Search Results (5,943)

This paper proposes a novel heart rate detection scheme to address key challenges in millimeter-wave radar-based vital sign monitoring, including weak signals, various types of interference, and the demand for high-precision and super-resolution frequency estimation under practical computational constraints. First, we propose a multi-dimensional coherent accumulation (MDCA) method to enhance the signal-to-noise ratio (SNR) by fully utilizing both spatial information from multiple receiving channels and temporal information from adjacent range bins. Additionally, we are the first to apply the fast iterative interpolated beamforming (FIIB) algorithm to radar-based heart rate detection, enabling super-resolution frequency estimation with low computational complexity. Compared to the traditional fast Fourier transform (FFT) method, the FIIB achieves an improvement of 1.08 beats per minute (bpm). A reordering strategy is also introduced to mitigate potential misjudgments by FIIB. Key parameters of FIIB, including the number of frequency components L and the number of iterations Q, are analyzed and recommended. Dozens of subjects were recruited for experiments, and the root mean square error (RMSE) of heart rate estimation was less than 1.12 bpm on average at a distance of 1 meter. Extensive experiments validate the high accuracy and robust performance of the proposed framework in heart rate estimation. Full article

Clouds are closely related to precipitation, as their type, microphysical characteristics, and dynamic properties determine the intensity, duration, and form of rainfall. While geostationary satellites offer continuous cloud-top observations, they cannot capture the full three-dimensional structure of clouds, limiting the accuracy of precipitation forecasting based on geostationary satellite data. However, cloud–precipitation relationships contain valuable physical information that can be leveraged to improve forecasting performance. To further enhance the precision of satellite precipitation forecasting, this study proposes a multi-channel satellite precipitation forecasting method that integrates cloud classification products. The method combines precipitation-prior information from Himawari-8 satellite cloud classification products with multi-channel satellite observations to generate precipitation forecasts for the next four hours. This approach further exploits the potential of satellite observations in precipitation forecasting. Experimental results show that integrating cloud classification products improves the Critical Success Index by 8.0%, improves the Correlation Coefficient by 5.8%, and reduces the Mean Squared Error by 3.0%, but increases the MAE by 4.5%. It is proven that this method can effectively improve the accuracy of multi-channel satellite precipitation forecasting. Full article

Localizing ground-penetrating radar (LGPR) benefits from deep subsurface coupling, ensuring robustness against surface variations and adverse weather. While LGPR is widely recognized as the complement of existing vehicle localization methods, its reliance on prior maps introduces significant challenges. Channel misalignment during traversal positioning and time-dimension distortion caused by non-uniform platform motion degrade matching accuracy. Furthermore, rain and snow conditions induce subsurface water-content variations that distort ground-penetrating radar (GPR) echoes, further complicating the localization process. To address these issues, we propose a weather-resilient adaptive spatio-temporal mask alignment algorithm for LGPR. The method employs adaptive alignment and dynamic time warping (DTW) strategies to sequentially resolve channel and time-dimension misalignments in GPR sequences, followed by calibration of GPR query sequences. Moreover, a multi-level discrete wavelet transform (MDWT) module enhances low-frequency GPR features while adaptive alignment along the channel dimension refines the signals and significantly improves localization accuracy under rain or snow. Additionally, a local matching DTW algorithm is introduced to perform robust temporal image-sequence alignment. Extensive experiments were conducted on both public LGPR datasets: GROUNDED and self-collected data covering five challenging scenarios. The results demonstrate superior localization accuracy and robustness compared to existing methods. Full article

Skeletal muscle, constituting ~40% of body mass, serves as a primary effector for movement and a key metabolic regulator through myokine secretion. Hereditary myopathies, including dystrophinopathies (DMD/BMD), limb–girdle muscular dystrophies (LGMD), and metabolic disorders like Pompe disease, arise from pathogenic mutations in structural, metabolic, or ion channel genes, leading to progressive weakness and multi-organ dysfunction. Gene therapy has emerged as a transformative strategy, leveraging viral and non-viral vectors to deliver therapeutic nucleic acids. Adeno-associated virus (AAV) vectors dominate clinical applications due to their efficient transduction of post-mitotic myofibers and sustained transgene expression. Innovations in AAV engineering, such as capsid modification (chemical conjugation, rational design, directed evolution), self-complementary genomes, and tissue-specific promoters (e.g., MHCK7), enhance muscle tropism while mitigating immunogenicity and off-target effects. Non-viral vectors (liposomes, polymers, exosomes) offer advantages in cargo capacity (delivering full-length dystrophin), biocompatibility, and scalable production but face challenges in transduction efficiency and endosomal escape. Clinically, AAV-based therapies (e.g., Elevidys^® for DMD, Zolgensma^® for SMA) demonstrate functional improvements, though immune responses and hepatotoxicity remain concerns. Future directions focus on AI-driven vector design, hybrid systems (AAV–exosomes), and standardized manufacturing to achieve “single-dose, lifelong cure” paradigms for muscular disorders. Full article

