Search Results (930)

Observations of time-varying scenes using a Fourier-transform spectrometer can produce scene-change artifacts in the measured spectra. These artifacts typically appear as oscillations in the spectra and are often mistaken for noise. Interferogram-offset scene-change artifacts arise from an incorrect interferogram offset estimate. The error is Fourier-transformed and superimposed onto the measured spectrum. The recently developed smooth offset correction method removes these artifacts. Prior to this work, this correction method had only been applied to spectrally smooth targets. Concerns have been raised regarding its application to targets with structured spectra. In addition to the interferogram-offset scene-change artifacts, higher-order artifacts are predicted to be significant for structured spectra. Linear scene-change artifacts occur when a target moves with constant velocity through the field of view, and quadratic scene-change artifacts occur when a target moves with constant acceleration. These artifacts are largest near abrupt spectral transitions. Despite this, the higher-order artifacts remain relatively small and have minimal impact on spectral accuracy. We conclude that, after smooth offset correction, the remaining scene-change artifacts can be ignored when examining spectrally smooth targets such as notch filters. Full article

Existing zero-shot low-light image enhancement methods often underutilize image priors, leading to noise amplification and color distortion. To address these issues, we propose a zero-shot framework for low-light image enhancement. The framework first performs illumination-aware self-supervised denoising to generate a cleaner reference image, which is then used to guide diffusion-based enhancement with a pre-trained backbone. Specifically, the denoising module uses pairwise downsampling together with the proposed illumination prior to suppress noise in dark regions. We then guide the reverse sampling of the pre-trained diffusion model with a refinement strategy operating in both the frequency and spatial domains, so that illumination enhancement and local detail refinement can be jointly achieved during sampling. At each step, Fourier-based reconstruction contributes to illumination enhancement while preserving structural information, and illumination-guided spatial adjustment further refines local brightness. Experiments on multiple benchmark datasets show that the proposed method improves illumination while preserving structural details. Full article

In practical industrial applications, rolling bearing fault samples are often scarce and costly to annotate, making small-sample fault diagnosis challenging. To address this issue, this paper proposes a frequency-aware time–frequency representation learning framework, named Multi-branch Frequency Enhancement Temporal Attention Network (MFETA-Net). In the proposed framework, dual-channel vibration signals are first transformed into time–frequency representations using the Short-Time Fourier Transform (STFT). Then, a multi-branch frequency enhancement encoder is used to extract local frequency-band patterns, cross-band correlations, and frequency variation features. A temporal-frequency dependency modeling mechanism preserves the correspondence between temporal positions and frequency distributions during sequential modeling, while a temporal attention aggregation module emphasizes diagnostically important regions. Extensive experiments on the CWRU and HUST bearing datasets show that MFETA-Net achieves accuracies of 77.26% and 79.60% under the smallest training setting, respectively, indicating its capability to learn discriminative fault representations from limited labeled samples. Ablation studies further verify the effectiveness of each proposed module, while noise experiments confirm the robustness of the proposed framework under controlled noisy conditions. Full article

To address the issues of element failures and performance degradation in antenna arrays caused by harsh outdoor environments, in this paper, we propose a neural network-based fault diagnosis method alongside an adaptive-threshold radiation pattern recovery algorithm based on the Fast Fourier Transform (FFT). For fault diagnosis, the proposed method utilizes the far-field patterns of the damaged array as input data to train and test a Convolutional Neural Network (CNN). The training dataset comprises simulated data embedded with Gaussian noise to replicate real-world conditions. Distinguishing itself from conventional neural network-based diagnostic approaches, this method innovatively applies sum-and-difference beam processing to the far-field data, effectively resolving the long-standing challenge of diagnosing symmetrical element failures while maintaining low computational complexity and achieving superior identification accuracy. Regarding performance recovery, an adaptive threshold mechanism is integrated into the traditional iterative FFT optimization algorithm. This mechanism dynamically adjusts the restoration criteria according to diverse element failure scenarios and significantly reduces the number of iterations, thereby lowering the computational overhead while enhancing the efficiency of radiation pattern recovery. Full article

