Search Results (3,354)

Multi-modal land cover classification plays an important role in remote sensing applications such as urban monitoring and environmental analysis. By integrating complementary information from hyperspectral imagery (HSI) and LiDAR data, multimodal learning can significantly improve classification performance. However, existing Transformer-based fusion methods often suffer from high computational complexity and inefficient cross-modal interaction modeling, which limits their applicability in resource-constrained scenarios. To address these challenges, we propose LMFusion, an efficient framework for multimodal feature learning. Specifically, LMFusion enables efficient bidirectional feature interaction through a linear-complexity cross-attention mechanism and enhances long-range spatial-spectral representation learning with Mamba-based state space modeling, thereby achieving effective multimodal dependency modeling with linear computational complexity. In addition, a selective quantization-aware optimization strategy is introduced to support multiple bit-width settings (down to 1-bit), yielding a more compact and efficient model while improving representation robustness under low-bit constraints. Extensive experiments on the Houston2013, MUUFL, and Augsburg datasets demonstrate the effectiveness of LMFusion. It achieves overall accuracies of 95.84%, 94.95%, and 99.05%, respectively, consistently outperforming representative multimodal classification methods and showing strong potential for accurate and efficient multimodal remote sensing classification. Full article

The processing of two-dimensional (2D) spectral images constitutes a critical and multifaceted discipline in contemporary astronomical data analysis. As spectroscopic instruments evolve towards higher multiplexing, resolution, and sensitivity, the raw 2D data captured by detectors present increasingly complex challenges that transcend simple one-dimensional extraction. This review provides a systematic and comprehensive examination of the methodological evolution in this field over the past two decades. It gathered relevant studies by searching mainstream academic repositories and general search engines with the core keyword ‘2D Spectral Image’, and selected qualified references according to accessibility and research relevance. We categorize the landscape into three major paradigms: (1) physics-based modeling and algorithmic correction techniques for geometric distortion, scattered light, and sky background; (2) data-driven machine learning and deep learning approaches for image correction, spectral classification, and faint signal detection; and (3) the development of open-source software pipelines that democratize advanced processing. A central contribution of this review is a detailed comparative analysis of the performance metrics, underlying assumptions, and practical limitations of prominent algorithms. We highlight the transformative impact of convolutional neural networks (CNNs) and vision transformers (ViTs) on tasks such as celestial object classification and exoplanet detection, while also acknowledging the enduring importance of robust physical models for calibration and uncertainty quantification. The discussion culminates in an assessment of persistent challenges—including computational scalability, model generalizability, and interpretability—and outlines promising future directions at the intersection of AI, statistical inference, and large-scale survey science. Full article

Aircraft targets in SAR imagery often exhibit discrete scattering characteristics, significant variations in pose and scale, strong speckle noise in background clutter, and complex background interference, which jointly hinder stable structural feature extraction and accurate target localization. Existing detectors for SAR aircraft recognition primarily rely on bounding-box regression and classification; they do not completely exploit target structural cues, spatial attention, and frequency-domain information. To address these limitations, we propose a collaborative detection framework that integrates an uncertainty-aware keypoint-driven module (UAKM) with a fractional Fourier convolution backbone (S-FRConv). UAKM introduces a center-keypoint regression branch that jointly predicts keypoint coordinates and Laplacian scale parameters and employs a 2D Laplace negative log-likelihood loss to estimate uncertainty. The derived dense uncertainty heatmap is then used as spatial attention weights to guide distribution-based regression and multi-scale feature re-weighting, without requiring any additional annotations. S-FRConv embeds the Fractional Fourier Transform into shallow backbone layers and C2f modules, enabling joint spatial–spectral feature modeling that suppresses speckle noise and enhances edge and orientation representations. Experiments on the public SAR-AIRcraft-1.0 dataset demonstrate that the proposed method systematically improves the detection performance. For the Nano model, the overall mAP50 increases from 0.810 to 0.867, and the mAP 50:95 improves from 0.637 to 0.655 compared with the baseline, corresponding to gains of 5.7 and 1.8 percentage points, respectively. These results validate the effectiveness and generalization potential of combining uncertainty-driven spatial attention with fractional spectral feature enhancement for SAR aircraft target detection. Full article

