Search Results (373)

Infrared small-target detection remains a critical challenge in military reconnaissance, environmental monitoring, forest-fire prevention, and search-and-rescue operations, owing to the targets’ extremely small size, sparse texture, low signal-to-noise ratio, and complex background interference. Traditional convolutional neural networks (CNNs) struggle to detect such weak, low-contrast objects due to their limited receptive fields and insufficient feature extraction capabilities. To overcome these limitations, we propose a Multi-Scale Edge-Aware Convolution (MEAC) module that enhances feature representation for small infrared targets without increasing parameter count or computational cost. Specifically, MEAC fuses (1) original local features, (2) multi-scale context captured via dilated convolutions, and (3) high-contrast edge cues derived from differential Gaussian filters. After fusing these branches, channel and spatial attention mechanisms are applied to adaptively emphasize critical regions, further improving feature discrimination. The MEAC module is fully compatible with standard convolutional layers and can be seamlessly embedded into various network architectures. Extensive experiments on three public infrared small-target datasets (SIRSTD-UAVB, IRSTDv1, and IRSTD-1K) demonstrate that networks augmented with MEAC significantly outperform baseline models using standard convolutions. When compared to eleven mainstream convolution modules (ACmix, AKConv, DRConv, DSConv, LSKConv, MixConv, PConv, ODConv, GConv, and Involution), our method consistently achieves the highest detection accuracy and robustness. Experiments conducted across multiple versions, including YOLOv10, YOLOv11, and YOLOv12, as well as various network levels, demonstrate that the MEAC module achieves stable improvements in performance metrics while slightly increasing computational and parameter complexity. These results validate the MEAC module’s significant advantages in enhancing the detection of small and weak objects and suppressing interference from complex backgrounds. These results validate MEAC’s effectiveness in enhancing weak small-target detection and suppressing complex background noise, highlighting its strong generalization ability and practical application potential. Full article

Crack detection in complex pavement scenarios remains challenging due to the sparse small-target features and computational inefficiency of existing methods. To address these limitations, this study proposes an enhanced architecture based on Mask2Former. The framework integrates two key innovations. A Local Perception Module (LPM) reconstructs geometric topological relationships through a Sequence-Space Dynamic Transformation Mechanism (DS2M), enhancing neighborhood feature extraction via depthwise separable convolutions. Simultaneously, an Auxiliary Convolutional Layer (ACL) combines lightweight residual convolutions with shallow high-resolution features, preserving critical edge details through channel attention weighting. Experimental evaluations demonstrate the model’s superior performance, achieving improvements of 3.2% in mIoU and 2.7% in mAcc compared to baseline methods, while maintaining computational efficiency with only 12.8 GFLOPs. These results validate the effectiveness of geometric relationship modeling and hierarchical feature fusion for pavement crack detection, suggesting practical potential for infrastructure maintenance systems. The proposed approach balances precision and efficiency, offering a viable solution for real-world applications with complex crack patterns and hardware constraints. Full article

High-resolution ISAR (Inverse Synthetic Aperture Radar) imaging plays a crucial role in dynamic target monitoring for aerospace, maritime, and ground surveillance. Among various remote sensing techniques, ISAR is distinguished by its ability to produce high-resolution images of non-cooperative maneuvering targets. To meet the increasing demands for resolution and robustness, modern ISAR systems are evolving toward wideband and multi-channel architectures. In particular, multi-channel configurations based on large-scale receiving arrays have gained significant attention. In such systems, each receiving element functions as an independent spatial channel, acquiring observations from distinct perspectives. These multi-angle measurements enrich the available echo information and enhance the robustness of target imaging. However, this setup also brings significant challenges, including inter-channel coupling, high-dimensional joint signal modeling, and non-Gaussian, mixed-mode interference, which often degrade image quality and hinder reconstruction performance. To address these issues, this paper proposes a Hybrid Variational Bayesian Multi-Interference (HVB-MI) imaging algorithm based on a hierarchical Bayesian framework. The method jointly models temporal correlations and inter-channel structure, introducing a coupled processing strategy to reduce dimensionality and computational complexity. To handle complex noise environments, a Gaussian mixture model (GMM) is used to represent nonstationary mixed noise. A variational Bayesian inference (VBI) approach is developed for efficient parameter estimation and robust image recovery. Experimental results on both simulated and real-measured data demonstrate that the proposed method achieves significantly improved image resolution and noise robustness compared with existing approaches, particularly under conditions of sparse sampling or strong interference. Quantitative evaluation further shows that under the continuous sparse mode with a 75% sampling rate, the proposed method achieves a significantly higher Laplacian Variance (LV), outperforming PCSBL and CPESBL by 61.7% and 28.9%, respectively and thereby demonstrating its superior ability to preserve fine image details. Full article