This paper presents an adaptive noise-aware bearing fault diagnosis framework that integrates Fast Fourier Transform (FFT)-windowed feature extraction, wavelet-based Signal-to-Noise Ratio (SNR) estimation, and Long Short-Term Memory (LSTM) classification to maintain high diagnostic accuracy under both clean and severely noisy operating conditions. The core novelty of the proposed framework lies in its adaptive model selection mechanism, which automatically selects the most appropriate LSTM classifier according to the estimated SNR, thereby improving diagnostic robustness across different noise environments. Experiments were conducted on two benchmark datasets, the Case Western Reserve University (CWRU) dataset and the Huazhong University of Science and Technology (HUST) bearing dataset, to evaluate the generalization capability of the proposed approach. Two preprocessing pipelines were examined: time-domain normalization before FFT and frequency-domain normalization after FFT. Vibration signals were segmented without overlap to ensure unbiased evaluation. The results demonstrate that both the choice of window function and the normalization strategy significantly influence classification accuracy and robustness. Under noise-free conditions, several window types achieved accuracies above 99%, with triangular and Hamming windows providing the best performance. The combination of triangular windowing and time-domain normalization achieved the highest accuracy of 99.69%. Furthermore, time-domain normalization combined with triangular windowing exhibited superior stability and noise resistance compared with frequency-domain normalization. Under noisy conditions, noise-augmented training was found to be essential for achieving robust generalization. Models trained with moderate noise levels (8–12 dB) provided the best trade-off between accuracy and robustness, whereas excessive noise during training degraded performance. To accommodate varying noise environments, a lightweight wavelet-based SNR estimator was used to categorize operating conditions into low-, medium-, and high-SNR regions and select the corresponding LSTM classifier. The proposed framework was successfully implemented on a ZedBoard FPGA (Field-Programmable Gate Array) development board using a System-on-Chip (SoC) architecture. Experimental results show that, with a sampling frequency of 48 kHz and a processing window of 2048 samples, the proposed system updates the diagnostic result every 42.7 ms, demonstrating its suitability for real-time industrial condition monitoring and intelligent predictive maintenance applications. Full article

To address ambiguous maneuver boundaries, background interference, and uneven multi-sensor quality in long-duration flight parameter recordings, this paper proposes an adaptive flight maneuver boundary localization algorithm that integrates spectral entropy-weighted multi-channel spectrogram fusion with attitude-constrained structural correction. Multi-channel Short-Time Fourier Transform (STFT) spectrograms are first constructed from flight parameter time series. Spectral entropy (SE) is introduced to quantify the uncertainty of each channel’s time–frequency energy distribution and is combined with the maneuver activation ratio (MAR) and the linear contrast ratio (LCR) to form objective credibility weights, thereby suppressing channels dominated by aerodynamic turbulence and high frequency structural vibration. Normal overload soft gating and logarithmic noise floor subtraction are then applied to obtain an enhanced fused spectrogram, from which candidate intervals are extracted by low band energy thresholding. Finally, roll and pitch angle steady-state priors refine the event structure through local boundary refinement, cross-segment expansion/chain merging, and semantic post-processing, recovering continuous maneuvers fragmented by instantaneous energy valleys. On the held-out test sorties (SE_018–SE_020; 61 annotated intervals), the proposed algorithm achieves Precision, Recall, and F1-scores of 0.967. On the full primary corpus of 20 sorties (461 intervals), used for ablation and sensitivity analyses, the corresponding figures are Precision 0.934, Recall 0.959, and F1 0.946, with start and end boundary mean absolute errors of 1.484 s and 1.471 s. Under the same IoU protocol, consistent superiority is observed against learning-based baselines, and an independent external set of 10 sorties yields F1 = 0.938. The results indicate that entropy-constrained multi-sensor time–frequency fusion mainly improves maneuver/background separability, whereas attitude-constrained structural correction restores the integrity of long continuous maneuvers. Full article

Automatic modulation recognition (AMR) identifies the modulation scheme of received radio frequency (RF) signals under unknown channel conditions and underpins spectrum monitoring and signal demodulation in wireless systems. Under low signal-to-noise ratio (SNR), multipath fading, and limited observation length, however, the discriminative features of modulated signals are severely attenuated, degrading recognition robustness. We propose MSTFFNet, a multi-scale time-frequency fusion network that addresses these challenges with two designs. First, it fuses the raw in-phase/quadrature (I/Q) signal with its short-time Fourier transform (STFT) time-frequency map at the token level through dual-stream heterogeneous encoding, capturing complementary temporal and spectral features. Second, rather than relying on external SNR ground truth, the network self-estimates an SNR-bin probability from the I/Q features and generates a channel-quality embedding that conditions the classifier, requiring no SNR label at inference. On the RadioML2016.10a and 10b benchmark datasets, MSTFFNet achieves overall accuracies of 67.33% and 70.87%, outperforming state-of-the-art methods by 3.53% and 5.33%, with improvements of 5.91% and 9.52% in the low-SNR regime. These results demonstrate improved recognition performance across the SNR conditions represented in the two synthetic RadioML2016 benchmarks, particularly at low SNR. Full article

