Search Results (2,942)

Dual-comb ranging enables rapid, high-precision absolute distance measurements, but its performance is constrained by intrinsic phase noise, which induces temporal jitter and degrades pulse-to-pulse mutual coherence. Here, we propose a deep learning network Wavelet-Fused DenseNet (WFDNet) for hardware-free computational phase correction in dual-comb ranging. Through integration of complex wavelet decomposition and physics-guided feature encoding, the network, trained on model-generated data, can directly extract multi-scale time–frequency features to correct phase distortions and recover temporal coherence of the signals. Results from both simulated and experimental scenarios reveal that the approach can effectively suppress spectral noise and retrieve robust and unambiguous phases information, achieving high ranging accuracy with a standard deviation of 0.6 μm. Full article

Glacier mass balance estimation is important for understanding glacier responses to climate change and for assessing mountain water resources. Data-driven methods are widely used, but their cross-regional transferability remains unclear, especially in High Mountain Asia (HMA), where observations are limited. This study develops a unified framework to compare 16 machine learning and deep learning models across the European Alps and HMA. A degree-day-based monthly decomposition scheme is used to generate physically constrained monthly mass balance estimates. These are used as intermediate supervision signals. All models are trained at the monthly scale, and the outputs are aggregated to annual values for evaluation against observations. In transfer experiments, models are trained on Alpine data and tested in HMA. In joint-training experiments, different proportions of HMA samples are gradually added to the training set to assess the role of target-region information. Results show that machine learning models outperform deep learning models in cross-regional settings. Random Forest and K-Nearest Neighbors remain relatively stable under limited HMA data, while deep learning models are more sensitive to distribution shifts. Adding a small amount of HMA data improves annual prediction performance, highlighting the value of region-specific information. Overall, this study provides guidance for modeling glacier mass balance in data-scarce regions. Full article

Reliable fault detection and quantification are essential for the operational integrity of electric machines. While traditional current-based analysis relies on harmonic signatures or wavelet-based time-frequency representations, this study investigates modern learning formulations that capture spectral, multiscale, and temporal characteristics of fault-affected signals. Moving beyond conventional models, including our earlier CNN-based approaches, we develop sequence-based and operator-learning architectures within a multi-output formulation for eccentricity fault analysis. Three models are investigated: Mamba for temporal dynamics, the Fourier Neural Operator for global spectral mapping, and the Wavelet Neural Operator for localized multiscale decomposition. Evaluated on induction, salient pole synchronous, and inverter-based reluctance synchronous machines, each model maps stator current waveforms to multiple diagnostic quantities, including voltages, operating conditions, and fault severity. With time-delay embedding, all three achieve low prediction errors, with severity RMSE reaching the ${10}^{-4}$ scale for the induction machine, a notable reduction from the $0.04$ errors of our earlier hierarchical CNN models. These results show that modern sequence-based and operator-learning formulations can broaden machine fault analysis by enabling simultaneous prediction and estimation of multiple aspects of machine condition within a single model. Full article

Transitioning predictive maintenance from expensive, high-frequency piezoelectric sensors to affordable, edge-deployed MEMS sensors poses a significant challenge in industrial tool condition monitoring (TCM). Both technologies differ in signal quality, frequency capability, robustness, and reliability, which would affect how accurately machine faults can be detected. This work presents a systematic framework to bridge this gap, enabling real-time tool wear prediction and cross-sensor transferability. The methodology employs unsupervised Wavelet Packet Decomposition (WPD) and dynamic programming on high-resolution vibration signals to establish ground-truth wear phases: initial, steady-state, and accelerated. Multi-resolution time-frequency features are extracted and globally ranked using a multi-metric scoring system. A multi-task Bidirectional Long Short-Term Memory (Bi-LSTM) network is then trained to simultaneously predict a continuous wear index and classify discrete wear zones. To ensure model portability, Canonical Correlation Analysis (CCA) is utilised to align the high-fidelity piezoelectric feature space with the lower-frequency MEMS domain. The optimised multi-task Bi-LSTM architecture achieved up to 97.9% zone classification accuracy and a mean absolute error of 0.042 for wear index regression. Furthermore, CCA-based domain adaptation successfully transferred a model trained on piezoelectric data to classify unseen low-cost MEMS sensor data, maintaining a robust 87 % accuracy. Combining optimised WPD features with CCA effectively overcomes hardware and sampling rate discrepancies, proving the viability of using low-cost sensors for reliable industrial retrofitting and real-time degradation tracking. Full article

