Search Results (702)

Transmission error (TE) is a major excitation source in geared systems, but microgeometry deviations are usually evaluated through nominal amplitudes rather than their tooth-to-tooth spatial distribution. This study investigates how different tooth-level barreling deviation patterns influence TE modulation and spectral characteristics in a controlled single helical gear-pair model. The nominal barreling value was kept constant, while four deviation patterns were imposed on the 23-tooth pinion: harmonic, phase-shifted harmonic, clustered with an outlier, and random. The TE response was evaluated in the time domain and by Fast Fourier Transform (FFT)-based spectral analysis, with particular attention to the gear mesh frequency (GMF) and shaft-frequency-spaced sidebands. The results show that identical nominal barreling levels can produce different TE waveforms and spectral signatures. Harmonic distributions mainly preserve a regular response, whereas phase-shifted and clustered patterns increase waveform asymmetry and sideband activity. The clustered outlier case produced the most fault-like response. The findings indicate that tooth-level spatial distribution should be considered explicitly in simulation-based gear microgeometry and noise, vibration, and harshness (NVH) sensitivity studies. Full article

Background/Objectives: Accurate land cover mapping from multispectral Sentinel-2 imagery is fundamental for environmental monitoring, efficient natural resource management, and spatial planning. While deep learning has become the dominant approach for semantic segmentation, the combined impact of spectral input selection and network architecture on cross-regional robustness remains insufficiently explored. This study systematically investigates multispectral land cover segmentation in Serbia and evaluates its transferability to Western Balkan regions using a structured experimental framework. Methods: A comprehensive band-combination ablation analysis (3–10 spectral bands and index-only inputs) was first conducted using Attention U-Net, followed by a comparative evaluation of representative convolutional and transformer-based architectures, including ResNet-UNet-50, ConvNeXt-UNet, DeepLabV3+ (ResNet-50), and DINOv2-S/14. Model performance is evaluated on an internal Serbian test split (Test SR), an external Serbian dataset (Ext SR), and a cross-regional Balkan dataset (Ext WB). Results: The results demonstrate that compact multispectral configurations (6–9 bands) provide the most stable performance, achieving mIoU values of approximately 0.72–0.74 under in-domain evaluation and remaining robust under external testing. The inclusion of near-infrared and shortwave infrared bands proved critical for effective land cover discrimination, whereas increasing spectral dimensionality beyond this range did not yield systematic improvements in external robustness. Notably, the magnitude of performance degradation under pronounced geographic domain shift exceeds the performance differences observed between architectures under in-domain conditions, indicating that distribution shift exerts a stronger influence on segmentation accuracy than model choice alone. Class-wise analysis revealed agricultural areas as the most domain-sensitive category, while Shapley-based explainability analysis provides additional insight into class-specific spectral dependencies and their role in generalization behavior. Conclusions: Although transformer-based models demonstrated competitive robustness, attention-enhanced convolutional architectures achieved comparable stability across evaluation scenarios. Overall, the findings emphasize the importance of balanced spectral design, class-aware robustness analysis, and explicit out-of-domain evaluation for developing transferable land cover segmentation models in remote sensing applications. Full article

Hyperspectral image change detection (HSI-CD) is becoming increasingly important in understanding how the Earth’s surface evolves over time, from monitoring ecosystems to tracking urban expansion. Unlike traditional pixel-based or hand-crafted approaches, deep learning models can automatically learn powerful spectral–spatial features, making them especially effective for this task. In this review, we bring together recent advances in deep learning for HSI-CD, combining a meta-analysis of the literature with an overview of the main model families and training strategies. We cover supervised, semi-supervised, and unsupervised methods, as well as newer directions such as transfer learning, self-supervised frameworks, and hybrid designs that blend CNNs, transformers, and graph neural networks. We also discuss benchmark datasets, evaluation protocols, and case studies that show how these methods perform in practice. Beyond summarizing the current progress, the review highlights ongoing gaps, such as limited labeled data, generalization across sensors, computational efficiency, and the need for interpretability, and points to emerging opportunities for future work. Our goal is to provide both a snapshot of the current state of the field and a road map for advancing deep learning-based HSI-CD. Full article

