Search Results (956)

This study presents an innovative pipeline for processing, compressing, and remotely visualizing large-scale numerical simulations of fluid dynamics in a virtual wind tunnel (VWT), leveraging virtual and augmented reality (VR/AR) for enhanced analysis and high-end visualization. The workflow addresses the challenges of handling massive databases generated using Direct Numerical Simulation (DNS) while maintaining visual fidelity and ensuring efficient rendering for user interaction. Fully immersive visualization of supersonic (Mach number 2.86) spatially developing turbulent boundary layers (SDTBLs) over strong concave and convex curvatures was achieved. The comprehensive DNS data provides insights on the transport phenomena inside turbulent boundary layers under strong deceleration or an Adverse Pressure Gradient (APG) caused by concave walls as well as strong acceleration or a Favorable Pressure Gradient (FPG) caused by convex walls under different wall thermal conditions (i.e., Cold, Adiabatic, and Hot walls). The process begins with a .vts file input from a DNS, which is visualized using ParaView software. These visualizations, representing different fluid behaviors based on a DNS with a high spatial/temporal resolution and employing millions of “numerical sensors”, are treated as individual time frames and exported in GL Transmission Format (GLTF), which is a widely used open-source file format designed for efficient transmission and loading of 3D scenes. To support the workflow, optimized Extract–Transform–Load (ETL) techniques were implemented for high-throughput data handling. Conversion of exported Graphics Library Transmission Format (GLTF) files into Graphics Library Transmission Format Binary files (typically referred to as GLB) reduced the storage by 25% and improved the load latency by 60%. This research uses Unity’s Profile Analyzer and Memory Profiler to identify performance limitations during contour rendering, focusing on the GPU and CPU efficiency. Further, immersive VR/AR analytics are achieved by connecting the processed outputs to Unity engine software and Microsoft HoloLens Gen 2 via Azure Remote Rendering cloud services, enabling real-time exploration of fluid behavior in mixed-reality environments. This pipeline constitutes a significant advancement in the scientific visualization of fluid dynamics, particularly when applied to datasets comprising hundreds of high-resolution frames. Moreover, the methodologies and insights gleaned from this approach are highly transferable, offering potential applications across various other scientific and engineering disciplines. 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

Frame-wise steganalysis is a crucial task in low-bit-rate speech streams that can achieve active defense. However, there is no common theory on how to extract steganalysis features for frame-wise steganalysis. Moreover, existing frame-wise steganalysis methods cannot extract fine-grained steganalysis features. Therefore, in this paper, we propose a frame-wise steganalysis method based on mask-gating attention and bilinear codeword feature interaction mechanisms. First, this paper utilizes the mask-gating attention mechanism to dynamically learn the importance of the codewords. Second, the bilinear codeword feature interaction mechanism is used to capture an informative second-order codeword feature interaction pattern in a fine-grained way. Finally, multiple fully connected layers with a residual structure are utilized to capture higher-order codeword interaction features while preserving lower-order interaction features. The experimental results show that the performance of our method is better than that of the state-of-the-art frame-wise steganalysis method on large steganography datasets. The detection accuracy of our method is 74.46% on 1000K testing samples, whereas the detection accuracy of the state-of-the-art method is 72.32%. Full article

In this paper, we study the classification problem of short-time-window steady-state visual evoked potentials (SSVEPs) and propose a novel deep convolutional network named EEGResNet based on the idea of residual connection to further improve the classification performance. Since the frequency-domain features extracted from short-time-window signals are difficult to distinguish, the EEGResNet starts from the filter bank (FB)-based feature extraction module in the time domain. The FB designed in this paper is composed of four sixth-order Butterworth filters with different bandpass ranges, and the four bandwidths are 19–50 Hz, 14–38 Hz, 9–26 Hz, and 3–14 Hz, respectively. Then, the extracted four feature tensors with the same shape are directly aggregated together. Furthermore, the aggregated features are further learned by a six-layer convolutional neural network with residual connections. Finally, the network output is generated through an adaptive fully connected layer. To prove the effectiveness and superiority of our designed EEGResNet, necessary experiments and comparisons are conducted over two large public datasets. To further verify the application potential of the trained network, a virtual simulation of brain computer interface (BCI) based quadrotor control is presented through V-REP. Full article