This paper proposes a novel rolling bearing fault diagnosis method to address the difficulty of accurate feature extraction from nonlinear and non-stationary vibration signals. First, a Levy–Cauchy Optimized Sparrow Search Algorithm (LOCSSA) is developed to optimize the two core parameters (decomposition level and penalty factor) of Variational Mode Decomposition (VMD), and the optimized VMD is used to decompose raw vibration signals to obtain optimal intrinsic mode functions (IMFs). Second, the extracted IMF features are fed into a convolutional neural network (CNN) for local pattern extraction, followed by a bidirectional long short-term memory (BiLSTM) network to model temporal dependencies, with the final fault classification completed via a fully connected layer. Comparative experiments and ablation studies with five benchmark models are conducted to verify the effectiveness of the proposed framework. The results show that the proposed method achieves 96.33% accuracy, 96.67% recall, and 96.54% F1-score, outperforming all benchmark models. Ablation analysis confirms that both LOCSSA-optimized VMD and BiLSTM contribute significantly to performance improvement (p < 0.05), validating the rationality of the proposed method. Full article

We study Membership Inference Attack (MIA) risk in Federated Learning through a two-stage lens that separates (i) whether a target client’s contribution is detectable after aggregation and system noise (Stage I: Signal Survival) from (ii) whether a surviving contribution induces a generative membership score change attributable to the target’s private data (Stage II: Signal Attribution). Stage I models aggregation as a target–background decomposition and shows that detectability hinges on target–background alignment, which can induce cancellation. Stage II connects the surviving target component to a generative MIA score via a local path representation and Lipschitz/smoothness bounds, avoiding architecture-specific assumptions. Our analysis reveals that the leading attribution term is governed by the alignment between the target update and the score geometry of the target data at an appropriate baseline. We validate the theoretical bounds and illustrate risk trajectories across several scenarios. Full article

A central goal of neuroeconomics is to understand how humans make decisions and how their neural processes interact during strategic situations. Game theory provides mathematical tools for modeling such interactions, with equilibrium concepts, most notably the Nash equilibrium, predicting stable patterns of behavior. Classical equilibrium analysis, however, treats cognition as a black box and assumes fully rational agents, whereas human decision making is shaped by bounded rationality, heuristics, and neural constraints. To bridge this gap, we investigate equilibrium behavior directly in the space of neurocognitive activity. Electroencephalogram (EEG) signals provide a high-resolution measurement of neural dynamics underlying attention, conflict monitoring, and evidence accumulation. In this work, we introduce a Neuronic Nash equilibrium, an equilibrium concept defined not in the action space but in the EEG-derived neural representation space. We develop a framework for analyzing two-player turn-based games in EEG space by constructing DMD-based neural embeddings and associated directed network representations. Dynamic Mode Decomposition (DMD) reveals statistically significant differences between the neural dynamics associated with distinct strategic actions, demonstrating that EEG-derived features preserve behaviorally meaningful cognitive structure. The resulting neuronic network representation enables equilibrium analysis directly at the neural level and provides a principled method for linking strategic behavior with stable patterns of neural activity. Our findings suggest that neural-state equilibrium concepts can capture the cognitive foundations of strategic interaction and offer a pathway toward characterizing cognitive equilibrium outcomes in multi-agent settings. Full article