Traditional antenna arrays for direction-of-arrival (DOA) estimation typically require numerous elements to achieve target performance, increasing system complexity and cost. Reconfigurable intelligent surfaces (RISs) offer a promising alternative, yet their performance critically depends on phase coding design. To address this, we propose a phase coding design method for RIS-aided DOA estimation with a single receiving channel. First, we establish a system model where averaged received signals construct a power-based formulation. This transforms DOA estimation into a compressed sensing-based sparse recovery problem, with the RIS far-field power radiation pattern serving as the measurement matrix. Then, we derive the decoupled expression of the measurement matrix, which consists of the phase coding matrix, propagation phase shifts, and array steering matrix. The phase coding design is then formulated as a Frobenius norm minimization problem, approximating the Gram matrix of the equivalent measurement matrix to an identity matrix. Accordingly, the phase coding design problem is reformulated as a Frobenius norm minimization problem, where the Gram matrix of the equivalent measurement matrix is approximated to an identity matrix. The phase coding is deterministically constructed as the product of a unitary matrix and a partial Hadamard matrix. Simulations demonstrate that the proposed phase coding design outperforms random phase coding in terms of angular estimation accuracy, resolution probability, and the requirement of coding sequences. Full article

Wallboard outsourcing is a critical task in cloud-based manufacturing, where demand enterprises seek suitable suppliers for machining services through online platforms. However, the recommendation process faces significant challenges, including sparse rating data, unstructured textual descriptions from suppliers, and complex, non-linear user preferences. To address these issues, this paper proposes AttVAE-PMF, a novel recommendation method based on dual-channel neural networks and probabilistic matrix factorization. Specifically, an attention-enhanced long short-term memory (LSTM) is employed to extract semantic features from free-text supplier descriptions, while a variational autoencoder (VAE) is used to model latent preferences from sparse demand-side ratings. These two types of latent representations are then fused via probabilistic matrix factorization (PMF) to complete the rating matrix and infer enterprise preferences. Experiments conducted on both the wallboard dataset and the MovieLens-100K dataset demonstrate that AttVAE-PMF outperforms baseline methods—including PMF, DLCRS, and SSAERec—in terms of convergence speed and robustness to data sparsity, validating its effectiveness in handling sparse and heterogeneous information in wallboard outsourcing recommendation scenarios. Full article

Multi-source remote sensing spatiotemporal fusion aims to enhance the temporal continuity of high-spatial, low-temporal-resolution images. In recent years, deep learning-based spatiotemporal fusion methods have achieved significant progress in this field. However, existing methods face three major challenges. First, large differences in spatial resolution among heterogeneous remote sensing images hinder the reconstruction of high-quality texture details. Second, most current deep learning-based methods prioritize spatial information while overlooking spectral information. Third, these methods often depend on complex network architectures, resulting in high computational costs. To address the aforementioned challenges, this article proposes a Sparse Fast Transformer fusion method based on Generative Adversarial Network (SFT-GAN). First, the method introduces a multi-scale feature extraction and fusion architecture to capture temporal variation features and spatial detail features across multiple scales. A channel attention mechanism is subsequently designed to integrate these heterogeneous features adaptively. Secondly, two information compensation modules are introduced: detail compensation module, which enhances high-frequency information to improve the fidelity of spatial details; spectral compensation module, which improves spectral fidelity by leveraging the intrinsic spectral correlation of the image. In addition, the proposed sparse fast transformer significantly reduces both the computational and memory complexity of the method. Experimental results on four publicly available benchmark datasets showed that the proposed SFT-GAN achieved the best performance compared with state-of-the-art methods in fusion accuracy while reducing computational cost by approximately 70%. Additional classification experiments further validated the practical effectiveness of SFT-GAN. Overall, this approach presents a new paradigm for balancing accuracy and efficiency in spatiotemporal fusion. Full article

