struggle with visually similar characters, where subtle stroke differences lead to systematic recognition errors that limit practical deployment accuracy. This study develops FLIP (Feedback Learning-based Intelligent Plugin), a lightweight post-processing plugin designed to improve Chinese OCR accuracy across different systems without external dependencies. The plugin operates through three core components as follows: UTF-8 encoding-based output parsing that converts OCR results into mathematical representations, error correction using information entropy and weighted similarity measures to identify and fix character-level errors, and adaptive feedback learning that optimizes parameters through user interactions. The approach functions entirely through mathematical calculations at the character encoding level, ensuring universal compatibility with existing OCR systems while effectively handling complex Chinese character similarities. The plugin’s modular design enables seamless integration without requiring modifications to existing OCR algorithms, while its feedback mechanism adapts to domain-specific terminology and user preferences. Experimental evaluation on 10,000 Chinese document images using four state-of-the-art OCR models demonstrates consistent improvements across all tested systems, with precision gains ranging from 1.17% to 10.37% and overall Chinese character recognition accuracy exceeding 98%. The best performing model achieved 99.42% precision, with ablation studies confirming that feedback learning contributes additional improvements from 0.45% to 4.66% across different OCR architectures. Full article

Reconfigurable Intelligent Surface (RIS) has emerged as a promising enabling technology for wireless communications, which significantly enhances system performance through real-time manipulation of electromagnetic wave reflection characteristics. In RIS-assisted communication systems, existing deep learning-based channel state information (CSI) feedback methods often suffer from excessive parameter requirements and high computational complexity. To address this challenge, this paper proposes LwCSI-Net, a lightweight autoencoder network specifically designed for RIS-assisted multiple-input single-output (MISO) systems, aiming to achieve efficient and low-complexity CSI feedback. The core contribution of this work lies in an innovative lightweight feedback architecture that deeply integrates multi-layer convolutional neural networks (CNNs) with attention mechanisms. Specifically, the network employs 1D convolutional operations with unidirectional kernel sliding, which effectively reduces trainable parameters while maintaining robust feature-extraction capabilities. Furthermore, by incorporating an efficient channel attention (ECA) mechanism, the model dynamically allocates weights to different feature channels, thereby enhancing the capture of critical features. This approach not only improves network representational efficiency but also reduces redundant computations, leading to optimized computational complexity. Additionally, the proposed cross-channel residual block (CRBlock) establishes inter-channel information-exchange paths, strengthening feature fusion and ensuring outstanding stability and robustness under high compression ratio (CR) conditions. Our experimental results show that for CRs of 16, 32, and 64, LwCSI-Net significantly improves CSI reconstruction performance while maintaining fewer parameters and lower computational complexity, achieving an average complexity reduction of 35.63% compared to state-of-the-art (SOTA) CSI feedback autoencoder architectures. Full article

Aiming to enable intelligent vehicles to achieve autonomous charging under low-battery conditions, this paper presents a navigation system for autonomous charging that integrates an improved bidirectional A* algorithm for path planning and an optimized YOLOv11n model for visual recognition. The system utilizes the improved bidirectional A* algorithm to generate collision-free paths from the starting point to the charging area, dynamically adjusting the heuristic function by combining node–target distance and search iterations to optimize bidirectional search weights, pruning expanded nodes via a greedy strategy and smoothing paths into cubic Bézier curves for practical vehicle motion. For precise localization of charging areas and piles, the YOLOv11n model is enhanced with a CAFMFusion mechanism to bridge semantic gaps between shallow and deep features, enabling effective local–global feature fusion and improving detection accuracy. Experimental evaluations in long corridors and complex indoor environments showed that the improved bidirectional A* algorithm outperforms the traditional improved A* algorithm in all metrics, particularly in that it reduces computation time significantly while maintaining robustness in symmetric/non-symmetric and dynamic/non-dynamic scenarios. The optimized YOLOv11n model achieves state-of-the-art precision (P) and mAP@0.5 compared to YOLOv5, YOLOv8n, and the baseline model, with a minor 0.9% recall (R) deficit compared to YOLOv5 but more balanced overall performance and superior capability for small-object detection. By fusing the two improved modules, the proposed system successfully realizes autonomous charging navigation, providing an efficient solution for energy management in intelligent vehicles in real-world environments. Full article

