Search Results (1,043)

CNNs can effectively extract features with low computational costs, achieving significant progress in hyperspectral image classification. However, due to the limited receptive field of CNNs, they have difficulty in capturing the multi-scale structural and global contextual information. Moreover, the class imbalance in hyperspectral images often causes the model to focus disproportionately on certain spectral bands, thereby reducing the average accuracy. To address these challenges, a method called the Cascaded Spatial-Frequency Convolutional Network (CSFCNet) was proposed for hyperspectral image classification. It integrates rich spatial-domain information and frequency-domain information by jointly modeling both domains. Specifically, a Dual Spatial Fourier Convolution (DSF-Conv) module was proposed to project feature maps into parallel spatial and frequency representations. In the Spatial pathway, input features are grouped and processed with multi-scale convolutions to extract hierarchical structures; in the Fourier pathway, frequency-domain convolutions can aggregate the global context. Subsequently, a group-cascaded structure connects the DSF-Conv modules with residual connections, alleviating the class imbalance problem by promoting more balanced contributions from different spectral components. Additionally, we introduce a Lightweight Local Attention module to enhance the feature discrimination. Furthermore, experiments on three datasets achieved competitive accuracies, demonstrating the effectiveness of CSFCNet. Ablation studies further verify the effectiveness of the core components within the network. Full article

Aiming to address the problem of extracting the remote sensing FTIR spectral characteristics of the hot jet of a certain type of aero-engine under different working conditions, this paper proposes a feature construction algorithm for the remote sensing FTIR spectral characteristics of the aero-engine hot jet based on the fusion of the original spectral features and the deep spectral features. The infrared spectrum was collected at a distance of 280 m, covering the spectral range of 2.5–15 μm with a resolution of 1 cm⁻¹. The Neighborhood–Autoencoder Integration Dual-Branch Network (NAIDN) feature construction algorithm is proposed. This algorithm contains a neighborhood integration branch and an autoencoder branch. The neighborhood integration branch converts the radiation intensity values of discrete wavenumber points into local energy aggregation features through a sliding window, accurately extracting the key physical information in the original spectrum. The autoencoder branch uses a three-layer fully connected neural network architecture to mine the deep spectral features of the spectral data. The algorithms of the two branches not only retain the physical interpretability of spectral analysis but also capture the multi-parameter coupling information hidden in the hot jet spectrum through the representation learning ability of the autoencoder, achieving feature fusion across spatial dimensions. Compared with traditional feature construction algorithms, the dual-branch feature construction algorithm proposed in this paper has stronger comprehensive representation capabilities. The content of carbon dioxide (CO₂) and cyanide groups (-C≡N) in the hot jet under different operating conditions varies significantly. In the experiment, an unsupervised clustering algorithm, the Agglomerative Clustering classifier, is selected, and the classification accuracy of the features extracted by the algorithm in this paper reaches 92.97% on this classifier, thereby verifying the effectiveness of the algorithm in this paper. Full article

Differential operators often admit multiple algebraically equivalent symbolic formulations, yet those formulations can differ in the organization of their internal structure prior to solution analysis. A reproducible symbolic framework is introduced to compare such formulations at the level of operator expressions. Within a declared symbolic specification consisting of a fixed grammar, an admissible weight class, canonical compression rules, and an admissible family of reformulations, we define four encoding-relative structural descriptors: structural strain τ, structural curvature κ, compressibility σ, and the balance ratio Γ = κ/τ. Structural strain compares an encoding to a designated reference representation, while compressibility measures reduction under canonical symbolic compression. These quantities are deterministic descriptors within the declared encoding class rather than coordinate-free invariants of the underlying operator. The structural length functional underlying these descriptors is developed, canonical compression is formalized, and finite symbolic comparison is distinguished from pathwise symbolic deformation. A robustness theorem shows that, away from the threshold surface Γ = σ, sufficiently small admissible perturbations preserve the induced diagnostic label. A supporting weight-robustness result further shows that qualitative labels persist across a local admissible family of weight choices under corresponding nondegeneracy conditions. The framework serves as a reproducible diagnostic for operator representations alongside Lyapunov, spectral, pseudospectral, and energy-based stability theories. Examples of representative ordinary and partial differential operators illustrate how the descriptors are computed and how they behave under admissible re-expression, while the appendices provide the technical backbone of the paper: formal definitions, reproducibility protocol, extended perturbation arguments, and explicit failure-mode analysis. Additional sensitivity checks regarding encoding, weights, and threshold variation clarify the method’s scope, and explicit failure modes delineate the boundary cases in which the descriptors cease to apply. The main contribution of this study is a formally delimited and reproducible symbolic framework for comparing differential operators under a fixed, declared specification, together with robustness results and worked examples that clarify the method’s scope. Full article

