Search Results (1,914)

Convolutional neural network (CNN)-based methods have been widely adopted in hyperspectral image (HSI) classification tasks and have demonstrated superior performance due to their potent nonlinear fitting capabilities. However, as network depth increases, existing methods suffer from significant issues such as gradient vanishing and information loss, which limit further improvements in model performance. Meanwhile, current approaches primarily design entirely new network architectures to extract abstract features but fail to fully exploit the explicit gradient prior information inherent in the data, which affects model performance in complex scenarios. To address these issues, this paper proposes a Multiscale Dense HOG-driven Self-Attention Network (MDHANet) that incorporates the Histogram of Oriented Gradients (HOG) as prior knowledge. First, the model employs three densely connected branches at different scales to obtain diverse multi-level feature representations through multi-scale feature reuse. Furthermore, since HOG can explicitly encode the distribution of gradient orientations and magnitudes in local neighborhoods and accurately characterize the feature distribution, a dynamic HOG-driven self-attention module is designed. Within this module, a HOG prior-based feature rearrangement strategy together with a dual-branch self-attention mechanism enables the network to more effectively learn the spatial information of the data, enhancing the extraction of discriminative spatial–structure features and further improving classification performance. Extensive experimental results on multiple datasets demonstrate that the proposed method outperforms existing state-of-the-art approaches. Extensive experimental results on four HSI datasets (IP, LK, HH, and HC) demonstrate that the proposed method outperforms existing state-of-the-art approaches, achieving OA of 99.13%, 97.32%, 99.02%, and 99.24%, respectively, with improvements of 0.83%, 0.41%, 2.69%, and 2.47% over the best competing methods. Full article

This study aimed to develop and evaluate a deep learning diagnostic model integrating a convolutional autoencoder (CAE) and ResNet18 for the early and accurate diagnosis of developmental dysplasia of the hip (DDH) in children, addressing the subjectivity of traditional methods. This study began with the construction of a CAE network. By introducing a multi-layer compression structure and a Dropout layer, the network was forced to learn the low-dimensional and robust feature representations of the input X-ray images (frog-leg lateral view). The CAE was used to reconstruct the input images and generate enhanced images that highlight abnormal regions. Subsequently, the original and enhanced images were concatenated along the channel dimension to form an information-rich enhanced input. Finally, the pretrained ResNet18 was adopted as the backbone classification network, and its input layer was modified to adapt to multi-channel input to conduct training and classification for the stitched images. Compared to those achieved by the four benchmark models (ResNet18, DarkNet19, AlexNet, and MobileNetV2), the CAE-ResNet18 model achieves excellent performance on the test set. The accuracy, recall rate, and F1-score of the Normal class are 0.9890, 1.0000, and 0.9945, respectively. The accuracy, recall rate, and F1-score of the DDH class were 1.0000, 0.9912, and 0.9956, respectively. Visual analysis shows that the t-SNE visualization of the fully connected layer feature of this model presents a more obvious inter-class separation. The CAE-ResNet18 model effectively leverages both original image information and abnormal features, significantly improving the accuracy and reliability of DDH diagnosis. It provides a potential intelligent tool for clinical auxiliary diagnosis, which may enhance patient prognosis. Full article

Tight reservoirs exhibit complex pore structures and strong heterogeneity, which complicate reservoir characterization. Although spectral induced polarization (SIP) is sensitive to pore structure, existing polarization models are formulated at the pore scale and are difficult to connect with measurements across different core volumes. We adopted an improved membrane polarization model and coupled it with a three-dimensional impedance network to investigate two-stage SIP upscaling: from pore systems to core-scale networks, and from local core volumes represented by subnetworks to larger parent cores. The framework was used to determine the representative elementary volume (REV), evaluate subnetwork representativeness, examine fracture-controlled heterogeneity, and compare simulations with laboratory measurements. The results show that REV size is controlled by the distribution ranges of pore radius and pore length. Homogeneous networks converge with sufficient sampling, whereas subnetworks from strongly heterogeneous fractured cores may exhibit relative deviations exceeding tenfold when fracture structures are not adequately captured. Impedance network inversion can reproduce measured spectra, but the recovered pore distributions are non-unique and represent electrically equivalent structures. Laboratory-scale SIP data may not fully capture large-scale heterogeneity; integrating logging or imaging information may, therefore, help constrain cross-scale non-local effects and improve the reliability of comprehensive reservoir evaluation. Full article

