Search Results (2,419)

Flying Ad Hoc Networks (FANETs) composed of multiple unmanned aerial vehicles (UAVs) are a promising solution for emergency wireless communications when terrestrial infrastructure is unavailable. However, ensuring reliable Quality of Service (QoS) in these highly dynamic networks remains challenging due to topology changes, varying propagation conditions, and congestion. This work proposes a lightweight machine learning-based QoS optimization framework for multi-UAV emergency communications that combines realistic mobility modeling, empirical channel measurements, and adaptive traffic prioritization. UAV mobility patterns are generated with ArduSim, while LoS/NLoS propagation models are derived from real UAV flight experiments and integrated into ns-3. Multiple supervised machine learning algorithms—including Decision Trees, Random Forest, Support Vector Machines, k-NN, Gradient Boosting, and CatBoost—are trained using four input features derived from the network state: ${\mathrm{CBR}}_{\mathrm{src}}$, ${\mathrm{QP}}_{\mathrm{src}}$, ${\mathrm{CBR}}_{\mathrm{dst}}$, and ${\mathrm{QP}}_{\mathrm{dst}}$. Simulation results show that the proposed AI SMOTE EMERGENCY scheme, based on CatBoost, improves the Packet Delivery Ratio (PDR) by approximately 43% over the No-QoS baseline, achieving 89–93% delivery across all four application ports. Compared with EDCA, the proposed scheme maintains reliable delivery for all services, increases emergency throughput by 34–36%, and reduces end-to-end delay by about 70%. In addition, the higher delivery reliability translates into clear communication energy benefits, reducing energy waste across all evaluated topologies when compared with the No-QoS baseline. The inference time remains below 0.002 s, supporting real-time QoS adaptation in resource-constrained UAV networks. Full article

Modern user authentication systems increasingly need user and device-behavior-aware adaptive mechanisms to detect evolving threats beyond the traditional authentication framework of static credential verification. This paper proposes a hybrid multi-model framework for personalized user-level anomaly detection using a data-driven Hybrid Anomaly Score (HAS). The primary contribution lies in deriving the HAS using the joint integration of three adaptive attributes: dynamically computed per-user deviation thresholds conditioned on individual behavioral history, profile-age-aware baseline weights reflecting user cohort maturity, and criticality-scaled aggregation with the security impact of each detection methodology. The framework is evaluated on a large-scale real-world dataset and demonstrates strong detection performance, while achieving low inference latency suitable for real-time enterprise deployment. The ablation analysis of the framework confirms that dynamic weighting and personalized threshold substantially improve detection stability and convergence with an effective and deployable solution for large-scale authentication environments. Full article

Multi-objective flexible job shop scheduling requires balancing conflicting objectives while supporting real-time decision-making in industrial environments. However, although traditional metaheuristics are effective for global search, their high computational cost limits their applicability in time-sensitive scenarios. To address this issue, this paper proposes dual-pool guided preference-conditioned graph reinforcement learning (DPG-GRL), an encoder–decoder framework for the multi-objective flexible job shop scheduling problem. In DPG-GRL, a graph attention network encoder extracts operation and machine-level representations from a heterogeneous graph, while the decoder is conditioned on a preference vector to generate scheduling solutions with different trade-offs using a single trained policy. To improve sample efficiency and training stability, a dual-pool guidance mechanism is introduced, in which an offline expert pool provides a stable behavioral prior for policy initialization and an online elite pool continuously replays high-quality trajectories to refine the policy. Experimental results show that DPG-GRL outperforms representative multi-objective evolutionary algorithms, including the non-dominated sorting genetic algorithm II (NSGA-II) and the multi-objective evolutionary algorithm based on decomposition (MOEA/D), on synthetic instances, with more pronounced advantages in solution quality and inference efficiency as the problem scale grows. In addition, evaluations on public benchmark instances using a model trained only on the small synthetic setting demonstrate rapid Pareto-front approximation, high-quality solution sets, and promising generalization to unseen instances. These results indicate the potential of DPG-GRL for real-time production scheduling and energy-aware manufacturing. Full article

