Search Results (2,116)

With the increase in the penetration rate of distributed sources and loads, the sensor monitoring data is increasing dramatically. Power grid maintenance services require a rapid response in power quality data analysis. To achieve a rapid response and highly accurate classification of power quality disturbances (PQDs), this paper proposes an efficient classification algorithm for PQDs based on Lissajous trajectory (LT) and a lightweight DenseNet, which utilizes the concept of Lissajous curves to construct an ideal reference signal and combines it with the original PQD signal to synthesize a feature trajectory with a distinctive shape. Meanwhile, to enhance the ability and efficiency of capturing trajectory features, a lightweight L-DenseNet skeleton model is designed, and its feature extraction capability is further improved by integrating an attention mechanism with L-DenseNet. Finally, the LT image is input into the fusion model for training, and PQD classification is achieved using the optimally trained model. The experimental results demonstrate that, compared with current mainstream PQD classification methods, the proposed algorithm not only achieves superior disturbance classification accuracy and noise robustness but also significantly improves response speed in PQD classification tasks through its concise visualization conversion process and lightweight model design. Full article

Skin cancer is one of the most prevalent forms of cancer worldwide, and early and accurate diagnosis critically impacts patient outcomes. Given the sensitive nature of medical data and its fragmented distribution across institutions (data silos), privacy-preserving collaborative learning is essential to enable knowledge-sharing without compromising patient confidentiality. While federated learning (FL) offers a promising solution, existing methods struggle with heterogeneous and missing modalities across institutions, which reduce the diagnostic accuracy. To address these challenges, we propose an effective and flexible Personalized Multimodal Federated Learning framework (PMM-FL), which enables efficient cross-client knowledge transfer while maintaining personalized performance under heterogeneous and incomplete modality conditions. Our study contains three key contributions: (1) A hierarchical aggregation strategy that decouples multi-module aggregation from local deployment via global modular-separated aggregation and local client fine-tuning. Unlike conventional FL (which synchronizes all parameters in each round), our method adopts a frequency-adaptive synchronization mechanism, updating parameters based on their stability and functional roles. (2) A multimodal fusion approach based on multitask learning, integrating learnable modality imputation and attention-based feature fusion to handle missing modalities. (3) A custom dataset combining multi-year International Skin Imaging Collaboration(ISIC) challenge data (2018–2024) to ensure comprehensive coverage of diverse skin cancer types. We evaluate PMM-FL through diverse experiment settings, demonstrating its effectiveness in heterogeneous and incomplete modality federated learning settings, achieving 92.32% diagnostic accuracy with only a 2% drop in accuracy under 30% modality missingness, with a 32.9% communication overhead decline compared with baseline FL methods. Full article

Accurate and efficient object detection is essential for aerial airport surveillance, playing a critical role in aviation safety and the advancement of autonomous operations. Although recent deep learning approaches have achieved notable progress, significant challenges persist, including severe object occlusion, extreme scale variation, dense panoramic clutter, and the detection of very small targets. In this study, we introduce a novel and unified detection framework designed to address these issues comprehensively. Our method integrates a Normalized Gaussian Wasserstein Distance loss for precise probabilistic bounding box regression, Dilation-wise Residual modules for improved multi-scale feature extraction, a Hierarchical Screening Feature Pyramid Network for effective hierarchical feature fusion, and DualConv modules for lightweight yet robust feature representation. Extensive experiments conducted on two public airport surveillance datasets, ASS1 and ASS2, demonstrate that our approach yields substantial improvements in detection accuracy. Specifically, the proposed method achieves an improvement of up to 14.6 percentage points in mean Average Precision (mAP@0.5) compared to state-of-the-art YOLO variants, with particularly notable gains in challenging small-object categories such as personnel detection. These results highlight the effectiveness and practical value of the proposed framework in advancing aviation safety and operational autonomy in airport environments. Full article