With the widespread adoption of multiple-input–multiple-output (MIMO) technology, channel state information (CSI) prediction has become a crucial technique for enhancing the performance of wireless communication systems. Traditional channel prediction methods face performance bottlenecks under high-speed mobility and complex channel conditions, making it difficult to meet the requirements of modern communication systems. To address this issue, this paper proposes a fully complex-valued cross-domain modeling framework, termed a complex-valued multi-scale transformer with time–frequency cross-attention network (CMTF-Net), for MIMO CSI prediction. CMTF-Net integrates a learnable multi-scale short-time Fourier transform (LMS-STFT), complex-valued multi-head self-attention (C-MHSA), and bidirectional cross-domain attention for complex-valued sequences (BCDA-CVS). These modules are designed to preserve amplitude–phase consistency, adapt time–frequency representations to CSI evolution, and enable information interaction between temporal and spectral features. On the simulated Overall Test set, CMTF-Net achieves the lowest MAE of 0.000032 and the highest Corr. ($\rho$) of 0.8230 among the compared methods, while maintaining competitive SE and BER values of 0.4240 and 0.2411 at SNR = 10 dB. On the DICHASUS measured datasets, CMTF-Net also shows favorable Test-ID and Test-OOD performance. For example, on DICHASUS-2186, it obtains Corr. ($\rho$)/SE/BER values of 0.8367/0.4935/0.2243 on Test-ID and 0.8061/0.4697/0.2351 on Test-OOD. These results indicate that CMTF-Net provides a balanced performance profile across prediction accuracy, spatial alignment, and communication-oriented evaluation. Full article

Plant leaf starch content is a critical indicator of metabolic status, yet traditional enzymatic methods are destructive, labor-intensive, and costly. This study proposes a novel non-destructive detection method using watermelon–pumpkin grafted seedlings. To optimize hardware design, 12 characteristic wavelengths were identified via competitive adaptive reweighted sampling (CARS). A portable multispectral imaging system was developed, featuring narrowband LEDs and integrated human–computer interaction software for real-time visualization. We constructed a multimodal deep learning architecture that integrates a convolutional neural network (CNN) for spatial feature extraction from RGB images, a fully connected neural network (FCNN) for spectral data, and a Transformer network for high-level feature fusion. Experimental results showed that the ShuffleNet v2-Transformer model achieved an R² of 0.956 (RMSE = 0.036) for watermelon leaves, while the EfficientNet b1-Transformer model reached an R² of 0.967 (RMSE = 0.052) for pumpkin leaves. This multimodal approach significantly outperformed conventional PLSR and single-modal CNN models, demonstrating superior ability in processing long-range dependencies within spectral–spatial data. The system enables accurate detection with a throughput of 120 samples per hour at a hardware cost approximately 90% lower than commercial multispectral cameras. This provides an efficient, low-cost solution for large-scale monitoring of plant physiological indicators in precision breeding. Full article

The development of offshore wind energy in tropical cyclone-prone regions requires analytical frameworks that capture non-stationary climate dynamics. This study presents a multi-scale spectral approach to characterize Atlantic tropical cyclone variability and assess implications for offshore wind resilience in the Caribbean Basin. The methodology integrates Fast Fourier Transform (FFT) and Continuous Wavelet Transform (CWT) to resolve temporal variability in sea surface temperature, cyclone frequency, and intensity, complemented by two-dimensional kernel density estimation (KDE) and non-stationarity analysis. Using NOAA and National Hurricane Center datasets, results identify dominant periodicities at annual and ENSO (2–7 year) scales, a post-1995 spectral energy shift associated with the positive AMO phase, and a thermodynamically consistent energy corridor along 12–16° N. A statistically significant change point in 1987 (Pettitt test, p < 0.05) is detected, although spatial displacement is not significant. An integrated Wind Risk Index highlights the central-western Caribbean as a high-exposure zone overlapping offshore wind development areas. Exceedance analysis shows that 39.8% of observations surpass 25 m/s, 6.0% exceed 50 m/s, and 1.3% approach 70 m/s, indicating relevant design considerations. These findings support the need for non-stationary, multi-scale approaches in offshore wind risk assessment under tropical cyclone influence. Full article

