Search Results (741)

The super-resolution (SR) of Magnetic Resonance Imaging (MRI) is essential for utilizing clinical scans with limited resolution, noise, and anisotropic sampling, such as multi-modal brain tumor imaging. In this work, we propose a Tri-Representation hybrid framework for MRI SR, TRT-GLA, that redefines the MRI SR task as a joint spatial–spectral–structural high-resolution image generation problem. TRT-GLA utilizes (i) spatial global–local attentions for modeling the spatial anatomy, (ii) a Fourier spectral transfer mechanism for upholding spectral consistency, and (iii) multi-scale hierarchical spectral decomposition for improved edge details. To adapt the learning framework to medical imaging characteristics, we introduce a tri-representation consistent loss function that explicitly combines pixel-wise, spectral, and edge structure priors from the high-resolution ground-truth, as well as a progressive resolution learning strategy. Our large-scale brain tumor experiments, on the IXI, BraTS 2019, 2020, and 2023 datasets, show that TRT-GLA achieves state-of-the-art results at upsampling factors of ×2, ×4, and ×8, respectively, achieving substantial improvements across CNN, GAN, and transformer-based methods in Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index (SSIM), and Multi-scale Structural Similarity Index (MS-SSIM). We further demonstrate how SR benefits brain tumor segmentation through the downstream task evaluation of a dual-branch segmentation framework. TRT-GLA produces highly accurate tumor segmentation results from low-resolution inputs, improving over native high-resolution inputs at ×8 in critical tumor boundary regions and in small tumor regions. There remains a small gap between native, high-resolution imaging and SR-enhanced performance, which TRT-GLA nearly closes under realistic scenarios. Our results highlight the importance of synthesizing unified priors over spatial, spectral, and structural domains within a transformer for anatomically faithful reconstructions. Importantly, we also establish the utility of TRT-GLA in supporting quantitative analysis through a downstream tumor segmentation experiment that is clinically relevant. Full article

Based on generalized Lorenz–Mie theory (GLMT) and the Maxwell stress tensor (MST) method, this study investigates the modulation mechanism of the axial optical torque N_z exerted on Cs₂AgBiBr₆ (CABB) perovskite-coated gold nanospheres under vector Bessel-beam illumination. The results show that the CABB shell reconstructs the torque-resonance channels of the coated particle by modifying both the dispersive dielectric environment around the gold core and the core–shell interfacial response. As the shell thickness increases, the dominant response undergoes a continuous redshift. The polarization state, half-cone angle α₀, and order l of the incident vector Bessel beam serve as external optical-field degrees of freedom that regulate the incident angular-momentum channels, thereby enabling coordinated control over the torque peak magnitude, spectral line shape, and torque direction. Analyses of the near-field distributions, Poynting-vector distributions, and Mie-order decomposition reveal that the strong torque response arises from selective coupling between the intrinsic Mie channels of the core–shell particle and the vectorial structure of the incident light, rather than simply from local field-intensity enhancement. This study provides a theoretical basis for tunable N_z responses in perovskite–plasmonic hybrid nanostructures and for structured-light-driven rotational manipulation at the nanoscale. Full article

Accurate forecasts of O₃, NO₂, and SO₂ from regulatory daily summary records support early warning and environmental management, whereas the inherent nonlinearity, non-stationarity, and multi-scale fluctuations of pollutant sequences severely hinder prediction precision. This paper develops a hybrid CEEMDAN-VMD-GRU-AC model for one-step-ahead concentration prediction of three typical air pollutants. Chronologically ordered valid daily summary records from the Los Angeles–North Main Street monitoring station from 2015 to 2025 were used for evaluation. The original pollutant sequences are first decomposed into multi-scale intrinsic mode functions via complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN). Variational mode decomposition (VMD) is further applied to refine high-frequency IMF1 and IMF2 to decouple irregular short-term oscillations. A gated recurrent unit (GRU) equipped with an additive correction (AC) branch is constructed to predict each decomposed component, and all subseries predictions are aggregated to obtain the final concentration forecasts. The evaluation was conducted under an offline full-series decomposition protocol, in which CEEMDAN and VMD were applied to the complete pollutant sequence before the chronological training–validation–test split; therefore, the reported metrics should not be interpreted as fully prospective rolling-origin forecasting performance. Because the extracted records were not reindexed to a complete daily calendar, the 30-step input represents 30 consecutive valid records rather than 30 uninterrupted calendar days. Compared with benchmark prediction methods, the proposed framework yields the lowest RMSE and MAE, together with the highest R² values of 0.9646, 0.9516, and 0.9035 for O₃, NO₂, and SO₂, respectively. The ablation results reveal pollutant-dependent effects: VMD refinement provides the largest improvement for O₃, whereas the final GRU-AC configuration performs best for NO₂ and SO₂. These results demonstrate the feasibility of the proposed framework under the stated offline protocol, while calendar-complete rolling-origin and multi-station validation remains necessary before operational deployment. Full article