Millimeter-wave (mmWave) MIMO systems have emerged as a key enabling technology for next-generation wireless networks, addressing the growing demand for ultra-high data rates through the utilization of wide bandwidths and large-scale antenna configurations. Beyond communication capabilities, these systems offer inherent advantages for integrated sensing applications, particularly in scenarios requiring precise object detection and localization. The sparse mmWave channel in the beamspace domain allows fewer radio-frequency (RF) chains by selecting dominant beams, boosting both communication efficiency and sensing resolution. However, existing channel estimation methods, such as learned approximate message passing (LAMP) networks, rely on computationally intensive iterations. This becomes particularly problematic in large-scale system deployments, where estimation inaccuracies can severely degrade sensing performance. To address these limitations, we propose a low-complexity channel estimator using a non-iterative reconstruction network (NIRNet) with a learning-based selection matrix (LSM). NIRNet employs a convolutional layer for efficient, non-iterative beamspace channel reconstruction, significantly reducing computational overhead compared to LAMP-based methods, which is vital for real-time sensing. The LSM generates a signal-aware Gaussian measurement matrix, outperforming traditional Bernoulli matrices, while a denoising network enhances accuracy under low SNR conditions, improving sensing resolution. Simulations show the NIRNet-based algorithm achieves a superior normalized mean squared error (NMSE) and an achievable sum rate (ASR) with lower complexity and reduced training overhead. Full article

LiDAR point clouds, as direct carriers of 3D spatial information, comprehensively record the geometric features and spatial topological relationships of object surfaces, providing intelligent systems with rich 3D scene representation capability. However, current point cloud semantic segmentation methods primarily extract features through operations such as convolution and pooling, yet fail to adequately consider sparse features that significantly influence the final results of point cloud-based scene perception, resulting in insufficient feature representation capability. To address these problems, a sparse feature dynamic graph convolutional neural network, abbreviated as SFDGNet, is constructed in this paper for LiDAR point clouds of complex scenes. In the context of this paper, sparse features refer to feature representations in which only a small number of activation units or channels exhibit significant responses during the forward pass of the model. First, a sparse feature regularization method was used to motivate the network model to learn the sparsified feature weight matrix. Next, a split edge convolution module, abbreviated as SEConv, was designed to extract the local features of the point cloud from multiple neighborhoods by dividing the input feature channels, and to effectively learn sparse features to avoid feature redundancy. Finally, a multi-neighborhood feature fusion strategy was developed that combines the attention mechanism to fuse the local features of different neighborhoods and obtain global features with fine-grained information. Taking S3DIS and ScanNet v2 datasets, we evaluated the feasibility and effectiveness of SFDGNet by comparing it with six typical semantic segmentation models. Compared with the benchmark model DGCNN, SFDGNet improved overall accuracy $\left(OA\right)$, mean accuracy $\left(mAcc\right)$, mean intersection over union $\left(mIoU\right)$, and $sparsity$ by $1.8\%$, $3.7\%, 3.5\%$, and $85.5\%$ on the S3DIS dataset, respectively. The $mIoU$ on the ScanNet v2 validation set, $mIoU$ on the test set, and $sparsity$ were improved by $3.2\%, 7.0\%$, and $54.5\%$, respectively. Full article