Rolling-element bearings are a leading cause of unplanned downtime in continuous-process manufacturing, and the migration toward Industry 4.0 condition-based maintenance (CBM) has intensified the need for diagnostic methods evaluated on real in-service assets. This paper reports an exploratory, longitudinal single-asset industrial field demonstration of Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN)-based Hilbert spectral analysis for rolling-element bearing condition monitoring. An in-service bearing on a critical production machine was monitored over eight measurements spanning approximately four months and analyzed with the Hilbert–Huang Transform, using CEEMDAN in place of the classical Empirical Mode Decomposition to suppress mode mixing. The Hilbert spectra tracked the evolution of the bearing’s vibration signature as a growing concentration of vibration amplitude in a stable band of the 0–400 Hz analysis window (approximately 280–380 Hz); because the analysis characterizes the distribution of amplitude within the band rather than resolving discrete defect lines, this is reported as band-amplitude trending, and the band is treated as compatible with bearing-related excitation rather than attributed to a specific kinematic fault frequency. At the final pre-replacement measurement (M8), a bounded consistency cross-check against a conventional single-sided Fast Fourier Transform (FFT) amplitude spectrum computed from the same exported waveform recovered co-located dominant content. This establishes cross-method consistency for the measurement examined, but does not independently validate diagnostic correctness or the full campaign trend. Interpretability of the representation is argued qualitatively and remains to be tested. The contribution is therefore the documented field application and its explicit consistency cross-check procedure; applicability beyond this asset and its operating conditions requires multi-asset evaluation. Full article

Data-driven models are transforming structural health monitoring (SHM) for composites. However, excessive sensor costs and scarce, noise-contaminated data hinder model accuracy and generalizability. In this study, an electromechanical impedance (EMI)-based physical features and data-driven framework for high-precision damage assessment under conditions with noise and limited data is proposed. An experimental system that incorporates random noise to simulate operational environment noise was used to simulate seven progressive simulated damage states in CFRP laminates. Adaptive low-pass parabolic filtering via a fast Fourier transform smoothing filter (FFT-SF) denoised conductance signals in the frequency domain, increased efficiency over the Hinkley criterion, and significantly suppressed false alarms from sensor drift. Three input variables were selected: the resonant frequency F (reflecting structural stiffness), the resonant amplitude A (reflecting structural damping), and the root mean square deviation (RMSD) index (a statistical measure of spectral deviation). These three variables, two physics-based features and one statistical index, formed the inputs to a three-input artificial neural network (ANN). The fusion model achieved an RMSE of 0.0752 and an R² of 0.9807 on 105 small samples, significantly outperforming a purely data-driven single-input RMSD-ANN (RMSE of 0.1066; R² of 0.9612). Critically, Shapley Additive Explanation (SHAP) analysis revealed that the physical features significantly enhance model interpretability and predictive reliability, maintaining >98% simulated damage identification accuracy with extremely limited real data. This provides a cost-effective, high-precision, and scalable paradigm for aerospace composite SHM. Full article

Accurate sea surface wind speed fields are essential for marine navigation, offshore operations, and air–sea interaction studies. However, limited communication bandwidth makes it difficult to receive forecasts from land-based centers, motivating wind speed reconstruction using sparse observations. To address this challenge, we propose SwiftWind, a coordinate-based deep learning framework for sea surface wind speed reconstruction at arbitrary locations by fusing multi-source observations. SwiftWind embeds non-gridded, variable-length observations through adaptive latent representations and latitude–longitude coordinate encoding. We conduct Observing System Simulation Experiments (OSSEs), real-world observational experiments, and arbitrary-location inference experiments. Under ERA5-based evaluation, SwiftWind consistently outperforms existing data-driven baselines, including Fourier Neural Operator (FNO) and Vision Transformer (ViT) models, demonstrating robustness to observation number, noise level, and spatial distribution. Compared to the GFS 6 h forecast fields, SwiftWind achieves approximately 20–23% reductions in RMSE and 19–22% reductions in MAE under real-world observational settings. In independent buoy validation, SwiftWind performs comparably to ViT and slightly worse than FNO, likely due to differences in scattered-point processing and buoy distribution. These findings indicate that SwiftWind is suitable for near-real-time onboard wind speed reconstruction under sparse-observation conditions. Full article