Bearings play crucial roles in industrial machinery. Therefore, the continuous monitoring and effective detection of bearing failures are essential to ensure the safety and reliability of motors. Traditional fault diagnosis methods often require information from both the time and frequency domains; however, converting them into a two-dimensional representation significantly increases computational costs. Conversely, utilizing only time-domain features while ignoring frequency-domain features results in incomplete fault information, reducing accuracy under various operating conditions. This study proposes an efficient dual-stream network with soft-gated fusion for bearing fault diagnosis that simultaneously analyzes acoustic emission signals in the time and frequency domains. Our approach employs two separate feature-learning branches: the time-domain branch directly extracts features from the segmented raw acoustic emission signals, and the frequency-domain branch learns features from one-dimensional spectral vectors obtained using the fast Fourier transform. A gated fusion mechanism adaptively balances the contribution of each domain before classifying fault types. The experimental results show that the proposed method significantly reduces the computational cost compared with that of a two-dimensional-representation-based model and improves accuracy over time-only or frequency-only baselines. Full article

Impulsive noise significantly degrades the performance of power line communication (PLC) systems due to their non-Gaussian amplitude distribution, burst clustering, and inherent temporal dependence. Conventional statistical and spectral models often describe marginal behavior but do not fully account for the underlying temporal organization of such noise processes. This paper introduces an ensemble-based non-linear dynamical framework for the short-window characterization of impulsive PLC noise using delay-embedded phase-space reconstruction (PSR). Rather than relying on extended stationary recordings, the analysis is conducted across multiple independent short-duration acquisition windows obtained from indoor low-voltage networks. For each realization, the delay parameter is selected using average mutual information, and the embedding dimension is determined through the false nearest neighbors (FNN) criterion. The reconstructed trajectories are then examined using correlation dimension estimation, largest Lyapunov exponent analysis, and recurrence quantification measures. The resulting non-linear descriptors reveal structured phase-space organization and low-dimensional dynamical characteristics that are not readily observable in the original time-domain representation. In addition, these findings show that short-window PLC data preserve meaningful dynamical characteristics and support the use of non-linear geometric descriptors for impulsive PLC noise analysis and future mitigation approaches. Full article

The Zeta-Minimizer Theorem establishes that the Riemann zeta function $\zeta \left(s\right)$ and the primes arise variationally as unique minimizers of a phase functional defined on a symmetric measure space $\left(X,\mu ,G\right)$ equipped with helical operators. Three fundamental axioms—strict concave entropy maximization (Axiom 1), spectral Gibbs minima with non-vanishing ground states (Axiom 2), and irreducible bounded oscillations with flux conservation (Axiom 3)—allow for the selection of the non-proper Archimedean conical helix as the sole topology satisfying all constraints. Primes emerge as indivisible minimal cycles in the associated representation graph $\Gamma$ (via Hilbert irreducibility and Maschke’s theorem), while the Euler product is recovered through the spectral Dirichlet mapping of the helical eigenvalues. The partial zeta product, $Z\left(s\right)=\prod _j{\displaystyle \frac{1}{1-p_j^{-s}}},s\in \mathbb{R}\left\{0\right\},$ constitutes the exact grand partition function of any finite subsystem. Numerical inversion of this product directly recovers the mixture frequency $s$ from any experimental compressibility factor $Z_{\mathrm{m}\mathrm{i}\mathrm{x}}$. Mole fractions $x_i\left(s\right)$, interaction parameters $\Delta \left(x_i\right)$, and the Lyapunov spectrum $\lambda \left(x_i\right)$ then follow deductively via the helical transfer matrix and the closed-form linear ODE for $\Delta$. Occupation numbers $N\left(x_i\right)$ attain sharp maxima precisely at Fibonacci ratios $F_r/F_{r+1}$, leading to the molecular prime-ID rule. For twelve representative purely binary (irreducible) systems spanning atomic noble gases, simple diatomics, polar molecules, and an aromatic ring, the residuals satisfy $|Z\left(s\right)-Z_{\mathrm{m}\mathrm{i}\mathrm{x}}|<1.5\times {10}^{-8}$. The resulting $\lambda \left(x_i\right)$ curves accurately reproduce critical points, liquid ranges, and thermodynamic anomalies with zero adjustable parameters. The Riemann Hypothesis follows rigorously as a theorem: the unique fixed point of the duality functor $s\mapsto 1-s$ that preserves the orthogonality condition $\sum {\mathrm{c}\mathrm{o}\mathrm{s}}^2{\theta }^k=1$ is $\mathrm{R}\mathrm{e}\left(s\right)=1/2$, enforced by Axiom 1 concavity and Axiom 3 irreducibility. The framework is fully deductive and parameter-free and extends naturally to arbitrary mixtures and multiplicities through the helical representation graph. It provides a variational unification of analytic number theory, spectral geometry, thermodynamic phase behavior, and the Riemann Hypothesis from first principles. Full article