Reconfigurable Intelligent Surfaces (RISs) are among the key technologies envisaged for sixth-generation (6G) multiple-input multiple-output (MIMO)–orthogonal frequency division multiplexing (OFDM) wireless systems. However, their passive nature and the frequent absence of a line-of-sight (LoS) path in dense urban environments make uplink channel estimation and localization challenging tasks. Therefore, to achieve channel estimation and localization, this study models the RIS-mobile station (MS) channel as a double-sparse angular structure and proposes a hybrid channel parameter estimation framework for RIS-assisted MIMO-OFDM systems. In the hybrid framework, Simultaneous Orthogonal Matching Pursuit (SOMP) first estimates coarse angular supports. The coarse estimates are refined by a novel refinement stage employing a Variational Bayesian Expectation Maximization (VBEM)-based Off-Grid Sparse Bayesian Learning (OG-SBL) algorithm, which jointly updates azimuth and elevation offsets via Newton-style iterations. An Angle of Arrival (AoA)–Angle of Departure (AoD) matching algorithm is introduced to associate angular components, followed by a 3D localization procedure based on non-LoS (NLoS) multipath geometry. Simulation results show that the proposed framework achieves high angular resolution; high localization accuracy, with 97% of the results within 0.01 m; and a channel estimation error of 0.0046% at 40 dB signal-to-noise ratio (SNR). Full article

Infrared small target detection (IRSTD) aims to locate and separate targets from complex backgrounds. The challenges in IRSTD primarily come from extremely sparse target features and strong background clutter interference. However, existing methods typically perform discrimination directly on the features extracted by deep networks, neglecting the distinct characteristics of weak and small targets in the frequency domain, thereby limiting the improvement of detection capability. In this paper, we propose a frequency-aware masked-attention network (FM-Net) that leverages multi-scale frequency clues to assist in representing global context and suppressing noise interference. Specifically, we design the wavelet residual block (WRB) to extract multi-scale spatial and frequency features, which introduces a wavelet pyramid as the intermediate layer of the residual block. Then, to perceive global information on the long-range skip connections, a frequency-modulation masked-attention module (FMM) is used to interact with multi-layer features from the encoder. FMM contains two crucial elements: (a) a mask attention (MA) mechanism for injecting broad contextual feature efficiently to promote full-level semantic correlation and focus on salient regions, and (b) a channel-wise frequency modulation module (CFM) for enhancing the most informative frequency components and suppressing useless ones. Extensive experiments on three benchmark datasets (e.g., SIRST, NUDT-SIRST, IRSTD-1k) demonstrate that FM-Net achieves superior detection performance. Full article

With the rise of the Internet of Things (IoT), smart sensors are increasingly being deployed as compact edge processing units, necessitating continuously writable memory with low power consumption and fast access times. Magnetic random-access memory (MRAM) has emerged as a promising non-volatile alternative to conventional DRAM and SDRAM, offering advantages such as faster access speeds, reduced power consumption, and enhanced endurance. However, MRAM is subject to challenges including process variations and thermal fluctuations, which can induce random bit errors and result in imbalanced probabilities of 0 and 1 bits. To address these issues, we propose a novel sparse coding scheme characterized by a minimum Hamming distance of three. During the encoding process, three check bits are appended to the user data and processed using a generator matrix. If the resulting codeword fails to satisfy the sparsity constraint, it is inverted to comply with the coding requirement. This method is based on the error characteristics inherent in MRAM to facilitate effective error correction. Furthermore, we introduce a dynamic threshold detection technique that updates bit probability estimates in real time during data transmission. Simulation results demonstrate substantial improvements in both error resilience and decoding accuracy, particularly as MRAM density increases. Full article

In multi-vehicle traffic scenarios, achieving accurate environmental perception and motion trajectory tracking through LiDAR–camera fusion is critical for downstream vehicle planning and control tasks. To address the challenges of cross-modal feature interaction in LiDAR–image fusion and the low recognition efficiency/positioning accuracy of traffic participants in dense traffic flows, this study proposes an attention-based 3D object detection network integrating point cloud and image features. The algorithm adaptively fuses LiDAR geometric features and camera semantic features through channel-wise attention weighting, enhancing multi-modal feature representation by dynamically prioritizing informative channels. A center point detection architecture is further employed to regress 3D bounding boxes in bird’s-eye-view space, effectively resolving orientation ambiguities caused by sparse point distributions. Experimental validation on the nuScenes dataset demonstrates the model’s robustness in complex scenarios, achieving a mean Average Precision (mAP) of 64.5% and a 12.2% improvement over baseline methods. Real-vehicle deployment further confirms the fusion module’s effectiveness in enhancing detection stability under dynamic traffic conditions. Full article