Alternating glycopolymers bearing periodically arranged pendant carbohydrate residues were synthesized by reversible addition–fragmentation chain transfer (RAFT) copolymerization of maltose-containing vinyl ether (MalVE) and ethyl maleimide (EtMI). The resulting trithiocarbonate-terminated polymers were subsequently converted into thiol-terminated glycopolymers through post-polymerization end-group transformation. These structurally well-defined alternating glycopolymers were immobilized onto gold nanoparticles (AuNPs) via Au–S interactions to construct glycopolymer-functionalized glycointerfaces. Surface functionalization of the AuNPs was confirmed by an increase in hydrodynamic diameter from approximately 42 to 59 nm after polymer immobilization. The resulting glycopolymer-functionalized AuNPs exhibited concentration-dependent lectin-mediated aggregation behavior in the presence of concanavalin A, accompanied by characteristic red shifts and broadening of the localized surface plasmon resonance (LSPR) band arising from multivalent carbohydrate–lectin interactions at the nanoparticle interface. Although the apparent association constants obtained for free alternating glycopolymers using fluorescently labeled lectin cannot be directly compared with those obtained from LSPR-based aggregation assays of AuNP-immobilized glycopolymers, the values increased from the order of 10⁵ L mol⁻¹ in solution to the order of 10⁷ L mol⁻¹ at the nanoparticle interface. This trend suggests that immobilization onto AuNPs enhances multivalent carbohydrate–lectin interactions through multivalent presentation of the glycopolymer chains at the nanoparticle interface. As a control experiment, peanut agglutinin (PNA), which does not recognize maltose residues, was added to the glycopolymer-functionalized AuNPs. No significant LSPR shift or spectral broadening was observed, indicating that nanoparticle aggregation was not induced by nonspecific lectin addition but arose from specific interactions between maltose residues and Con A. Quantitative analysis suggested that polymer chain length may influence the aggregation behavior. These results demonstrate that alternating glycopolymers provide a useful platform for constructing sequence-regulated glycointerfaces and for investigating multivalent biomolecular interactions at nanoparticle surfaces. Full article

This article presents several new analytical results for a modified class of Bernoulli polynomials, namely, the Bernoulli polynomials of the second kind (BPs2). The paper mainly develops new connection and inverse connection formulas between the first and second kinds of Bernoulli polynomials using two different approaches. One of these approaches uses the generating functions for both polynomial families, whereas the other employs the power series representation, along with its inverse formula and certain closed forms of sums. Another principal contribution of the paper is the derivation of new explicit formulas for moments, derivatives, and higher-order derivatives of the BPs2, together with inverse derivative formulas and mixed linearization formulas involving several polynomial families, including Chebyshev-type and generalized Fibonacci polynomials. Furthermore, a collection of new definite integral formulas associated with the BPs2 is established. The obtained formulas provide new operational representations for the BPs2 and may be useful in spectral methods, basis transformations, and the treatment of differential equations involving polynomial approximations. Full article

Intelligent completion technologies, including Inflow Control Valves (ICVs), have become increasingly important for remotely managing zonal production in complex well architectures. However, quantifying flow rates and phase fractions in such systems remains challenging due to space constraints and the harsh downhole environment, which limit the deployment of conventional sensors. Distributed Acoustic Sensing (DAS) provides a promising solution by converting standard fiber-optic cables into dense arrays of acoustic sensors. While DAS has been successfully applied in applications such as integrity monitoring and leak detection, its use for direct two-phase flow characterization within intelligent completions remains largely unexplored. In this study, we present a DAS-based methodology to monitor and analyze oil–water two-phase flow in horizontal experiments that mimic field conditions. Acoustic data collected from DAS are transformed into time–frequency spectrograms using Short-Time Fourier Transform (STFT) to extract dynamic spectral features. These features are then correlated with pressure drop across the ICV and flow rate, revealing distinct frequency band behaviors associated with fluid changes. To quantify flow characteristics, a power-law model is trained using spectral features to predict flow rate and phase fractions. The results demonstrate strong predictive capability for pressure drop and flow rate under controlled laboratory conditions, highlighting the potential of DAS for multiphase flow diagnostics in field applications with intelligent completions, while water cut prediction remains challenging due to the complex and non-unique relationship between flow conditions and DAS response and is left for future work. This research not only provides new insights into the acoustic response of oil–water flows but also introduces a data-driven framework for leveraging DAS in real-time flow monitoring and control within ICV-equipped completions. Full article