The counter-diabatic shortcut to adiabaticity (CDSTA) has been explored in implementing qudit quantum Fourier transforms (QFTs) via stimulated Raman adiabatic passage (STIRAP) to suppress non-adiabatic leakage. While direct CD driving may introduce unwanted global microwave couplings, seeking an approach without explicit CD fields is highly desirable. By employing rotating-frame absorption, we implement an all-optical CDSTA strategy to synthesize the QFT. Direct CD driving (STIRSAP) removes the adiabatic time floor of STIRAP and sets the acceleration upper bound; the all-optical scheme reproduces this acceleration with a peak-amplitude overhead below $5\%$ in the working regime while eliminating the microwave coupling. The quartit encoding further reduces the integrated energy by a factor of 3 relative to the two-qubit decomposition. Extending to open quantum systems, the all-optical strategy shows improved robustness against amplitude noise and spontaneous emission. Full article

Temperature–time profiles obtained through thermistor-based monitoring provide a rich but noise-sensitive source of information for estimating kinetic and thermal parameters in exothermic batch reactions. Conventional workflows typically combine deterministic smoothing with numerical differentiation, an approach that can amplify measurement noise and fail to propagate preprocessing uncertainty into the resulting reaction-rate and parameter estimates. To address these limitations, this study presents an uncertainty-aware Bayesian machine-learning framework that integrates scalable random-Fourier-feature Gaussian-process (RFF–GP) smoothing, analytical differentiation, temperature-derived apparent conversion, Bayesian parameter inference, posterior validation, predictive calibration, model comparison, ablation, sensitivity analysis, probabilistic benchmarking, simulation of thermal nonideality, and endpoint diagnostics. The framework was applied to $379,631$ cleaned thermistor observations. The production RFF–GP achieved a validation root-mean-square error of $0.04805\mathrm{K}$, yielding a stable latent temperature trajectory and an uncertainty-aware estimate of $dT/dt$. On a smaller matched subset, exact Gaussian-process regression achieved the highest predictive accuracy and the best probabilistic scores, whereas the RFF–GP reduced central-processing-unit runtime by approximately $4.1$-fold and remained applicable to the larger production fit. A Monte Carlo dropout neural comparator produced larger prediction errors and substantially wider predictive intervals. Six apparent thermokinetic structures were evaluated using mean-field variational inference, after which the nth-order and autocatalytic structures were validated using the No-U-Turn Sampler (NUTS). Under mean-field variational inference, the apparent autocatalytic structure achieved the lowest point estimate of the widely applicable information criterion (WAIC), the lowest derivative-domain error, and the lowest full-profile temperature-reconstruction root-mean-square error of $0.2920\mathrm{K}$. Its posterior obtained using NUTS yielded $E_a=40.98\mathrm{kJ}{\mathrm{mol}}^{-1}$, $k_{\mathrm{ref}}=0.005815{\min }^{-1}$, $\Delta T_{\mathrm{ad}}=56.11\mathrm{K}$, $m=0.1694$, and $n=1.0784$. The sampling diagnostics indicated satisfactory convergence, large effective sample sizes, and no divergent transitions. Although the MFVI posterior means and NUTS posterior medians were similar, variational inference produced narrower uncertainty intervals for several correlated parameters. Moving-block bootstrap intervals did not establish a decisive separation in WAIC among the leading structures. Expanded sensitivity, ablation, imperfect-insulation simulation, and endpoint-holdout analyses further showed that the apparent parameter estimates were sensitive to optimization, thermal nonideality, sensor response, and Gaussian-process boundary behavior. The autocatalytic formulation should therefore be interpreted as the best-performing apparent structure among the candidates tested rather than as evidence of a unique chemical mechanism. Overall, the framework extracted physically plausible apparent thermokinetic information from noisy temperature-only measurements while explicitly quantifying uncertainty arising from prediction, parameter estimation, model form, computation, thermal nonideality, and boundary behavior. Full article