Hypertension disorders of pregnancy affect almost 10% of pregnancies. Most hypertensive disorders associated with pregnancy, including chronic hypertension and gestational hypertension, often persist into the postpartum period. Thus, many breastfeeding mothers require ongoing antihypertensive treatment with antihypertensive medications while nursing. This highlights the importance of understanding the efficacy, safety, and potential adverse effects of antihypertensive therapy in breastfeeding mothers. Unfortunately, research in this area is limited, and references in clinical guidelines remain sparse. Our review aims to provide a comprehensive summary of the current knowledge on antihypertensive medications during breastfeeding, drawing from available research and evidence-based guidelines. This article discusses all groups of antihypertensive drugs, presenting societies’ recommendations and available clinical data. Based on the available literature, calcium channel blockers (extended-release nifedipine as the first choice) and beta-blockers (labetalol, metoprolol) appear to be the drugs of choice. Our review highlights the need for further research to evaluate the long-term safety of antihypertensive medications during breastfeeding, improve clinical guidelines, and ensure optimal treatment for nursing mothers. Full article

To address the challenges in predicting roof water hazards in weakly cemented strata of Northwest China, this study pioneers an integrated CNN-BiLSTM model for aquifer water abundance prediction. Focusing on the 1301E working face in the Yili No. 1 Coal Mine, we employed kriging interpolation to process sparse hydrological datasets (mean relative error: 8.7%), identifying five dominant controlling factors—aquifer burial depth, hydraulic conductivity, core recovery rate, sandstone–mudstone interbedded layer count, and sandstone equivalent thickness. The proposed bidirectional architecture synergizes CNN-based spatial feature extraction with BiLSTM-driven nonlinear temporal modeling, optimized via Bayesian algorithms to determine hyperparameters (32-channel convolutional kernels and 64-unit BiLSTM hidden layers). This framework achieves the comprehensive characterization of multifactorial synergistic effects. The experimental results demonstrate: (1) that the test set root mean square error (1.57 × 10⁻³) shows 65.3% and 85.9% reductions compared to the GA-BP and standalone CNN models, respectively; (2) that the coefficient of determination (R² = 0.9966) significantly outperforms the conventional fuzzy analytic hierarchy process (FAHP, error: 0.071 L/(s·m)) and BP-based neural networks; (3) that water abundance zoning reveals predominantly weak water-rich zones (q = 0.05–0.1 L/(s·m)), with 93.3% spatial consistency between predictions and pumping test data. Full article

Renewable energy (RE) is pivotal to achieving both environmental sustainability and long-term energy security, yet systematic evidence on the efficiency of RE investment across South and Southeast Asia remains sparse. This study introduces a rejoice–regret utility cross-efficiency DEA (RRUCE-DEA) framework that fuses conventional quantitative efficiency measurement with the behavioral insights of regret theory. Applying the model to 16 countries shows India as the benchmark for efficient RE investment allocation, followed closely by Pakistan and Indonesia. The Philippines, Malaysia, and Vietnam also post strong results, whereas Sri Lanka and Thailand reveal moderate performance with clear room for improvement. At the lower end of the spectrum, Cambodia, Myanmar, and Afghanistan encounter significant hurdles that must be overcome to achieve a successful clean energy transition. A sensitivity analysis further explores how variations in the regret aversion and rejoice–regret coefficients affect the RRUCE-DEA outcomes. The findings provide actionable guidance for policymakers and investors seeking to channel resources toward a cleaner, more sustainable regional energy portfolio. Full article