Accurate feature matching between optical and synthetic aperture radar (SAR) images remains a significant challenge in remote sensing due to substantial modality discrepancies in texture, intensity, and geometric structure. In this study, we proposed an attention-context-aware deep learning framework (ACAMatch) for robust and efficient optical–SAR image registration. The proposed method integrates a structure-enhanced feature extractor, RS2FNet, which combines dual-stage Res2Net modules with a bi-level routing attention mechanism to capture multi-scale local textures and global structural semantics. A context-aware matching module refines correspondences through self- and cross-attention, coupled with a confidence-driven early-exit pruning strategy to reduce computational cost while maintaining accuracy. Additionally, a match-aware multi-task loss function jointly enforces spatial consistency, affine invariance, and structural coherence for end-to-end optimization. Experiments on public datasets (SEN1-2 and WHU-OPT-SAR) and a self-collected Gaofen (GF) dataset demonstrated that ACAMatch significantly outperformed existing state-of-the-art methods in terms of the number of correct matches, matching accuracy, and inference speed, especially under challenging conditions such as resolution differences and severe structural distortions. These results indicate the effectiveness and generalizability of the proposed approach for multimodal image registration, making ACAMatch a promising solution for remote sensing applications such as change detection and multi-sensor data fusion. Full article

Infrared small-target detection encounters significant challenges due to a low image signal-to-noise ratio, limited target size, and complex background noise. To address the issues of sparse feature loss for small targets during the down-sampling phase of the traditional U-Net network and the semantic gap in the feature fusion process, a multilevel feature extraction and fusion attention network (MEFA-Net) is designed. Specifically, the dilated direction-sensitive convolution block (DDCB) is devised to collaboratively extract local detail features, contextual features, and Gaussian salient features via ordinary convolution, dilated convolution and parallel strip convolution. Furthermore, the encoder attention fusion module (EAF) is employed, where spatial and channel attention weights are generated using dual-path pooling to achieve the adaptive fusion of deep and shallow layer features. Lastly, an efficient up-sampling block (EUB) is constructed, integrating a hybrid up-sampling strategy with multi-scale dilated convolution to refine the localization of small targets. The experimental results confirm that the proposed algorithm model surpasses most existing recent methods. Compared with the baseline, the intersection over union (IoU) and probability of detection $P_d$ of MEFA-Net on the IRSTD-1k dataset are increased by 2.25% and 3.05%, respectively, achieving better detection performance and a lower false alarm rate in complex scenarios. Full article

The rapid development of deepfake technologies has led to the widespread proliferation of facial image forgeries, raising significant concerns over identity theft and the spread of misinformation. Although recent dual-domain detection approaches that integrate spatial and frequency features have achieved noticeable progress, they still suffer from limited sensitivity to local forgery regions and inadequate interaction between spatial and frequency information in practical applications. To address these challenges, we propose a novel forgery-aware guided spatial–frequency feature fusion network. A lightweight U-Net is employed to generate pixel-level saliency maps by leveraging structural symmetry and semantic consistency, without relying on ground-truth masks. These maps dynamically guide the fusion of spatial features (from an improved Swin Transformer) and frequency features (via Haar wavelet transforms). Cross-domain attention, channel recalibration, and spatial gating are introduced to enhance feature complementarity and regional discrimination. Extensive experiments conducted on two benchmark face forgery datasets, FaceForensics++ and Celeb-DFv2, show that the proposed method consistently outperforms existing state-of-the-art techniques in terms of detection accuracy and generalization capability. The future work includes improving robustness under compression, incorporating temporal cues, extending to multimodal scenarios, and evaluating model efficiency for real-world deployment. Full article

Accurate land-use classification is critical for urban planning and environmental monitoring, yet effectively integrating heterogeneous data sources such as hyperspectral imagery and laser radar (LiDAR) remains challenging. To address this, we propose MixtureRS, a compact multimodal network that effectively integrates hyperspectral imagery and LiDAR data for land-use classification. Our approach employs a 3-D plus heterogeneous convolutional stack to extract rich spectral–spatial features, which are then tokenized and fused via a cross-modality transformer. To enhance model capacity without incurring significant computational overhead, we replace conventional dense feed-forward blocks with a sparse Mixture-of-Experts (MoE) layer that selectively activates the most relevant experts for each token. Evaluated on a 15-class urban benchmark, MixtureRS achieves an overall accuracy of 88.6%, an average accuracy of 90.2%, and a Kappa coefficient of 0.877, outperforming the best homogeneous transformer by over 12 percentage points. Notably, the largest improvements are observed in water, railway, and parking categories, highlighting the advantages of incorporating height information and conditional computation. These results demonstrate that conditional, expert-guided fusion is a promising and efficient strategy for advancing multimodal remote sensing models. Full article

