Search Results (1,155)

With increasingly scarce spectrum resources, frequency-domain signal overlap interference has become a critical issue, making multi-user modulation classification (MUMC) a significant challenge in wireless communications. Unlike single-user modulation classification (SUMC), MUMC suffers from feature degradation caused by signal aliasing, feature redundancy, and low inter-class discriminability. To address these challenges, this paper proposes a collaborative “separation–recognition” framework. The framework begins by separating overlapping signals via a band partitioning and FastICA module to alleviate feature degradation. For the recognition phase, we design a dual-branch network: one branch extracts prior knowledge features, including amplitude, phase, and frequency, from the I/Q sequence and models their temporal dependencies using a bidirectional LSTM; the other branch learns deep hierarchical representations directly from the raw signal through multi-scale convolutional layers. The features from both branches are then adaptively fused using a gated fusion module. Experimental results show that the proposed method achieves superior performance over several baseline models across various signal conditions, validating the efficacy of the dual-branch architecture and the overall framework. Full article

Neural networks are a state-of-the-art technology for fast and accurate holographic image reconstruction. However, at present, neural network-based reconstruction methods are predominantly applied to objects with simple, homogeneous spatial structures: blood cells, bacteria, microparticles in solutions, etc. However, in the case of objects with high contrast details, the reconstruction needs to be as precise as possible to successfully extract details and parameters. In this paper we investigate the use of neural networks in holographic reconstruction of spatially inhomogeneous binary data containers (QR codes). Two modified lightweight convolutional neural networks (which we named HoloLightNet and HoloLightNet-Mini) with an encoder–decoder architecture have been used for image reconstruction. These neural networks enable high-quality reconstruction, guaranteeing the successful decoding of QR codes (both in demonstrated numerical and optical experiments). In addition, they perform reconstruction two orders of magnitude faster than more traditional architectures. In optical experiments with a liquid crystal spatial light modulator, the obtained bit error rate was equal to only 1.2%. These methods can be used for practical applications such as high-density data transmission in coherent systems, development of reliable digital information storage and memory techniques, secure optical information encryption and retrieval, and real-time precise reconstruction of complex objects. Full article

The Electrical Capacitance Tomography (ECT) imaging pipeline relies on accurate estimation of electric field distributions to compute electrode capacitances and reconstruct permittivity maps. Traditional ECT forward model methods based on the Finite Element Method (FEM) offer high accuracy but are computationally intensive, limiting their use in real-time applications. In this proof-of-concept study, we investigate the use of Graph Convolutional Networks (GCNs) for direct, one-step prediction of electric field distributions associated with a circular ECT sensor numerical model. The network is trained on FEM-simulated data and outputs of full 2D electric field maps for all excitation patterns. To evaluate physical fidelity, we compute capacitance matrices using both GCN-predicted and FEM-based fields. Our results show strong agreement in both direct field prediction and derived quantities, demonstrating the feasibility of replacing traditional solvers with fast, learned approximators. This approach has significant implications for further real-time ECT imaging and control applications. Full article

Agricultural management in Europe faces increasing pressure to reduce its environmental footprint. Implementing precision agriculture for weed management could offer a solution and minimize the use of chemical products. High spatial resolution imagery from real time kinematic (RTK) unmanned aerial vehicles (UAV) in combination with supervised convolutional neural network (CNNs) models have proven successful in making location specific treatments. This site-specific advice limits the amount of herbicide applied to the field to areas that require action, thereby reducing the environmental impact and inputs for the farmer. To develop performant CNN models, there is a need for sufficient high-quality labelled data. To reduce the labelling effort and time, a new labelling method is proposed whereby image subsection pairs are labelled based on their relative differences in weed pressure to train a CNN ordinal regression model. The model is evaluated on detecting weed pressure in potato (Solanum tuberosum L.). Model performance was evaluated on different levels: pairwise accuracy, linearity (Pearson correlation coefficient), rank consistency (Spearman’s (r_s) and Kendal (τ) rank correlations coefficients) and binary accuracy. After hyperparameter tuning, a pairwise accuracy of 85.2%, significant linearity (r_s = 0.81) and significant rank consistency (r_s = 0.87 and τ = 0.69) were found. This suggests that the model is capable of correctly detecting the gradient in weed pressure for the dataset. A maximum binary accuracy and F1-score of 92% and 88% were found for the dataset after thresholding the predicted weed scores into weed versus non-weed images. The model architecture allows us to visualize the intermediate features of the last convolutional block. This allows data analysts to better evaluate if the model “sees” the features of interest (in this case weeds). The results indicate the potential of ordinal regression with relative labels as a fast, lightweight model that predicts weed pressure gradients. Experts have the freedom to decide which threshold value(s) can be used on predicted weed scores depending on the weed, crop and treatment that they want to use for flexible weed control management. Full article