Rice blast caused by Magnaporthe oryzae is a major cause of yield reductions and quality deterioration in rice. Therefore, early detection of the disease is necessary for controlling the spread of rice blast. This study proposed a dual-channel feature fusion model (DCFM) to achieve effective identification of rice blast. The DCFM model extracted spectral features using successive projection algorithm (SPA), random frog (RFrog), and competitive adaptive reweighted sampling (CARS), and extracted spatial features from spectral images using MobileNetV2 combined with the convolutional block attention module (CBAM). Then, these features were fused using the feature fusion adaptive conditioning module in DCFM and input into the fully connected layer for disease identification. The results show that the model combining spectral and spatial features was superior to the classification models based on single features for rice blast detection, with OA and Kappa higher than 90% and 88%, respectively. The DCFM model based on SPA screening obtained the best results, with an OA of 96.72% and a Kappa of 95.97%. Overall, this study enables the early and accurate identification of rice blast, providing a rapid and reliable method for rice disease monitoring and management. It also offers a valuable reference for the detection of other crop diseases. Full article

Neural networks (NNs) achieve breakthroughs in computer vision and natural language processing, yet their “black box” nature persists. Traditional methods prioritise parameter optimisation and loss design, overlooking NNs’ fundamental structure as topologically organised nonlinear computational systems. This work proposes a complex network theory framework decoding structure–function coupling by mapping convolutional layers, fully connected layers, and Dropout modules into graph representations. To overcome limitations of heuristic compression techniques, we develop a topology-sensitive adaptive pruning algorithm that evaluates critical paths via node strength centrality, preserving structural–functional integrity. On CIFAR-10, our method achieves 55.5% parameter reduction with only 7.8% accuracy degradation—significantly outperforming traditional approaches. Crucially, retrained pruned networks exceed original model accuracy by up to 2.63%, demonstrating that topology optimisation unlocks latent model potential. This research establishes a paradigm shift from empirical to topologically rationalised neural architecture design, providing theoretical foundations for deep learning optimisation dynamics. Full article

Edge computing (EC) plays a critical role in advancing the next-generation Industrial Internet of Things (IIoT) by enhancing production, maintenance, and operational outcomes across heterogeneous network boundaries. This study builds upon EC intelligence and integrates graph-based learning to propose a Cross-Layer Controller Tasking Scheme (CLCTS). The scheme operates through two primary phases: task grouping assignment and cross-layer control. In the first phase, controller nodes executing similar tasks are grouped based on task timing to achieve monotonic and synchronized completions. The second phase governs controller re-tasking both within and across these groups. Graph structures connect the groups to facilitate concurrent tasking and completion. A learning model is trained on inverse outcomes from the first phase to mitigate task acceptance errors (TAEs), while the second phase focuses on task migration learning to reduce task prolongation. Edge nodes interlink the groups and synchronize tasking, migration, and re-tasking operations across IIoT layers within unified completion periods. Departing from simulation-based approaches, this study presents a fully implemented framework that combines learning-driven scheduling with coordinated cross-layer control. The proposed CLCTS achieves an 8.67% reduction in overhead, a 7.36% decrease in task processing time, and a 17.41% reduction in TAEs while enhancing the completion ratio by 13.19% under maximum edge node deployment. Full article

In the task of PolSAR image classification, effectively utilizing convolutional neural networks and vision transformer models with limited labeled data poses a critical challenge. This article proposes a novel method for PolSAR image classification that combines channel-wise convolutional local perception, detachable self-attention, and a residual feedforward network. Specifically, the proposed method comprises several key modules. In the channel-wise convolutional local perception module, channel-wise convolution operations enable accurate extraction of local features from different channels of PolSAR images. The local residual connections further enhance these extracted features, providing more discriminative information for subsequent processing. Additionally, the detachable self-attention mechanism plays a pivotal role: it facilitates effective interaction between local and global information, enabling the model to comprehensively perceive features across different scales, thereby improving classification accuracy and robustness. Subsequently, replacing the conventional feedforward network with a residual feedforward network that incorporates residual structures aids the model in better representing local features, further enhances the capability of cross-layer gradient propagation, and effectively alleviates the problem of vanishing gradients during the training of deep networks. In the final classification stage, two fully connected layers with dropout prevent overfitting, while softmax generates predictions. The proposed method was validated on the AIRSAR Flevoland, RADARSAT-2 San Francisco, and RADARSAT-2 Xi’an datasets. The experimental results demonstrate that the proposed method can attain a high level of classification performance even with a limited amount of labeled data, and the model is relatively stable. Furthermore, the proposed method has lower computational costs than comparative methods. Full article