Accurate dynamic cost prediction is essential for budget optimization and risk mitigation in State Grid projects. However, traditional models and even recent deep learning approaches fall short, as they treat cost drivers independently, adopt simplistic concatenation that destroys sourcewise structure, or fail to handle irregularly sampled and partially missing multi-source data. This paper proposes a novel data-driven framework that integrates multi-source business data through a hierarchical tensor fusion mechanism and a hybrid spatiotemporal architecture. The problem is formalized as multivariate time-series prediction with irregular sampling and missing modalities. The framework comprises three synergistic innovations: a differentiable low-rank CANDECOMP/PARAFAC (CP) decomposition layer with adaptive attention weights that preserves cross-source structure while enabling compact dimensionality reduction; a spatiotemporal attention-based bidirectional gated recurrent unit (Bi-GRU) that captures long-range temporal dependencies; and a graph convolutional network (GCN) that explicitly learns interrelations among cost drivers, a capability absent in most existing forecasting methods. The entire system is trained end to end with a customized loss combining mean squared error, quantile loss, and temporal consistency regularization. Extensive experiments on three State Grid substation projects demonstrate that the proposed method outperforms state-of-the-art baselines by 12.7–18.4% in MAPE and maintains robust performance with up to 40% of data missing. These results confirm that explicitly modeling both temporal evolution and driver interdependencies within a unified fusion framework is the key to reliable cost forecasting in large-scale infrastructure projects. Full article

To address the high non-stationarity of COVID-19 pandemic time-series data and the severe error accumulation issue in long-horizon forecasting, a spatiotemporal two-branch multi-step forecasting model named CFC-FLCA is proposed. This model integrates closed-form continuous-time neural networks (CFC), a hybrid decomposition strategy combining variational mode decomposition (VMD) and jump plus AM-FM mode decomposition (JMD), and a cross-attention (CA) mechanism. First, the VMD-JMD hybrid mode decomposition method is applied to preprocess raw new case sequences. By leveraging the complementary advantages of the two decomposition algorithms, non-stationary sequences are adaptively decomposed into high-frequency noise components and low-to-mid-frequency trend-periodic components, eliminating random disturbance interference at the data source. On this basis, a time–frequency dual-branch feature extraction network is constructed. CFC provides ultra-long-range temporal dependency modeling capability; the time-domain branch adopts Legendre projection units (LPU) to extract robust temporal evolution features, while the frequency-domain branch employs frequency-enhanced units (FEU) to uncover latent periodic patterns that are difficult to capture using traditional time-domain methods. A cross-attention mechanism is introduced to dynamically learn the importance weights of time–frequency-domain features, enabling the adaptive deep integration of complementary information and effectively mitigating error accumulation in long-horizon forecasting. Multi-step forecasting experiments are conducted on real-world COVID-19 datasets from Belgium, the Czech Republic, and Ireland, with comprehensive comparisons against mainstream time series forecasting models. The experimental results demonstrate that the CFC-FLCA model outperforms all comparison models across all evaluation metrics for all prediction horizons. Full article