Motor fault identification is often constrained by scarce labeled samples and the limited representation capability of a single time–frequency transform. Conventional CNN–Softmax models may also produce unstable decision boundaries under small-sample conditions. To address these issues, this paper proposes a motor fault identification method based on the fusion of fixed-resolution and multiscale time–frequency features. Each vibration segment is transformed into short-time Fourier transform (STFT) and synchrosqueezed wavelet transform (SWT) maps. Two parallel convolutional branches extract complementary features, which are fused by element-wise addition and classified using a radial basis function support vector machine. Experiments on the HUST motor multimodal fault dataset show that the proposed method achieves 100% accuracy under the conventional 70%/30% train–test split. When the training proportion is reduced to 20%, 15%, 10%, and 5%, the corresponding accuracies remain at 99.46%, 99.10%, 98.78%, and 96.77%, respectively. Across operating speeds of 5, 10, 20, and 30 Hz, the average accuracies reach 98.75% and 94.61% under the 20% and 5% training conditions. The model also maintains 100% accuracy at signal-to-noise ratios of 15 dB and above. These results demonstrate that complementary time–frequency feature fusion combined with maximum-margin classification improves identification accuracy and decision-boundary stability under limited training data. Full article

With the increasing diversity of multimedia data types, single-modal steganography is insufficient to meet the demand for the simultaneous covert communication of multiple types of data, and single optical transformation encryption schemes are insufficiently secure against cryptanalytic attacks. To address these challenges, this paper designs and implements a multimodal secret information steganography system based on the optical Gyrator transform. We propose a multimodal steganographic system for the covert transmission of three types of heterogeneous secret data—text, color images, and audio—using a three-level cascaded optical encryption architecture. The system first uniformly encapsulates the multimodal data into a unified bitstream via a Type–Length–Value (TLV) format; it then uses the Ushiki chaotic map to generate a pure phase mask for random phase modulation of the carrier image, followed by spatial-frequency scrambling via a fractional Fourier transform (FrFT, order γ = 1.6). The secret bitstream is embedded into all eight bit planes of the amplitude components in the FrFT domain using binary square representation, achieving an embedding capacity of 2.23 × 10⁶ bits—approximately 8.5 times that of traditional LSB methods; finally, a speckle-noise-like ciphertext is output via a Gyrator transform (angle α = 0.5). Experiments demonstrate that under non-attack conditions, the system achieves lossless recovery with a zero bit-error rate. Under known-plaintext and chosen-plaintext attacks on the Gyrator layer, the PSNR of the recovered images was only 4.89 dB and 4.80 dB, respectively, and the secret information could not be effectively extracted, as the chaotic-FrFT pre-encryption statistically isolates the intermediate image from natural image statistics. This system provides a functionally complete and practically secure solution for multimodal covert communication. Full article

With the continuous penetration of renewable energy and power electronic equipment into modern power systems, the occurrence frequency of composite power quality disturbances has increased significantly. The accurate classification of various composite disturbances under strong noise remains a critical technical challenge. The existing single time–frequency transformation methods cannot simultaneously capture transient time-domain details and fine frequency-domain features of steady-state harmonics, while mainstream deep learning classification networks contain redundant parameters and introduce excessive computational overhead, failing to meet the real-time deployment requirements of power edge terminals. To address these limitations, a lightweight Coordinate Attention ResNet network named ResNet–LCA is proposed based on the dual-modal time–frequency fusion of the Continuous Wavelet Transform and Short-Time Fourier Transform. First, the two transforms are implemented separately to generate two groups of complementary time–frequency maps, which are concatenated along the channel dimension to fully extract the coupling features between the steady-state harmonics and the transient impulses. Second, a Haar wavelet subband mean aggregation module is designed for dimensionality reduction with negligible information loss. This module eliminates the channel redundancy introduced by the multimodal fusion and reduces the overall computational overhead at the input stage. Finally, a lightweight residual network integrated with Coordinate Attention is constructed, with Grouped Half-Convolution adopted to compress the model parameters. CA offsets the feature attenuation induced by the lightweight structural design and further improves the model’s noise immunity. A simulation verification was carried out on a simulated dataset covering 25 types of single and superimposed composite disturbances. At a signal-to-noise ratio of 20 dB, the proposed method achieved an average classification accuracy of 97.92%, with only 5.32 M total parameters and a single-sample GPU inference latency of 0.33 ms. Compared with standard ResNet-18 under 20 dB noisy conditions, the total parameter volume was reduced by 52.7%, the inference latency was shortened by 0.13 ms, and the classification accuracy was improved by 0.60 percentage points. The proposed method achieves coordinated optimization of classification accuracy, noise immunity and inference efficiency, and it can provide lightweight technical support for online intelligent power quality monitoring at the edge nodes of microgrids and islanded power systems. Full article