Search Results (303)

Accurate weed mapping in cereal fields requires pixel-level segmentation from unmanned aerial vehicle (UAV) imagery that remains reliable across fields, seasons, and illumination. Existing multispectral pipelines often depend on thresholded vegetation indices, which are brittle under radiometric drift and mixed crop–weed pixels, or on single-stream convolutional neural network (CNN) and Transformer backbones that ingest stacked bands and indices, where radiance cues and normalized index cues interfere and reduce sensitivity to small weed clusters embedded in crop canopy. We propose VISA (Vegetation Index and Spectral Attention), a two-stream segmentation network that decouples these cues and fuses them at native resolution. The radiance stream learns from calibrated five-band reflectance using local residual convolutions, channel recalibration, spatial gating, and skip-connected decoding, which preserve fine textures, row boundaries, and small weed structures that are often weakened after ratio-based index compression. The index stream operates on vegetation-index maps with windowed self-attention to model local structure efficiently, state-space layers to propagate field-scale context without quadratic attention cost, and Slot Attention to form stable region descriptors that improve discrimination of sparse weeds under canopy mixing. To support supervised training and deployment-oriented evaluation, we introduce BAWSeg, a four-year UAV multispectral dataset collected over commercial barley paddocks in Western Australia, providing radiometrically calibrated blue, green, red, red edge, and near-infrared orthomosaics, derived vegetation indices, and dense crop, weed, and other labels with leakage-free block splits. On BAWSeg, VISA achieves 75.6% mean Intersection over Union (mIoU) and 63.5% weed Intersection over Union (IoU) with 22.8 M parameters, outperforming a multispectral SegFormer-B1 baseline by 1.2 mIoU and 1.9 weed IoU. Under cross-plot and cross-year protocols, VISA maintains 71.2% and 69.2% mIoU, respectively. The full BAWSeg benchmark dataset, VISA code, trained model weights, and protocol files will be released upon publication. Full article

Automotive vision systems depend critically on front-view cameras, whose image quality frequently degrades under adverse conditions such as rain, fog, low illumination, and rapid motion. To address this challenge, we propose VMESR, a variable mamba-enhanced super-resolution network that integrates a selective state-space model into a lightweight super-resolution architecture. By serializing 2D feature maps and applying variable-depth mamba blocks, VMESR captures long-range dependencies with linear complexity. A multi-scale feature extractor, enhanced residual modules equipped with a convolutional block attention module, and dense fusion connections work together to improve the recovery of high-frequency details. Extensive experiments demonstrate that VMESR achieves competitive performance in both objective metrics and perceptual quality compared to state-of-the-art methods, while significantly reducing parameter counts and computational cost. VMESR provides a practical balance between efficiency and reconstructive accuracy, offering a deployable super-resolution solution for embedded automotive sensors and enhancing the robustness of autonomous driving perception pipelines. Full article

Background/Objectives: Lung cancer (LC) is the leading cause of cancer-related mortality worldwide, making early and accurate diagnosis crucial for improving patient outcomes. Although chest computed tomography (CT) enables detailed assessment of lung abnormalities, manual interpretation is time-consuming, requires expert expertise, and is prone to diagnostic variability. To address these challenges, this study proposes DE-SAMNet, a hybrid deep learning framework for automated multi-class LC classification from CT scans. Methods: The model integrates two pre-trained convolutional neural networks—DenseNet121 and EfficientNetB0—operating in parallel to extract complementary multi-scale features. A Spatial Attention Module (SAM) is applied to each feature stream to emphasize clinically important regions. Final classification is performed through a compact fusion mechanism involving global average pooling, batch normalization, and a fully connected layer. DE-SAMNet was evaluated on two datasets: a public dataset (IQ-OTH/NCCD) with benign, malignant, and normal cases, and a private clinical dataset including benign, malignant, cystic, and healthy cases. Results: On the public dataset, the model achieved a 99.00% F1-score, 98.41% recall, 99.64% precision, and 99.54% accuracy. On the private dataset, it obtained 95.96% accuracy, 95.99% precision, 96.04% F1-score, and 96.21% recall, outperforming existing approaches. To enhance reliability, explainable AI (XAI) techniques such as Grad-CAM were used to visualize the model’s decision rationale. The resulting heatmaps effectively highlight lesion-specific regions, offering transparency and supporting clinical interpretability. Conclusions: This explainability strengthens trust in automated predictions and demonstrates the clinical potential of the proposed system. Overall, DE-SAMNet delivers a highly accurate and interpretable solution for early LC detection. Full article