The generation of synthetic seismic accelerograms is a critical problem in earthquake engineering, where the scarcity of strong-motion records, particularly for high-magnitude and near-fault scenarios, limits the reliability of structural analyses and probabilistic seismic hazard assessments. This paper presents a proof-of-concept wavelet-decomposed conditional Generative Adversarial Network (WD-cGAN) for the synthesis of seismic accelerograms that reproduce the physical and statistical properties of real ground-motion records. Unlike prior GAN-based approaches that rely on Fourier-domain decomposition, the proposed architecture decomposes each training signal into N wavelet sub-bands (experimentally $N=7$, six detail sub-bands D1–D6 and one approximation sub-band A6) using the Daubechies-4 (db4) discrete wavelet transform (DWT), assigning each sub-band to a dedicated discriminator. A novel energy-based weighting scheme ${\alpha }_i$ modulates the relative contribution of each discriminator to the total generator loss, ensuring that physically dominant, low-frequency bands, which carry the bulk of seismic energy, receive proportionally higher training emphasis. Seismic moment magnitude $M_w$ serves as the primary conditioning variable, enabling targeted synthesis for specific hazard scenarios. The model is implemented in Python v3.9 using PyTorch v.2.10 and trained on accelerograms drawn from the Italian INGV/ITACA v4.0 archive. Preliminary evaluation on 500 synthetic accelerograms across five magnitude classes provides evidence that the proposed wavelet-domain multi-discriminator scheme reproduces the essential spectral shape and non-stationary temporal structure of real ground-motion records within the considered magnitude range; full quantitative validation on a larger and more diverse corpus, rigorous comparison with competing methods, and extended multi-parameter conditioning are identified as the principal avenues for future work. Full article

This paper investigates recursion operators and nonlocal symmetry structures for the modified Veronese web equation. The novelty of the work lies in the explicit construction of a direct recursion operator and its inverse in the tangent-covering framework. Starting from a compatible linear covering with a spectral parameter, we derive both operators and interpret them as auto-Bäcklund transformations for the corresponding linearized equation. We also determine the contact symmetry algebra and compute the action of the two recursion operators on its infinitesimal generators. In particular, the inverse recursion operator produces shadows of nonlocal symmetries associated with conservation-law coverings. These results provide a concrete recursive mechanism for the symmetry space of the modified Veronese web equation and clarify its covering-based nonlocal geometric structure. Full article

Populus pruinosa Schrenk is a keystone species in arid riparian ecosystems, where its physiological status is critical for biodiversity and soil stabilization. In this study, spectral reflectance, leaf chlorophyll density (CHD), and leaf water content (LWC) were measured for Populus pruinosa in the Tarim River headwater region and Awati County, Xinjiang, from July to October 2023. The aim was to estimate CHD using hyperspectral data combined with machine learning and to evaluate the effect of LWC on model accuracy. Raw spectra were preprocessed using Savitzky–Golay (SG) smoothing and continuous wavelet transform (CWT). A two-step feature selection strategy comprising Random Frog and iterative retaining informative variables (IRIV) was applied to extract characteristic bands. Three machine learning models—support vector machine (SVM), random forest (RF), and extreme gradient boosting (XGBoost)—were developed for CHD estimation with and without LWC as an additional input. Incorporating LWC consistently improved the predictive performance of all models. Without LWC, the RF model achieved the best accuracy (training R² = 0.842, test R² = 0.830), whereas after LWC integration, XGBoost reached the optimal performance (training R² = 0.871, test R² = 0.865). SHAP analysis identified the 687 nm wavelength and its interaction with LWC as the most important predictors. These results indicate that combining spectral information with LWC effectively improves the accuracy and stability of CHD estimation for Populus pruinosa, providing a reliable non-destructive approach for assessing forest ecosystem physiological status—a key contribution to the sustainable management of arid riparian forests. Full article