Deep learning methods have significantly improved hyperspectral image (HSI) classification by exploiting hierarchical feature learning to integrate spatial and spectral information, thus significantly improving classification accuracy. Nevertheless, current deep learning approaches (such as CNNs, Transformers and Mamba) still face three major challenges: inadequate mitigation of spectral redundancy, high computational costs associated with global modeling, and the loss of two-dimensional spatial structure during sequential processing. To address these issues, we propose LMamba, a task-oriented hybrid framework that combines multi-scale convolutional filtering with local-context-conditioned state space modeling for hyperspectral image classification. Rather than introducing a fundamentally new SSM formulation, LMamba focuses on adapting the input-dependent parameter projection of Mamba to HSI data by injecting local 2D neighborhood context into the generation of selective SSM parameters. This design enables the state space module to better preserve spatial continuity while maintaining linear-complexity sequence modeling. The framework consists of two core components. First, the Multi-scale Aggregation and Compression Block (MACB) employs parallel grouped convolutions with varying kernel sizes to capture spatial features at multiple scales while simultaneously reducing spectral redundancy through channel compression. Second, the Locally Guided 2D Scanning Mechanism replaces conventional unidirectional 1D scanning with a context-aware 2D scanning strategy, thereby preserving structural continuity and enhancing feature representation by integrating local neighborhood spatial information into state transitions. Validation on three prominent HSI datasets demonstrates that LMamba consistently outperforms state-of-the-art methods based on CNNs, Transformers, and SSMs as measured by overall accuracy (OA), average accuracy (AA), and the Kappa coefficient. In summary, LMamba provides an efficient and accurate HSI classification framework under the considered benchmark settings, and its compact complexity and low-sample robustness suggest potential usefulness for practical HSI analysis. Full article

Agriculture faces significant challenges from crop diseases, which threaten global food security and cause substantial economic losses annually. While deep learning has advanced plant disease detection, existing models often struggle with generalization across heterogeneous environments and real-time deployment constraints, hindering their practical application in diverse agricultural settings. This paper proposes AD-DETR, an enhanced real-time detection transformer framework specifically designed for agricultural scenarios. The model incorporates three key innovations to address these issues. First, the Multi-Scale Align Network (MSANet) achieves adaptive feature alignment through an Adapt Fusion Align (AFA) block, effectively preserving disease detail information across varying scales. Second, the Spatial–Spectral Attentive Feature Fusion (SSAFF) module integrates frequency-domain processing with attention mechanisms, enhancing feature representation quality by combining spatial and spectral information. Third, the IPIoUv2 loss function improves bounding-box regression accuracy through an internal perception mechanism and scale-adaptive weighting. Comprehensive experiments demonstrate that AD-DETR achieves strong performance, with 90.2% mean average precision at $IoU=0.5$ on the Crop Disease dataset and 97.4% on the PlantDoc dataset. It maintains high efficiency with 16.4 million parameters, 47.2 GFLOPs computational complexity, and inference speeds of 230–242 frames per second. These results indicate that AD-DETR is robust to domain shift and suitable for resource-constrained applications, such as real-time monitoring on mobile and edge platforms. Full article

Semantic segmentation of very-high-resolution remote sensing imagery benefits from combining RGB appearance with Digital Surface Model (DSM) height information, especially in urban scenes where spectrally similar objects often differ in elevation. On the ISPRS Vaihingen and Potsdam benchmarks, BATFNet achieves mIoU scores of 84.06% and 85.31%, respectively, outperforming representative RGB–DSM fusion baselines on most land-cover categories. BATFNet is a supervised boundary-aware Transformer fusion network that uses DSM-derived edge priors to guide bidirectional cross-modal attention and decoder refinement. With a dual-branch ResNet-50 backbone for modality-specific feature extraction, the proposed framework effectively integrates RGB and DSM information while recovering fine spatial details. These results show that exploiting DSM-derived structural cues improves boundary delineation and reduces confusion among spectrally similar urban classes. Full article

Remote sensing imagery is often degraded by cloud cover, causing severe information loss and hindering downstream Earth observation tasks. Although recent deep learning methods, including CNN- and Transformer-based models, have achieved promising progress in cloud removal, they mainly operate in the spatial domain and largely overlook the frequency-domain discrepancies introduced by clouds of different types and densities. This limitation restricts their ability to generalize across diverse cloud corruption scenarios. To address this issue, we propose a Frequency Interaction Cloud Removal Network (FI-CRNet), which introduces a novel Frequency-Aware Modulation (FAM) mechanism for high-fidelity cloud-free image reconstruction. The FAM module consists of two components. First, the Frequency Decomposition (FD) module explicitly separates input features into low-frequency cloud-affected components and high-frequency detail-rich components through spectral analysis, while aligning them with decoder features via cross-attention. Second, the Cross-Frequency Interaction (CFI) module adaptively integrates these components through a dual-gate weighting mechanism, including spatial and channel gates, to suppress cloud interference while enhancing structural and textural details. By jointly modeling frequency-domain cues and spatial features, FI-CRNet enables robust and adaptive reconstruction under diverse cloud conditions. Extensive experiments show that our method outperforms state-of-the-art techniques across diverse cloud scenarios. Full article