Robust decoding of latent cognitive states from non-stationary physiological time series is a challenging high-dimensional signal processing problem. Traditional unimodal frameworks based only on electroencephalography often show covariate shift and weak cross-task generalization. This study presents the Neuro-Cardiac Symbiotic Engine, a multimodal fusion architecture that combines high-frequency cortical EEG dynamics with low-frequency autonomic regulation derived from heart rate variability within a unified discriminative feature space. The pipeline integrates spectral decomposition and autonomic quadratic descriptors through a memory-optimized high-performance computing workflow on the CEDIA supercomputer. To reduce domain discrepancy between memory and piloting tasks, we design a few-shot calibration strategy based on affine manifold alignment and probabilistic ensemble inference. Validation on 29 subjects reaches a mean classification accuracy of 99.13 percent, far above the zero-shot baseline near 38 percent. Topological analysis also indicates phase-space contraction under high workload, where fused vagal and frontal-parietal biomarkers concentrate system dynamics into a low-entropy attractor. The results establish a mathematically grounded framework for passive brain–computer interfaces and show that orthogonal neuro-visceral integration is critical for reliable cognitive state estimation. Full article

In urban areas, where car congestion is increasing daily, improving traffic-signal control is a key area of study that directly affects people’s quality of life. It is expected that such improvement will reduce environmental traffic load and increase mobility. However, the inability to determine traffic load deterministically complicates the problem. Multi-agent reinforcement-learning approaches provide a solution thanks to their adaptive learning capabilities from instantaneous data. This study evaluates the Multi-Agent Deep Q-Network (MADQN) algorithm and the QMIX value decomposition method (QMIX) in an urban traffic network with 16 signalized intersections, comparing them with Fixed-Time and Max-Pressure. Experiments were conducted under three vehicle-density levels within the same network geometry and phase-matching rules. Performance was evaluated using waiting time, travel time, speed, efficiency, carbon dioxide (CO₂) emissions, time to collision below 1 s (TTC < 1 s), and post-encroachment time below 1 s (PET < 1 s).. In all demand scenarios, both reinforcement-learning controllers achieved successful results. MADQN consistently provided lower average waiting times, whereas QMIX consistently achieved higher efficiency and, in some settings, lower CO₂ and lower cross-seed variation. No statistical superiority between MADQN and QMIX was established. Overall, the results support the value of adaptive control in this test environment and indicate trade-offs among efficiency, emissions, and proxy safety. Full article

Power quality disturbance signals must be continuously monitored, stored, and transmitted for effective analysis, protection, and system planning in modern power systems. The large volume of data generated during power quality monitoring necessitates efficient storage techniques. The sparse representation of power quality signals can significantly reduce memory requirements while preserving important signal characteristics. Since several techniques exist for obtaining sparse representations, it is important to identify the most suitable Sparse Signal Decomposition (SSD) technique for different power quality disturbances. This paper presents a comparative study of various SSD techniques, including Orthogonal Matching Pursuit (OMP), Matching Pursuit (MP), Least Squares–Orthogonal Matching Pursuit (LS-OMP), and Thresholding and Basis Pursuit (BP), along with diverse dictionaries for the representation of power quality disturbances such as sag, swell, transients, and harmonics. Mean Square Error (MSE) and the ratio between the actual signals and reconstructed signals (A/R ratio) are used to evaluate the accuracy, while computation time is considered to compare the computational speed of different techniques. Simulation studies are carried out in MATLAB to evaluate the effectiveness of the SSD techniques. From the simulation results, it is observed that OMP and LS-OMP provide accurate representations of power quality disturbance signals. For sag, swell, and transients, the impulse dictionary performs best with OMP, offering faster computation. However, for harmonics, OMP with DCT dictionary is found to be more effective. Full article

To address the drawbacks of traditional convolutional neural network-based rolling bearing fault diagnosis techniques, including poor feature extraction, low diagnostic accuracy, and poor generalization capability, a dual-channel rolling bearing fault diagnosis model based on VMD-BiGRU and GADF-ResNet-CBAM was proposed. Variational mode decomposition (VMD) was used to first break down and reconstruct the original vibration signal. The rebuilt signal was then input into a bidirectional gated recurrent unit (BiGRU) network in order to extract temporal information. Second, the Gramian angular difference field (GADF) transformed the one-dimensional vibration signal into a two-dimensional picture. This image was then fed into a residual network that was merged with the convolutional block attention module (CBAM) in order to extract spatial characteristics. After concatenating and fusing the data from the two channels, Softmax was finally employed at the output layer to classify different types of faults. The Case Western Reserve University (CWRU) bearing dataset and a self-collected independent dataset from the Xinjiang University experimental rig were utilized for validation. The model achieved diagnosis accuracies of 99.39% and 99.58%, respectively. These results demonstrate the robustness and practical applicability of the proposed method on data acquired from distinct hardware sources and experimental environments, outperforming alternative approaches. Full article