The transition toward Agriculture 4.0 aims to improve farm performance and sustainability; however, existing macroeconomic indicators do not fully capture the depth of farm-level digital adoption. This study proposes the Digital Farm Index (DFI) as a tool for assessing digital maturity and regional disparities in European agriculture. The research combines bibliometric mapping of the scientific literature with an empirical DFI assessment for 18 European Union Member States using Eurostat data. The empirical assessment utilizes multiple linear regression, log-linear scale modeling, and hierarchical clustering to analyze adoption patterns and structural determinants. The index integrates four dimensions: connectivity, precision agriculture, robotics, and farm management information systems (FMIS). Results indicate that adoption is concentrated in larger farms, as area-weighted digital maturity (DFI-Hectares) consistently exceeds farm-level adoption (DFI-Farms). CAPEX-based cost modeling suggests the existence of a technological indivisibility threshold, whereby digitalization may become an entry barrier for fragmented farms with limited economies of scale. Multiple linear regression suggests an East–West structural trend: while farm size influences the territorial diffusion of technology, a more consolidated regional innovation ecosystem appears more relevant for farm-level adoption. Findings also highlight a hardware–software imbalance and limited use of data-driven managerial tools. Support policies should therefore move beyond equipment subsidies and include technology transfer networks, digital skills, and managerial data-integration tools. Full article

Accurate and interpretable brain tumour detection from magnetic resonance imaging (MRI) is important for the reliable use of computer-assisted diagnostic systems. This study examines whether image preprocessing can improve the localisation quality of explanations generated by convolutional neural network (CNN) classifiers while preserving high classification performance. Two pre-trained CNN architectures, ResNet50 and DenseNet121, were fine-tuned using the BRISC 2025 dataset, which contains 6000 annotated contrast-enhanced T1-weighted MRI images: 5000 training images and 1000 test images. The dataset includes four classes: glioma, meningioma, pituitary tumour, and healthy brain images. The original classification layers were replaced with custom fully connected heads designed for four-class classification. Model explanations were generated using Grad-CAM, Integrated Gradients, and LIME. Their localisation quality was evaluated against the available tumour segmentation masks using Intersection over Union (IoU), the Dice coefficient, and the Pointing Game metric. Tests show that both models (99.1% for ResNet50 and 99.2% for DenseNet121) perform well in terms of validation accuracy, but the explanation maps often operate in regions outside the clinically relevant area. To combat this issue, an image preprocessing pipeline utilising Otsu threshold masking, hole filling, and brightness–contrast jittering was implemented to filter noise from the background and isolate the focus area—brain region. After preprocessing, the validation accuracy of the DenseNet121 model was 99.6%, and the average Grad-CAM explainability metrics improved from 21.49% to 23.08% IoU, from 30.21% to 32.49% Dice coefficient, and from 48.33% to 51.67% Pointing Game score. The results indicate that conventional image preprocessing can moderately improve the spatial agreement between explanation maps and annotated tumour regions without reducing classification accuracy. Full article

