Search Results (4,828)

Background and Objectives: Head and neck cancer (HNC) frequently necessitates reconstructive surgery due to defects following oncologic resection. The influence of age on reconstructive outcomes in head and neck cancer remains controversial. This study aimed to evaluate the impact of age on oncologic characteristics, reconstructive strategies, and functional outcomes following microvascular free flap reconstruction. Materials and Methods: A retrospective review was conducted on 286 patients who underwent free flap reconstruction for head and neck cancer between 2016 and 2020. Patients were stratified into three age groups: <40 years, 40–60 years, and >60 years. Demographic characteristics, tumor features, reconstructive approaches, complications, and functional outcomes—including postoperative dietary tolerance and tube feeding dependency—were analyzed. Results: The oral cavity was the most common tumor site across all age groups. Advanced-stage tumors (T4) were more frequently observed in older patients (>60 years), although the difference was not statistically significant (p = 0.0575). The overall flap survival rate was 98.6%. The mean hospital stay was 24.6 ± 15.86 days and was significantly longer in the >60-years group (p < 0.001). Postoperative dietary tolerance was comparable across age groups, with 56.8% of patients resuming a regular diet. Tube feeding dependency was slightly higher in the >60-years group but did not reach statistical significance (p = 0.1599). Conclusions: Age alone does not significantly affect reconstructive outcomes following microvascular free flap reconstruction for head and neck cancer. Despite a higher prevalence of comorbidities in and longer hospital stays for older patients, flap success rates and functional outcomes were comparable across age groups. Full article

The inherent non-uniformity of Infrared Focal Plane Arrays (IRFPA) inevitably results in stripe noise, which severely degrades image quality and hinders downstream applications. Existing deep learning methods often struggle to strike a balance between effective denoising and the preservation of fine thermal textures. To address this issue, we propose a Bottleneck-free Channel Dual-path Aggregation Network (BCDA-Net) based on a “Perception-Reconstruction” design principle. In the perception stage, the network jointly employs the Dual-Path Channel Down-sampling (DCD) module and the Context-Guided Stripe Attention Block (CGSAB). The DCD module utilizes a channel split strategy to simultaneously extract semantic features and preserve high-frequency textures, while the CGSAB performs global context modeling on these features to precisely perceive and locate global stripe noise patterns. In the reconstruction stage, we integrate the Cascaded Dense Feature Aggregation (CDFA) module with a Bottleneck-Free Aggregation Strategy (BFAS). The CDFA utilizes the perceived information to densely aggregate features and progressively reconstruct clean image details, whereas the BFAS structurally blocks the propagation of low-resolution noise during decoding, effectively mitigating aliasing artifacts induced by deep feature upsampling. Together, these components form a complete closed loop from accurate noise perception to high-fidelity reconstruction. Extensive experiments on public and real-world datasets demonstrate that BCDA-Net maximally preserves image details while removing non-uniform stripe noise. Both objective metrics and subjective visual quality outperform existing state-of-the-art methods. Full article

Deepfake content forgery compromises the integrity of digital media and the protection of personal identity, making its detection essential for preserving trust and enabling effective forensic analysis. Most deepfake detection approaches focus on global classification with a binary decision, which is inadequate for precise localization of manipulated regions. This limitation becomes particularly evident under image processing distortions. This paper proposes a dual-decoder architecture for the detection and segmentation of original and deepfake facial manipulations. Unlike conventional single-decoder segmentation models, the proposed approach introduces two decoding branches that learn complementary feature representations of authentic and forgery facial textures. In addition, attention mechanism modules are incorporated to refine encoder features based on decoder context, introducing adaptive feature selection during reconstruction. This architectural design reduces feature interference during reconstruction and enhances the localization of subtle inconsistencies introduced by deepfake manipulations. This approach generates complementary masks for real and forged regions, providing more precise boundary delineation. Experimental results highlight the robustness of the proposed method under image processing distortions, achieving intersection over union (IoU) scores of 0.9387 for real faces and 0.9254 for deepfake segmentation. These results underscore the effectiveness of the dual-decoder architecture in accurately detecting and localizing deepfake facial manipulations. Full article

Super-resolution reconstruction of remote sensing images has significant application value in fields such as smart cities, land monitoring, and traffic management. However, current super-resolution methods often overlook the differences between semantic and texture feature representations. This limitation makes it difficult to collaboratively preserve semantic structures and fine details during reconstruction, thereby affecting overall reconstruction quality. To address these challenges, this paper proposes a novel remote sensing image super-resolution network based on feature decoupling and differential window design, termed FDWD-Net. Specifically, we introduce an Adaptive Energy-driven Channel Selection module and a Multi-Directional Gradient-based Semantic–Texture Decoupling module to identify informative channels from the feature maps and decouple them into semantic and texture representations for independent optimization. Furthermore, we design a Differential Window-based Cross-scale Interaction module that dynamically adjusts window sizes based on local texture complexity, enabling adaptive feature modeling and effective multi-scale information interaction. Experimental results confirm that our method surpasses existing mainstream models on several remote sensing datasets. It also performs better in preserving structures and restoring detailed information. Full article