Cracks are the initial manifestation of various diseases on highways. Preventive maintenance of cracks can delay the degree of pavement damage and effectively extend the service life of highways. However, existing crack detection methods have poor performance in identifying small cracks and are unable to calculate crack width, leading to unsatisfactory preventive maintenance results. This article proposes an integrated method for crack detection, segmentation, and width calculation based on digital image processing technology. Firstly, based on convolutional neural network, a optimized crack detection network called CFSSE is proposed by fusing the fast spatial pyramid pooling structure with the squeeze-and-excitation attention mechanism, with an average detection accuracy of 97.10%, average recall rate of 98.00%, and average detection precision at 0.5 threshold of 98.90%; it outperforms the YOLOv5-mobileone network and YOLOv5-s network. Secondly, based on the U-Net network, an optimized crack segmentation network called CBU_Net is proposed by using the CNN-block structure in the encoder module and a bicubic interpolation algorithm in the decoder module, with an average segmentation accuracy of 99.10%, average intersection over union of 88.62%, and average pixel accuracy of 93.56%; it outperforms the U_Net network, DeepLab v3+ network, and optimized DeepLab v3 network. Finally, a laser spot center positioning method based on information entropy combination is proposed to provide an accurate benchmark for crack width calculation based on parallel lasers, with an average error in crack width calculation of less than 2.56%. Full article

The temperature of the thermal energy storage unit is a critical parameter for the stable operation of seasonal borehole thermal energy storage (BTES) systems. However, existing temperature prediction models predominantly focus on estimating single-point temperatures or borehole wall temperatures, while lacking effective methods for calculating the average temperature of the storage unit. This limitation hinders accurate assessment of the thermal charging and discharging states. Furthermore, some models involve complex computations and exhibit low operational efficiency, failing to meet the practical engineering demands for rapid prediction and response. To address these challenges, this study first develops a thermal response model for the average temperature of the storage unit based on the finite line source theory and further proposes a simplified engineering algorithm for predicting the storage unit temperature. Subsequently, two-dimensional discrete convolution and Fast Fourier Transform (FFT) techniques are introduced to accelerate the solution of the storage unit temperature distribution. Finally, the model’s accuracy is validated against practical engineering cases. The results indicate that the single-point temperature engineering algorithm yields a maximum relative error of only 0.3%, while the average temperature exhibits a maximum relative error of 1.2%. After employing FFT, the computation time of both single-point and average temperature engineering algorithms over a 10-year simulation period is reduced by more than 90%. When using two-dimensional discrete convolution to calculate the temperature distribution of the storage unit, expanding the input layer from 200 × 200 to 400 × 400 and the convolution kernel from 25 × 25 to 51 × 51 reduces the time required for temperature superposition calculations to approximately 0.14–0.82% of the original time. This substantial improvement in computational efficiency is achieved without compromising accuracy. Full article