High-speed maneuvering flight vehicles operating in the subsonic-to-transonic regime (250–500 m/s) pose severe challenges to defense interception systems due to their rapid and unpredictable maneuvering behaviors. Accurate short-term trajectory prediction is essential for effective terminal-phase interception guidance. This paper proposes DSGF-Net (Dual-Stream Gated Fusion Network), a hybrid deep learning architecture for 3D trajectory prediction that simultaneously exploits frequency-domain and temporal-domain information through independent parallel streams. DSGF-Net employs two Temporal Convolutional Networks (TCNs) as parallel encoders: a frequency stream processes Wavelet Packet Decomposition (WPD) features (24-dimensional, db4 wavelet, level-3 decomposition), and a temporal stream processes raw 3D coordinates. An adaptive sigmoid gating module dynamically fuses the two independently encoded streams at each time step and feature dimension, followed by an LSTM sequence learner and a single-step fully connected decoder. Experiments on a simulated dataset covering five representative maneuvering modes (cruise, dive, climb, serpentine, composite) reveal a three-level performance hierarchy. First, incorporating raw 3D coordinates alongside WPD features substantially improves clean-data accuracy over WPD-only baselines: DSGF-Net achieves ADE = 3.476 ± 0.010 m (5 random seeds) versus TCN-LSTM (WPD-only) at 3.938 ± 0.103 m (11.7% improvement). Second, a single-stream concatenation baseline (Concat-TCNLSTM) using identical inputs achieves comparable clean-data accuracy (3.333 ± 0.009 m), confirming that input information—rather than fusion mechanism—drives clean-data gains. Third, and most critically, DSGF-Net’s independently encoded dual-stream architecture enables adaptive suppression of degraded sensor inputs: under multi-sensor noise (complementary radar/GPS profiles), DSGF-Net achieves ADE = 13.91 m versus TCN-LSTM’s 21.32 m (34.9% advantage)—a substantially larger margin than on clean data—a capability structurally unavailable to concatenation-based models. With 300K parameters and a 4.96 ms inference time on an A100 GPU, DSGF-Net meets real-time terminal interception requirements (<10 ms). Full article

Predictive maintenance (PdM) is central to Industry 5.0 strategies for reducing unplanned downtime in rotating machinery. This work proposes and evaluates, as a proof of concept on a controlled single-machine testbed, a multimodal TinyML edge architecture for PdM designed to remain compatible across the application plane’s evolution toward sixth-generation (6G) networks. Three complementary modalities run local inference on commercial off-the-shelf smart sensor nodes—vibration, acoustic, and thermography—with an embedded gateway bridging per-modality decisions to a serverless cloud back-end. Using real vibration data from a controlled static-unbalance protocol, five anomaly-detection model variants, operating on ten frequency-independent time-domain features extracted from 6 s windows, are benchmarked on the actual Cortex-M4F target; the INT8-quantized fully connected autoencoder, scored by per-window reconstruction error, reaches F1 = 0.9807 with 254 µs inference latency and a 6056 B Flash footprint, well within the microcontroller budget. In a second acquisition session with the remounted sensor, the frozen model retains perfect fault recall, and a short per-installation healthy-baseline recalibration restores F1 = 0.975 without any weight retraining. The acoustic modality is classified in-sensor on log-Mel filterbank energies by the Syntiant NDP120 neural coprocessor, and the thermographic modality by a lightweight binary CNN on 96 × 96 px frames. A preliminary intra-session late-fusion analysis suggests that a logistic-regression meta-learner over the three modality confidence scores can improve on single-modality baselines when no single modality already saturates, motivating multimodal sensing primarily for robustness and redundancy. An end-to-end latency experiment shows that the cloud-uplink leg dominates the budget (79–88%), establishing edge-first inference as a necessary condition for 6G URLLC gains to be observable at the application level. All experiments are conducted over Wi-Fi and MQTT with no 5G or 6G radio, so 6G compatibility is presented as a forward-looking roadmap rather than a tested capability. Full article

Deploying Autonomous Underwater Vehicle (AUV) swarms is pivotal for oceanographic exploration. However, swarm formation control is constrained by harsh Underwater Acoustic Communication Networks (UACNs), especially in dynamic, non-fully connected topologies. To address high packet collision rates and excessive signaling overhead in existing Medium Access Control (MAC) protocols, this paper proposes a novel Cluster-based Mobile MAC (CM-MAC) protocol for hierarchical clustered AUV networks. Operating under a decentralized three-tier architecture, the protocol coordinates transmissions using local state information. We establish transmission constraints to prevent packet collisions among mobile nodes. Building upon the transmission constraints, genetic algorithms are applied to the transmission scheduling across all layers to optimize the sending sequence and timing, reducing overall latency. Simulation results show that the CM-MAC protocol significantly improves network throughput and reduces information-sharing update intervals when compared to traditional TDMA, pure Aloha, and random-access CM-MAC. This study presents a robust communication framework for coordinating large-scale AUV swarms in complex underwater environments. Full article