To improve the predictive accuracy of wind-field distributions during fires in high-rise buildings, this study targets the shortcomings of traditional prediction methods, including insufficient information fusion and dispersed feature representations under high-rise fire conditions. An efficient attention mechanism, termed Adaptive Channel and Multi-Scale Spatial Fusion Attention Mechanism (CSFAM), is proposed, which endows the model with enhanced adaptive focusing and multi-scale integration capabilities. CSFAM can account for environmental features across multiple dimensions to enable high-spatial-resolution wind-field reconstruction, thereby improving robustness and prediction accuracy in complex environments. To validate the effectiveness of CSFAM for predicting wind fields under high-rise-fire conditions, CFD-based scenario modeling was employed to generate a dataset of 1050 CFD-derived wind-field distributions across diverse inflow-wind and fire-source scenarios, partitioned into training, testing, and validation sets according to the fire-source size. When applying the CSFAM-enhanced multi-layer perceptron (MLP), the wind-field predictions achieved a mean squared error (MSE) of 0.0004, a mean absolute error (MAE) of 0.0141, and an R² of 0.9766, outperforming state-of-the-art methods. The results demonstrate that CSFAM plays a significant role in markedly improving wind-speed prediction accuracy during high-rise-building fires, and enhances the model’s ability to identify and express vortex-like and other key aerodynamic features generated by the fire, thereby improving the capture of the complex nonlinear aerodynamic structures induced by fire. Full article

Owing to the intricate mechanical coupling characteristics and the considerable difficulty in extracting synergistic spatio-temporal features from high-dimensional sensor data under fluctuating alternating loads, this study proposes a robust anomaly detection framework that combines Normalized Mutual Information (NMI) and Spatio-Temporal Graph Neural Networks (STGNN). First, NMI is utilized to quantify the nonlinear physical coupling intensity among multi-source sensors, thereby filtering out weakly correlated noise and reconstructing the spatial topological structure of the coupler system. Subsequently, a deep learning architecture incorporating Graph Convolutional Networks (GCN), Gated Recurrent Units (GRU), and one-dimensional convolutional residual connections is developed to capture the dynamic evolutionary characteristics of equipment states across both spatial interactions and temporal sequences. Finally, based on the model’s health-state predictions, a moving average algorithm is introduced to smooth the residual sequences, and an anomaly early-warning baseline is established in conjunction with the 3σ criterion. Experimental validation conducted using field service data from heavy-haul trains demonstrates that, compared to conventional serial CNN and Long Short-Term Memory (LSTM) models, the proposed method exhibits superior fitting performance and robustness against noise, effectively reducing the false alarm rate within normal working intervals. In a real-world case study, the method successfully identified variations in spatial linkage features induced by local damage and triggered timely alerts. Notably, the spatial alarm nodes were highly consistent with the fatigue crack initiation sites identified through on-site magnetic particle inspection. This study provides a viable data-driven analytical framework for the condition monitoring and anomaly identification of critical load-bearing components in heavy-haul trains. Full article

Surface roughness is a key tribological property commonly characterized by the power spectral density (PSD) of surface topography. However, the recent Surface Topography Challenge demonstrated that measurements of identical surfaces may yield PSD curves differing by several orders of magnitude depending on the laboratory and measurement method. Such discrepancies can arise from measurement artifacts, including spike-like outliers and macroscopic surface curvature. In this work, we analyze these effects and propose a correction procedure for recovering the intrinsic roughness spectrum. The method combines nonlinear median filtering for artifact detection with robust PSD reconstruction based on multiple one-dimensional surface sections. Outliers are removed in real space, the macroscopic shape is eliminated by detrending, and the PSD is obtained as the median of spectra from individual line scans. Tests on synthetic surfaces with known roughness spectra contaminated by curvature and artificial spikes demonstrate that the method reliably recovers the original spectrum even when artifacts dominate the raw data. Application to experimentally measured surfaces further indicates that some apparent roughness features may originate from measurement noise and stitching artifacts rather than the true surface structure. Full article

