Search Results (39)

The increasing volume, velocity, and sophistication of cyber threats have placed immense pressure on modern Security Operations Centers (SOCs). Traditional rule-based and manual processes are proving insufficient, leading to alert fatigue, delayed responses, high false-positive rates, analyst dependency, and escalating operational costs. Recent advancements in Artificial Intelligence (AI) offer new opportunities to transform SOC workflows through automation and augmentation. Large Language Models (LLMs) and autonomous AI agents have shown strong potential in enhancing capabilities such as log summarization, alert triage, threat intelligence, incident response, report generation, asset discovery, and vulnerability management. This paper reviews recent developments in the application of LLMs and AI agents across these SOC functions, introducing a taxonomy that organizes their roles and capabilities within operational pipelines. While these technologies improve detection accuracy, response time, and analyst support, challenges persist, including model interpretability, adversarial robustness, integration with legacy systems, and the risk of hallucinations or data leakage. A detailed capability-maturity model outlines the levels of integration with SOC tasks. This survey synthesizes trends, identifies persistent limitations, and outlines future directions for trustworthy, explainable, and safe AI integration in SOC environments. Full article

Weather radar reflectivity plays a critical role in precipitation estimation and convective storm identification. However, due to terrain limitations and the uneven spatial distribution of radar stations, oceanic regions have long suffered from a lack of radar observations, resulting in extensive monitoring gaps. Geostationary meteorological satellites have wide-area coverage and near-real-time observation capability, offering a viable solution for synthesizing radar reflectivity in these regions. Most previous synthesis studies have adopted fixed time-window data partitioning, which introduces significant noise into visible-light observations under large-scale, low-illumination conditions, thereby degrading synthesis quality. To address this issue, we propose an integrated deep-learning method that combines illumination-based classification and reflectivity synthesis to enhance the accuracy of radar reflectivity synthesis from geostationary meteorological satellites. This approach integrates a classification network with a synthesis network. First, visible-light observations from the Himawari-8 satellite are classified based on illumination conditions to separate valid signals from noise; then, noise-free infrared observations and multimodal fused data are fed into dedicated synthesis networks to generate composite reflectivity products. In experiments, the proposed method outperformed the baseline approach in regions with strong convection (≥35 dBZ), with a 9.5% improvement in the critical success index, a 7.5% increase in the probability of detection, and a 6.1% reduction in the false alarm rate. Additional experiments confirmed the applicability and robustness of the method across various complex scenarios. Full article

The rapid spread of unmanned aerial vehicles (UAVs) has created new challenges for airspace security, as drones are increasingly used for surveillance, smuggling, and potentially for attacks near critical infrastructure. A key difficulty lies in reliably distinguishing UAVs from visually similar birds in electro-optical surveillance channels, where complex backgrounds and visual noise often increase false alarms. To address this, we investigated recent YOLO architectures and developed an enhanced model named YOLOv12-ADBC, incorporating an adaptive hierarchical feature integration mechanism to strengthen multi-scale spatial fusion. This architectural refinement improves sensitivity to subtle inter-class differences between drones and birds. A dedicated dataset of 7291 images was used to train and evaluate five YOLO versions (v8–v12), together with the proposed YOLOv12-ADBC. Comparative experiments demonstrated that YOLOv12-ADBC achieved the best overall performance, with precision = 0.892, recall = 0.864, mAP50 = 0.881, mAP50–95 = 0.633, and per-class accuracy reaching 96.4% for drones and 80% for birds. In inference tests on three video sequences simulating realistic monitoring conditions, YOLOv12-ADBC consistently outperformed baselines, achieving a detection accuracy of 92.1–95.5% and confidence levels up to 88.6%, while maintaining real-time processing at 118–135 frames per second (FPS). These results demonstrate that YOLOv12-ADBC not only surpasses previous YOLO models but also offers strong potential as the optical module in multi-sensor fusion frameworks. Its integration with radar, RF, and acoustic channels is expected to further enhance system-level robustness, providing a practical pathway toward reliable UAV detection in modern airspace protection systems. Full article

