Search Results (13,651)

Industrial control systems (ICSs) face escalating security challenges due to evolving cyber threats and the inherent limitations of traditional intrusion detection methods, which fail to adequately model spatiotemporal dependencies or interpret complex protocol semantics. To address these gaps, this paper proposes DLG–IDS —a lightweight intrusion detection framework that innovatively integrates dynamic graph construction for capturing real–time device interactions and logical control relationships from traffic, LLM–driven semantic enhancement to extract fine–grained embeddings from graphs, and a spatio–temporal graph neural network (STGNN) optimized via sparse attention and local window Transformers to minimize computational overhead. Evaluations on SWaT and SBFF datasets demonstrate the framework’s superiority, achieving a state–of–the–art accuracy of 0.986 while reducing latency by 53.2% compared to baseline models. Ablation studies further validate the critical contributions of semantic fusion, sparse topology modeling, and localized temporal attention. The proposed solution establishes a robust, real–time detection mechanism tailored for resource–constrained industrial environments, effectively balancing high accuracy with operational efficiency. Full article

With the strict requirements of national policies on truck dimensions, axle loads, and weight limits, along with the implementation of tolls based on vehicle types, rapid and accurate identification of vehicle axle types has become essential for toll station management. To address the limitations of existing methods in distinguishing between drive and driven axles, complex equipment setup, and image evidence retention, this article proposes a panoramic image detection technology for vehicle chassis based on enhanced ORB and YOLOv11. A portable vehicle chassis image acquisition system, based on area array cameras, was developed for rapid on-site deployment within 20 min, eliminating the requirement for embedded installation. The FeatureBooster (FB) module was employed to optimize the ORB algorithm’s feature matching, and combined with keyframe technology to achieve high-quality panoramic image stitching. After fine-tuning the FB model on a domain-specific area scan dataset, the number of feature matches increased to 151 ± 18, substantially outperforming both the pre-trained FB model and the baseline ORB. Experimental results on axle type recognition using the YOLOv11 algorithm combined with ORB and FB features demonstrated that the integrated approach achieved superior performance. On the overall test set, the model attained an mAP@50 of 0.989 and an mAP@50:95 of 0.780, along with a precision (P) of 0.98 and a recall (R) of 0.99. In nighttime scenarios, it maintained an mAP@50 of 0.977 and an mAP@50:95 of 0.743, with precision and recall both consistently at 0.98 and 0.99, respectively. The field verification shows that the real-time and accuracy of the system can provide technical support for the axle type recognition of toll stations. Full article

Background: Heart disease continues to be one of the foremost causes of mortality worldwide, emphasizing the urgent need for reliable and early diagnostic tools. Accurate prediction methods can support timely interventions and improve patient outcomes. Methods: This study presents the development and comparative evaluation of multiple machine learning models for heart disease prediction using a structured clinical dataset. Algorithms such as Logistic Regression, Random Forest, Support Vector Machine (SVM), XGBoost, and Deep Neural Networks were implemented. Additionally, a hybrid ensemble model combining XGBoost and SVM was proposed. Models were evaluated using key performance metrics including accuracy, precision, recall, and F1-score. Results: Among all models, the proposed hybrid model demonstrated the best performance, achieving an accuracy of 89.3%, a precision of 0.90, recall of 0.91, and an F1-score of 0.905, and outperforming all individual classifiers. These results highlight the benefits of combining complementary algorithms for improved generalization and diagnostic reliability. Conclusions: The findings underscore the effectiveness of ensemble and deep learning techniques in addressing key challenges such as data imbalance, feature selection, and model interpretability. The proposed hybrid model shows significant potential as a clinical decision-support tool, contributing to enhanced diagnostic accuracy and supporting medical professionals in real-world settings. Full article

Accurate object detection is fundamental to computer vision, yet detecting small targets in complex backgrounds remains challenging due to feature loss and limited model efficiency. To address this, we propose LCW-YOLO, a lightweight detection framework that integrates three innovations: Wavelet Pooling, a CGBlock-enhanced C3K2 structure, and an improved LDHead detection head. The Wavelet Pooling strategy employs Haar-based multi-frequency reconstruction to preserve fine-grained details while mitigating noise sensitivity. CGBlock introduces dynamic channel interactions within C3K2, facilitating the fusion of shallow visual cues with deep semantic features without excessive computational overhead. LDHead incorporates classification and localization functions, thereby improving target recognition accuracy and spatial precision. Extensive experiments across multiple public datasets demonstrate that LCW-YOLO outperforms mainstream detectors in both accuracy and inference speed, with notable advantages in small-object, sparse, and cluttered scenarios. Here we show that the combination of multi-frequency feature preservation and efficient feature fusion enables stronger representations under complex conditions, advancing the design of resource-efficient detection models for safety-critical and real-time applications. Full article