Hyperspectral image classification (HSIC) is a crucial task for remote sensing applications, requiring accurate pixel-level labeling while effectively capturing both spectral and spatial information. Traditional convolutional neural network architectures often struggle to balance local texture detail and global contextual consistency, and existing neural architecture search (NAS) methods rarely incorporate attention mechanisms, limiting their performance. To address these challenges, this study proposes a multi-scale Transformer-based NAS framework (TR-NAS) for fine-grained hyperspectral image classification. The framework combines local cube sampling, shallow and deep multi-scale convolutions, and a searchable Transformer module that adaptively selects global, local window, and multi-scale attention operators. Lightweight enhanced convolution operators, including dual-gated (DG-Conv) and mixed depthwise (MixConv) convolutions, are incorporated to improve spectral discrimination and scale robustness. Extensive experiments on the PU and Hanchuan datasets demonstrate that TR-NAS achieves superior classification accuracy, stability, and boundary consistency compared to traditional methods and existing NAS architectures, showing improved robustness to spectral similarity and spatial heterogeneity in complex remote sensing scenes. Full article

Human performance in critical environments is frequently degraded by mistimed communication delivered during periods of visual–cognitive saturation. In such settings, failures arise not only from individual limitations but also from poor coordination between operators under rapidly changing workload conditions. We present a dual-loop neuro-adaptive simulation framework based on real-time spectral–topographic EEG representations, in which multichannel cortical activity is transformed into dynamic spatial maps and decoded to regulate both operator assistance and team communication. The system integrates 14-channel wireless EEG (Emotiv EPOC X, 256 Hz), gaze tracking, telemetry, and communication events through an LSL-based multimodal synchronization pipeline. A hybrid CNN–LSTM model processes sequences of spectral-topographic EEG maps to classify three operationally actionable neurocognitive states—Channelized Attention, Diverted Attention, and Surprise/Startle—while also estimating a continuous Cognitive Load Index (CLI). These representation-derived features are then used by a multi-agent proximal policy optimization (MAPPO) controller to generate two coordinated outputs: (i) adaptive haptic guidance for the pilot, designed to reduce reliance on overloaded visual and auditory channels, and (ii) a traffic-light communication gate for the telemetry engineer, regulating whether radio intervention should proceed, be delayed, or be withheld. In a high-fidelity dual-station simulation with 25 pilot–engineer pairs, the proposed framework was associated with a reduction of more than 30% in communication breakdown errors relative to open-loop telemetry, with the strongest effects observed during peak-load windows, while preserving realistic task progression. It also improved pilot reaction time to time-critical warnings and reduced engineer decision load under the tested conditions. These findings support the use of spectral-topographic EEG representations as a practical basis for combining multimodal neurophysiological sensing, spatiotemporal pattern decoding, and adaptive coordination in high-pressure human–machine teams. At the same time, the study should be interpreted as evidence of controlled feasibility in a simulated setting rather than as definitive proof of field-level generalization. We further discuss deployment constraints and propose privacy-by-design safeguards to ensure that neurocognitive signals are used exclusively for operational adaptation rather than employability assessment or performance scoring. Full article

Forest above-ground biomass (AGB) estimation is crucial for evaluating carbon dynamics. Although optical and synthetic aperture radar (SAR) data provide complementary spectral and structural information, limitations in existing fusion approaches restrict AGB estimation accuracy. This study proposes a multi-source data fusion framework comparing two image fusion strategies—the conventional Hue-Intensity-Saturation Wavelet (HIS-Wavelet) method and a deep learning-based HIS-Non-Subsampled Shearlet Transform combined with Pulse Coupled Neural Network (HIS-NSST + PCNN) approach—for forest AGB estimation using Gaofen-1 (GF-1), Gaofen-2 (GF-2), and Gaofen-3 (GF-3) satellite imagery in a subtropical forest area of Yunnan Province, China. Three regression models—Multiple Linear Stepwise Regression (MLSR), K-Nearest Neighbor (KNN), and KNN with Fast Iterative Feature Selection (KNN-FIFS)—were systematically compared to evaluate estimation performance and justify model selection. Results indicate that the HIS-NSST + PCNN method outperforms HIS-Wavelet in fusion quality metrics, with the GF-2 Red-Near-infrared-Blue (RNB) band and GF-3 combination using HH co-polarization achieving the highest image quality. The optimal AGB retrieval was achieved with the GF-1RNB and GF-3 combination under HIS-NSST + PCNN (coefficient of determination (R²) = 0.80, root mean square error (RMSE) = 14.79 t/ha), improving R² by 0.07 and RMSE by 2.35 t/ha over HIS-Wavelet. However, for GF-2 + GF-3, HIS-Wavelet achieved marginally better inversion accuracy (R² = 0.71) than HIS-NSST + PCNN (R² = 0.69), indicating that superior fusion quality does not directly translate to higher inversion accuracy. Bootstrap resampling analysis (1000 iterations) confirmed the statistical robustness, with the optimal KNN-FIFS yielding R² = 0.800 (95% confidence interval (CI): 0.678–0.924) and RMSE = 14.79 t/ha (95% CI: 12.51–17.22 t/ha), showing non-overlapping confidence intervals with both benchmark models. These findings demonstrate that spectral complementarity between optical and SAR data plays a more critical role than spatial resolution alone in fusion-based AGB estimation, and that adaptive feature selection is essential for maximizing inversion accuracy. Full article