In cognitive radio networks (CRNs), primary users (PUs) have the highest priority in channel resource allocation. Secondary users (SUs) can generally only utilize temporarily unused channels of PUs, share channels with PUs, or cooperate with PUs to gain priority through the interweave, underlay, and overlay modes. Traditional optimization schemes for channel resource allocation often lead to structural wastage of channel resources, whereas approaches such as reinforcement learning—though effective—require high computational power and thus exhibit poor adaptability in industrial deployments. Moreover, existing works typically optimize a single performance metric with limited scenario scalability. To address these limitations, this paper proposes a CR network algorithm based on the hybrid users (HU) concept, which links the Interweave and Underlay modes through an adaptive threshold for mode switching. The algorithm employs the Hungarian method for SU channel allocation and applies a multi-level power adjustment strategy when PUs and SUs share the same channel to maximize channel resource utilization. Simulation results under various parameter settings show that the proposed algorithm improves the average signal to interference plus noise ratio (SINR) of SUs while ensuring PU service quality, significantly enhances network energy efficiency, and markedly improves Jain’s fairness among SUs in low-power scenarios. Full article

To address the issues of false detections and missed detections in object detection for intelligent driving scenarios, this study focuses on optimizing the YOLOv10 algorithm to reduce model complexity while enhancing detection accuracy. The method involves three key improvements. First, it involves the design of multi-scale flexible convolution (MSFC), which can capture multi-scale information simultaneously, thereby reducing network stacking and computational load. Second, it reconstructs the neck network structure by incorporating Shallow Auxiliary Fusion (SAF) and Advanced Auxiliary Fusion (AAF), enabling better capture of multi-scale features of objects. Third, it improves the detection head through the combination of multi-scale convolution and channel adaptive attention mechanism, enhancing the diversity and accuracy of feature extraction. Results show that the improved YOLOv10 model has a size of 13.4 MB, meaning a reduction of 11.8%, and that the detection accuracy mAP@0.5 reaches 93.0%, outperforming mainstream models in comprehensive performance. This work provides a detection framework for intelligent driving scenarios, balancing accuracy and model size. Full article

The male flower of the maize plant, known as the tassel, is a strong indicator of the growth, development, and reproductive stages of maize crops. Monitoring maize tassels under natural conditions is significant for maize breeding, management, and yield estimation. Unmanned aerial vehicle (UAV) remote sensing combined with deep learning-based semantic segmentation offers a novel approach for monitoring maize tassel phenotypic traits. The morphological and size variations in maize tassels, together with numerous similar interference factors in the farmland environment (such as leaf veins, female ears, etc.), pose significant challenges to the accurate segmentation of tassels. To address these challenges, we propose DECC-Net, a novel segmentation model designed to accurately extract maize tassels from complex farmland environments. DECC-Net integrates the Dynamic Kernel Feature Extraction (DKE) module to comprehensively capture semantic features of tassels, along with the Lightweight Channel Cross Transformer (LCCT) and Adaptive Feature Channel Enhancement (AFE) modules to guide effective fusion of multi-stage encoder features while mitigating semantic gaps. Experimental results demonstrate that DECC-Net achieves advanced performance, with IoU and Dice scores of 83.3% and 90.9%, respectively, outperforming existing segmentation models while exhibiting robust generalization across diverse scenarios. This work provides valuable insights for maize varietal selection, yield estimation, and field management operations. Full article

Accurate detection of tomato fruits is a critical component in vision-guided robotic harvesting systems, which play an increasingly important role in automated agriculture. However, this task is challenged by variable lighting conditions and background clutter in natural environments. In addition, the arbitrary orientations of fruits reduce the effectiveness of traditional horizontal bounding boxes. To address these challenges, we propose a novel object detection framework named SN-YOLO. First, we introduce the StarNet’ backbone to enhance the extraction of fine-grained features, thereby improving the detection performance in cluttered backgrounds. Second, we design a Color-Prior Spatial-Channel Attention (CPSCA) module that incorporates red-channel priors to strengthen the model’s focus on salient fruit regions. Third, we implement a multi-level attention fusion strategy to promote effective feature integration across different layers, enhancing background suppression and object discrimination. Furthermore, oriented bounding boxes improve localization precision by better aligning with the actual fruit shapes and poses. Experiments conducted on a custom tomato dataset demonstrate that SN-YOLO outperforms the baseline YOLOv8 OBB, achieving a 1.0% improvement in precision and a 0.8% increase in mAP@0.5. These results confirm the robustness and accuracy of the proposed method under complex field conditions. Overall, SN-YOLO provides a practical and efficient solution for fruit detection in automated harvesting systems, contributing to the deployment of computer vision techniques in smart agriculture. Full article