This paper addresses the design and performance analysis of nonorthogonal multiple access (NOMA) for ultra-dense networking of the Internet of Things (IoT) based on low-power sensors. The proposed NOMA schemes consist of an $N_r$-antenna access point and K single antenna sensors given $K\gg N_r$. A power allocation technique and forward error correction (FEC) are combined to enable concurrent uplink transmission and the successful separation of all K sensors at the access point. In scenarios where $K\gg N_r$, large dimensional analysis is employed to derive a deterministic expression for the received signal-to-interference-plus-noise ratio (SINR) within the finite blocklength regime. Three distinct Forward Error Correction (FEC) codes—convolutional codes (CCs), polar codes, and low-density parity-check codes (LDPCs)—are assessed. These evaluations indicate that all three codes achieve near-capacity performance while supporting massive connectivity in the finite-blocklength context. Notably, convolutional codes demonstrate comparable performance with reduced complexity, a desirable attribute for prolonging the life cycle of wireless sensor network-based IoT applications. Full article

The assessment of reliability in non-repairable subsystems of mining electronic equipment represents a computationally challenging problem, particularly for complex and highly connected structures. This study presents a systematic comparative analysis of several deterministic approaches for reliability estimation, focusing on their computational efficiency, accuracy, and applicability. The investigated methods include classical boundary techniques (minimal paths and cuts), analytical decomposition based on the Bayes theorem, the logic–probabilistic method (LPM) employing triangle–star transformations, and the algorithmic Structure Convolution Method (SCM), which is based on matrix reduction of the system’s connectivity graph. The reliability problem is formally represented using graph theory, where each element is modeled as a binary variable with independent failures, which is a standard and practically justified assumption for power electronic subsystems operating without common-cause coupling. Numerical experiments were carried out on canonical benchmark topologies—bridge, tree, grid, and random connected graphs—representing different levels of structural complexity. The results demonstrate that the SCM achieves exact reliability values with up to six orders of magnitude acceleration compared to the LPM for systems containing more than 20 elements, while maintaining polynomial computational complexity. Qualitatively, the compared approaches differ in the nature of the output and practical applicability: boundary methods provide fast interval estimates suitable for preliminary screening, whereas decomposition may exhibit a systematic bias for highly connected (non-series–parallel) topologies. In contrast, the SCM consistently preserves exactness while remaining computationally tractable for medium and large sparse-to-moderately dense graphs, making it preferable for repeated recalculations in design and optimization workflows. The methods were implemented in Python 3.7 using NumPy and NetworkX, ensuring transparency and reproducibility. The findings confirm that the SCM is an efficient, scalable, and mathematically rigorous tool for reliability assessment and structural optimization of large-scale non-repairable systems. The presented methodology provides practical guidelines for selecting appropriate reliability evaluation techniques based on system complexity and computational resource constraints. Full article