Against the backdrop of large-scale integration of renewables into the power grid, frequent load-following operation of thermal power units substantially increases the difficulty of controlling boiler NOx emissions. Accurate forecasting of boiler NOx emissions is crucial for guiding efficient and clean operation under such flexible operating conditions. However, under frequent load-following conditions, NOx dynamics are highly nonlinear and non-stationary, making it challenging to achieve accurate prediction using only time-domain information. To address these issues, we propose DTTE-Net, a time–frequency feature fusion framework for predicting SCR-inlet NOx concentration in coal-fired boilers. DTTE-Net consists of three components: a time-domain branch, a frequency-domain branch, and a gated feature fusion module. The time-domain branch captures short-term fluctuations and long-range temporal dependencies, while the frequency-domain branch extracts complementary spectral representations to enhance the characterization of non-stationary fluctuations. The gated feature fusion module then adaptively integrates the two-domain features by using a gated mechanism and produces the NOx concentration forecast. In addition, a Gaussian kernel-based loss is introduced to improve robustness to nonlinear error structures. Experiments on real distributed control system data from a 660 MW ultra-supercritical coal-fired unit show that DTTE-Net outperforms existing baseline models, achieving lower forecasting errors and higher R². Full article

Hyperspectral imaging provides rich spatial–spectral information but generates huge data volumes, posing significant challenges for storage, transmission, and real-time processing in remote sensing applications. In this study, we propose SpecResNet, a 3D autoencoder-based model for hyperspectral image compression. This framework introduces hybrid residual blocks for preserving representational power and a spectral calibration (SC) block to enhance spectral fidelity. It also uses Squeeze-and-Excitation (SE) blocks for adaptive feature recalibration. Our model obtains different compression operating points by varying model capacity, with bitrate emerging implicitly from the learned latent representations. Experiments on several benchmark datasets show that SpecResNet surpasses the performance of existing frameworks on most datasets in terms of PSNR, MS-SSIM, and SAM, demonstrating its strong potential. Our results suggest that SpecResNet offers a promising trade-off for efficient hyperspectral image compression, with potential for further refinement in complex scenes. Full article

The synergistic integration of Hyperspectral Imaging (HSI) and Light Detection and Ranging (LiDAR) data has become a pivotal strategy in remote sensing for precise land-cover classification. However, existing multimodal deep learning frameworks frequently suffer from intrinsic limitations, including rigid feature extraction protocols, underutilization of LiDAR-derived textural information, and asymmetric fusion mechanisms that fail to balance the contribution of spectral and elevation features effectively. To address these challenges, this paper proposes a novel framework named DGC-BCAF, which integrates Dynamic Group Convolution and Bidirectional Guided Cross-Attention Fusion to achieve adaptive feature representation and robust cross-modal interaction. First, a Dynamic Group Convolution (DGConv) module embedded within a ResNet18 backbone is designed to function as the central spatial context extractor. Unlike traditional group convolution, this module learns a dynamic relationship matrix to automatically group input channels, thereby facilitating flexible and context-aware feature representation that adapts to complex spatial distributions. Second, to overcome the insufficient exploitation of elevation data, we introduce a dedicated LiDAR texture encoding branch. This branch innovatively fuses Gray-Level Co-occurrence Matrix (GLCM) statistical features with multi-scale convolutional representations, capturing both geometric height information and fine-grained surface textural details that are critical for distinguishing objects with similar elevations. Finally, central to our architecture is the Bidirectional Cross-Attention Fusion (BCAF) module. Unlike standard unidirectional fusion approaches, BCAF employs a LiDAR geometry to guide the selection of salient spectral bands, while simultaneously utilizing spectral signatures to emphasize informative LiDAR channels. This mutual guidance ensures a balanced contribution from both modalities. Extensive experiments conducted on three benchmark datasets—Houston 2013, Trento, and MUUFL—demonstrate that DGC-BCAF consistently outperforms state-of-the-art methods in terms of overall accuracy, average accuracy, and Kappa coefficient. The results confirm that the proposed adaptive grouping and bidirectional guidance strategies significantly improve classification performance, particularly in distinguishing spectrally similar materials and delineating complex urban structures. Full article