Solid-state LiDAR systems are widely recognized for their high reliability, low cost, and lightweight design, but they encounter significant challenges in SLAM tasks due to their limited field of view and uneven horizontal scanning patterns, especially in indoor environments with geometric constraints. To address these challenges, this paper proposes SS-LIO, a precise, robust, and real-time LiDAR–Inertial odometry solution designed for solid-state LiDAR systems. SS-LIO uses uncertainty propagation in LiDAR point-cloud modeling and a tightly coupled iterative extended Kalman filter to fuse LiDAR feature points with IMU data for reliable localization. It also employs voxels to encapsulate planar features for accurate map construction. Experimental results from open-source datasets and self-collected data demonstrate that SS-LIO achieves superior accuracy and robustness compared to state-of-the-art methods, with an end-to-end drift of only 0.2 m in indoor degraded scenarios. The detailed and accurate point-cloud maps generated by SS-LIO reflect the smoothness and precision of trajectory estimation, with significantly reduced drift and deviation. These outcomes highlight the effectiveness of SS-LIO in addressing the SLAM challenges posed by solid-state LiDAR systems and its capability to produce reliable maps in complex indoor settings. Full article

Federated learning (FL) enables multiple participants to collaboratively train models while efficiently mitigating the issue of data silos. However, large-scale heterogeneous data distributions result in inconsistent client objectives and catastrophic forgetting, leading to model bias and slow convergence. To address the challenges under non-independent and identically distributed (non-IID) data, we propose DPAO-PFL, a Dynamic Parameter-Aware Optimization framework that leverages continual learning principles to improve Personalized Federated Learning under non-IID conditions. We decomposed the parameters into two components: local personalized parameters tailored to client characteristics, and global shared parameters that capture the accumulated marginal effects of parameter updates over historical rounds. Specifically, we leverage the Fisher information matrix to estimate parameter importance online, integrate the path sensitivity scores within a time-series sliding window to construct a dynamic regularization term, and adaptively adjust the constraint strength to mitigate the conflict overall tasks. We evaluate the effectiveness of DPAO-PFL through extensive experiments on several benchmarks under IID and non-IID data distributions. Comprehensive experimental results indicate that DPAO-PFL outperforms baselines with improvements from $5.41\%$ to $30.42\%$ in average classification accuracy. By decoupling model parameters and incorporating an adaptive regularization mechanism, DPAO-PFL effectively balances generalization and personalization. Furthermore, DPAO-PFL exhibits superior performance in convergence and collaborative optimization compared to state-of-the-art FL methods. Full article

With the advancement of modern fan architectures, dedicated experimental benchmarks are becoming fundamental to improving the knowledge of flow physics, validating novel CFD methods, and fine-tuning existing methods. In this context the open test case ECL5/CATANA, representative of a modern Ultra High Bypass Ratio (UHBR) architecture, has been designed and experimentally investigated at École Centrale de Lyon (ECL) in a novel test facility with multi-physical instrumentation, providing a large database of high-quality aerodynamic and aeromechanic measurements. In this paper, a thorough numerical study of the fan stage aerodynamics was performed using the CFD TRAF code developed at the University of Florence. Fan stage performance was studied at design speed over the entire operating range. The results were discussed and compared with datasets provided by ECL. Detailed sensitivity on numerical schemes and state-of-the-art turbulence/transition models allowed for the selection of the best numerical setup to perform UHBR fan simulations. Moreover, to have a deeper understanding of the fan stall margin, unsteady simulations were also carried out. The results showed the appearance of blade tip instability, precursor of a rotating stall condition, which may generate non-synchronous blade vibrations. Full article

In recent years, domain adaptation (DA) has been extensively applied to predicting the remaining useful life (RUL) of bearings across conditions. Although traditional DA-based methods have achieved accurate predictions, most methods fail to extract multi-scale degradation information, focus only on global-scale DA, and ignore the importance of temporal weights. These limitations hinder further improvements in prediction accuracy. This paper proposes a novel model, called the health indicator-weighted subdomain alignment network (HIWSAN), which first learns feature representations at multiple scales, then constructs health indicators as temporal weights, and finally performs subdomain-level alignment. Two case studies based on the XJTU-SY and PRONOSTIA datasets were conducted, covering ablation, comparison, and generalization experiments to evaluate the proposed HIWSAN. Experimental results show that HIWSAN achieves an average MAE of 0.0989 and an average RMSE of 0.1189 across two datasets, representing reductions of 21.07% and 25.13%, respectively, compared to existing state-of-the-art methods. Full article