The integration of unmanned aerial vehicles (UAVs) and deep learning (DL) has significantly advanced crop disease detection by enabling scalable, high-resolution, and near real-time monitoring within precision agriculture. This systematic review analyzes peer-reviewed literature indexed in the Web of Science Core Collection as articles or proceeding papers through 2024. The main selection criterion was combining “unmanned aerial vehicle*” OR “UAV” OR “drone” with “deep learning”, “agriculture” and “leaf disease” OR “crop disease”. Results show a marked surge in publications after 2019, with China, the United States, and India leading research contributions. Multirotor UAVs equipped with RGB sensors are predominantly used due to their affordability and spatial resolution, while hyperspectral imaging is gaining traction for its enhanced spectral diagnostic capability. Convolutional neural networks (CNNs), along with emerging transformer-based and hybrid models, demonstrate high detection performance, often achieving F1-scores above 95%. However, critical challenges persist, including limited annotated datasets for rare diseases, high computational costs of hyperspectral data processing, and the absence of standardized evaluation frameworks. Addressing these issues will require the development of lightweight DL architectures optimized for edge computing, improved multimodal data fusion techniques, and the creation of publicly available, annotated benchmark datasets. Advancements in these areas are vital for translating current research into practical, scalable solutions that support sustainable and data-driven agricultural practices worldwide. Full article

Farmland ecosystems present complex pest–predator co-occurrence patterns, posing significant challenges for image-based multitarget recognition and ecological modeling in sensor-driven computer vision tasks. To address these issues, this study introduces a tree-guided Transformer framework enhanced with a knowledge-augmented co-attention mechanism, enabling effective feature extraction from sensor-acquired images. A hierarchical ecological taxonomy (Phylum–Family Species) guides prompt-driven semantic reasoning, while an ecological knowledge graph enriches visual representations by embedding co-occurrence priors. A multimodal dataset containing 60 pest and predator categories with annotated images and semantic descriptions was constructed for evaluation. Experimental results demonstrate that the proposed method achieves 90.4% precision, 86.7% recall, and 88.5% F1-score in image classification, along with 82.3% hierarchical accuracy. In detection tasks, it attains 91.6% precision and 86.3% mAP@50, with 80.5% co-occurrence accuracy. For hierarchical reasoning and knowledge-enhanced tasks, F1-scores reach 88.5% and 89.7%, respectively. These results highlight the framework’s strong capability in extracting structured, semantically aligned image features under real-world sensor conditions, offering an interpretable and generalizable approach for intelligent agricultural monitoring. Full article

This paper presents a robust and computationally efficient fault classification framework for wind energy conversion systems (WECS), built upon a Robust Random Vector Functional Link Network (Robust-RVFLN) and validated through real-time simulations on a Real-Time Digital Simulator (RTDS). Unlike existing studies that depend on high-dimensional feature extraction or purely data-driven deep learning models, our approach leverages a compact set of five statistically significant and physically interpretable features derived from rotor torque, phase current, DC-link voltage, and dq-axis current components. This reduced feature set ensures both high discriminative power and low computational overhead, enabling effective deployment in resource-constrained edge devices and large-scale wind farms. A synthesized dataset representing seven representative fault scenarios—including converter, generator, gearbox, and grid faults—was employed to evaluate the model. Comparative analysis shows that the Robust-RVFLN consistently outperforms conventional classifiers (SVM, ELM) and deep models (CNN, LSTM), delivering accuracy rates of up to 99.85% for grid-side line-to-ground faults and 99.81% for generator faults. Beyond accuracy, evaluation metrics such as precision, recall, and F1-score further validate its robustness under transient operating conditions. By uniting interpretability, scalability, and real-time performance, the proposed framework addresses critical challenges in condition monitoring and predictive maintenance, offering a practical and transferable solution for next-generation renewable energy infrastructures. Full article

Programmable Logic Controllers (PLCs), widely used in industrial automation, are often programmed in IEC 61131-3 Structured Text (ST), which is prone to subtle logic vulnerabilities. Traditional tools like static analysis and fuzzing struggle with the complexity and domain-specific semantics of ST. This work explores Large Language Models (LLMs) for PLC vulnerability detection, supported by both theoretical insights and empirical validation. Theoretically, we prove that control flow features carry the most vulnerability-relevant information, establish a feature informativeness hierarchy, and derive sample complexity bounds. We also propose an optimal synthetic data mixing strategy to improve learning with limited supervision. Empirically, we build a dataset combining real-world and synthetic ST code with five vulnerability types. We fine-tune open-source LLMs (CodeLlama, Qwen2.5-Coder, Starcoder2) using LoRA, demonstrating significant gains in binary and multi-class classification. The results confirm our theoretical predictions and highlight the promise of LLMs for PLC security. Our work provides a principled and practical foundation for LLM-based analysis of cyber-physical systems, emphasizing the role of domain knowledge, efficient adaptation, and formal guarantees. Full article