This work presents a novel deep learning workflow for estimating porosity and permeability from combined data, where numerical variables such as high-resolution bulk density (RHOB) and photoelectric factor (PEF) data are integrated with X-ray computed tomography (X-CT) image data, using a dual-energy X-CT approach (DECT). Convolutional neural networks (CNNs) were calibrated with routine core analysis (RCAL) laboratory measurements from one well from Sinú-San Jacinto Basin (Colombia). The CNN architecture combines two main branches: An image branch, in which a CNN extracts spatial features from normalized X-CT sections using 3 × 3 convolution layers, ReLU activation, batch normalization, and maxPooling, and a numerical branch, which processes the input vectors corresponding to RHOB and PEF using fully connected dense layers and dropout regularization. Both branches are concatenated in a fusion layer, from which the model’s final predictions are made. Results indicate a strong correlation between porosity, permeability, RHOB and PEF logs, and CT images. The porosity model achieved excellent predictive performance, with an R² = 0.996, MAE = 3.96 × 10⁻³, MSE = 3.82 × 10⁻⁵, and 0.064 maximum error. The permeability model also performed well, with a linear R² = 0.983, though metrics reflected the wide dynamic range of permeability. Consequently, artificial neural networks (ANNs) can accurately predict porosity and permeability at various depths where no corresponding laboratory data exists, demonstrating excellent predictive capabilities over several rock intervals, in a high vertical resolution because of X-CT data scale (0.625 mm). Full article

Accurate joint estimation of heterogeneous hydraulic conductivity fields and time-varying contaminant source parameters in groundwater systems constitutes a challenging high-dimensional inverse problem, particularly under sparse observational conditions and high computational demands. To alleviate this limitation, this study proposes an autoregressive depthwise convolutional neural network (AR-DWCNN) as a lightweight surrogate model for coupled groundwater flow and contaminant transport simulations. The proposed model employs depthwise separable convolutions and dense connectivity within an encoder–decoder framework to capture nonlinear flow and spatiotemporal transport dynamics while reducing model complexity and computational demand relative to conventional convolutional architectures. The AR-DWCNN is further integrated with an enhanced Iterative Local Updating Ensemble Smoother incorporating Levenberg–Marquardt regularization, enabling efficient joint inversion of high-dimensional hydraulic conductivity fields and multi-period contaminant source strengths. Numerical experiments conducted on a synthetic two-dimensional heterogeneous aquifer demonstrate that the surrogate-assisted inversion framework achieves posterior estimates that closely match those obtained using the numerical forward model, while significantly improving computational efficiency. These results indicate that the AR-DWCNN-based inversion method provides an effective and scalable solution for high-dimensional groundwater contaminant transport inverse problems, offering practical potential for uncertainty quantification and remediation design in complex subsurface systems. Full article

The advancement of hyperspectral image super-resolution (HSI-SR) has been significantly propelled by deep learning techniques. However, current methods predominantly rely on 2D or 3D convolutional networks, which are inherently local and thus limited in modeling long-range spectral–depth interactions. This work introduces a novel network architecture designed to address this gap through recursive deep feature learning. Our model initiates with 3D convolutions to extract preliminary spectral–spatial features, which are progressively refined via densely connected grouped convolutions. A core innovation is a recursively formulated generalized self-attention mechanism, which captures long-range dependencies across the spectral dimension with linear complexity. To reconstruct fine spatial details across multiple scales, a progressive upsampling strategy is further incorporated. Evaluations on several public benchmarks demonstrate that the proposed approach outperforms existing state-of-the-art methods in both quantitative metrics and visual quality. Full article

Recognizing handwritten Arabic characters written by children via scanned or camera-captured images is a challenging task due to variations in writing style, stroke irregularity, and diacritical marks. Although deep learning has advanced this field, building reliable systems remains challenging. This study introduces a stacking ensemble framework for sensor-acquired handwriting data, enhanced with a dynamic confidence-thresholding mechanism designed to improve prediction reliability. The framework integrates three high-performing convolutional neural networks (ConvNeXtBase, DenseNet201, and VGG16) through a fully connected meta-learner. A key feature is the use of an optimized threshold that filters out uncertain predictions by maximizing the macro ${\mathrm{F}}_1$ score on validation data. The framework is evaluated on two benchmark datasets for children’s Arabic handwriting: Hijja and Dhad. The results demonstrate state-of-the-art performance, with an accuracy of $95.13\%$ and ${\mathrm{F}}_1$ score of $94.62\%$ on Hijja and an accuracy of $96.14\%$ and ${\mathrm{F}}_1$ score of $95.59\%$ on Dhad. Compared to existing methods, the proposed approach achieves more than a $3\%$ improvement in Hijja accuracy while maintaining robust performance across diverse character classes. These findings highlight the effectiveness of confidence-based stacking ensembles in enhancing reliability for Arabic handwriting recognition and suggest strong potential for automated educational assessment tools and intelligent tutoring systems. Full article