Multi-sensor fire detection technology has been widely adopted in practical applications; however, existing methods still suffer from high false alarm rates and inadequate adaptability in complex environments due to their limited capacity to capture deep time-series dependencies in sensor data. To enhance robustness and accuracy, this paper proposes a novel model named BiLSTM-LN-SA, which integrates a Bidirectional Long Short-Term Memory (BiLSTM) network with Layer Normalization (LN) and a Self-Attention (SA) mechanism. The BiLSTM module extracts intricate time-series features and long-term dependencies. The incorporation of Layer Normalization mitigates feature distribution shifts across different environments, thereby improving the model’s adaptability to cross-scenario data and its generalization capability. Simultaneously, the Self-Attention mechanism dynamically recalibrates the importance of features at different time steps, adaptively enhancing fire-critical information and enabling deeper, process-aware feature fusion. Extensive evaluation on a real-world dataset demonstrates the superiority of the BiLSTM-LN-SA model, which achieves a test accuracy of 98.38%, an F1-score of 0.98, and an AUC of 0.99, significantly outperforming existing methods including EIF-LSTM, rTPNN, and MLP. Notably, the model also maintains low false positive and false negative rates of 1.50% and 1.85%, respectively. Ablation studies further elucidate the complementary roles of each component: the self-attention mechanism is pivotal for dynamic feature weighting, while layer normalization is key to stabilizing the learning process. This validated design confirms the model’s strong generalization capability and practical reliability across varied environmental scenarios. Full article

Low Earth orbit (LEO) satellites, characterized by low altitudes, high velocities, and strong ground signal reception, have become an essential and dynamic component of modern global navigation satellite systems (GNSS). However, orbit decay induced by atmospheric drag poses persistent challenges to maintaining stable trajectories. Frequent orbit maneuvers, though necessary to sustain nominal orbits, introduce significant difficulties for precise orbit determination (POD) and navigation augmentation, especially under complex operational conditions. Unlike most existing methods that rely on Two-Line Element (TLE) data—often affected by noise and limited accuracy—this study directly utilizes onboard GNSS observations in combination with real-time precise ephemerides. A novel time-series indicator is proposed, defined as the geometric root-mean-square (RMS) distance between reduced-dynamic and kinematic orbit solutions, which is highly responsive to orbit disturbances. To further enhance robustness, a sliding window-based adaptive thresholding mechanism is developed to dynamically adjust detection thresholds, maintaining sensitivity to maneuvers while suppressing false alarms. The proposed method was validated using eight representative maneuver events from the GRACE-FO satellites (May 2018–June 2022), successfully detecting seven of them. One extremely short-duration maneuver was missed due to the limited number of usable GNSS observations after quality-control filtering. To examine altitude-related applicability, two Sentinel-3A maneuvers were also analyzed, both successfully detected, confirming the method’s effectiveness at higher LEO altitudes. Since the thrust magnitudes and durations of the Sentinel-3A maneuvers are not publicly available, these cases primarily serve to verify applicability rather than to quantify sensitivity. Experimental results show that for GRACE-FO maneuvers, the proposed method achieves near-real-time responsiveness under long-duration, high-thrust conditions, with an average detection delay below 90 s. For Sentinel-3A, detections occurred approximately 7 s earlier than the reported maneuver epochs, a discrepancy attributed to the 30 s observation sampling interval rather than methodological bias. Comparative analysis with representative existing methods, presented in the discussion section, further demonstrates the advantages of the proposed approach in terms of sensitivity, timeliness, and adaptability. Overall, this study presents a practical, efficient, and scalable solution for real-time maneuver detection in LEO satellite missions, contributing to improved GNSS augmentation, space situational awareness, and autonomous orbit control. Full article

Electrocardiograms (ECGs) are critical for cardiovascular disease diagnosis, but their accuracy is often compromised by electrode motion (EM) artifacts—large, nonstationary distortions caused by patient movement and electrode-skin interface shifts. These artifacts overlap in frequency with genuine cardiac signals, rendering traditional filtering methods ineffective and increasing the risk of false alarms and misdiagnosis, particularly in wearable and ambulatory ECG applications. To address this, we propose the Feature-Shuffle Multi-Head Attention Autoencoder (FMHA-AE), a novel architecture integrating multi-head self-attention (MHSA) and a feature-shuffle mechanism to enhance ECG denoising. MHSA captures long-range temporal and spatial dependencies, while feature shuffling improves representation robustness and generalization. Experimental results show that FMHA-AE achieves an average signal-to-noise ratio (SNR) improvement of 25.34 dB and a percentage root mean square difference (PRD) of 10.29%, outperforming conventional wavelet-based and deep learning baselines. These results confirm the model’s ability to retain critical ECG morphology while effectively removing noise. FMHA-AE demonstrates strong potential for real-time ECG monitoring in mobile and clinical environments. This work contributes an efficient deep learning approach for noise-robust ECG analysis, supporting accurate cardiovascular assessment under motion-prone conditions. Full article