Accurate and timely diagnosis of respiratory diseases remains a critical challenge in clinical practice, particularly in resource-limited and remote healthcare settings. This study proposes a web-based automated respiratory disease classification system leveraging a hybrid Convolutional Neural Network–Long Short-Term Memory with Time-Distributed (CNN-LSTM-TD) architecture for lung sound analysis. The proposed model integrates three complementary time-frequency representations—Mel-Frequency Cepstral Coefficients (MFCCs), Mel-spectrograms, and Chroma Short-Time Fourier Transform (Chroma-STFT)—to comprehensively capture both local spectral characteristics and long-range temporal dependencies inherent in respiratory cycles. Specifically, the TimeDistributed CNN block extracts localised acoustic features from sequential frames, while the LSTM layer models their temporal evolution, enabling robust identification of pathological acoustic signatures such as wheezes and crackles. The model was rigorously evaluated on the benchmark ICBHI 2017 dataset across six diagnostic categories: healthy, asthma, chronic obstructive pulmonary disease (COPD), pneumonia, upper respiratory tract infection (URTI), and bronchiectasis. The CNN-LSTM-TD model achieved an F1-score of 0.94, recall of 0.91, precision of 0.97, overall accuracy of 96.40%, and an AUC-ROC of 0.96, significantly outperforming standalone CNN, LSTM, and CNN-LSTM baseline models. The accompanying web interface supports audio file upload, real-time visualisation of waveforms and spectrograms, and confidence score reporting, collectively facilitating clinical decision support and telemedicine integration. These results demonstrate that the synergy of temporally aware deep feature extraction and accessible web deployment positions the proposed system as a clinically viable, scalable tool for automated respiratory disease diagnosis and remote patient monitoring. Full article

Red tide events pose substantial threats to marine ecosystems, aquaculture, and coastal public health. Timely and accurate delineation of red tide extent from satellite imagery is therefore essential for operational monitoring and early warning. However, existing deep learning-based semantic segmentation methods generally treat multispectral bands as homogeneous inputs and do not fully exploit the domain knowledge embodied in spectral indices commonly used in traditional remote sensing analysis. To address this limitation, this study proposes a spectral-index-guided network (SIG-Net) that explicitly incorporates spectral-index priors into deep feature extraction through a dual-branch architecture. SIG-Net comprises three components: a spectral encoder based on a Mix Vision Transformer (MiT-B2) that learns spatial-spectral representations from the original Sentinel-2 bands; a lightweight CNN-based index encoder that extracts discriminative features from four spectral indices, namely the red-green index (RGI), blue-green index (BGI), normalized difference vegetation index (NDVI), and the normalized difference Noctiluca index (NDNI) proposed in this study; and a spectral-index-guided fusion (SIGF) module that adaptively integrates multi-scale features from the two branches using spatial-reduction cross-attention and a gated fusion mechanism. Experiments on a Sentinel-2 red tide dataset show that SIG-Net outperforms single-branch baselines, including U-Net, DeepLabV3+, and SegFormer, as well as naive multi-source fusion strategies. Ablation studies further confirm the contributions of the SIGF module, the gating mechanism, and the proposed NDNI to performance improvements. The proposed method provides an effective framework for integrating domain knowledge with deep learning for red tide remote sensing monitoring. Full article

This paper proposes a source-level electromagnetic interference suppression strategy for high-voltage inverters that uses a series-connected IGBT topology and discrete staircase voltage shaping. From an information-theoretic perspective, the staircase shaping transforms chaotic wideband switching noise into a deterministic harmonic structure, thereby reducing the spectral entropy of the EMI source. This information optimization is achieved using a CPLD-based sequential gate drive circuit, which eliminates the need for complex active gate profiling algorithms. Experimental results obtained using a 1140 V explosion-proof motor drive platform demonstrate harmonic attenuation of 4–16 dB μV within a 2 MHz band. Importantly, this targeted entropy reduction occurs alongside a 68.7% reduction in active-region switching losses, suggesting a concurrent decrease in local thermodynamic entropy production during switching transients. Increasing spectral determinism and relaxing requirements for subsequent physical filters effectively lower the conditional entropy of the overall electromagnetic environment. Leveraging the structural flexibility of series IGBTs, this method provides a practical, low-complexity solution and establishes a novel framework between power electronics and information theory for electromagnetic compatibility. Full article