Sweeping jet (SWJ) actuators are widely used in active flow control, but explicitly resolving actuator-scale unsteadiness in full-configuration computational fluid dynamics (CFD) remains prohibitively expensive because of the small geometric scales and high-frequency oscillations involved. Existing reduced-order boundary-condition models constructed from exit-plane data alone can reproduce the observed switching waveform, but they treat the actuator as an input–output black box and provide limited insight into the internal dynamics that generate the response. This work develops a causal state-space reduced-order modeling framework that links internal mixing-chamber dynamics to time-resolved exit-plane boundary conditions. Proper orthogonal decomposition (POD) is used to obtain a low-dimensional representation of the internal flow, and a data-driven linear evolution operator is identified in the reduced space by least-squares regression of successive snapshot pairs. A POD truncation rank of $r=60$ is selected from cumulative-energy and validation-error sensitivity analyses, capturing well above 99% of the fluctuation energy while lying within the converged performance regime. A corresponding reduced operator is identified for the exit plane, and spectral comparison reveals near-neutrally stable oscillatory modes in both regions. Using a $\pm 1\%$ relative frequency-matching tolerance, the dominant reduced-operator modes exhibit a 28.3% frequency overlap, providing operator-level evidence that exit-plane oscillations are dynamically linked to internal coherent structures. This correspondence is further supported by cross-spectral coherence analysis between representative internal and exit-plane probe signals, which shows strong coherence at dynamically relevant frequencies. A delayed causal output mapping is then formulated in which the internal reduced state drives the exit-plane response after an identified lag of 149 time steps, corresponding to $2.98\times {10}^{-3}$ s. This delay provides a physically interpretable convective transport timescale from the mixing chamber to the actuator exit. Over the validation interval, the model maintains a mean relative $L_2$ error below 0.02, with maximum normalized errors below 0.04 for most of the prediction horizon, and localized increases are confined to rapid jet-switching events. Field-level reconstructions of streamwise velocity and total pressure show that the model captures both phases of the jet-switching cycle, with errors concentrated primarily in high-gradient shear-layer regions. Compared with exit-only reduced-order models, the proposed internal-driven formulation improves amplitude and phase fidelity over extended prediction horizons. The resulting framework provides a compact, interpretable, operator-based representation of SWJ actuator dynamics suitable for use as a CFD-embeddable dynamic boundary condition. Full article

Traffic flow prediction is an important and fundamental task for the operation of Intelligent Transportation Systems. In recent years, most studies on traffic prediction have focused on two-dimensional network traffic flow prediction, while there is still no clear consensus on the study of one-dimensional highway traffic flow prediction, for instance, regarding which model is the most appropriate. To address this gap, we conducted a systematic comparative evaluation of 27 models across five classes, including Statistical models, Machine Learning, Artificial Neural Networks, Deep Neural Networks, and Graph Neural Networks, based on five representative highway traffic datasets. To ensure fairness, evaluations were performed on raw data without signal decomposition or auxiliary modules. Surprisingly, the experimental results reveal that complex deep learning models do not demonstrate advantages in terms of conventional metrics. Instead, simple models, particularly Historical Averaging and tree-based Machine Learning models, exhibit superior performance in most scenarios. And then, we study the underlying reasons for this phenomenon from various perspectives, including the complexity of prediction tasks, the tabular data characteristics, the spectral bias of Neural Networks, and theoretical error bounds. Furthermore, we also analyze why these findings were overlooked in the previous literature, attributing the oversight to the predominant focus on signal decomposition preprocessing, inconsistent prediction settings, and the lack of comprehensive benchmarking. Supported by rich data and extensive information, this work offers valuable references and practical implications for researchers in highway traffic flow prediction. It further advocates that in the era of pursuing sophisticated models, scenario-specific analysis and appropriate simple models still deserve more attention. Full article