This study advances the unmanned aerial vehicle (UAV) localization technology within the framework of a low-altitude economy, with particular emphasis on the accurate and real-time identification and tracking of unauthorized (“black-flying”) drones. Conventional YOLOv8s-based target detection algorithms often suffer from missed detections due to their reliance on single-frame features. To address this limitation, this paper proposes an improved detection algorithm that integrates a long-short-term memory (LSTM) network into the YOLOv8s framework. By incorporating time-series modeling, the LSTM module enables the retention of historical features and dynamic prediction of UAV trajectories. The loss function combines bounding box regression loss with binary cross-entropy and is optimized using the Adam algorithm to enhance training convergence. The training data distribution is validated through Monte Carlo random sampling, which improves the model’s generalization to complex scenes. Simulation results demonstrate that the proposed method significantly enhances UAV detection performance. In addition, when deployed on the RK3588-based embedded system, the method achieves a low false negative rate and exhibits robust detection capabilities, indicating strong potential for practical applications in airspace management and counter-UAV operations. Full article

Hyperspectral imaging for gas plume identification holds significant potential for applications in industrial emission control and environmental monitoring, including critical needs in livestock farm environments. Conventional pixel-by-pixel spectral identification methods primarily rely on spectral information, often overlooking the rich spatial distribution features inherent in hyperspectral images. This oversight can lead to challenges such as inaccurate identification or leakage along the edge regions of gas plumes and false positives from isolated pixels in non-gas areas. While infrared imaging for gas plumes offers a new perspective by leveraging multi-frame image variations to locate plumes, these methods typically lack spectral discriminability. To address these limitations, we draw inspiration from the multi-frame analysis framework of infrared imaging and propose a novel hyperspectral gas plume identification method based on image background modeling and suppression. Our approach begins by employing background modeling and suppression techniques to accurately detect the primary gas plume region. Subsequently, a representative spectrum is extracted from this identified plume region for precise gas identification. To further enhance the identification accuracy, especially in the challenging plume edge regions, a spatial-spectral combined judgment operator is applied as a post-processing step. The effectiveness of the method was validated through experiments using both simulated and real-world measured data from ammonia and methanol gas releases. We compare its performance against classical methods and an ablation version of our model. Results consistently demonstrate that our method effectively detects low-concentration, thin, and diffuse gas plumes, offering a more robust and accurate solution for hyperspectral gas plume identification with strong applicability to real-world industrial and livestock farm scenarios. Full article

This paper presents a resilient observer-based and event-triggered control scheme for discrete-time Cyber–Physical Systems (CPS) under Markovian Cyber-Attacks (MCA). The proposed framework integrates a Luenberger observer for cyberattack detection with a state-feedback controller designed to preserve system stability in the presence of Denial-of-Service (DoS) and False Data Injection (FDI) attacks. Attack detection is achieved through residual signal generation combined with Markovian modeling of the attack dynamics. System stability is guaranteed by formulating relaxed Linear Matrix Inequality (LMI) conditions that incorporate relaxation variables, a diagonal Lyapunov function, the S-procedure, and congruence transformations. Moreover, the Event-Triggered Mechanism (ETM) efficiently reduces communication load without degrading control performance. Numerical simulations conducted on a three-tank system benchmark confirm enhanced detection accuracy, faster recovery, and strong robustness against uncertainties. Full article