As a crucial prerequisite for intelligent transportation and urban digitalization, the importance of road extraction is evident. In recent years, the rapid development of remote sensing technology and deep learning has made road extraction from remote sensing images a research focus in both academia and industry. However, the topological complexity of road networks, interference from ground-object occlusion, and the spectral and spatial limitations of remote sensing images have presented numerous challenges to the design and optimization of related algorithms. To address these issues, this paper proposes a road extraction algorithm, U3-Road, which combines the advantages of CNN and Transformer architectures. This algorithm adopts an encoder–decoder structure and uses multi-path nesting technology in the encoder and bridge modules, enabling the extraction of multi-scale contextual features and semantic information, which are fully integrated with the decoder. Additionally, it employs a composite loss function to focus on difficult-to-identify sections and constrain problems such as road breaks and deformations, thereby achieving better accuracy and connectivity. Tests on the DeepGlobe, Massachusetts, and CHN6-CUG datasets show that the Intersection over Union (IoU) of U3-Road reaches 70.47%, 69.55%, and 70.87%, demonstrating leading performance. It effectively alleviates the problems of road breaks and misidentification, and compared with other representative methods, U3-Road performs better in the completeness and accuracy of road extraction results, achieving the best overall extraction effect while maintaining a lower parameter count and computational cost. This model provides a new solution for road extraction from remote sensing images. Full article

Hyperspectral image classification (HSIC) plays a crucial role in fine-grained Earth observation tasks. However, balancing efficient long-range dependency modeling with the extraction of fine-grained local features remains a significant challenge, primarily due to the inherent high-dimensional spectral redundancy and complex spatial variability of hyperspectral data. Existing modeling paradigms exhibit distinct limitations: Convolutional Neural Networks (CNNs) are constrained by localized receptive fields, while Vision Transformers (ViTs), despite their global receptive capabilities, incur prohibitive quadratic computational complexity. Meanwhile, the emerging Mamba architecture has demonstrated remarkable effectiveness in sequence modeling with linear complexity, but it often lacks sufficient sensitivity to local textures when directly applied to non-causal 2D images. To address these limitations, this paper proposes a novel parallel hybrid architecture termed DualMambaFormer. Deviating from the traditional serial stacking paradigm, the proposed network utilizes a dual-stream design to achieve the complementary fusion of global static attention and dynamic sequence reasoning. Specifically, the model first employs an SS-ResNet for spectral dimensionality reduction and local feature embedding. Subsequently, the architecture bifurcates into a parallel encoding stage: one branch leverages Multi-Head Self-Attention (MHSA) to capture global spatial correlations, while the other introduces a Local Enhanced Mamba (LEM) branch. By integrating State Space Models (SSM) with depthwise separable convolutions, the LEM branch simultaneously captures long-range causal dependencies and local spatial context. Finally, a dual class token fusion strategy is designed to integrate heterogeneous representations at the decision level. Extensive experiments on four benchmark datasets—Indian Pines, Pavia University, Salinas, and WHU-HongHu—show that DualMambaFormer achieves OA values of 96.56%, 98.95%, 97.60%, and 96.09%, respectively, with consistently high AA and Kappa coefficients. These results demonstrate the effectiveness, robustness, and generalization capability of the proposed method for hyperspectral image classification. Compared with the second-best competing methods, DualMambaFormer improves OA by 5.55, 2.30, 1.68, and 4.30 percentage points on the Pavia University, Indian Pines, Salinas, and WHU-HongHu datasets, respectively. Full article