Real-time detection of apple leaf diseases in orchard environments faces ongoing challenges, particularly in preserving fine-grained disease features with limited computing resources. To address these issues, we propose a high-precision lightweight model based on YOLOv10n, called YOLO-ALD. First, we introduce Spatial and Channel Reconstruction Convolution into deeper backbone networks to replace standard downsampling layers and convolutions. This suppresses spatial and channel redundancy caused by environmental noise and optimizes feature representation. Second, we design a new C2f-Faster-SimAM module for the neck network. This module combines the inference efficiency of FasterNet with a parameter-free 3D attention mechanism to adaptively focus on early lesions, effectively distinguishing them from leaf veins without increasing model complexity. Third, in the detection head section, we use the Focaler-ShapeIoU loss function to optimize bounding box regression. It utilizes a dynamic focusing mechanism and geometric constraints to ensure the localization accuracy of irregular shapes and hard-to-detect samples. Experimental results on our self-built dataset covering four specific diseases and healthy leaves showed that, compared with YOLOv10n, the mAP@0.5 of YOLO-ALD reached 92.1%, achieving a 2.1% increase. In addition, the model has an inference speed of 105 FPS, with only 2.1 M parameters and 5.6 GFLOPs. Therefore, YOLO-ALD achieves a good balance between efficiency and robustness, showing strong theoretical potential for resource-constrained mobile agriculture diagnosis. Full article

The global poultry hatching industry faces severe challenges of resource waste and animal ethics issues due to the routine culling of day-old male chicks. Meanwhile, early sex identification of 4-day-incubated chicken embryos is limited by low accuracy, as embryos at this stage have weak, low-contrast blood vessels that are highly susceptible to interference from the eggshell’s texture. To address these issues, this paper proposes a non-destructive early sex identification method for chicken embryos based on an improved MobileViT-V3 model. Taking the lightweight hybrid architecture MobileViT-V3 as the backbone, we embedded a Micro Feature Enhancement module (MFE-Module) in Stage 3 to strengthen the extraction of fine vascular details, and a Multi-Scale Adaptive Attention Fusion module (MSAAF-Module) in Stage 4 to realize adaptive weighted screening of multi-source features. Experiments on the self-constructed dataset of 4-day-incubated embryos show that the improved model achieves a test set classification accuracy of 92.26%, with an F1-score of 92.15%, a recall rate of 92.12%, and a Kappa coefficient of 0.845. It outperforms mainstream models such as YOLOv12, ShuffleNetV2, ConvNeXt-T, ResNet, and Swin-ViT, with only 2.98 M parameters and an inference speed of 97.6 FPS, well exceeding the 30 FPS real-time requirement of industrial sorting lines and showing high potential for practical industrial deployment. This method provides a new scheme for non-destructive, high-precision, and high-efficiency early sex identification in poultry hatching. Full article

This study proposes a lightweight crack-segmentation model optimized for industrial and edge-computing environments, where both high accuracy and real-time inference are required. Conventional convolution-based and U-Net-based crack segmentation models offer relatively simple architectural designs, but often suffer from limited boundary precision or an unfavorable accuracy–efficiency trade-off. Swin Transformer-based approaches can model broader contextual information but may still show poor segmentation quality relative to their computational cost in fine crack analysis. To address these limitations, we propose the Stabilized Crack Network++ (SCN++), a U-Net backbone crack segmentation network that integrates edge fusion, hybrid loss with deep supervision, exponential moving average (EMA)-based stabilization, and lightweight post-processing. The model was trained and evaluated on 40,000 concrete surface images, including 20,000 crack images and 20,000 non-crack images, using quantitative metrics such as intersection over union (IoU), Dice coefficient, frames per second (FPS), giga floating-point operations (GFLOPs), and the number of parameters, together with overlay-based qualitative analysis. Compared with the CNN, U-Net, and Swin Transformer baselines, SCN++ achieved the best overall balance between segmentation accuracy and computational efficiency, with an IoU of 0.7346, a Dice coefficient of 0.8457, 35.09 FPS, 8.45 GFLOPs, and only 2.22 M parameters. These results demonstrate that SCN++ effectively mitigates the conventional accuracy–efficiency trade-off and is a strong candidate for practical structural crack segmentation in edge-computing environments. Full article