Recently, a network based on selective state space models (SSMs), Mamba, has emerged as a research focus in hyperspectral image (HSI) classification due to its linear computational complexity and strong long-range dependency modeling capability. Originally designed for 1D causal sequence modeling, Mamba is challenging for HSI tasks that require simultaneous awareness of spatial and spectral structures. Current Mamba-based HSI classification methods typically convert spatial structures into 1D sequences and employ various scanning patterns to capture spatial dependencies. However, these approaches inevitably disrupt spatial structures, leading to ineffective modeling of complex spatial relationships and increased computational costs due to elongated scanning paths. Moreover, the lack of neighborhood spectral information utilization fails to mitigate the impact of spatial variability on classification performance. To address these limitations, we propose a novel model, Dual-Aware Discriminative Fusion Mamba (DADFMamba), which is simultaneously aware of spatial-spectral structures and adaptively integrates discriminative features. Specifically, we design a Spatial-Structure-Aware Fusion Module (SSAFM) to directly establish spatial neighborhood connectivity in the state space, preserving structural integrity. Then, we introduce a Spectral-Neighbor-Group Fusion Module (SNGFM). It enhances target spectral features by leveraging neighborhood spectral information before partitioning them into multiple spectral groups to explore relations across these groups. Finally, we introduce a Feature Fusion Discriminator (FFD) to discriminate the importance of spatial and spectral features, enabling adaptive feature fusion. Extensive experiments on four benchmark HSI datasets demonstrate that DADFMamba outperforms state-of-the-art deep learning models in classification accuracy while maintaining low computational costs and parameter efficiency. Notably, it achieves superior performance with only 30 training samples per class, highlighting its data efficiency. Our study reveals the great potential of Mamba in HSI classification and provides valuable insights for future research. Full article

As a key component in the hydraulic brake system of automobiles, the brake joint directly affects the braking performance and driving safety of the vehicle. Therefore, improving the quality of brake joints is crucial. During the processing, due to the complexity of the welding material and welding process, the weld seam is prone to various defects such as cracks, pores, undercutting, and incomplete fusion, which can weaken the joint and even lead to product failure. Traditional weld seam detection methods include destructive testing and non-destructive testing; however, destructive testing has high costs and long cycles, and non-destructive testing, such as radiographic testing and ultrasonic testing, also have problems such as high consumable costs, slow detection speed, or high requirements for operator experience. In response to these challenges, this article proposes a defect detection and classification method for laser welding seams of automotive brake joints based on machine vision inspection technology. Laser-welded automotive brake joints are subjected to weld defect detection and classification, and image processing algorithms are optimized to improve the accuracy of detection and failure analysis by utilizing the high efficiency, low cost, flexibility, and automation advantages of machine vision technology. This article first analyzes the common types of weld defects in laser welding of automotive brake joints, including craters, holes, and nibbling, and explores the causes and characteristics of these defects. Then, an image processing algorithm suitable for laser welding of automotive brake joints was studied, including pre-processing steps such as image smoothing, image enhancement, threshold segmentation, and morphological processing, to extract feature parameters of weld defects. On this basis, a welding seam defect detection and classification system based on the cascade classifier and AdaBoost algorithm was designed, and efficient recognition and classification of welding seam defects were achieved by training the cascade classifier. The results show that the system can accurately identify and distinguish pits, holes, and undercutting defects in welds, with an average classification accuracy of over 90%. The detection and recognition rate of pit defects reaches 100%, and the detection accuracy of undercutting defects is 92.6%. And the overall missed detection rate is less than 3%, with both the missed detection rate and false detection rate for pit defects being 0%. The average detection time for each image is 0.24 s, meeting the real-time requirements of industrial automation. Compared with infrared and ultrasonic detection methods, the proposed machine-vision-based detection system has significant advantages in detection speed, surface defect recognition accuracy, and industrial adaptability. This provides an efficient and accurate solution for laser welding defect detection of automotive brake joints. Full article