Magnetic Flux Leakage (MFL) sensors are pivotal for the non-destructive inspection of oil and gas pipelines. However, the accuracy of defect quantification is severely compromised by pervasive noise in field-acquired MFL sensor signals, leading to substantial measurement uncertainty. To address this, we introduce a novel hybrid denoising framework that synergizes Improved Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (ICEEMDAN) and Wavelet Packet Decomposition (WPD). The key innovation is the employment of the Rime Optimization Algorithm (RIME) to automatically fine-tune the critical parameters of ICEEMDAN—the signal-to-noise ratio (SNR) and the number of noise additions—thereby customizing the decomposition for superior sensor signal enhancement. This optimization effectively suppresses mode aliasing and yields intrinsic mode functions that faithfully represent underlying defect features. The framework’s efficacy is rigorously validated through mathematical modeling, COMSOL Multiphysics 6.3-based finite element simulation, and real-field MFL sensor data. Results demonstrate remarkable improvements in sensor signal quality: a 53.69% increase in the SNR and reductions of 61.03% in MAE and 62.05% in RMSE over conventional methods. Crucially, the method achieved a Feature Preservation Rate (FPR) of 97.18% on simulated defects, underscoring its exceptional capability to retain critical metrological features for defect sizing. This work provides a robust signal-processing framework that significantly advances the measurement fidelity of MFL sensors, enabling more reliable pipeline integrity assessment. Full article

The increasing proportion of wind power integration in the power systems and the dynamic interaction of power electronic equipment lead to frequent subsynchronous oscillation, which seriously threatens the safety and stability of the system. Therefore, it is urgent to develop a high-precision and robust identification method. Traditional standalone identification methods are vulnerable to wind speed fluctuations and noise, resulting in unsatisfactory accuracy and robustness. To accurately extract the oscillation parameters from the active power signal, this paper proposes a hybrid method for identifying subsynchronous oscillation in power systems. First, the active power signal is preprocessed using the wavelet threshold denoising strategy, which effectively filters out noise through multi-scale decomposition and signal reconstruction. Second, VMD is applied to the preprocessed signal to decompose it into intrinsic mode functions, thereby achieving effective separation of different oscillatory characteristics. Finally, the fast Fourier transform is used to perform spectral analysis on each IMF to accurately capture the dominant frequency and amplitude of each oscillating component. On the four-machine two-area system with DFIG, the verification is carried out under the wind speeds of 9 m/s, 10.5 m/s and 12 m/s and the no noise, 60 dB and 40 dB noise conditions. SSO is excited by inserting 20 Hz, 30.5 Hz or 40 Hz subsynchronous oscillation components into the external part of the mechanical power input of the generator. The results show that the relative error of frequency identification of the proposed method is less than 0.0426% under all test conditions. The relative error of amplitude identification is less than 1.4155%. Compared with different methods, the proposed method exhibits excellent performance under noise conditions and has robustness to wind change and noise interference. Full article

Accurately predicting the strain time series of orthotropic steel bridge decks (OSBDs) is highly challenging due to their strong stochasticity and nonlinear characteristics. This paper proposes a hybrid prediction framework integrating wavelet decomposition with a cascaded Convolutional Neural Network and Long Short-Term Memory architecture. Initially, the raw strain signals are decoupled into temperature-dominated low-frequency trends and vehicle-induced high-frequency dynamic components using the 6-level Daubechies 10 wavelet transform. Subsequently, a deep architecture comprising three CNN layers and two LSTM layers is constructed to precisely extract and learn the local spatial features and long-term temporal dependencies of the decoupled signals. Based on real-world monitoring data, the proposed model is comparatively evaluated against baseline models, including CNN-GRU, LSTM, and Gated Recurrent Unit (GRU), across three time horizons: 24 h, 1 h, and 10 min. The results demonstrate that the proposed method consistently exhibits superior predictive performance across multiple scales. Specifically, the mean absolute percentage error (MAPE) is strictly maintained below 0.6% across all tested horizons, with an R² reaching 0.961. Furthermore, the single-step inference latency is merely 0.63 milliseconds, which is significantly lower than conventional sensor acquisition intervals. This decouple-then-predict analytical framework effectively avoids the feature interference typically encountered when a single network directly processes complex mixed signals. Moreover, while strictly satisfying real-time computational constraints, it provides an undistorted, high-fidelity data foundation for future online fatigue evaluations and continuous state tracking of bridge structures. Full article