Quicker identifying abilities are required due to the rising frequency and severity of wildfires. Although polar-orbiting satellites with medium and high resolution can accurately identify wildfires, the majority of available fire detection images originate from such platforms. However, their low temporal revisit rates restrict the potential for early warning. Geostationary satellites provide minute-level, continuous monitoring that corresponds with the quick onset of wildfires; however, their dependence on conventional threshold methods and coarse spatial resolution result in notable detection errors. This study developed an integrated deep learning framework for accurate wildfire detection in low-resolution geostationary imagery in order to get over these restrictions. A novel dynamic index, the Dynamic Normalized Burn Ratio—Thermal (DNBRT), was proposed to characterize wildfire progression by integrating instantaneous thermal anomalies with dynamic vegetation signals. Based on this, a Fire Spatiotemporal Network (FST-Net) was designed, with an efficient residual backbone, a Convolutional Block Attention Module (CBAM) for feature refinement, and a Bidirectional Long Short-Term Memory (BiLSTM) network to capture temporal evolution. Trained and evaluated on an FY-4B-based fire/non-fire dataset, the proposed framework demonstrated superior performance. FST-Net outperformed benchmark models, improving accuracy and recall by averages of 10.30% and 9.32% respectively while achieving faster inference speed. An ablation experiment confirmed the critical role of fusing thermal and vegetation features in DNBRT, with 92.7% accuracy and 94.9% recall. Compared to the FY-4B fire product, the proposed framework enables earlier detection, maintains more complete tracking of fire progression, and exhibits greater robustness under complex burning conditions while achieving sub-hectare (0.36 ha) detection sensitivity at the 2 km resolution. By synergizing a discriminative dynamic index with an efficient spatiotemporal architecture, this work provides an effective solution for operational, real-time monitoring of small and early-stage wildfires from geostationary satellites. Full article

Electroencephalogram (EEG)-based brain–computer interfaces (BCIs) offer a promising pathway for restoring communication. Decoding tonal languages like Mandarin from EEG remains challenging due to homophones and complex temporal dynamics. This study investigates the decoding of six high-frequency Mandarin action verbs—Chi (eat), He (drink), Chuan (wear), Na (take), Kan (look), and Dai (put on)—from EEG signals. We designed a visual-cue-based overt speech production experiment and collected EEG data from 30 participants during visually guided verb reading aloud. A recurrent neural network framework incorporating dual Long Short-Term Memory (LSTM) layers was implemented to model the long-range temporal dependencies in EEG patterns. The proposed model was compared against a traditional Common Spatial Pattern combined with Support Vector Machine (CSP-SVM) baseline. Our LSTM-based model achieved an average classification accuracy of 69.93% ± 3.07% for the six-class task, significantly outperforming the CSP-SVM baseline (36.53% ± 3.17%). Accuracy exceeded 75% under specific training conditions, including more than 15 training repetitions and a training-data proportion of 38%. Furthermore, the model attained this performance level utilizing approximately 38% of the available trial data for training, demonstrating data efficiency. The results indicate that the LSTM architecture can effectively capture the neural signatures associated with Mandarin verb processing, providing a foundation for developing practical EEG-based assistive communication technologies. The inference latency of the trained model, quantified as the post-training per-trial testing time, was under 2 s, supporting near-real-time applications. Full article

This study proposes a scalable Explainable Artificial Intelligence (XAI)–driven Bayesian–AI decision–control framework for multi-objective optimisation in uncertain and dynamic systems. The framework integrates Bayesian networks, stochastic control, and expected utility theory within a unified probabilistic architecture. Unlike traditional black-box models, the proposed framework provides intrinsic interpretability through probabilistic reasoning and dependency-aware modelling. This allows users to understand how decisions are formed and how variables influence outcomes. To further strengthen explainability, the framework incorporates post hoc XAI techniques, including SHAP-based feature attribution and sensitivity-based local explanations. These methods quantify the contribution of each variable and provide clear explanations at both global and local levels. The system is formulated as a stochastic state-space model and implemented as a closed-loop adaptive architecture. It updates decisions continuously as new data becomes available. Scalable inference is achieved using variational inference, Markov Chain Monte Carlo, and Sequential Monte Carlo methods. This ensures efficient performance in complex and high-dimensional environments. A simulation study based on 370 observations shows that the proposed framework improves decision quality, robustness under uncertainty, and transparency compared to conventional methods. Explainability is evaluated using Fidelity, Stability, and Transparency metrics. The results confirm that the model produces consistent and reliable explanations. The framework supports human-centred decision-making by providing visual analytics and clear probabilistic explanations. This makes it suitable for high-stakes applications such as cyber–physical systems, intelligent platforms, and real-time AI systems. The main contribution of this study is the integration of intrinsic probabilistic interpretability with post hoc XAI techniques into a single, scalable framework. This approach bridges a key gap in XAI research and offers a practical and transparent solution for decision-making under uncertainty. Full article