Shortwave infrared (SWIR) imagery plays an important role in land–water boundary delineation, coastal monitoring, and complex aquatic environment observation. However, the spatial resolution of SWIR bands is usually lower than that of visible bands, which limits their capability to represent fine-scale targets and boundary structures. To address this problem, this study proposes MLE-ResUNet, a SWIR image super-resolution method that integrates along-track oversampling with visible-light-guided deep learning. The proposed method first exploits dual-view SWIR observations with sub-pixel displacement generated by increasing the sampling line rate in the push-broom imaging process. A maximum likelihood estimation (MLE)-based physical prior module is then introduced to transform multi-view degraded observations into a physically consistent latent high-resolution prior. Finally, high-resolution visible images are used to provide edge, texture, and structural guidance, and a ResUNet-based network is employed for multi-source feature fusion and residual reconstruction. Based on multi-region measured data acquired by the LHRSI (Lightweight High-Resolution Spectral Imager) payload onboard the BlueCarbon-1A satellite, a SWIR super-resolution dataset covering typical urban, farmland, and coastal scenarios was constructed. Comparative experiments were conducted against PCA, BDSD, PanNet, GPPNN, and two additional lightweight-guided deep learning baselines, namely LGPConv and a CANConv-style visible-guided baseline. The results show that MLE-ResUNet achieves the best performance across different scenarios and consistently outperforms the comparison methods in terms of SSIM, SAM, ERGAS, and Q-index. The proposed method effectively enhances spatial detail recovery while maintaining favorable spectral consistency. Ablation experiments further demonstrate that both along-track oversampling information and the MLE-based physical prior contribute to improved reconstruction quality and more stable training convergence. These findings indicate that the proposed method can enhance fine-scale SWIR observation capability without substantially increasing hardware complexity, providing an effective technical solution for shoreline identification, land–water boundary extraction, and complex surface target monitoring. Full article

Hyperspectral images (HSIs) and Light Detection and Ranging (LiDAR) data offer complementary spectral and spatial information and are extensively applied to land cover classification. Nevertheless, current fusion–classification approaches frequently suffer from cross-modal feature entanglement and insufficient exploitation of LiDAR physical priors, particularly the Digital Surface Model (DSM), which limits the interpretability of learned features and restricts classification accuracy. To address these issues, this study presents a Physics-Guided Adaptive Decoupling and Collaborative Enhancement Network (ADCE-Net) that embeds explicit geometric guidance into multimodal feature learning. In ADCE-Net, the DSM serves as an explicit geometric conditioning signal to guide feature decoupling, decomposing input representations into modality-shared semantic features (SSF) and modality-specific discriminative features (MSF), thereby mitigating cross-modal interference at an early stage. Based on this decomposition, an adaptive collaborative enhancement mechanism is designed using bidirectional cross-attention and dynamic gating to achieve context-aware mutual refinement between SSF and MSF, facilitating more effective utilization of cross-modal complementary information. Furthermore, a multi-level collaborative classification architecture is constructed to integrate multi-scale contextual representations, enhancing spatial consistency and boundary delineation. Extensive experiments on three benchmark datasets—Trento, Houston 2013, and Muufl Gulfport—demonstrate that ADCE-Net achieves overall accuracies of 99.69%, 97.37%, and 94.90%, respectively, surpassing multiple representative methods including support vector machines, 3D convolutional neural networks, transformer-based models, and recurrent neural networks. Noticeable improvements are also achieved for minority classes and classes with highly similar spectral signatures. The DSM-driven physics guidance boosts both classification performance and feature interpretability, providing a reliable and explainable paradigm for multimodal remote sensing classification. Full article

The microstructure of metal matrix composites is inherently governed by fabrication routes and processing parameters, yet technological and physical constraints often prevent the realization of intended structural designs. In particle-reinforced composites produced via casting, interactions between the solidification front and inclusions frequently lead to agglomeration, segregation, and hence, a non-uniform distribution of the inclusions concentration. To mitigate these effects, post-processing techniques such as Friction Stir Processing offering particular promise for cast materials by refining microstructures and enhancing phase homogeneity. This study addresses these challenges by application of Fourier transform analysis to characterize stochastic inclusion distributions. Building on the Windows Washing method, we extend its application to heterogeneous media with varying inclusion concentrations. Through computer simulations and experimental analysis of real composites, we demonstrate that discrete Fourier transform can reveal hidden stochastic periodicity. The proposed framework provides a pathway toward improved predictive models and optimization strategies for metal matrix composites processing and performance. Full article