To address the deep spatiotemporal coupling of source-load dual uncertainties attributed to the high penetration of distributed photovoltaics (PVs) and electric vehicles (EVs) into distribution grids, and the difficulty of analyzing composite disturbances using traditional methods, this paper proposes a voltage quality analysis method that considers spatiotemporal coupling of source-load uncertainty, focusing on steady-state voltage deviation and three-phase imbalance problems. First, a probabilistic model of PV generation is constructed using the beta distribution combined with Monte Carlo-based scenario reduction, and high-precision forecasting of EV charging loads is achieved by an attention-based convolutional neural network and long short-term memory network. Second, multi-scenario spatiotemporal power flow calculations are conducted on the distribution network to analyze the complementary effects of voltage deviation and three-phase imbalance under the hybrid integration of PV and EV. Finally, gray wolf optimization-based variational mode decomposition is introduced to adaptively decompose the source-load power. This reveals the intrinsic mechanisms where low-frequency components dominate the fundamental amplitude variations of bus voltages, while high-frequency components exert a significant impact on voltage quality. Simulation results demonstrate that the proposed method can effectively analyze the spatiotemporal coupling of source-load uncertainties, providing technical support for the comprehensive management of voltage quality in distribution networks. Full article

Despite recent advancements in solving the Capacitated Vehicle Routing Problem (CVRP), state-of-the-art learning-based methods remain hindered by costly offline training, while classical population solvers rely on implicit mechanisms and rigid parameter tuning. To bridge this methodological gap, this paper introduces the Group Learning Algorithm hybridized with a Multi-Armed Bandit (GLA-MAB), a training-free metaheuristic that transforms evolutionary search into an explicit, controllable learning process. The framework partitions the population into leader-learner groups to extract and inject proven topological structures directly into weaker solutions. Simultaneously, a hierarchical MAB layer oversees the search online, utilizing real-time reward feedback to dynamically manage operator selection and stagnation recovery. Furthermore, a spatial decomposition wrapper ensures strict scalability, extending the framework’s applicability to massive topologies of up to 1200 nodes. Comprehensive evaluations across 117 established CVRP benchmark instances validate the architecture’s efficacy. GLA-MAB achieves near-optimal convergence on classical instances, maintaining mean gaps below 0.03% on Sets A and E, and delivers highly competitive performance on large-scale heterogeneous sets such as Set Li. Ultimately, GLA-MAB provides the dynamic adaptability of modern artificial intelligence while completely eliminating the prohibitive overhead of offline dataset generation. Full article

Coordinating a shared fleet across multiple owners under tight time windows is a challenging multi-objective problem balancing cost, timeliness, and equity. We study it for multi-cooperative agricultural machinery dispatch, formulating the Multi-Cooperative Agricultural Machinery Scheduling Problem under Continuous Workload Sharing (MAMSP-CWS) as a three-objective model that minimizes inter-area transfer cost, time-window violation, and cross-cooperative workload imbalance. To approximate the Pareto front, we develop a Multi-Objective Hybrid Particle Swarm Optimization with Tabu Search and Sparsity Repair (MO-HPSO-TS-SR), which couples particle-swarm search, tabu-search refinement, and a sparsity-repair operator within an external crowding-distance archive. The method is evaluated on three scales (a real instance from Liyang, China, and two synthetic ones) against NSGA-II-CWS and HTSMOGA-CWS over 20 independent runs each. MO-HPSO-TS-SR attains the best mean value on every metric-by-scale combination, with a decisive convergence advantage (hypervolume and IGD; Holm-adjusted $p<0.001$, Cliff’s $\delta \approx 1$). A mechanism decomposition identifies Sparsity Repair as the dominant contributor to hypervolume, with Tabu Search as a complementary refiner. The advantage over NSGA-II-CWS widens with problem scale, from 19.4% on the Small instance to 74.2% on the Large instance, reflecting the disproportionate degradation of the genetic baseline rather than a growing advantage of the proposed method. Beyond agriculture, the framework extends to other continuous-encoding scheduling problems, providing a transferable decision-support tool. Full article

The new type of multi-airbag hybrid airship is a novel lighter-than-air platform, but its flexible structures pose challenges for accurate modal parameter identification under complex fluid-structure interaction. Traditional methods often fail to capture the dynamic characteristics of such compliant systems. In this paper, a stochastic subspace identification method is proposed to estimate the modal parameters of the three capsule hybrid airship. The method constructs the Hankel matrix using only output response data and extracts the system matrix by singular value decomposition so as to identify the natural frequency and damping coefficient. Moreover, the numerical model of the airship (aspect ratio 2.22) is built, and the simulated response data (first five modes) are used to validate the approach. The results show that the identified frequencies and damping ratios match the theoretical values with a maximum error of 6.35%, demonstrating good accuracy and robustness. The proposed technique can provide a reliable tool for online modal identification of flexible airships, supporting structural health monitoring and vibration control. Full article