With the rapid improvement of deep learning, significant progress has been made in cloud removal for remote sensing images (RSIs). However, the practical deployment of existing methods on multi-platform devices faces several limitations, including high computational complexity preventing real-time processing, substantial hardware resource demands that are unsuitable for edge devices, and inadequate performance in complex cloud scenarios. To address these challenges, we propose PMSAF-Net, a lightweight Progressive Multi-Scale Asymmetric Fusion Network designed for efficient thin cloud removal. The proposed network employs a Dual-Branch Asymmetric Attention (DBAA) module to optimize spatial details and channel dependencies, reducing computation cost while improving feature extraction. A Multi-Scale Context Aggregation (MSCA) mechanism captures multi-level contextual information through hierarchical dilated convolutions, effectively handling clouds of varying scales and complexities. A Refined Residual Block (RRB) minimizes boundary artifacts through reflection padding and residual calibration. Additionally, an Iterative Feature Refinement (IFR) module progressively enhances feature representations via dense cross-stage connections. Extensive experimental multi-platform datasets results show that the proposed method achieves favorable performance against state-of-the-art algorithms. With only 0.32 M parameters, PMSAF-Net maintains low computational costs, demonstrating its strong potential for multi-platform deployment on resource-constrained edge devices. Full article

Fault diagnosis in axial piston pumps is key to ensuring the proper operation of a hydraulic system. Slipper wear, as a typical fault in piston pumps, is challenging to accurately diagnose because the faults are very similar for different forms and degrees of wear. The achievement of accurate fault diagnosis of different forms and degrees of wear in the slipper will greatly improve the reliability of axial piston pump operation and, at the same time, provide new ideas for research into similar fault diagnosis problems in other rotating machinery. Therefore, a method of fault diagnosis based on the following symmetric dot pattern (SDP) and multi-channel densely connected convolutional networks (DenseNet) is proposed in this paper. The method applies an SDP transformation to transform the slipper failure signal into an SDP image, which achieves the fusion of triaxial vibration signals and enriches the signal features. The inception module is improved by replacing the original structure with larger convolutional kernels in multiple branches and decomposing the larger convolutional kernels. The inception module, the convolutional block attention module (CBAM), and the DropBlock method are introduced into DenseNet to improve feature extraction capability, computational efficiency, and model generalization ability. Experiments are performed on several slipper wear fault SDP image datasets, and all the indices produced by the proposed method are higher than those of the traditional convolutional neural networks, which fully proves the effectiveness and superiority of the procedure. Full article

This paper provides an overview of artificial intelligence (AI) applications in ophthalmology, with a focus on diagnosing dry eye disease (DED). We aim to synthesize studies that explicitly compare AI-based diagnostic models with clinical tests employed by ophthalmologists, examine results obtained using similar imaging modalities, and identify recurring limitations to propose recommendations for future work. We conducted a systematic literature search following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines across four databases: Google Scholar, PubMed, ScienceDirect, and the Cochrane Library. We targeted studies published between 2020 and 2025 and applied predefined inclusion criteria to select 30 original peer-reviewed articles. We then analyzed each study based on the AI models used, development strategies, diagnostic performance, correlation with clinical parameters, and reported limitations. The imaging modalities covered include videokeratography, smartphone-based imaging, tear film interferometry, anterior segment optical coherence tomography, infrared meibography, in vivo confocal microscopy, and slit-lamp photography. Across modalities, deep learning models (e.g., U-shaped Convolutional Network (U-Net), Residual Network (ResNet), Densely Connected Convolutional Network (DenseNet), Generative Adversarial Networks (GANs), transformers) demonstrated promising performance, often matching or surpassing clinical assessments, with reported accuracies ranging from 82% to 99%. However, few studies performed external validations or addressed inter-expert variability. The findings confirm AI’s potential in DED diagnosis, but emphasize gaps in data diversity, clinical use, and reproducibility. It offers practical recommendations for future research to bridge these gaps and support AI deployment in routine eye care. Full article