The deployment of airborne hyperspectral sensors has expanded rapidly, driven by their ability to capture spectral information beyond the visual range and to reveal objects that remain obscured in conventional imaging. In scenarios where prior target signatures are unavailable, anomaly detection provides an effective alternative by identifying deviations from the spectral background. However, real-world reconnaissance and monitoring missions frequently take place in complex and dynamic environments, requiring anomaly detectors to demonstrate robustness and adaptability. These requirements have rarely been met in current research, as evaluations are still predominantly based on small, context-restricted datasets, offering only limited insights into detector performance under varying conditions. To address this gap, we propose a context-adaptive hyperspectral sensor and perception management (hSPM) architecture that integrates sensor context extraction, band selection, and detector management into a single adaptive processing pipeline. The architecture is systematically evaluated on a new, large-scale airborne hyperspectral dataset comprising more than 1100 annotated samples from two diverse test environments, which we publicly release to support future research. Comparative experiments against state-of-the-art anomaly detectors demonstrate that conventional methods often lack robustness and efficiency, while hSPM consistently achieves superior detection accuracy and faster processing. Depending on evaluation conditions, hSPM improves anomaly detection performance by 28–204% while reducing computation time by 70–99%. These results highlight the advantages of adaptive sensor processing architectures and underscore the importance of large, openly available datasets for advancing robust airborne hyperspectral anomaly detection. Full article

Self-supervised monocular depth estimation from oblique UAV videos is crucial for enabling autonomous navigation and large-scale mapping. However, existing self-supervised monocular depth estimation methods face key challenges in UAV oblique video scenarios: depth discontinuity from geometric distortion under complex viewing angles, and spatial ambiguity in weakly textured regions. These challenges highlight the need for models that combine global reasoning with geometric awareness. Accordingly, we propose RMTDepth, a self-supervised monocular depth estimation framework for UAV imagery. RMTDepth integrates an enhanced Retentive Vision Transformer (RMT) backbone, introducing explicit spatial priors via a Manhattan distance-driven spatial decay matrix for efficient long-range geometric modeling, and embeds a neural window fully-connected CRF (NeW CRFs) module in the decoder to refine depth edges by optimizing pairwise relationships within local windows. To mitigate noise in COLMAP-generated depth for real-world UAV datasets, we constructed a high-fidelity UE4/AirSim simulation environment, which generated a large-scale precise depth dataset (UAV SIM Dataset) to validate robustness. Comprehensive experiments against seven state-of-the-art methods across UAVID Germany, UAVID China, and UAV SIM datasets demonstrate that our model achieves SOTA performance in most scenarios. Full article

This paper proposes a residual network model integrated with an attention mechanism module for the detection and classification of malware on railway mobile terminals. To address the issues of insufficient and imbalanced samples, Wasserstein Generative Adversarial Networks (WGANs) are utilized to synthesize grayscale image data of malware with high similarity to real samples. The performance of the model is evaluated on the publicly available CIC-InvesAndMal2019 dataset and an extended balanced dataset. Experimental results demonstrate that the synergistic integration of residual networks, WGANs, and attention mechanisms significantly enhances the performance of the malware detection model. In the context of railway applications, the proposed approach also achieves favorable classification performance when applied to image datasets derived from malware samples of railway mobile terminals. Multiple ablation studies are conducted to individually validate the contributions of each technical component in improving the classification model’s efficacy. The adoption of the SE-ResNet architecture combined with WGAN-based data augmentation presents a practical and efficient technical solution. Full article

In the Internet of Vehicles (IoV), zero-day attacks pose a significant security threat. These attacks are characterized by unknown patterns and limited sample availability. Traditional anomaly detection methods often fail because they rely on oversimplified assumptions, hindering their ability to model complex normal IoV behavior. This limitation results in low detection accuracy and high false alarm rates. To overcome these challenges, we propose a novel zero-day attack detection framework based on Feature-Enhanced Inverse Mapping (IM-ZDD). The framework introduces a two-stage process. In the first stage, a feature enhancement module mitigates data scarcity by employing an innovative multi-generator, multi-discriminator Conditional GAN (CGAN) with dynamic focusing loss to generate a large-scale, high-quality synthetic normal dataset characterized by sharply defined feature boundaries. In the second stage, a learning-based inverse mapping module is trained exclusively on this synthetic data. Through adversarial training, the module learns a precise inverse mapping function, thereby establishing a compact and expressive representation of normal behavior. During detection, samples that cannot be effectively mapped are identified as attacks. Experimental results on the F2MD platform show IM-ZDD achieves superior accuracy and a low false alarm rate, yielding an average AUC of 98.25% and F1-Score of 96.41%, surpassing state-of-the-art methods by up to 4.4 and 10.8 percentage points. Moreover, with a median detection latency of only 3 ms, the framework meets real-time requirements, providing a robust solution for zero-day attack detection in data-scarce IoV environments. Full article