Dark web traffic classification is an important research direction in cybersecurity; however, traditional classification methods have many limitations. Although deep learning architectures like CNN and LSTM, as well as multi-structural fusion frameworks, have demonstrated partial success, they remain constrained by shallow feature representation, localized decision boundaries, and poor generalization capacity. To improve the prediction accuracy and classification precision of dark web traffic, we propose a novel dark web traffic classification model integrating multi-channel image deep learning and a three-dimensional convolutional neural network (3D-CNN). The proposed framework leverages spatial–temporal feature fusion to enhance discriminative capability, while the 3D-CNN structure effectively captures complex traffic patterns across multiple dimensions. The experimental results show that compared to common 2D-CNN and 1D-CNN classification models, the dark web traffic classification method based on multi-channel image visual features and 3D-CNN can improve classification by 5.1% and 3.3% while maintaining a smaller total number of parameters and feature recognition parameters, effectively reducing the computational complexity of the model. In comparative experiments, 3D-CNN validates the model’s superiority in accuracy and computational efficiency compared to state-of-the-art methods, offering a promising solution for dark web traffic monitoring and security applications. Full article

The Buades Gallery (1973–2003) was not merely a commercial space in Madrid. In the history of art in Spain, it served as a professional and political node for Spanish conceptualism, an art form which, due to its idiosyncrasies, required its own channels of distribution. This article seeks to examine the trajectory of Mercedes Buades in alignment with this movement, re-evaluating her role from a feminist perspective and highlighting the importance of certain agents who have traditionally been invisibilised. To this end, a theoretical approach is adopted, following the sociology of art and the social history of art, paying particular attention to the contributions of Enrico Castelnuovo, Pierre Bourdieu and Núria Peist. These frameworks enable an analysis of the role of the gallerist as a structuring agent within the artistic field, capable of generating symbolic capital and establishing dynamics of production, circulation and consumption in the context of post-Franco Spain, a country that lacked a consolidated museum infrastructure at the time. Even so, Mercedes Buades established a model of gallery practice that, beyond its commercial dimension, contributed decisively to the symbolic configuration of contemporary art in Spain and formed part of a network of artistic visibility that promoted experimental art. Full article

Random Forests are powerful machine learning models widely applied in classification and regression tasks due to their robust predictive performance. Nevertheless, traditional Random Forests face computational challenges during tree construction, particularly in high-dimensional data or on resource-constrained devices. In this paper, a novel node-splitting algorithm, BayesSplit, is proposed to accelerate decision tree construction via a Bayesian-based impurity estimation framework. BayesSplit treats impurity reduction as a Bernoulli event with Beta-conjugate priors for each split point and incorporates two main strategies. First, Dynamic Posterior Parameter Refinement updates the Beta parameters based on observed impurity reductions in batch iterations. Second, Posterior-Derived Confidence Bounding establishes statistical confidence intervals, efficiently filtering out suboptimal splits. Theoretical analysis demonstrates that BayesSplit converges to optimal splits with high probability, while experimental results show up to a 95% reduction in training time compared to baselines and maintains or exceeds generalization performance. Compared to the state-of-the-art MABSplit, BayesSplit achieves similar accuracy on classification tasks and reduces regression training time by 20–70% with lower MSEs. Furthermore, BayesSplit enhances feature importance stability by up to 40%, making it particularly suitable for deployment in computationally constrained environments. Full article

Intrusion detection systems are crucial for cybersecurity applications. Network traffic data originate from diverse terminal sources, exhibiting multi-view feature spaces, while the collection of unknown intrusion data is costly. Current one-class classification (OCC) approaches are mainly designed for single-view data. Multi-view OCC approaches usually require collecting multi-view traffic data from all sources and have difficulty detecting intrusion independently in each view. Furthermore, they commonly ignore the potential subcategories in normal traffic data. To address these limitations, this paper utilizes the Broad Learning System (BLS) technique and proposes an intrusion detection framework based on a multi-view cluster structure guided one-class BLS-autoencoder (IDF-MOCBLSAE). Specifically, a multi-view co-association matrix optimization objective function with doubly-stochastic constraints is first designed to capture the cross-view cluster structure. Then, a multi-view cluster structure guided one-class BLS-autoencoder (MOCBLSAEs) is proposed, which learns the discriminative patterns of normal traffic data by preserving the cross-view clustering structure while minimizing the intra-view sample reconstruction errors, thereby enabling the identification of unknown intrusion data. Finally, an intrusion detection framework is constructed based on multiple MOCBLSAEs to achieve both individual and ensemble intrusion detection. Through experimentation, IDF-MOCBLSAE is validated on real-world network traffic datasets for multi-view one-class classification tasks, demonstrating its superiority over state-of-the-art one-class approaches. Full article