To address the poor computational efficiency of traditional fixed-stratification methods in very low frequency (VLF) ionospheric propagation modeling, this paper proposes a dynamic stratification algorithm. First, filtering optimization is applied to the electron density, and dynamic adaptive stratification is implemented in the vertical direction. By establishing a nonlinear mapping relationship between the electron density gradient and the stratification thickness, the algorithm integrates dynamic ionospheric stratification with a hybrid regularization algorithm for the transmission matrix. Specifically, Singular Value Decomposition (SVD) and dynamic truncation techniques are employed to process the transmission matrix, effectively resolving the numerical ill-posedness in regions with abrupt ionospheric changes. This enables high-precision calculation of reflection coefficients in the 3–30 kHz frequency band. By tuning parameters such as the reference stratification thickness and adjustment factors, an optimized stratification model and an algorithm quality evaluation coefficient are obtained. The simulation results demonstrate that, compared with fixed stratification, the proposed algorithm achieves an average relative error of 4.7% for the reflection coefficient in the VLF range while improving computational efficiency by more than 50%. This provides a promising approach for efficient and high-precision prediction of VLF wave propagation. Full article

Edge artificial intelligence (Edge AI) requires real-time inference under stringent constraints on computation, memory, energy, and connectivity. Although training can be offloaded to servers, efficient, high-capacity inference and rapid on-device adaptation remain central challenges. Cloud-based inference offers substantial computational power but depends on connectivity, latency, privacy, and reliability conditions that edge deployments cannot always guarantee. Classical model-compression methods—including quantization, pruning, distillation, and neural architecture search—have extended the feasibility of on-device inference, yet they leave largely unchanged the fundamental cost of the linear-algebraic, sampling, and optimization primitives that dominate modern deep learning. Quantum computing has therefore been proposed as a complementary accelerator for selected AI workloads, with theoretical advantages in linear systems, singular value decomposition, sampling, kernel evaluation, and optimization. This review surveys the emerging field of quantum-accelerated AI for edge systems under a hybrid architectural premise: edge devices remain classical, while quantum processors operate as remote, cloud, MEC, or near-edge accelerators. We synthesize advances across quantum learning models, hybrid optimization methods, hardware and deployment architectures, and quantum-inspired approaches suitable for constrained devices. We also assess the practical barriers that currently separate asymptotic quantum advantage from deployable edge intelligence, including data loading, measurement overhead, noise, latency, and benchmarking gaps. Finally, we outline a staged research roadmap from near-term hybrid workflows to fault-tolerant and integrated quantum-edge architectures. Full article

Accurate extraction of typical load curves (TLCs) is essential for electricity market trading, demand-side management, and optimal design of energy storage systems. However, conventional methods are highly sensitive to anomalous consumption days caused by equipment failures or maintenance, which can distort normal electricity consumption patterns. To address this issue, this paper proposes a two-stage unsupervised framework that integrates a deep sequence model with an anomaly detection algorithm for robust TLC extraction. First, a Transformer-based autoencoder is employed to learn complex temporal dependencies and intrinsic patterns from historical daily load data, extracting robust periodic features by reconstructing the input load sequences. Subsequently, the reconstruction error of each daily load curve is computed as an anomaly assessment metric. These reconstruction error features are then fed into an Isolation Forest algorithm to identify anomaly loads that significantly deviate from the learned normal patterns, without requiring predefined thresholds or labeled data. Validation using real-world commercial and industrial electricity consumption data demonstrates that the proposed method effectively filters out various anomalies (e.g., spikes, troughs, and shape distortions) that conventional methods fail to exclude. The extracted TLCs exhibit improved robustness and representativeness. Further case studies indicate that adopting purified TLCs to guide electricity procurement in market trading facilitates more scientific trading strategies and avoids increased electricity costs caused by distorted load patterns. In summary, the proposed Transformer-Isolation Forest hybrid framework provides an effective data-driven solution for robust TLC extraction. The resulting TLCs can be directly used to guide day-ahead market bidding, optimize power purchase contract decomposition, and assess user demand response potential. Full article