The complex, heterogeneous nature of many subsurface environments makes accurate Rate of Penetration (ROP) prediction both critical and challenging for achieving drilling efficiency, cost control, and operational safety. Although artificial intelligence has demonstrated strong potential in extracting nonlinear patterns from drilling and well-log data, its application to heterogeneous formations remains limited by: (i) overreliance on operational parameters that lack formation-physics context, (ii) rigid train–test splits that ignore geological variability, and (iii) heuristic hyperparameter selection practices that are not reproducible. This study presents a geomechanically augmented deep learning framework applied to two vertical wells in a Middle East carbonate-clastic field (Well A: 9375 records, 1000–3370 m; Well B: 4443 records, 1945–3131 m). Five contributions are introduced: (1) a physics-informed input space integrating lithology-specific geomechanical properties (UCS, CCS, Young’s modulus, shear modulus, friction angle), validated against core measurements (R² = 0.79–0.95); (2) a heterogeneity-adaptive train–test partitioning strategy demonstrating that formation complexity, rather than a fixed universal ratio, governs the optimal split; (3) a residual Fully Connected Neural Network (FCNN) with Swish activation and systematic hyperparameter sensitivity analysis; (4) a rigorous preprocessing pipeline comprising 99th-percentile Winsorization, interaction-term feature engineering (WOB × CCS, RPM × UCS), Lasso selection, Z-score normalization, and Gaussian noise augmentation, with all transforms fitted exclusively on training data to prevent leakage; and (5) a hybrid LSTM-FCNN that processes depth-ordered sequences via Savitzky–Golay denoising and a ten-step sliding window. The standalone FCNN achieved R² = 0.8641 (Well A) and R² = 0.9062 (Well B). The LSTM-FCNN improved intra-well accuracy to R² = 0.9877 and R² = 0.9551 and resolved a severe cross-well transfer asymmetry (B → A: R² = 0.0388 for FCNN versus R² = 0.8217 for LSTM-FCNN; A → B: R² = 0.8963), confirming that depth-sequential modeling captures transferable formation patterns across contrasting lithological profiles. Full article

Conventional analysis of nuclear power plant accident transient responses heavily relies on physical simulation programs, whose computational time significantly exceeds the actual accident response duration, thereby severely hindering real-time safety assessment. This paper proposes a novel framework that integrates a Transformer-based Variational Autoencoder (VAE) with knowledge distillation for the fast prediction of nuclear power plant (NPP) accident transient responses. The approach involves constructing a latent space to extract essential features from transient response data using an Encoder–Decoder model based on the VAE architecture. A key innovation is the establishment of a direct mapping between plant operating condition parameters and the latent space, enabling the one-step generation of accident transients without iterative sequential prediction. The Encoder and Decoder leverage Self-Attention and Cross-Attention mechanisms to enhance feature extraction and conditional generation. Furthermore, the Encoder is distilled into a Mapper network, which predicts the latent features directly from the operating conditions, resulting in an efficient Mapper–Decoder pipeline for rapid prediction. The proposed model was evaluated against traditional Long Short-Term Memory (LSTM) and fully connected neural networks. Experimental results demonstrate that the proposed framework achieves superior performance in predicting NPP accident transients, indicating its strong potential for efficient safety analysis and system design optimization. Full article

Infrared small-target detection plays a vital role in applications such as imaging detection and remote sensing. Because infrared small targets are weak and lack distinctive features, they are easily submerged in cluttered backgrounds, which makes their detection challenging. Preserving spatial details, jointly modeling local and global features, and strengthening feature representation are therefore critical to improving detection accuracy and robustness. However, existing methods often fail to fully exploit multi-level feature relationships, struggle to integrate local and global complementary information, and lack mechanisms to compress redundant features while emphasizing salient information. To address these issues, we propose MACT-Net, a network designed specifically for infrared small-target detection. First, a multi-level aggregation encoder–decoder architecture with convolution-enhanced skip connections and multi-scale decoder fusion is employed to progressively abstract and reconstruct features, preserving spatial details and improving multi-scale responsiveness. Second, a CNN–Transformer hybrid feature modeling module is introduced to adaptively capture local textures and global semantic dependencies, enhancing feature representation and discriminative capability. Third, a vector quantization-based feature discretization and representation enhancement mechanism is embedded at the network bottleneck to compress redundant information and emphasize salient features, further improving robustness under low signal-to-noise ratio conditions. We evaluate MACT-Net on three public datasets: SIRST, IRSTD-1K, and NUDT-SIRST. Extensive experimental results confirm that the combination of multi-level aggregation, hybrid feature modeling, and feature discretization mechanisms effectively enhances infrared small-target detection performance. Full article