To address the urgent demand for real-time reconstruction in remote sensing satellite imaging, as well as the difficulty of extracting sparse target features from dark backgrounds under low-illumination conditions, this paper proposes a lightweight, scalable attention-guided super-resolution reconstruction framework (SASR). The framework adopts an efficient, scalable visual backbone with staged feature extraction to capture discriminative information at three hierarchical scales. A refined multi-scale channel attention module, improved from the classic MS-CAM structure, is further introduced to fuse high-level semantic features and low-level texture details comprehensively. Finally, stacked sub-pixel convolution operations are employed to achieve high-precision image super-resolution enhancement. The proposed method maintains superior lightweight characteristics and fast inference efficiency while embedding effective channel attention optimisation for accurate feature representation. Experimental validations are conducted on the GF-5 satellite datasets: at 2× magnification, the proposed model achieves 32.2346 dB PSNR and 0.8791 SSIM; at 3× magnification, 31.6040 dB PSNR and 0.8376 SSIM; at 4× magnification, PSNR remains above 30 dB, and SSIM exceeds 0.8. The framework also exhibits robust generalization performance on marine remote sensing image datasets. Comparative experiments with recent super-resolution methods on multiple public datasets further verify the effectiveness and practical superiority of the proposed approach. Full article

EEG-based driver fatigue detection faces three signal-level challenges: inter-subject spectral variability, coupled frequency–spatial–temporal dynamics that existing methods process independently, and dependence on a single labeling scheme. This paper presents DCAMNet, a lightweight CNN (12.3 K parameters) that addresses these challenges through three end-to-end blocks. An SE-driven dynamic convolution block adapts spectral sensitivity per sample via input-dependent kernel weighting—applied here for the first time to fatigue detection. A spatial convolution block encodes electrode-level cortical patterns, and a temporal attention block captures fatigue dynamics through windowed variance descriptors with group-wise attention scoring. DCAMNet was evaluated on SEED-VIG (PERCLOS labels) and MESD (reaction-time labels) under both subject-mixed and leave-one-subject-out (LOSO) protocols. Under LOSO cross-validation—the operationally relevant test that eliminates within-subject information leakage and simulates deployment on unseen drivers—DCAMNet achieved 85.43% accuracy on SEED-VIG with a 2.86-point advantage over the strongest baseline, and $79\pm 5$% accuracy on MESD with a 3-point advantage. As upper-bound estimates under the subject-mixed protocol, accuracy reached 97.47% (SEED-VIG) and 96.52% (MESD). With 1.35 ms inference latency on a standard GPU, the compact architecture suggests potential suitability for real-time embedded deployment, although on-device validation on representative automotive hardware remains necessary. Full article

Sleep disorders, such as insomnia, obstructive sleep apnea (OSA), narcolepsy, REM sleep behavior disorder, and circadian rhythm disturbances, represent a rapidly expanding global health burden that is strongly associated with cardiovascular, metabolic, neurological, and psychiatric diseases. Advancements in wearable sensing technologies and Internet of Medical Things (IoMT) infrastructures have expanded the possibilities for continuous, home-based sleep assessment beyond conventional polysomnography laboratories. These Sleep Health Internet of Things (S-HIoT) systems combine multimodal physiological sensing (EEG, ECG, SpO₂, respiratory effort and actigraphy) with wireless communication and cloud-based analytics for automated sleep-stage classification and disorder detection. Nonetheless, the digitization of sleep medicine brings about significant cybersecurity concerns. The constant transmission of sensitive biomedical information makes S-HIoT networks open to anomalous traffic flows, signal manipulation, replay attacks, spoofing, and data integrity violation. Existing studies mostly focus on analyzing physiological signals and network intrusion detection independently, resulting in a systemic vulnerability of cyber–physical sleep monitoring ecosystems. With the aim of addressing this empirical deficiency, this review integrates emerging advances (2022–2026) in the AI-assisted categorization of sleep phases and IoMT anomaly detector designs on the finer analysis of CNN, LSTM/BiLSTM, Transformer-based systems, and a component part of federated schemes and the lightweight, edge-deployable intruder assessor models available. The aim of this study is to uncover a gap in the literature: integrated architectures to trade off audiences of faithfulness of physiological modeling with communication-layer security. To counter it, we present a single framework to include CNN-based spatial feature extraction, Bidirectional Long Short-Term Memory (BiLSTM)-based temporal models and Random Forest-based ensemble classification using a dual task-learning approach. We propose a multi-objective optimization framework to jointly optimize the performance of sleep-stage prediction and that of network anomaly detection. Performance on publicly available datasets (Sleep-EDF and CICIoMT2024) confirms that hybrid integration can be tailored to achieve high accuracy [99.8% sleep staging; 98.6% anomaly detection] whilst being characterized by low inference latency (<45 ms), which is promising for feasibility in real-time deployment in view of targeting edge devices. This work presents a comprehensive framework for developing secure, intelligent, and clinically robust digital sleep health ecosystems by bridging chronobiological signal modeling with cybersecurity mechanisms. Furthermore, it highlights future research directions, including explainable AI, federated secure learning, adversarial robustness, and energy-aware edge optimization. Full article