This paper proposes a co-aperture reflective metasurface that successfully generates four-channel Bessel vortex beams with equal divergence angle in both Ka and Ku bands. Initially, a frequency-selective surface (FSS) is employed to suppress inter-unit crosstalk. Subsequently, modified cross-dipole metasurface units are implemented using spin-decoupling theory to achieve independent multi-polarization control. Through theoretical calculation-based divergence angle engineering, the dual-concentric-disk structure integrated with multi-polarization control demonstrates enhanced aperture utilization efficiency compared to conventional partitioning strategies, yielding high-purity equal-divergence-angle Bessel vortex beams across multiple modes. Finally, experiments on the metasurface fabricated via printed circuit board (PCB) technology verify that the design simultaneously generates x-polarization +1 mode and y-polarization +2 mode equal divergence angle Bessel vortex beams in the Ku band and ±3 mode beams in the Ka band. Vortex beam divergence angles remain stable at 9° ± 0.5° under diverse polarization states and modes, with modal purity reaching 65–80% at the main radiation direction. This work provides a straightforward implementation method for generating equal-divergence-angle vortex beams applicable to Orbital Angular Momentum (OAM) multimode multiplexing and vortex wave detection. Full article

Hyperspectral imagery (HSI) has demonstrated significant potential in remote sensing applications because of its abundant spectral and spatial information. However, current mainstream hyperspectral image classification models are generally characterized by high computational complexity, structural intricacy, and a strong reliance on training samples, which poses challenges in meeting application demands under resource-constrained conditions. To this end, a lightweight hyperspectral image classification model inspired by bionic design, named BioLiteNet, is proposed, aimed at enhancing the model’s overall performance in terms of both accuracy and computational efficiency. The model is composed of two key modules: BeeSenseSelector (Channel Attention Screening) and AffScaleConv (Scale-Adaptive Convolutional Fusion). The former mimics the selective attention mechanism observed in honeybee vision for dynamically selecting critical spectral channels, while the latter enables efficient fusion of spatial and spectral features through multi-scale depthwise separable convolution. On multiple hyperspectral benchmark datasets, BioLiteNet is shown to demonstrate outstanding classification performance while maintaining exceptionally low computational costs. Experimental results show that BioLiteNet can maintain high classification accuracy across different datasets, even when using only a small amount of labeled samples. Specifically, it achieves overall accuracies (OA) of 90.02% ± 0.97%, 88.20% ± 5.26%, and 78.64% ± 7.13% on the Indian Pines, Pavia University, and WHU-Hi-LongKou datasets using just 5% of samples, 10% of samples, and 25 samples per class, respectively. Moreover, BioLiteNet consistently requires fewer computational resources than other comparative models. The results indicate that the lightweight hyperspectral image classification model proposed in this study significantly reduces the requirements for computational resources and storage while ensuring classification accuracy, making it well-suited for remote sensing applications under resource constraints. The experimental results further support these findings by demonstrating its robustness and practicality, thereby offering a novel solution for hyperspectral image classification tasks. Full article

In high-resolution and wide-swath (HRWS) synthetic aperture radar (SAR) imaging, the azimuth multi-channel technique effectively suppresses azimuth ambiguity, serving as a reliable approach for achieving wide-swath imaging. However, due to mechanical vibrations of the platform and airflow instabilities, airborne SAR may experience errors in attitude and flight path during operation. Furthermore, errors also exist in the antenna patterns, frequency stability, and phase noise among the azimuth multi-channels. The presence of these errors can cause azimuth multi-channel reconstruction failure, resulting in azimuth ambiguity and significantly degrading the quality of HRWS images. This article presents a novel error correction method for airborne HRWS SAR based on azimuth-variant attitude and range-variant Doppler domain pattern, which simultaneously considers the effects of various errors, including channel attitude errors and Doppler domain antenna pattern errors, on azimuth reconstruction. Attitude errors are the primary cause of azimuth-variant errors between channels. This article uses the vector method and attitude transformation matrix to calculate and compensate for the attitude errors of azimuth multi-channels, and employs the two-dimensional frequency-domain echo interferometry method to calculate the fixed delay errors and fixed phase errors. To better achieve channel error compensation, this scheme also considers the estimation and compensation of Doppler domain antenna pattern errors in wide-swath scenes. Finally, the effectiveness of the proposed scheme is confirmed through simulations and processing of airborne real data. Full article