To address the challenges of strong volatility, pronounced non-stationarity, and the inability of single models to simultaneously capture local dynamics and global dependencies in photovoltaic (PV) power series under complex weather conditions, this study proposes a short-term PV power forecasting framework that integrates weather-based clustering, signal decomposition, parameter optimization, and hybrid neural networks. First, a density-based clustering algorithm, namely Density-Based Spatial Clustering of Applications with Noise (DBSCAN), is employed to partition historical samples into distinct weather regimes, thereby mitigating the impact of heterogeneous meteorological conditions on model stability. Second, to handle the strong non-stationarity of PV power series, Variational Mode Decomposition (VMD) is introduced to decompose the original signal into multiple intrinsic components. The Crested Porcupine Optimizer (CPO) is further utilized to adaptively optimize key VMD parameters, including the number of modes and the penalty factor, thereby improving decomposition quality. Finally, a hybrid LSTM–Transformer forecasting model is constructed to jointly capture local temporal dynamics and long-range dependencies. The Newton–Raphson-Based Optimizer (NRBO) is employed to optimize critical hyperparameters, including the learning rate, regularization coefficient, and the number of hidden units, thereby enhancing model performance. The proposed method is validated using real-world data from a PV power station in Alice Springs, Australia. Experimental results demonstrate that, compared with the LSTM–Transformer baseline, the proposed model achieves reductions in RMSE of 0.086, 0.082, and 0.097 kW, and reductions in MAE of 0.062, 0.082, and 0.081 kW under clear-sky, cloudy, and rainy/snowy conditions, respectively. The corresponding R² values reach 0.993, 0.968, and 0.958. These results indicate that the proposed framework exhibits strong predictive performance across different weather scenarios and provides a reliable reference for short-term PV power forecasting and grid dispatching decisions. Full article

To address the key problems of low-frequency oscillation and insufficient regulation accuracy at the Point of Common Coupling (PCC) in hydro–wind–photovoltaic hybrid systems, which are caused by the randomness of wind and photovoltaic output, the water-hammer effect of hydropower units, and multi-source power coupling, a joint control strategy based on Fractional-Order Proportional Integral Derivative (FOPID) and Co-evolutionary Multi-objective Particle Swarm Optimization (CMOPSO) is proposed. First, a small-signal transfer function model of the system covering photovoltaic inverters, doubly fed induction generators (DFIGs), hydropower units and voltage-source converter-based high-voltage direct current (VSC-HVDC) converter stations is established to accurately characterize the water-hammer effect and multi-source dynamic coupling characteristics. Second, a Caputo-type FOPID controller is designed. Compared with traditional integer-order controllers with limited tuning flexibility, the FOPID controller utilizes its five degrees of freedom to address specific multi-source coupling challenges. This precisely compensates for the non-minimum phase lag caused by the water-hammer effect in hydropower units via the fractional derivative link, and effectively smooths the impact of stochastic wind–solar fluctuations on PCC voltage through the memory characteristics of the fractional integral link. This multi-parameter regulation mechanism prevents a trade-off between response speed and overshoot suppression, achieving effective decoupling of complex multi-source dynamic interactions. Third, a dual-objective optimization framework with the Integral of Time-weighted Absolute Error (ITAE) and Oscillatory Disturbance Risk Index (ODRI) as the objectives is constructed. The multi-population co-evolution mechanism of the CMOPSO algorithm is adopted to solve the Pareto-optimal solution set, realizing the coordinated optimization of dynamic response accuracy and oscillation instability risk. Finally, comparative simulations are carried out on the Simulink platform with traditional PI/FOPI controllers and optimization algorithms such as Multi-objective Particle Swarm Optimization based on the Decomposition/Simple Indicator-Based Evolutionary Algorithm (MPSOD/SIBEA). The results show that the proposed strategy can effectively suppress low-frequency oscillations in the range of 0~30 Hz. Compared with the traditional PI controller, the PCC voltage overshoot is reduced by more than 40%, the oscillation decay time is shortened by 33%, the ITAE and ODRI indices are decreased by 12.58% and 2.47%, respectively, and the stability of DC bus voltage is significantly improved. Its robustness and comprehensive control performance are superior to existing methods, providing an efficient and stable control scheme for power electronics-dominated complex new energy grid-connected systems. Full article