Peanut leaf disease detection in complex field environments faces two major challenges: distinguishing visually similar symptoms and identifying severely occluded lesions. This study presents YOLOv8-MSDH, a lightweight detection model built upon an improved YOLOv8 framework to address these issues. Four architectural enhancements are introduced. First, the MHSA attention mechanism is integrated to enhance sequential feature dependency modeling and suppress background noise. Second, the Slim-Neck module is adopted for neck reconstruction, which lowers computational cost and facilitates multi-scale feature fusion. Third, the original C2f module is replaced with the C2f-Dual module to further reduce computational load. Last, the HWD downsampling module is incorporated into the backbone to improve the retention of disease-specific features while promoting lightweight design. Evaluated on a peanut leaf disease dataset, YOLOv8-MSDH achieves 90.14% precision, 82.16% recall, 90.71% mAP50 and 72.14% mAP50-95 under complex conditions—surpassing the baseline YOLOv8 by 3.5, 0.7, 1.5 and 2.89 percentage points, respectively. Parameter count and computational complexity are reduced by 12.9% and 20.7%, confirming effective lightweighting. Operating at 509.95 FPS, the model maintains strong real-time performance and exhibits high robustness across varying lighting conditions. Full article

There are numerous benefits associated with creating digital copies of anatomical structures, which can be used during patient diagnosis. Such models can be used not only for visualization, but also in order to assess the condition of the patient. As advances in both medical imaging and 3D graphics are made, it is necessary to determine areas of application of the known reconstruction algorithms. Specifically, it is crucial to find advantages and disadvantages of known approaches to mesh generation, depending on the properties of the object and compare the quality of their results. In order to provide reliable ground-truth data, three 3D models with features resembling those identified in anatomical structures have been created. Based on these meshes, sets of CT-like DICOM images have been generated. Five different reconstruction approaches were proposed: using 3D occupancy information directly, two ways of obtaining point clouds and two methods that utilize Signed Distance Field. A neural network architecture for the SDF upsampling has also been presented. The obtained results justify the popularity of the Marching Cubes algorithm, as it produced accurate reconstructions most reliably. However, for certain scenarios, promising alternatives have been found. The presented outcomes make it clear that the approach to reconstruction must be tailored to the specific problem. Full article

Non-negative matrix factorization directly decomposes data features into a base matrix and community matrix, which are easily affected by noise. Multi-view datasets have multiple feature matrices, each with a different angle. The data features need to be re-synthesized rather than simply concatenated or added. Based on the advantages and disadvantages of multi-view clustering and non-negative matrix factorization, we attempt to transplant the method of analyzing abstract connected graphs, analogize the similarity between edges and samples in the graph, and propose a deep non-negative matrix factorization model for clustering by constructing a similarity matrix and decomposing it. At the same time, in order to reduce the interference of noise, we introduce a denoising auto-encoder and non-negative matrix factorization in series, and research the reconstruction features, ultimately forming a model structure framework of “denoising auto-encoder, non-negative matrix factorization, clustering”. Through experiments, the denoising auto-encoder-enhanced non-negative matrix factorization achieved good results on five datasets. It achieved an accuracy of 87 percenton the BBC Sport dataset and 61 percent on Wiki-fea, which increased by two percentage points. The clustering results demonstrate that the model can effectively alleviate the impact of noise and provide new ideas for how to integrate multi-view features. Full article

Airfoil flow-field prediction is important for aerodynamic design, but wind-tunnel testing and computational fluid dynamics (CFD) remain costly and time-consuming. Deep learning enables fast inference, yet many existing models still rely on fixed grid representations, which may lead to insufficient learning in high-gradient regions and larger local errors. This study proposes Spatial Multilayer Perceptron (Spatial MLP) together with an Error-Gradient-Guided Data Sampling (EGDS) strategy for airfoil flow-field prediction. Spatial MLP adopts a coordinate-based point-wise prediction framework. A spatial decoder is introduced as an auxiliary branch to enhance global flow consistency during pretraining, while channel-wise multi-head attention is incorporated to improve cross-variable feature coupling. EGDS prioritizes physically informative points according to relative prediction error and gradient magnitude, while retaining random samples to preserve data diversity. Experiments on an independent test set show that Spatial MLP reduces the mean relative error (averaged over the velocity components u, v, and pressure p) by 15.2% relative to the MLP baseline. With EGDS, the overall mean relative error is further reduced by 34.5% relative to the MLP baseline. These results demonstrate that combining global consistency constraints with targeted sampling effectively improves both global prediction accuracy and local reconstruction quality in high-gradient flow regions. Full article