Steel surface defect detection is a crucial step in ensuring industrial production quality. However, due to significant variations in scale and irregular geometric morphology of steel surface defects, existing detection algorithms show notable deficiencies in multi-scale feature representation and cross-layer multi-scale feature fusion efficiency. To address these challenges, this paper proposes an improved real-time steel surface defect detection model, NGD-YOLO, based on YOLOv5s, which achieves fast and high-precision defect detection under relatively low hardware conditions. Firstly, a lightweight and efficient Normalization-based Attention Module (NAM) is integrated into the C3 module to construct the C3NAM, enhancing multi-scale feature representation capabilities. Secondly, an efficient Gather–Distribute (GD) mechanism is introduced into the feature fusion component to build the GD-NAM network, thereby effectively reducing information loss during cross-layer multi-scale information fusion and adding a small target detection layer to enhance the detection performance of small defects. Finally, to mitigate the parameter increase caused by the GD-NAM network, a lightweight convolution module, DCConv, that integrates Efficient Channel Attention (ECA), is proposed and combined with the C3 module to construct the lightweight C3DC module. This approach improves detection speed and accuracy while reducing model parameters. Experimental results on the public NEU-DET dataset show that the proposed NGD-YOLO model achieves a detection accuracy of 79.2%, representing a 4.6% mAP improvement over the baseline YOLOv5s network with less than a quarter increase in parameters, and reaches 108.6 FPS, meeting the real-time monitoring requirements in industrial production environments. Full article

To address the current issue of large computations and the difficulty in balancing model complexity and detection accuracy in pavement defect detection models, a lightweight pavement defect detection algorithm, PGS-YOLO, is proposed based on YOLOv8, which integrates perception enhancement and feature optimization. The algorithm first designs the Receptive-Field Convolutional Block Attention Module Convolution (RFCBAMConv) and the Receptive-Field Convolutional Block Attention Module C2f-RFCBAM, based on which we construct an efficient Perception Enhanced Feature Extraction Network (PEFNet) that enhances multi-scale feature extraction capability by dynamically adjusting the receptive field. Secondly, the dynamic upsampling module DySample is introduced into the efficient feature pyramid, constructing a new feature fusion pyramid (Generalized Dynamic Sampling Feature Pyramid Network, GDSFPN) to optimize the multi-scale feature fusion effect. In addition, a shared detail-enhanced convolution lightweight detection head (SDCLD) was designed, which significantly reduces the model’s parameters and computation while improving localization and classification performance. Finally, Wise-IoU was introduced to optimize the training performance and detection accuracy of the model. Experimental results show that PGS-YOLO increases mAP50 by 2.8% and 2.9% on the complete GRDDC2022 dataset and the Chinese subset, respectively, outperforming the other detection models. The number of parameters and computations are reduced by 10.3% and 9.9%, respectively, compared to the YOLOv8n model, with an average frame rate of 69 frames per second, offering good real-time performance. In addition, on the CRACK500 dataset, PGS-YOLO improved mAP50 by 2.3%, achieving a better balance between model complexity and detection accuracy. Full article

This study investigates the application of deep learning (DL) techniques for predicting temperature fields in the SM1 swirl-stabilized turbulent non-premixed flame. Two distinct DL approaches were developed using a comprehensive CFD database generated via the steady laminar flamelet model coupled with the SST k-ω turbulence model. The first approach employs a fully connected dense neural network to directly map scalar input parameters—fuel velocity, swirl ratio, and equivalence ratio—to high-resolution temperature contour images. In addition, a comparison was made with different deep learning networks, namely Res-Net, EfficientNetB0, and Inception Net V3, to better understand the performance of the model. In the first approach, the results of the Inception V3 model and the developed Dense Model were found to be better than Res-Net and Efficient Net. At the same time, file sizes and usability were examined. The second framework employs a U-Net-based convolutional neural network enhanced by an RGB Fusion preprocessing technique, which integrates multiple scalar fields from non-reacting (cold flow) conditions into composite images, significantly improving spatial feature extraction. The training and validation processes for both models were conducted using 80% of the CFD data for training and 20% for testing, which helped assess their ability to generalize new input conditions. In the secondary approach, similar to the first approach, studies were conducted with different deep learning models, namely Res-Net, Efficient Net, and Inception Net, to evaluate model performance. The U-Net model, which is well developed, stands out with its low error and small file size. The dense network is appropriate for direct parametric analyses, while the image-based U-Net model provides a rapid and scalable option to utilize the cold flow CFD images. This framework can be further refined in future research to estimate more flow factors and tested against experimental measurements for enhanced applicability. Full article