Automated Road defect detection using Unmanned Aerial Vehicles (UAVs) has emerged as an efficient and safe solution for large-scale infrastructure inspection. However, object detection in aerial imagery poses unique challenges, including the prevalence of extremely small targets, complex backgrounds, and significant scale variations. Mainstream deep learning-based detection models often struggle with these issues, exhibiting limitations in detecting small cracks, high computational demands, and insufficient generalization ability for UAV perspectives. To address these challenges, this paper proposes a novel comprehensive network, RoadNet, specifically designed for high-precision road defect detection in UAV-captured imagery. RoadNet innovatively integrates Transformer modules with a convolutional neural network backbone and detection head. This design not only significantly enhances the global feature modeling capability crucial for understanding complex aerial contexts but also maintains the computational efficiency necessary for potential real-time applications. The model was trained and evaluated on a self-collected UAV road defect dataset (UAV-RDD). In comparative experiments, RoadNet achieved an outstanding mAP@0.5 score of 0.9128 while maintaining a fast-processing speed of 210.01 ms per image, outperforming other state-of-the-art models. The experimental results demonstrate that RoadNet possesses superior detection performance for road defects in complex aerial scenarios captured by drones. Full article

Rapid and accurate detection of trapped victims is vital in disaster rescue operations, yet most existing object detection methods cannot simultaneously deliver high accuracy and fast inference under resource-constrained conditions. To address this limitation, we propose the LightSeek-YOLO, a lightweight, real-time victim detection framework for disaster scenarios built upon YOLOv11. Our LightSeek-YOLO integrates three core innovations. First, it employs HGNetV2 as the backbone, whose HGStem and HGBlock modules leverage depthwise separable convolutions to markedly reduce computational cost while preserving feature extraction. Secondly, it introduces Seek-DS (Seek-DownSampling), a dual-branch downsampling module that preserves key feature extrema through a MaxPool branch while capturing spatial patterns via a progressive convolution branch, thereby effectively mitigating background interference. Third, it incorporates Seek-DH (Seek Detection Head), a lightweight detection head that processes features through a unified pipeline, enhancing scale adaptability while reducing parameter redundancy. Evaluated on the common C2A disaster dataset, LightSeek-YOLO achieves 0.478 AP@small for small-object detection, demonstrating strong robustness in challenging conditions such as rubble and smoke. Moreover, on the COCO, it reaches 0.473 mAP@[0.5:0.95], matching YOLOv8n while achieving superior computational efficiency through 38.2% parameter reduction and 39.5% FLOP reduction, and achieving 571.72 FPS on desktop hardware, with computational efficiency improvements suggesting potential for edge deployment pending validation. Full article

This paper presents HE-DMDeception, a novel adversarial attack network that integrates human visual deception with deep model deception to enhance the security of 3D object detection. Existing patch-based and camouflage methods can mislead deep learning models but struggle to generate visually imperceptible, high-quality textures. Our framework employs a CycleGAN-based camouflage network to generate highly camouflaged background textures, while a dedicated deception module disrupts non-maximum suppression (NMS) and attention mechanisms through optimized constraints that balance attack efficacy and visual fidelity. To overcome the scarcity of annotated vehicle data, an image segmentation module based on the pre-trained Segment Anything (SAM) model is introduced, leveraging a two-stage training strategy combining semi-supervised self-training and supervised fine-tuning. Experimental results show that the minimum P@0.5 values (50%, 55%, 20%, 25%, 25%) were achieved by HE-DMDeception across You Only Look Once version 8 (YOLOv8), Real-Time Detection Transformer (RT-DETR), Fast Region-based Convolutional Neural Network (Faster-RCNN), Single Shot MultiBox Detector (SSD), and MaskRegion-based Convolutional Neural Network (Mask RCNN) detection models, while maintaining high visual consistency with the original camouflage. These findings demonstrate the robustness and practicality of HE-DMDeception, offering new insights into 3D object detection adversarial attacks. Full article