Hyperspectral image (HSI) classification is a core task in remote sensing data interpretation. Although recently introduced state space models (SSMs), such as Mamba, have demonstrated promising performance in hyperspectral analysis due to their linear computational complexity and strong long-sequence modeling capability, existing single-stream scanning mechanisms struggle to effectively balance the intrinsic spectral continuity dependency and the high-dimensional redundancy inherent in HSI data. Moreover, they often suffer from representation discrepancies when fusing features from heterogeneous representation spaces. To address these challenges, we propose a continuous–discrete collaborative framework, termed Confluence Mamba (CF-Mamba). Specifically, the continuous modeling path (AHSE) introduces a multi-view adaptive routing mechanism to accurately capture anisotropic spectral–spatial continuous evolution patterns. Simultaneously, the discrete interaction path (IISE) employs interval sampling and channel shuffling strategies to efficiently decouple high-dimensional redundancy while maintaining fine-grained feature interactions. Furthermore, the confluence gating unit (CGU) leverages a bidirectional cross-modulation mechanism to constrain discrete feature distributions using continuous contextual information, effectively alleviating representation discrepancies during multi-scale feature fusion. Extensive experiments conducted on four benchmark datasets, namely, Indian Pines, Pavia University, Houston, and WHU-Hi-Longkou, demonstrate that CF-Mamba achieves overall accuracies of 97.77%, 99.68%, 99.06%, and 99.59%, respectively. The proposed method consistently outperforms existing CNN-, Transformer-, and Mamba-based approaches in terms of both classification performance and computational efficiency. Full article

Multispectral remote sensing image super-resolution (RSISR) aims to reconstruct high-frequency details while preserving cross-band structural consistency under strict computational budgets. However, real-world satellite imagery exhibits heterogeneous distortions, ranging from band-dependent noise to spatially varying texture degradation, rendering uniform restoration strategies suboptimal. To address these challenges, we propose a unified framework that integrates cue extraction, expert specialization, and efficiency-aware restoration. Specifically, a Distortion-Aware Feature Extractor (DAFE) explicitly encodes distortion cues by synthesizing fixed frequency bases, learnable residual components, lightweight spatial edge representations, and noise proxies. Subsequently, a Distortion-Aware Expert Choice (DAEC) router utilizes these cues to establish distortion-conditioned affinities and performs capacity-constrained, load-balanced expert assignment. Finally, a parameter-shared Mixture-of-Experts (PS-MoE) architecture employs shared expert parameters across spectral bands, augmented by band-wise low-rank adapters, to enable coarse-to-fine restoration with minimal computational overhead. Extensive experiments on the SEN2VENμS and OLI2MSI datasets demonstrate that the proposed method achieves a PSNR of 49.38 dB on SEN2VENμS 2×, 45.91 dB on SEN2VENμS 4×, and 45.94 dB on OLI2MSI 3×. Compared to the strongest baseline for each task, our method yields PSNR improvements of 0.12 dB, 0.10 dB, and 0.09 dB, respectively, while simultaneously reducing FLOPs and parameter counts. These results confirm that explicit distortion modeling and parameter-shared expert specialization provide an effective and computationally efficient solution for multispectral remote sensing image super-resolution. Full article

With the large-scale integration of renewable energy and the increasing use of power electronics, the issue of wide-band oscillations in power grids has become increasingly prominent. The scarcity and uneven distribution of oscillation samples pose significant challenges for training data-driven models, and traditional generative models struggle to ensure fidelity in both time and frequency domains. To address this, this paper proposes a Time–Frequency Fusion Generative Adversarial Network (TFF-GAN) for generating power grid oscillation risk scenarios. The method constructs a dual-path generation and discrimination framework, where the generator decomposes the signal using Short-Time Fourier Transform (STFT), with time-domain features extracted by a convolutional neural network (CNN) and frequency-domain features extracted from the STFT representation by a dedicated spectral network. These features are then fused using a U-Net structure. The discriminator simultaneously evaluates the authenticity of both the time-domain waveform and the frequency-domain spectrum. A composite loss function, incorporating time-domain loss, frequency-domain loss, and adversarial loss, is used for joint optimization. Experimental results demonstrate that the proposed method generates oscillation scenarios with high fidelity in both time-domain waveforms and frequency-domain spectra, effectively supporting power grid oscillation risk assessment and control strategy validation. Full article