With the increasing sophistication of network attacks, machine learning (ML)-based methods have showcased promising performance in attack detection. However, ML-based methods often suffer from high false rates when tackling encrypted malicious traffic. To break through these bottlenecks, we propose EFTransformer, an encrypted flow transformer framework which inherits semantic perception and multi-scale feature fusion, can robustly and efficiently detect encrypted malicious traffic, and make up for the shortcomings of ML in the context of modeling ability and feature adequacy. EFTransformer introduces a channel-level extraction mechanism based on quintuples and a noise-aware clustering strategy to enhance the recognition ability of traffic patterns; adopts a dual-channel embedding method, using Word2Vec and FastText to capture global semantics and subword-level changes; and uses a Transformer-based classifier and attention pooling module to achieve dynamic feature-weighted fusion, thereby improving the robustness and accuracy of malicious traffic detection. Our systematic experiments on the ISCX2012 dataset demonstrate that EFTransformer achieves the best detection performance, with an accuracy of up to 95.26%, a false positive rate (FPR) of 6.19%, and a false negative rate (FNR) of only 5.85%. These results show that EFTransformer achieves high detection performance against encrypted malicious traffic. Full article

Land–sea segmentation is a fundamental task in remote sensing image analysis, and plays a vital role in dynamic coastline monitoring. The complex morphology and blurred boundaries of coastlines in remote sensing imagery make fast and accurate segmentation challenging. Recent deep learning approaches lack the ability to model spatial continuity effectively, thereby limiting a comprehensive understanding of coastline features in remote sensing imagery. To address this issue, we have developed VMMT-Net, a novel dual-branch semantic segmentation framework. By constructing a parallel heterogeneous dual-branch encoder, VMMT-Net integrates the complementary strengths of the Mix Transformer and the Visual State Space Model, enabling comprehensive modeling of local details, global semantics, and spatial continuity. We design a Cross-Branch Fusion Module to facilitate deep feature interaction and collaborative representation across branches, and implement a customized decoder module that enhances the integration of multiscale features and improves boundary refinement of coastlines. Extensive experiments conducted on two benchmark remote sensing datasets, GF-HNCD and BSD, demonstrate that the proposed VMMT-Net outperforms existing state-of-the-art methods in both quantitative metrics and visual quality. Specifically, the model achieves mean F1-scores of 98.48% (GF-HNCD) and 98.53% (BSD) and mean intersection-over-union values of 97.02% (GF-HNCD) and 97.11% (BSD). The model maintains reasonable computational complexity, with only 28.24 M parameters and 25.21 GFLOPs, striking a favorable balance between accuracy and efficiency. These results indicate the strong generalization ability and practical applicability of VMMT-Net in real-world remote sensing segmentation tasks. Full article

This paper proposes a hybrid method for skin lesion classification combining deep learning features with conventional descriptors such as HOG, Gabor, SIFT, and LBP. Feature extraction was performed by extracting features of interest within the tumor area using suggested fusion methods. We tested and compared features obtained from different deep learning models coupled to HOG-based features. Dimensionality reduction and performance improvement were achieved by Principal Component Analysis, after which SVM was used for classification. The compared methods were tested on the reference database skin cancer-malignant-vs-benign. The results show a significant improvement in terms of accuracy due to complementarity between the conventional and deep learning-based methods. Specifically, the addition of HOG descriptors led to an accuracy increase of 5% for EfficientNetB0, 7% for ResNet50, 5% for ResNet101, 1% for NASNetMobile, 1% for DenseNet201, and 1% for MobileNetV2. These findings confirm that feature fusion significantly enhances performance compared to the individual application of each method. Full article