Flange bolts are vital fasteners in civil, mechanical, and aerospace structures, where preload stability directly affects overall safety. Conventional methods for bolt loosening detection often suffer from missed detections, weak feature representation, and insufficient cross-scale fusion under complex backgrounds. This paper presents an integrated detection and angle estimation framework using a lightweight deep learning detection network. A MobileViT backbone is employed to balance local texture with global context. In the spatial pyramid pooling stage, large separable convolutional kernels are combined with a channel and spatial attention mechanism to highlight discriminative features while suppressing noise. Together with content-aware upsampling and bidirectional multi-scale feature fusion, the network achieves high accuracy in detecting small and low-contrast targets while maintaining real-time performance. For angle estimation, the framework adopts an efficient training-free pipeline consisting of oriented FAST and rotated BRIEF feature detection, approximate nearest neighbor matching, and robust sample consensus fitting. This approach reliably removes false correspondences and extracts stable rotation components, maintaining success rates between 85% and 93% with an average error close to one degree, even under reflection, blur, or moderate viewpoint changes. Experimental validation demonstrates strong stability in detection and angular estimation under varying illumination and texture conditions, with a favorable balance between computational efficiency and practical applicability. This study provides a practical, intelligent, and deployable solution for bolt loosening detection, supporting the safe operation of large-scale equipment and infrastructure. Full article

Automated quality control is critical in modern manufacturing, especially for metallic cast components, where fast and accurate surface defect detection is required. This study evaluates classical Machine Learning (ML) algorithms using extracted statistical parameters and deep learning (DL) architectures including ResNet50, Capsule Networks, and a 3D Convolutional Neural Network (CNN3D) using 3D image inputs. Using the Dataset Original, ML models with the selected parameters achieved high performance: RF reached 99.4 ± 0.2% precision and 99.4 ± 0.2% sensitivity, GB 96.0 ± 0.2% precision and 96.0 ± 0.2% sensitivity. ResNet50 trained with extracted parameters reached 98.0 ± 1.5% accuracy and 98.2 ± 1.7% F1-score. Capsule-based architectures achieved the best results, with ConvCapsuleLayer reaching 98.7 ± 0.2% accuracy and 100.0 ± 0.0% precision for the normal class, and 98.9 ± 0.2% F1-score for the affected class. CNN3D applied on 3D image inputs reached 88.61 ± 1.01% accuracy and 90.14 ± 0.95% F1-score. Using the Dataset Expanded with ML and PCA-selected features, Random Forest achieved 99.4 ± 0.2% precision and 99.4 ± 0.2% sensitivity, K-Nearest Neighbors 99.2 ± 0.0% precision and 99.2 ± 0.0% sensitivity, and SVM 99.2 ± 0.0% precision and 99.2 ± 0.0% sensitivity, demonstrating consistent high performance. All models were evaluated using repeated train-test splits to calculate averages of standard metrics (accuracy, precision, recall, F1-score), and processing times were measured, showing very low per-image execution times (as low as $3.69\times {10}^{-4}$ s/image), supporting potential real-time industrial application. These results indicate that combining statistical descriptors with ML and DL architectures provides a robust and scalable solution for automated, non-destructive surface defect detection, with high accuracy and reliability across both the original and expanded datasets. Full article

In recent years, convolutional neural network-based object detectors have achieved extensive applications in remote sensing (RS) image interpretation. While multi-scale feature modeling optimization remains a persistent research focus, existing methods frequently overlook the symmetrical balance between feature granularity and morphological diversity, particularly when handling high-aspect-ratio RS targets with anisotropic geometries. This oversight leads to suboptimal feature representations characterized by spatial sparsity and directional bias. To address this challenge, we propose the Parallel Interleaved Convolutional Kernel Network (PICK-Net), a rotation-aware detection framework that embodies symmetry principles through dual-path feature modulation and geometrically balanced operator design. The core innovation lies in the synergistic integration of cascaded dynamic sparse sampling and symmetrically decoupled feature modulation, enabling adaptive morphological modeling of RS targets. Specifically, the Parallel Interleaved Convolution (PIC) module establishes symmetric computation patterns through mirrored kernel arrangements, effectively reducing computational redundancy while preserving directional completeness through rotational symmetry-enhanced receptive field optimization. Complementing this, the Global Complementary Attention Mechanism (GCAM) introduces bidirectional symmetry in feature recalibration, decoupling channel-wise and spatial-wise adaptations through orthogonal attention pathways that maintain equilibrium in gradient propagation. Extensive experiments on RSOD and NWPU-VHR-10 datasets demonstrate our superior performance, achieving 92.2% and 84.90% mAP, respectively, outperforming state-of-the-art methods including EfficientNet and YOLOv8. With only 12.5 M parameters, the framework achieves symmetrical optimization of accuracy-efficiency trade-offs. Ablation studies confirm that the symmetric interaction between PIC and GCAM enhances detection performance by 2.75%, particularly excelling in scenarios requiring geometric symmetry preservation, such as dense target clusters and extreme scale variations. Cross-domain validation on agricultural pest datasets further verifies its rotational symmetry generalization capability, demonstrating 84.90% accuracy in fine-grained orientation-sensitive detection tasks. Full article