Reservoir-induced landslides threaten infrastructures and downstream communities, making continuous deformation monitoring vital. Time-series InSAR, notably the SBAS algorithm, provides high-precision surface-displacement mapping but suffers from voids due to layover/shadow effects and temporal decorrelation. Existing deep-learning approaches often operate on fixed-size patches or ignore irregular spatio-temporal dependencies, limiting their ability to recover missing pixels. With this objective, a hybrid spatio-temporal Graph Attention (ST-GAT) framework was developed and trained on SBAS-InSAR values using 24 influential features. A unified spatio-temporal graph is constructed, where each node represents a pixel at a specific acquisition time. The nodes are connected via inverse distance spatial edges to their K-nearest neighbors, and they have bidirectional temporal edges to themselves in adjacent acquisitions. The two spatial GAT layers capture terrain-driven influences, while the two temporal GAT layers model annual deformation trends. A compact MLP with per-map bias converts the fused node embeddings into normalized LOS estimates. The SBAS-InSAR results reveal LOS deformation, with 48% of missing pixels and 20% located near the Dasu dam. ST D-GAT reconstructed fully continuous spatio-temporal displacement fields, filling voids at critical sites. The model was validated and achieved an overall R² (0.907), ρ (0.947), per-map R² ≥ 0.807 with RMSE ≤ 9.99, and a ROC-AUC of 0.91. It also outperformed the six compared baseline models (IDW, KNN, RF, XGBoost, MLP, simple-NN) in both RMSE and R². By combining observed LOS values with 24 covariates in the proposed model, it delivers physically consistent gap-filling and enables continuous, high-resolution landslide monitoring in radar-challenged mountainous terrain. Full article

In response to the issues of severe pitch oscillation and unstable roll attitude present in existing reinforcement learning-based aircraft cruise control methods during dynamic maneuvers, this paper proposes a precise control method for aircraft cruising based on proximal policy optimization (PPO) with nonlinear attitude constraints. This method first introduces a combination of long short-term memory (LSTM) and a fully connected layer (FC) to form the policy network of the PPO method, improving the algorithm’s learning efficiency for sequential data while avoiding feature compression. Secondly, it transforms cruise control into tracking target heading, altitude, and speed, achieving a mapping from motion states to optimal control actions within the policy network, and designs nonlinear constraints as the maximum reward intervals for pitch and roll to mitigate abnormal attitudes during maneuvers. Finally, a JSBSim simulation platform is established to train the network parameters, obtaining the optimal strategy for cruise control and achieving precise end-to-end control of the aircraft. Experimental results show that, compared to the cruise control method without dynamic constraints, the improved method reduces heading deviation by approximately 1.6° during ascent and 4.4° during descent, provides smoother pitch control, decreases steady-state altitude error by more than 1.5 m, and achieves higher accuracy in overlapping with the target trajectory during hexagonal trajectory tracking. Full article

To address the challenge of fault diagnosis for in-wheel motors in four-wheel independent driving systems under variable driving conditions and harsh environments, this paper proposes a novel method based on two-stream 2DCNNs (two-dimensional convolutional neural networks) with a DCBA (depthwise convolution block attention) module. The main contributions are twofold: (1) A DCBA module is introduced to extract multi-scale features—including prominent, local, and average information—from grayscale images reconstructed from vibration signals across different domains; and (2) a two-stream network architecture is designed to learn complementary feature representations from time-domain and time–frequency-domain signals, which are fused through fully connected layers to improve diagnostic accuracy. Experimental results demonstrate that the proposed method achieves high recognition accuracy under various working speeds, loads, and road surfaces. Comparative studies with SENet, ECANet, CBAM, and single-stream 2DCNN models confirm its superior performance and robustness. The integration of DCBA with dual-domain feature learning effectively enhances fault feature extraction under complex operating conditions. Full article