Reliable gesture interfaces are essential for coordinating distributed robot teams in the field. However, models trained in a single domain often perform poorly when confronted with new users, different sensors, or unfamiliar environments. To address this challenge, we propose a memory-efficient replay-based domain incremental learning (DIL) framework, ReDIaL, that adapts to sequential domain shifts while minimizing catastrophic forgetting. Our approach employs a frozen encoder to create a stable latent space and a clustering-based exemplar replay strategy to retain compact, representative samples from prior domains under strict memory constraints. We evaluate the framework on a multi-domain air-marshalling gesture recognition task, where an in-house dataset serves as the initial training domain and the NATOPS dataset provides 20 cross-user domains for sequential adaptation. During each adaptation step, training data from the current NATOPS subject is interleaved with stored exemplars to retain prior knowledge while accommodating new knowledge variability. Across 21 sequential domains, our approach attains $97.34\%$ accuracy on the domain incremental setting, exceeding pooled fine-tuning ($91.87\%$), incremental fine-tuning ($80.92\%$), and Experience Replay ($94.20\%$) by $+5.47$, $+16.42$, and $+3.14$ percentage points, respectively. Performance also approaches the joint-training upper bound ($98.18\%$), which represents the ideal case where data from all domains are available simultaneously. These results demonstrate that memory-efficient latent exemplar replay provides both strong adaptation and robust retention, enabling practical and trustworthy gesture-based human–robot interaction in dynamic real-world deployments. Full article

Accurately forecasting the interval-valued green electricity (GE) supply is challenging due to the unpredictable and instantaneous nature of its source; yet, reliable multi-step-ahead forecasting is essential for providing the lead time required in operations, resource allocation, and system management. This study proposes an augmented-feature multi-step interval-valued forecasting (AFMIF) scheme that aims to address the challenges in forecasting interval-valued GE supply data by extracting additional features hidden within an interval. Unlike conventional methods that rely solely on original interval bounds, AFMIF integrates augmented features that capture statistical and dynamic properties to reveal hidden patterns. These features include basic interval boundaries and statistical distributions from an interval. Three effective forecasting methods, based on gated recurrent units (GRUs), long short-term memory (LSTM), and a temporal convolutional network (TCN), are constructed under the proposed AFMIF scheme, while the mean ratio of exclusive-or (MRXOR) is used to evaluate the forecasting performance. Two different real datasets of wind-based GE supply data from Belgium and Germany are used as illustrative examples. Empirical results demonstrate that the proposed AFMIF scheme with GRUs can generate promising results, achieving a mean MRXOR of 0.7906 from the Belgium data and 0.9719 from the Germany data for one-step- to three-steps-ahead forecasting. Moreover, the TCN yields an average improvement of 13% across all time steps with the proposed scheme. The results highlight the potential of the AFMIF scheme as an effective alternative approach for accurate multi-step-ahead interval-valued GE supply forecasting that offers practical benefits supporting GE management. Full article

Cyprus is located between Europe, Asia and Africa, and its location is vulnerable to dust transport from the Sahara Desert, wildfire smoke particles from surrounding regions, and other anthropogenic emissions caused by several factors, mostly due to business activities on harbor areas. Moreover, the country suffers from heavy traffic conditions caused by the limited public transportation system in Cyprus. Therefore, taking into consideration the country’s geographic location, heavy commercial activities, and lack of good public transportation system, Cyprus is exposed to dust episodes and high anthropogenic emissions associated with multiple health and environmental issues. Therefore, continuous and qualitative air quality monitoring is essential. The Department of Labor Inspection of Cyprus (DLI) has established an air quality monitoring network that consists of 11 stations at strategic geographic locations covering rural, residential, traffic and industrial zones. This network measures the following pollutants: nitrogen oxide, nitrogen dioxide, sulfur dioxide, ozone, carbon monoxide, particulate matter 2.5, and particulate matter 10. This case study compares and evaluates the agreement between Copernicus Atmosphere Monitoring Service (CAMS) air quality products and ground-truth data from the DLI air quality network. The study period spans from January to December 2024. This study focuses on the following three pollutants: particulate matter 2.5, particulate matter 10, and ozone, using Ensemble Median, EMEP, and CHIMERE near-real-time model data provided by CAMS. A data analysis was performed to identify the agreement and the error rate between those two datasets (i.e., ground-truth air quality data and CAMS air quality data). In addition, this study assesses the reliability of assimilated datasets from CAMS across rural, residential, traffic and industrial zones. The results showcase how CAMS near-real-time analysis data can supplement air quality monitoring in locations without the availability of ground-truth data. Full article