MRI (magnetic resonance imaging) technology aims to map the internal structure image of organisms. It is an important application scenario of Non-Uniform Fast Fourier Transform (NUFFT), which can help doctors quickly locate the lesion site of patients. However, in practical application, it has disadvantages such as large computation and difficulty in parallel. Under the architecture of multi-core shared memory, using block pretreatment, color block scheduling NUFFT convolution interpolation offers a parallel solution, and then using a static linked list solves the problem of large memory requirements after the parallel solution on the basis of multithreading to cycle through more source code versions. Then, manual vectorization, such as processing, using short vector components, further accelerates the process. Through a series of optimizations, the final Random, Radial, and Spiral dataset obtained an acceleration effect of 273.8×, 291.8× and 251.7×, respectively. Full article

Phishing, especially brand impersonation attacks, is a critical cybersecurity threat that harms user trust and organization security. This paper establishes a lightweight model for real-time detection that relies on URL-only sequences, addressing limitations for multimodal methods that leverage HTML, images, or metadata. This approach is based on a Temporal Convolutional Network with Attention (TCNWithAttention) that utilizes character-level URLs to capture both local and long-range dependencies, while providing interpretability with attention visualization and Shapley additive explanations (SHAP). The model was trained and tested on the balanced GramBeddings dataset (800,000 URLs) and validated on the PhiUSIIL dataset of real-world phishing URLs. The model achieved 97.54% accuracy on the GramBeddings dataset, and 81% recall on the PhiUSIIL dataset. The model demonstrated strong generalization, fast inference, and CPU-only deployability. It outperformed CNN, BiLSTM and BERT baselines. Explanations highlighted phishing indicators, such as deceptive subdomains, brand impersonation, and suspicious tokens. It also affirmed real patterns in the legitimate domains. To our knowledge, a Streamlit application to facilitate single and batch URL analysis and log feedback to maintain usability is the first phishing detection framework to integrate TCN, attention, and SHAP, bridging academic innovation with practical cybersecurity techniques. Full article

Renewable energy technologies play a key role in mitigating climate change and advancing sustainable development. Among these, photovoltaic (PV) systems have experienced significant growth in recent years. However, shading, one of the most common faults in PV modules, can drastically degrade their performance. This study investigates the application of convolutional neural networks (CNNs) for the automated detection and classification of shading faults, including multiple severity levels, using current–voltage (I–V) curves. Four scenarios were simulated in Simulink: a healthy module and three levels of shading severity (light, moderate, and severe). The resulting I–V curves were transformed into grayscale images and used to train and evaluate several custom-designed CNN architectures. The goal is to assess the capability of CNN-based models to accurately identify shading faults and discriminate between severity levels. Multiple network configurations were tested, varying image resolution, network depth, and filter parameters, to explore their impact on classification accuracy. Furthermore, robustness was evaluated by introducing Gaussian noise at different levels. The best-performing models achieved classification accuracies of 99.5% under noiseless conditions and 90.1% under a 10 dB noise condition, demonstrating that CNN-based approaches can be both effective and computationally lightweight. These results underscore the potential of this methodology for integration into automated diagnostic tools for PV systems, particularly in applications requiring fast and reliable fault detection. Full article