The vast volume of media content, combined with the costs of manual annotation, challenges scalable codebook analysis and risks reducing decision-making accuracy. This study evaluates the effectiveness of large language models (LLMs) and multi-agent teams in structured media content analysis based on codebook-driven annotation. We construct a dataset of 200 news articles on U.S. tariff policies, manually annotated using a 26-question codebook encompassing 122 distinct codes, to establish a rigorous ground truth. Seven state-of-the-art LLMs, spanning low- to high-capacity tiers, are assessed under a unified zero-shot prompting framework incorporating role-based instructions and schema-constrained outputs. Experimental results show weighted global F1-scores between 0.636 and 0.822, with Claude-3-7-Sonnet achieving the highest direct-prompt performance. To examine the potential of agentic orchestration, we propose and develop a multi-agent system using Meta’s Llama 4 Maverick, incorporating expert role profiling, shared memory, and coordinated planning. This architecture improves the overall F1-score over the direct prompting baseline from 0.757 to 0.805 and demonstrates consistent gains across binary, categorical, and multi-label tasks, approaching commercial-level accuracy while maintaining a favorable cost–performance profile. These findings highlight the viability of LLMs, both in direct and agentic configurations, for automating structured content analysis. Full article

Precision irrigation plays a crucial role in managing crop production in a sustainable and environmentally friendly manner. This study builds on the results of the GreenWaterDrone project, aiming to estimate, in real time, the actual water requirements of crop fields using the crop water stress index, integrating infrared canopy temperature, air temperature, relative humidity, and thermal and near-infrared imagery. To achieve this, a state-of-the-art aerial micrometeorological station (AMMS), equipped with an infrared thermal sensor, temperature–humidity sensor, and advanced multispectral and thermal cameras is mounted on an unmanned aerial system (UAS), thus minimizing crop field intervention and permanently installed equipment maintenance. Additionally, data from satellite systems and ground micrometeorological stations (GMMS) are integrated to enhance and upscale system results from the local field to the regional level. The research was conducted over two years of pilot testing in the municipality of Trifilia (Peloponnese, Greece) on pilot potato and watermelon crops, which are primary cultivations in the region. Results revealed that empirical irrigation applied to the rhizosphere significantly exceeded crop water needs, with over-irrigation exceeding by 390% the maximum requirement in the case of potato. Furthermore, correlations between high-resolution remote and proximal sensors were strong, while associations with coarser Landsat 8 satellite data, to upscale the local pilot field experimental results, were moderate. By applying a comprehensive model for upscaling pilot field results, to the overall Trifilia region, project findings proved adequate for supporting sustainable irrigation planning through simulation scenarios. The results of this study, in the context of the overall services introduced by the project, provide valuable insights for farmers, agricultural scientists, and local/regional authorities and stakeholders, facilitating improved regional water management and sustainable agricultural policies. Full article

Hyperspectral sparse unmixing (SU) networks have recently received considerable attention due to their model hyperspectral images (HSIs) with a priori spectral libraries and to capture nonlinear features through deep networks. This method effectively avoids errors associated with endmember extraction, and enhances the unmixing performance via nonlinear modeling. However, two major challenges remain: the use of large spectral libraries with high coherence leads to computational redundancy and performance degradation; moreover, certain feature extraction models, such as Transformer, while exhibiting strong representational capabilities, suffer from high computational complexity. To address these limitations, this paper proposes a hyperspectral unmixing dual-branch network integrating an adaptive hop-aware GCN and neighborhood offset Mamba that is termed DGMNet. Specifically, DGMNet consists of two parallel branches. The first branch employs the adaptive hop-neighborhood-aware GCN (AHNAGC) module to model global spatial features. The second branch utilizes the neighborhood spatial offset Mamba (NSOM) module to capture fine-grained local spatial structures. Subsequently, the designed Mamba-enhanced dual-stream feature fusion (MEDFF) module fuses the global and local spatial features extracted from the two branches and performs spectral feature learning through a spectral attention mechanism. Moreover, DGMNet innovatively incorporates a spectral-library-pruning mechanism into the SU network and designs a new pruning strategy that accounts for the contribution of small-target endmembers, thereby enabling the dynamic selection of valid endmembers and reducing the computational redundancy. Finally, an improved ESS-Loss is proposed, which combines an enhanced total variation (ETV) with an $l_{1/2}$ sparsity constraint to effectively refine the model performance. The experimental results on two synthetic and five real datasets demonstrate the effectiveness and superiority of the proposed method compared with the state-of-the-art methods. Notably, experiments on the Shahu dataset from the Gaofen-5 satellite further demonstrated DGMNet’s robustness and generalization. Full article