Federated learning (FL) has emerged as a promising paradigm for enabling distributed intelligence in Internet of Things (IoT) environments while preserving data privacy and reducing the need for centralized data collection. However, the practical deployment of FL in IoT scenarios remains challenging due to heterogeneous data distributions, unreliable communication conditions, and the presence of faulty or malicious edge devices that can disrupt collaborative training. These limitations can significantly degrade convergence stability and predictive performance, particularly in resource-constrained and intermittently connected networks. This paper proposes a simulation-driven trust-aware federated learning framework for robust intelligent IoT networks. The proposed approach incorporates a dynamic trust-based aggregation mechanism that adaptively weights client contributions based on the consistency of their local model updates with the global model state. In addition, a controlled IoT-oriented federated simulation environment is developed to emulate heterogeneous edge conditions, including non-independent and identically distributed (non-IID) data partitioning, adversarial model manipulation, and intermittent client connectivity caused by communication dropouts. Extensive multi-seed experiments were conducted on the UCI Human Activity Recognition (UCI HAR) dataset and complemented with an auxiliary CIFAR-10 convolutional neural network (CNN) validation scenario. The evaluation considered multiple adversarial settings, including sign-flip, Gaussian-noise, scaling, and label-flip attacks, as well as communication-dropout probabilities up to 50%. In contrast with the initial FedAvg-only evaluation, the revised experimental analysis includes comparisons with representative robust aggregation baselines, namely Median, Trimmed Mean, Krum, Multi-Krum, and an auxiliary Bulyan configuration. The experimental results demonstrate that the proposed Trust-FedAvg framework substantially improves robustness over conventional FedAvg and remains competitive with established robust aggregation strategies, particularly under directional model-manipulation attacks and intermittent-connectivity conditions. Under a 20% sign-flip attack on UCI HAR, the proposed method achieved a final test accuracy of 86.2%, whereas conventional FedAvg degraded to approximately 44.7%. Furthermore, under combined adversarial and intermittent-connectivity conditions with 50% communication dropout, Trust-FedAvg maintained a final accuracy of 57.0%, compared with 21.3% for FedAvg, 24.8% for Median, and 14.6% for Trimmed Mean. The additional experiments also show that Trust-FedAvg is not universally superior across all perturbation types: under severe Gaussian-noise attacks, coordinate-wise Median and Multi-Krum provided stronger robustness in some settings. Overall, the results suggest that trust-aware aggregation can improve robustness against unreliable or malicious simulated clients while preserving a relatively simple aggregation procedure. Runtime measurements further indicate that the proposed method introduces only limited round-level overhead compared with FedAvg, while remaining simpler than more complex Byzantine-resilient alternatives. Further validation with real IoT deployments, additional sensor datasets, asynchronous communication models, energy profiling, and communication-overhead measurements is required to fully assess deployment feasibility in real IoT environments. The proposed framework provides a practical, extensible basis for the design and evaluation of resilient AI-enabled IoT networks operating under controlled but practically relevant edge-learning constraints. Full article

Human African trypanosomiasis (HAT) or sleeping sickness is a neglected tropical disease with a progressive central nervous system (CNS) involvement and marked sleep and circadian rhythm abnormalities. Even though this is a prominent feature of HAT, the connection between parasite neuroinvasion, neuroinflammation, circadian dysfunction, and neurological impairment is not fully understood. This narrative review aims to summarize the most up-to-date knowledge about sleep and circadian disturbance in HAT and proposes an integrated approach for the Trypanosome-Associated Sleep Disorder (TASD). The relevant literature was identified by searching major biomedical databases for HAT, sleep disorders, circadian rhythms, neuroinflammation, and CNS invasion. The review covers the steps by which the CNS becomes invaded, how the barriers are disrupted, how the CNS becomes activated by inflammatory responses, and how the hypothalamic and circadian regulatory networks are disrupted. The evidence suggests that excessive daytime sleepiness, fragmented nocturnal sleep, circadian misalignment, and neuropsychiatric manifestations are related to the activation of inflammatory cytokines, altered neurotransmitter signaling, activation of the kynurenine pathway, dysregulation of clock genes, and disruption of the suprachiasmatic nucleus. We also discuss TASD as a syndrome-like phenotype of CNS involvement and propose a three-stage model of sleep–wake dysfunction in HAT. The review unites these integral mechanisms in a single mechanistic framework to offer a unified understanding of the sleep pathology associated with HAT. There are still important gaps in our knowledge of biomarkers, disease staging, and irreversible neuronal damage, which indicate priorities for future research and better clinical management. Full article