The precise identification of minute, high-velocity entities within unconstrained visual fields represents a significant hurdle in computational perception. This difficulty primarily arises from the geometric degradation stemming from scale volatility, motion-induced asymmetry, and heterogeneous background clutter. To mitigate the critical deficit of high-fidelity benchmarks for dynamic micro-targets, we present Soccer-Wild. This comprehensive dataset is characterized by the extreme visual complexity of microscopic objects in diverse ecological settings. Built upon this empirical foundation, we introduce GOAL (Global Object Alignment for Localization). This novel computational paradigm is designed to enhance the weak features of tiny targets by integrating frequency-domain filtering, dynamic feature routing, and entropy-guided probabilistic modeling. The GOAL framework rigorously preserves spatial-structural equilibrium and information fidelity through three synergetic mechanisms: (1) Spectral Purification: We implement a Frequency-aware Spectral Gating approach that operates in the Fourier manifold, suppressing stochastic noise to accentuate the spectral signatures of the targets; (2) Geometric Adaptation: A Multi-Granularity Mixture of Experts (MG-MoE) is formulated with heterogeneous receptive fields to dynamically rectify anisotropic distortions caused by kinetic blurring. This adaptive routing ensures cross-state representation consistency; (3) Information Recovery: We propose Information-Guided Gaussian Distribution Estimation (IGDE), which utilizes information entropy to conceptualize target coordinates as radially symmetric probability densities. This facilitates the implicit recovery of latent signals typically discarded by rigid deterministic regression. Empirical validations on the Soccer-Wild and VisDrone2019 benchmarks reveal that the proposed methodology yields substantial gains in precision. Specifically, our model achieves 40.0% and 40.4% AP (Average Precision), respectively, establishing a new state-of-the-art for localizing highly dynamic, micro-scale objects. Full article

Based on the Direct Probability Integral Method (DPIM), this study investigates the global seismic reliability of reinforced concrete (RC) frame structures considering the randomness of material parameters and the non-stationarity of ground motions. A doubly non-stationary ground motion model is established using evolutionary power spectrum theory combined with the spectral representation–stochastic function method. A dimensionality reduction technique is adopted to generate ground motion samples compatible with the design response spectrum. A finite element model of the RC frame is developed in Abaqus. Modal analysis and deterministic time history analysis are conducted to obtain the dynamic characteristics and seismic responses of the structure. Based on 600 representative ground motion time histories generated using the maximum frontier (MF) discrepancy sampling method, nonlinear time history analyses are performed. The DPIM is then employed to calculate the statistical characteristics of structural responses and quantify response variability, enabling a rational evaluation of the structural safety margin. Finally, based on the equivalent extreme value event theory and DPIM, the reliability of the structure under a single failure mode and the global reliability under multiple failure modes are computed. The results show that the global reliability of the structure is 82.088%, which is significantly lower than that of any single failure mode. This study provides a quantitative reference for evaluating the global seismic reliability of RC frame structures subjected to nonstationary seismic excitation. Full article

Spectral methods form a cornerstone of linear dynamics, where evolution is resolved into harmonic modes governed by eigenvalues and spectral measures of normal operators. For nonlinear dynamical systems, however, the harmonic eigenfunction paradigm typically breaks down: Koopman operators are often non-normal, may possess a continuous spectrum, and rarely admit complete eigenbases on natural observable spaces. This work develops a resolvent-centered operator-theoretic framework for generalized spectral representations of nonlinear flows through their associated Koopman $C_0$ semigroups. Rather than relying on diagonalization, we construct resolvent-generated generalized spectral operators that yield weak integral representations of the semigroup valid in non-normal and continuous-spectrum regimes. We show that, under mild polynomial resolvent growth bounds along vertical lines, these spectral distributions become finite complex Radon measures on bounded spectral regions, thereby recovering a measure-theoretic interpretation analogous to classical spectral integrals. In the normal case, the framework reduces to the standard spectral theorem. The resulting resolvent-based perspective naturally incorporates pseudospectral amplification and transient growth, providing a unified description of both asymptotic and non-modal dynamics. Full article