Accurate sleep stage classification is essential for evaluating sleep quality, yet clinical polysomnography is impractical for continuous home-based monitoring. Ballistocardiography (BCG) enables unobtrusive sleep monitoring through sensors embedded in sleep furniture; however, existing BCG-based approaches either rely on complex physiological feature extraction or employ fixed-parameter signal-to-image transformations that cannot adapt to inter-subject variability. This study proposes a learnable recurrence plot (RP) framework for three-stage sleep classification (Wake, NREM, REM) from single-channel BCG signals. The Learnable RP introduces three innovations: multi-scale phase-space reconstruction at physiologically motivated time delays (τ = 5, 10, 20), differentiable per-scale thresholds optimized end-to-end, and attention-based spatial fusion of multi-scale recurrence maps. The framework was evaluated through 10-fold stratified cross-validation across six backbone architectures using 50 overnight recordings. The Learnable RP consistently outperformed four baseline transformation methods (GAF, MTF, Classical RP, Modified RP), achieving an aggregate mean accuracy of 73.60%, with EfficientNet-B5 reaching 78.91%. and 78.91%. Statistical validation across all 24 pairwise comparisons (4 baselines × 6 backbones) confirmed consistent superiority (all p < 0.001). The proposed framework achieves competitive performance without explicit physiological feature engineering, offering a viable path toward end-to-end unobtrusive sleep monitoring. Full article

The output power of photovoltaic (PV) systems is influenced by various environmental factors, exhibiting strong nonlinearity and non-stationarity, which poses significant challenges for accurate forecasting. To address these issues, this paper proposes a short-term PV power forecasting method based on wavelet convolutional neural networks and an improved Transformer. First, the Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) is employed to decompose the original PV power sequence into several intrinsic mode functions (IMFs). Fuzzy entropy is then utilized to evaluate the complexity of each component, and subsequences with similar entropy values are reconstructed to reduce the non-stationarity of the original series. Subsequently, Pearson correlation coefficients and the maximal information coefficient (MIC) are applied to capture both linear and nonlinear relationships between each reconstructed component and meteorological features, enabling the selection of strongly correlated variables. On this basis, a wavelet convolutional network (WTConv) is introduced to perform multi-scale decomposition and frequency-band feature extraction on the reconstructed components by integrating wavelet transform with convolution operations, effectively expanding the receptive field and extracting deep-seated features of the sequences. Finally, an improved iTransformer model is adopted for time-series modeling, leveraging its inverted encoding structure and self-attention mechanism to fully capture long-term dependencies among multivariate variables. The proposed model is validated using actual power data from a PV plant in Ningxia, China, across four seasons. Comprehensive experiments, including ablation studies, comparative analyses, loss function convergence evaluation, and Diebold–Mariano significance tests, are conducted to thoroughly assess the model’s effectiveness and superiority. Experimental results demonstrate that the proposed model achieves excellent prediction accuracy and stability in spring, summer, autumn, and winter, showing strong potential for engineering applications. Full article

Adaptive beamforming based on polarization-sensitive arrays enables joint spatial–polarization filtering for mainlobe interference suppression, but mainlobe distortion and performance degradation occur when the received data include the desired signal or multiple mainlobe interferences. Accordingly, this paper proposes a mainlobe interference suppression method based on Polarimetric Sparse Iterative Covariance-based Estimation (POL-SPICE) and covariance matrix reconstruction. This method utilizes the POL-SPICE algorithm to accurately estimate the direction of arrival (DOA), polarization, and power parameters. It reconstructs the covariance matrix by nulling the corresponding source power and constructs a feature projection matrix to preprocess the received signal. These eliminate the impact of the desired signal and mainlobe interference components on subsequent joint spatial–polarization domain beamforming, ultimately achieving interference suppression and mainlobe shape preservation. Simulation results illustrate that the proposed method is applicable to scenarios with the coexistence of the desired signal and multiple mainlobe interferences, and its superiority over existing methods is verified. Full article

Dynamic multi-exposure high dynamic range (HDR) image reconstruction remains challenging because it must preserve globally consistent luminance and structure while recovering fine-grained local textures from low dynamic range (LDR) inputs corrupted by saturation, under-exposure, and motion-induced artifacts. Existing CNN-based methods are effective at local detail restoration but remain limited in global context modeling, whereas Transformer-based methods improve long-range interaction but can still weaken local-detail refinement. Current hybrid designs suggest that the two representation types are complementary, but they do not fully address branch specialization, cross-branch collaboration, and local-feature reliability control. To address this gap, we propose a dual-branch Transformer-CNN framework with a base branch built on Window-based Residual Transformer Blocks (WRTBs), a detail branch equipped with Detail-Aware Gating (DAG) for reliability-aware local refinement, and Bidirectional Cross-Branch Fusion (BCBF) for stage-wise collaboration between the two branches. Experiments on Kalantari17, the Tel benchmark, and Challenge123 show that the proposed design remains competitive on the standard benchmark, achieving the best HDR-VDP2 and tied best with $\mu$-SSIM on Kalantari17, while yielding clearer gains on the more challenging Tel and Challenge123 benchmarks. Full article