Road extraction from remote sensing imagery plays a critical role in applications such as autonomous driving, urban planning, and infrastructure development. Although deep learning methods have achieved notable progress, current approaches still struggle with complex backgrounds, varying road widths, and strong texture interference, often leading to fragmented road predictions or the misclassification of background regions. Given that roads typically exhibit smooth low-frequency characteristics while background clutter tends to manifest in mid- and high-frequency ranges, incorporating frequency-domain information can enhance the model’s structural perception and discrimination capabilities. To address these challenges, we propose a novel frequency-aware road extraction network, termed PWFNet, which combines frequency-domain modeling with multi-scale feature enhancement. PWFNet comprises two key modules. First, the Pyramidal Wavelet Convolution (PWC) module employs multi-scale wavelet decomposition fused with localized convolution to accurately capture road structures across various spatial resolutions. Second, the Frequency-aware Adjustment Module (FAM) partitions the Fourier spectrum into multiple frequency bands and incorporates a spatial attention mechanism to strengthen low-frequency road responses while suppressing mid- and high-frequency background noise. By integrating complementary modeling from both spatial and frequency domains, PWFNet significantly improves road continuity, edge clarity, and robustness under complex conditions. Experiments on the DeepGlobe and CHN6-CUG road datasets demonstrate that PWFNet achieves IoU improvements of 3.8% and 1.25% over the best-performing baseline methods, respectively. In addition, we conducted cross-region transfer experiments by directly applying the trained model to remote sensing images from different geographic regions and at varying resolutions to assess its generalization capability. The results demonstrate that PWFNet maintains the continuity of main and branch roads and preserves edge details in these transfer scenarios, effectively reducing false positives and missed detections. This further validates its practicality and robustness in diverse real-world environments. Full article

To meet the demands of deep grid integration of renewable energy and long-distance power transmission, this paper presents a hybrid multi-infeed DC system architecture that includes an AC power source (AC), a voltage source converter (VSC), and a modular multilevel converter (MMC). Addressing the limitations of traditional differential protection—such as insufficient sensitivity under high-resistance grounding and susceptibility to false operations under out-of-zone disturbances—this paper introduces an enhanced current differential criterion based on dynamic phasor analysis. By effectively decoupling DC bias and load current components and optimizing the calculation of action and braking quantities, the proposed method enables the rapid and accurate identification of typical faults, including high-resistance grounding, three-phase short circuits, and out-of-zone faults. A multi-scenario simulation platform is built using MATLAB to thoroughly validate the improved criterion. Simulation results demonstrate that the proposed method offers excellent sensitivity, selectivity, and resistance to false operations in multi-infeed complex systems. It achieves fast fault detection (~2.0 ms), strong sensitivity to high-resistance internal faults, and low false tripping under a variety of test scenarios, providing robust support for next-generation DC protection systems. Full article

Zero-day attacks pose a persistent threat to computing infrastructure by exploiting previously unknown software vulnerabilities that evade traditional signature-based network intrusion detection systems (NIDSs). To address this limitation, machine learning (ML) techniques offer a promising approach for enhancing anomaly detection in network traffic. This study evaluates several ML models on a labeled network traffic dataset, with a focus on zero-day attack detection. Ensemble learning methods, particularly eXtreme gradient boosting (XGBoost), achieved perfect classification, identifying all 6231 zero-day instances without false positives and maintaining efficient training and prediction times. While classical support vector machines (SVMs) performed modestly at 64% accuracy, their performance improved to 98% with the use of the borderline synthetic minority oversampling technique (SMOTE) and SMOTE + edited nearest neighbours (SMOTEENN). To explore quantum-enhanced alternatives, a quantum SVM (QSVM) is implemented using three-qubit and four-qubit quantum circuits simulated on the aer_simulator_statevector. The QSVM achieved high accuracy (99.89%) and strong F1-scores (98.95%), indicating that nonlinear quantum feature maps (QFMs) can increase sensitivity to zero-day exploit patterns. Unlike prior work that applies standard quantum kernels, this study introduces a parameterised quantum feature encoding scheme, where each classical feature is mapped using a nonlinear function tuned by a set of learnable parameters. Additionally, a sparse entanglement topology is derived from mutual information between features, ensuring a compact and data-adaptive quantum circuit that aligns with the resource constraints of noisy intermediate-scale quantum (NISQ) devices. Our contribution lies in formalising a quantum circuit design that enables scalable, expressive, and generalisable quantum architectures tailored for zero-day attack detection. This extends beyond conventional usage of QSVMs by offering a principled approach to quantum circuit construction for cybersecurity. While these findings are obtained via noiseless simulation, they provide a theoretical proof of concept for the viability of quantum ML (QML) in network security. Future work should target real quantum hardware execution and adaptive sampling techniques to assess robustness under decoherence, gate errors, and dynamic threat environments. Full article