Rice diseases pose a critical threat to global food security. While deep learning offers a promising path toward automated diagnosis, clear guidelines for model selection in resource-constrained agricultural environments are still lacking. This study presents a systematic benchmark of five deep convolutional neural networks (CNNs)—Visual Geometry Group (VGG)16, VGG19, Residual Network (ResNet)101V2, Xception, and Densely Connected Convolutional Network (DenseNet)121—for rice disease identification using a public leaf image dataset. The models, initialized with ImageNet pre-trained weights, were rigorously evaluated under a unified framework, including 5-fold cross-validation and a challenging out-of-distribution (OOD) generalization test. Our results demonstrate a clear performance hierarchy, with DenseNet121 emerging as the superior model. It achieved the highest OOD accuracy and F1-score (both 85.08%) while exhibiting the greatest parameter efficiency (8.1 million parameters), making it ideally suited for edge deployment. In contrast, architectures with large fully connected layers (VGG) or less efficient feature learning mechanisms (Xception, ResNet101V2) showed lower performance in this specific task. This study confirms the critical impact of architectural design choices, provides a reproducible performance baseline, and identifies DenseNet121 as a robust, efficient, and highly recommendable CNN for practical rice disease diagnosis in precision agriculture. Full article

Activation functions are fundamental to the representational capacity and optimization dynamics of deep neural networks. Although numerous nonlinearities have been proposed, ranging from classical sigmoid and tanh to modern smooth and trainable functions, no single activation is universally optimal, as each involves trade-offs among gradient flow, stability, computational cost, and expressiveness. This study introduces TRex, a novel activation function that combines the efficiency and linear growth of rectified units with the smooth gradient propagation of saturating functions. TRex features a non-zero, smoothed negative region inspired by tanh while maintaining near-linear behavior for positive inputs, preserving gradients and reducing neuron inactivation. We evaluate TRex against five widely used activation functions (ReLU, ELU, Swish, Mish, and GELU) across eight convolutional architectures (AlexNet, DenseNet-121, EfficientNet-B0, GoogLeNet, LeNet, MobileNet-V2, ResNet-18, and VGGNet) on two benchmark datasets (MNIST and Fashion-MNIST) and a real-world medical imaging dataset (SkinCancer). The results show that TRex achieves competitive accuracy, AUC, and convergence stability across most deep, connectivity-rich architectures while maintaining computational efficiency comparable to those of other smooth activations. These findings highlight TRex as a contextually efficient activation function that enhances gradient flow, generalization, and training stability, particularly in deeper or densely connected architectures, while offering comparable performance in lightweight and mobile-optimized models. Full article

Detecting corroded metal fittings in UAV-based transmission line inspections is challenging due to the small object size and environmental interference, causing high false and missed detection rates. To address these, this paper proposes a novel knowledge-distilled lightweight YOLO model, integrating a densely-connected convolutional network and spatial pixel-aware self-attention mechanism in the teacher model training stage to enhance feature transfer and structured feature utilization for reducing environmental interference, while employing the lightweight MobileNet as the feature extractor in the student model training stage and optimizing candidate box migration via the teacher model’s efficient intersection-over-union non-maximum suppression (EIoU-NMS). This model overcomes the challenges of small-object fitting detection in complex environments, improving fault identification accuracy and reducing manual inspection costs and missed detection risks, while its lightweight design enables rapid deployment and real-time detection on UAV terminals, providing a reliable technical solution for unmanned smart grid operation. Experimental results on actual UAV inspection images demonstrate that the model significantly enhances detection accuracy, reduces false and missed detections, and achieves faster speeds with substantially fewer parameters, highlighting its outstanding effectiveness and practicality in power system maintenance scenarios. Full article