This study presents an integrated workflow to characterize and optimize hydraulic fracturing operations in horizontal shale reservoirs using passive wellhead pressure monitoring (PWPM). Pressure data from offset wells in the Horn River Shale Basin were analyzed to identify passive pressure responses and distinguish between direct hydraulic communication and stress-induced behavior, providing insight into fracture dynamics and inter-well connectivity. A multivariate sensitivity analysis was performed to evaluate how key fracture and reservoir mechanical properties, fracture orientation, and in situ stresses govern passive pressure signatures. A fully coupled hydro-mechanical model, implemented using a distinct element formulation, was developed based on the observed passive pressure and microseismic data to generate a physics-based representation of fracture propagation and fluid migration. The modeling framework enables forward prediction of passive pressure responses during future stimulation stages, supporting improved treatment design, real-time operational adjustments, and more reliable refracturing strategies under evolving subsurface conditions. By enhancing fracture network characterization and complementing microseismic monitoring, PWPM demonstrates strong diagnostic value for supporting safer and more efficient injection practices in unconventional reservoir development, as well as broader sustainable energy applications. Full article

Complex diseases often involve distributed interactions among biological regions, physiological systems, imaging phenotypes, and clinical variables that are not fully captured by anatomical proximity, isolated biomarkers, or conventional feature-based representations. In oncology, neuroimaging, critical care, and systems medicine, distant or apparently separate biomedical sectors may show strong statistical or functional coupling associated with multimodal imaging signatures, inflammatory responses, metabolic constraints, treatment-induced changes, or shared disease-state organization. In this work, we introduce a proof-of-concept relational graph framework for representing such candidate hidden connectivity in terms of correlation-induced accessibility bridges. The novelty of the framework is that it does not treat biomedical correlation, graph distance, and network connectivity as separate descriptors but explicitly couples non-factorizable inter-sector correlation to localized accessibility compression in an emergent disease-state geometry. The proposed framework represents a biomedical system as a weighted relational graph in which nodes correspond to clinically relevant entities, such as tissue regions, imaging-derived features, biomarker modules, physiological variables, or disease states, while weighted edges encode constraints on functional, statistical, or pathological accessibility. Within this structure, coarse-grained biomedical sectors are defined as organized subsystems, and non-factorizable coupling between sectors is quantified using mutual-information-type measures. Candidate biomedical bridges are then defined operationally as localized, high-gain reductions in effective inter-sector accessibility distance. We introduce explicit coupling rules linking sector-level correlation to bridge-specific accessibility compression, including an effective distance-compression model and an ensemble-based formulation. Numerical proof-of-concept simulations on randomized modular graph ensembles show that increasing correlation strength systematically reduces effective inter-sector distance and increases bridge gain. The strongest compression occurs when correlation modulates a designated bridge architecture, exceeding the effects observed under random non-bridge or generic inter-sector modulation. These simulations are not intended to validate a disease-specific biological mechanism but to test whether the proposed correlation–compression rule produces bridge-specific effects distinguishable from null graph perturbations. The resulting structures should not be interpreted as physical anatomical tunnels or direct causal pathways unless supported by additional biological evidence. Rather, they represent correlation-induced accessibility bridges: localized, high-gain routes in a patient- or disease-specific relational geometry. The framework may therefore provide a theoretical and computational basis for prioritizing candidate hidden connectivity patterns in radiomics, multimodal prognosis, physiological deterioration, recurrence modeling, and systems-level disease networks. Full article