Early detection and accurate segmentation of colorectal polyps during colonoscopy are crucial for the prevention of colorectal cancer. However, automated polyp segmentation remains challenging because of high inter-class variance, complex intestinal backgrounds, and blurred boundaries. To address these issues while maintaining computational efficiency, DSF-BRNet was developed for endoscopic polyp segmentation. In this framework, a Dual-Gated Semantic Fusion (DSF) module is introduced to reduce spatial misalignment between cross-level features and to provide a more reliable semantic basis for lesion localization. To further alleviate boundary ambiguity, a High-Frequency Boundary Refinement (HBR) module is used to sharpen segmentation contours under aligned semantic guidance. Together, these components form an Align-then-Refine framework in which semantic localization is strengthened before boundary refinement is performed. Experiments on four public benchmark datasets—Kvasir-SEG, CVC-ClinicDB, CVC-ColonDB, and ETIS-LaribPolypDB—showed competitive performance with favorable computational efficiency. Mean Dice scores of 0.943 on CVC-ClinicDB and 0.818 on ETIS-LaribPolypDB were achieved, with 25.55 M parameters and an inference speed of 80.08 FPS. These results indicate that accurate semantic localization and fine boundary preservation can be achieved simultaneously, suggesting that the method may be promising for real-time computer-aided diagnosis (CAD). Full article

Unmanned aerial vehicle (UAV) imaging systems are increasingly deployed in surveillance, infrastructure monitoring, and smart-city applications, where the integrity of captured visual data is critical. Recent advances in generative models enable highly realistic deepfake manipulations that can compromise aerial sensor streams, particularly under real-world degradations such as motion blur, sensor noise, and compression artifacts. This paper introduces DeepLayer-ID, a degradation-aware multi-domain forensic framework specifically designed for UAV sensing environments. The proposed architecture decomposes forensic evidence into complementary spatial, frequency, and residual domains. A discrete wavelet transform module captures sub-band energy inconsistencies, while high-pass residual filtering isolates sensor pattern anomalies. A lightweight transformer-based fusion mechanism adaptively integrates cross-domain representations to enhance robustness under heterogeneous acquisition conditions. To emulate operational UAV pipelines, we construct a balanced dataset of 1096 aerial frames derived from the VisDrone2019-DET validation subset, incorporating synthetic manipulations and physics-consistent degradations. The experimental results show that DeepLayer-ID achieves 97.8% accuracy and 0.991 AUC, outperforming ResNet-50 (90.9%, 0.942 AUC), XceptionNet (92.4%, 0.957 AUC), and Noiseprint CNN (93.1%, 0.964 AUC). Notably, the model maintains real-time feasibility, with only 5.4 M parameters and 9.8 ms inference latency. These findings demonstrate that structured multi-domain signal decomposition combined with attention-guided fusion provides a robust and computationally efficient solution for deepfake detection in degraded UAV sensing systems. Full article

Computer vision–based weed detection plays a critical role in agricultural robotics, enabling accurate, selective weeding. These systems operate on resource-constrained embedded platforms, which introduces a significant trade-off between accuracy and efficiency. This study presents a comparative evaluation of six detection models (YOLOv11n, YOLOv11s, SSD-Lite, NanoDet, Faster R-CNN, RT-DETR) for agro-robotic applications, measuring precision, recall, mAP@0.5, and runtime on low-power hard-ware. NanoDet achieved the highest detection accuracy (precision 98.6%, recall 94.2%, mAP@0.5 97.7%). YOLOv11s demonstrated similar performance (mAP@0.5: 96.1%) but required more computation. YOLOv11n provides the most favourable balance between accuracy and throughput (mAP@0.5: 94.6%, 207 FPS on a workstation). On Raspberry Pi 5, light models achieved 3–5 FPS. RT-DETR and Faster R-CNN exhibited high latency (3112–6500 ms/frame), which prevents real-time operation. NanoDet excelled in detection, while YOLOv11n provides the best balance between accuracy and efficiency for limited devices. Full article