The advent of quantum computing has introduced new opportunities for enhancing classical machine learning architectures. In this study, we propose a novel hybrid model, the HQDNN (Hybrid Quantum–Deep Neural Network), designed for the automatic detection of fake news. The model integrates classical fully connected neural layers with a parameterized quantum circuit, enabling the processing of textual data within both classical and quantum computational domains. To assess its effectiveness, we conducted experiments on the widely used LIAR dataset utilizing Term Frequency–Inverse Document Frequency (TF-IDF) features, as well as transformer-based DistilBERT embeddings. The experimental results demonstrate that the HQDNN achieves a superior recall performance—92.58% with TF-IDF and 94.40% with DistilBERT—surpassing traditional machine learning models such as Logistic Regression, Linear SVM, and Multilayer Perceptron. Additionally, we compare the HQDNN with SetFit, a recent CPU-efficient few-shot transformer model, and show that while SetFit achieves higher precision, the HQDNN significantly outperforms it in recall. Furthermore, an ablation experiment confirms the critical contribution of the quantum component, revealing a substantial drop in performance when the quantum layer is removed. These findings highlight the potential of hybrid quantum–classical models as effective and compact alternatives for high-sensitivity classification tasks, particularly in domains such as fake news detection. Full article

High-resolution remote sensing imagery plays an essential role in urban management and environmental monitoring, providing detailed insights for applications ranging from land cover mapping to disaster response. Semantic segmentation methods are among the most effective techniques for comprehensive land cover mapping, and they commonly employ ImageNet-based pre-training semantics. However, traditional fine-tuning processes exhibit poor transferability across different downstream tasks and require large amounts of labeled data. To address these challenges, we introduce Denoising Diffusion Probabilistic Models (DDPMs) as a generative pre-training approach for semantic features extraction in remote sensing imagery. We pre-trained a DDPM on extensive unlabeled imagery, obtaining features at multiple noise levels and resolutions. In order to integrate and optimize these features efficiently, we designed a multi-layer perceptron module with residual connections. It performs channel-wise optimization to suppress feature redundancy and refine representations. Additionally, we froze the feature extractor during fine-tuning. This strategy significantly reduces computational consumption and facilitates fast transfer and deployment across various interpretation tasks on homogeneous imagery. Our comprehensive evaluation on the sparsely labeled dataset MiniFrance-S and the fully labeled Gaofen Image Dataset achieved mean intersection over union scores of 42.7% and 66.5%, respectively, outperforming previous works. This demonstrates that our approach effectively reduces reliance on labeled imagery and increases transferability to downstream remote sensing tasks. Full article

Street networks provide an invaluable source of information about the different temporal and spatial patterns emerging in our cities. These streets are often represented as graphs where intersections are modeled as nodes and streets as edges between them. Previous work has shown that raster representations of the original data can be created through a learning algorithm on low-dimensional representations of the street networks. In contrast, models that capture high-level urban network metrics can be trained through convolutional neural networks. However, the detailed topological data is lost through the rasterization of the street network, and the models cannot recover this information from the image alone, failing to capture complex street network features. This paper proposes a model capable of inferring good representations directly from the street network. Specifically, we use a variational autoencoder with graph convolutional layers and a decoder that generates a probabilistic, fully connected graph to learn latent representations that encode both local network structure and the spatial distribution of nodes. We train the model on thousands of street network segments and use the learned representations to generate synthetic street configurations. Finally, we proposed a possible application to classify the urban morphology of different network segments, investigating their common characteristics in the learned space. Full article

Neural Architecture search (NAS) aims to automate the design process of Deep Neural Networks, reducing the Deep Learning (DL) expertise required and avoiding a trial-and-error process. Nonetheless, one of the main drawbacks of NAS is the high consumption of computational resources. Consequently, efficient evaluation methods (EEMs) to assess the quality of candidate architectures are an open research problem. This work tests various EEMs in the Deep Genetic Algorithm (DeepGA), including early stopping, population memory, and training-free proxies. The Fashion MNIST, CIFAR-10, and CIFAR-100 datasets were used for experimentation. The results show that population memory has a valuable impact on avoiding repeated evaluations. Additionally, early stopping achieved competitive performance while significantly reducing the computational cost of the search process. The training-free configurations using the Logsynflow and Linear Regions proxies, as well as a combination of both, were only partially competitive but dramatically reduced the search time. Finally, a comparison of the architectures and hyperparameters obtained with the different algorithm configurations is presented. The training-free search processes resulted in deeper architectures with more fully connected layers and skip connections than the ones obtained with accuracy-guided search configurations. Full article