Accurate real-time tracking of forest fires using UAV platforms is crucial for timely early warning, reliable spread prediction, and effective autonomous suppression. Existing detection-based multi-object tracking methods face challenges in accurately associating targets and maintaining smooth tracking trajectories in complex forest environments. These difficulties stem from the highly nonlinear movement of flames relative to the observing UAV and the lack of robust fire-specific feature modeling. To address these challenges, we introduce AO-OCSORT, an association-optimized observation-centric tracking framework designed to enhance robustness in dynamic fire scenarios. AO-OCSORT builds on the YOLOX detector. To associate detection results across frames and form smooth trajectories, we propose a temporal–physical similarity metric that utilizes temporal information from the short-term motion of targets and incorporates physical flame characteristics derived from optical flow and contours. Subsequently, scene classification and low-score filtering are employed to develop a hierarchical association strategy, reducing the impact of false detections and interfering objects. Additionally, a virtual trajectory generation module is proposed, employing a kinematic model to maintain trajectory continuity during flame occlusion. Locally evaluated on the 1080P-resolution FireMOT UAV wildfire dataset, AO-OCSORT achieves a 5.4% improvement in MOTA over advanced baselines at 28.1 FPS, meeting real-time requirements. This improvement enhances the reliability of fire front localization, which is crucial for forest fire management. Furthermore, AO-OCSORT demonstrates strong generalization, achieving 41.4% MOTA on VisDrone, 80.9% on MOT17, and 92.2% MOTA on DanceTrack. Full article

Background: Effective early risk stratification in COVID-19 remains a critical challenge in emergency care, particularly due to the limitations of RT-PCR testing, including delayed processing and false negatives. There is an unmet need for imaging tools that are fast, reliable, and safe for repeated use in acute clinical settings. Methods: In this prospective, multicenter study, over 1000 patients hospitalized with suspected or confirmed COVID-19 were initially screened. A total of 555 patients with PCR-confirmed infection were ultimately included for analysis. All participants underwent low-dose chest CT (LDCT) at admission. Pulmonary involvement was assessed using the chest CT severity score (CTSS) based on a unified protocol. CTSS values were analyzed in relation to ICU admission, in-hospital mortality, demographic data, oxygen saturation, dyspnea scores, and laboratory markers (CRP, LDH, lymphocyte, and neutrophil counts). Imaging was interpreted by board-certified radiologists under harmonized reporting standards. Results: CTSS values ≥13 and ≥15 were significantly associated with ICU admission and in-hospital mortality, respectively (p < 0.01). Strong correlations were observed between the CTSS and CRP, LDH, and dyspnea scores, with negative correlations to oxygen saturation and lymphocyte count. The standardized LDCT protocol ensured consistent image quality and minimized radiation exposure. Conclusions: LDCT combined with the CTSS provides a robust, reproducible, and radiation-sparing method for emergency risk stratification in COVID-19. Its high clinical utility supports deployment in frontline triage systems and future AI-enhanced diagnostic workflows. Full article

This study addresses three major challenges in non-motorized vehicle rider helmet detection: multi-spectral interference between the helmet and hair color (HSV spatial similarity > 0.82), target occlusion in high-density traffic flows (with peak density reaching 11.7 vehicles/frame), and perception degradation under complex weather conditions (such as overcast, foggy, and strong light interference). To tackle these issues, we developed the GMAL-YOLO detection algorithm. This algorithm enhances feature representation by constructing a Feature-Enhanced Neck Network (FENN) that integrates both global and local features. It employs the Global Mamba Architecture Enhancement (GMET) to reduce parameter size while strengthening global context capturing ability. It also incorporates Multi-Scale Spatial Pyramid Pooling (MSPP) combined with multi-scale feature extraction to improve the model’s robustness. The enhanced channel attention mechanism with self-attention (ECAM) is designed to enhance local feature extraction and stabilize deep feature learning through partial convolution and residual learning, resulting in a 13.04% improvement in detection precision under occlusion scenarios. Furthermore, the model’s convergence speed and localization precision are optimized using the modified Enhanced Precision-IoU loss function(EP-IoU). Experimental results demonstrate that GMAL-YOLO outperforms existing algorithms on the self-constructed HelmetVision dataset and public datasets. Specifically, in extreme scenarios, the false detection rate is reduced by 17.3%, and detection precision in occluded scenes is improved by 13.6%, providing an effective technical solution for intelligent traffic surveillance. Full article