In order to solve the problems of modulation signals in low signal-to-noise ratio (SNR), such as poor feature extraction ability, strong dependence on single modal data, and insufficient recognition accuracy, this paper proposes a multi-dimensional feature MFCA-transformer recognition network that integrates phase, frequency and power information. The network uses Triple Dynamic Feature Fusion (TDFF) to fuse constellation, time-frequency, and power spectrum features through the adaptive dynamic mechanism to improve the quality of feature fusion. A Channel Prior Convolutional Attention (CPCA) module is introduced to solve the problem of insufficient information interaction between different channels in multi-dimensional feature recognition tasks, promote information transmission between various feature channels, and enhance the recognition ability of the model for complex features. The label smoothing technique is added to the loss function to reduce the overfitting of the model to the specific label and improve the generalization ability of the model by adjusting the distribution of the real label. Experiments show that the recognition accuracy of the proposed method is significantly improved on the public datasets, at high signal-to-noise ratios, the recognition accuracy can reach 93.2%, which is 3% to 14% higher than those of the existing deep learning recognition methods. Full article

Precoding technology is one of the core technologies that significantly impacts the performance of massive Multiple-Input Multiple-Output (MIMO) Integrated Sensing and Communication (ISAC) systems. Traditional precoding methods, due to their inherent limitations, struggle to adapt to complex channel conditions. Although more advanced neural network-based precoding schemes can accommodate complex channel environments, they suffer from high computational complexity. To address these issues, this paper proposes a KAN-and-Attention based ISAC Precoding (KAIP) scheme for massive MIMO ISAC systems. KAIP extracts channel interference features through multi-layer attention mechanisms and leverages the nonlinear fitting capability of the Kolmogorov–Arnold Network (KAN) to generate precoding matrices, significantly enhancing system performance. Simulation results demonstrate that compared with conventional precoding schemes, the proposed KAIP scheme exhibits significant performance enhancements, including a 70% increase in sum rate (SR) and a 96% decrease in computing time (CT) compared with fully connected neural network (FCNN) based precoding, and a 4% improvement in received power (RP) over the precoding based on convolutional neural network (CNN). Full article

Integrated Sensing And Communication (ISAC) has been applied to the Internet of Things (IoT) network as a promising 6G technology due to its ability to enhance spectrum utilization and reduce resource consumption, making it ideal for high-precision sensing applications. However, while the introduction of millimeter Wave (mmWave) and massive Multiple-Input Multiple-Output (MIMO) technologies can enhance the performance of ISAC systems, they extend the near-field region, rendering traditional channel parameter estimation algorithms ineffective due to the spherical wavefront channel model. Aiming to address the challenge, we propose a tensor-based channel parameter estimation and localization algorithm for the near-field mmWave massive MIMO-Orthogonal Frequency Division Multiplexing (OFDM) ISAC systems. Firstly, the received signal at the User Terminal (UT) is constructed as a third-order tensor to retain the multi-dimensional features of the data. Then, the proposed tensor-based algorithm achieves the channel parameter estimation and target localization by exploiting the second-order Taylor expansion and intrinsic structure of tensor factor matrices. Furthermore, the Cramér–Rao Bounds (CRBs) of channel parameters and position are derived to establish the lower bound of errors. Simulation results show that the proposed tensor-based algorithm is superior compared to the existing algorithms in terms of channel parameter estimation and localization accuracy in ISAC systems for IoT network, achieving errors that approach the CRBs. Specifically, the proposed algorithm attains a 79.8% improvement in UT positioning accuracy compared to suboptimal methods at SNR = 5 dB. Full article

The critical component of the vision transformer (ViT) architecture is multi-head self-attention (MSA), which enables the encoding of long-range dependencies and heterogeneous interactions. However, MSA has two significant limitations: its limited ability to capture local features and its high computational costs. To address these challenges, this paper proposes an integrated multi-head self-attention approach with a bottleneck enhancement structure, named WMSA–WBS, which mitigates the aforementioned shortcomings of conventional MSA. Different from existing wavelet-enhanced ViT variants that mainly focus on the isolated wavelet decomposition in the attention layer, WMSA–WBS introduces a co-design of wavelet-based frequency processing and bottleneck optimization, achieving more efficient and comprehensive feature learning. Within WMSA–WBS, the proposed wavelet multi-head self-attention (WMSA) approach is combined with a novel wavelet bottleneck structure to capture both global and local information across the spatial, frequency, and channel domains. Specifically, this module achieves these capabilities while maintaining low computational complexity and memory consumption. Extensive experiments demonstrate that ViT models equipped with WMSA–WBS achieve superior trade-offs between accuracy and model complexity across various vision tasks, including image classification, object detection, and semantic segmentation. Full article