Search Results (8,075)

Fault diagnosis in grid-connected grid-forming hybrid energy storage station (GFM-HESS) systems is challenging because fault transients are jointly affected by converter control dynamics, multi-source electrical couplings, operating-condition variations, and measurement noise. To address these characteristics, this paper proposes a virtual synchronous generator (VSG)-constrained physics-informed heterogeneous temporal graph neural network (VSG-PI-HTGNN) for multi-class fault diagnosis. Based on VSG control characteristics and electrical relationships, 18-dimensional node-level features and eight-dimensional global physical features are constructed from ten monitored signals. These signals are further represented as a heterogeneous graph with five node types and eight predefined relation types, while node-type-specific transformations, heterogeneous graph convolution, learnable relation-scaling factors, and a primary–auxiliary dual-output framework are integrated for feature learning. A MATLAB/Simulink electromagnetic transient model is established to generate 3200 samples covering normal operation and nine fault conditions. At a signal-to-noise ratio (SNR) of 18 dB, the proposed model achieves 97.25% test accuracy and a macro-F1 score of 0.9727. Ablation results show that removing all physical information reduces the accuracy to 89.83%, while, under the unified experimental setting, the proposed model obtains higher values of the reported diagnostic metrics than the seven considered benchmark methods. Further evaluations show that the accuracy remains between 95.50% and 98.75% across SNR levels of 10–30 dB and reaches 95.38% with only 20% of the training data. Validation using an independently acquired hardware-in-the-loop (HIL) dataset further yields 92.75% accuracy and a macro-F1 score of 0.9282. Overall, these results indicate that the proposed method provides favorable diagnostic accuracy, noise robustness, data efficiency under limited-sample conditions, and simulation-to-HIL transferability under the evaluated conditions. Full article

This study proposes Multiple-Input Multiple-Output and Orthogonal Frequency-Division Multiplexing methods, as introduced in the IEEE 802.15.7a-2024 standard, to achieve higher data rates and longer transmission ranges in OCC systems where a camera is used to capture optical signals. OFDM is a multi-carrier modulation scheme extensively used in high-data-rate wireless communications to mitigate ISI caused by multipath propagation. In optical wireless communication (OWC) systems, OFDM has been widely adopted in both indoor and outdoor applications, including eHealth, smart home, and smart IoT systems. OWC technologies provide a secure and low-interference communication channel for IoT devices using visible light. In OWC-enabled edge computing, data processing is performed in nodes, reducing communication overhead and improving system scalability. Nevertheless, user mobility remains a major challenge for OWC systems, as time-varying optical channels significantly degrade signal processing performance. Furthermore, reliable signal detection under mobility is critical for improving the signal-to-noise ratio. To overcome these challenges, this paper proposes a deep learning-based LED detection scheme for a mobility-aware MIMO-OFDM system. Deep learning techniques are also utilized to identify OFDM frame boundaries and decode the transmitted data, replacing traditional signal processing approaches. Experimental results demonstrate that the proposed method enables long-range MIMO-OFDM communication over distances of up to 22 m while maintaining a low error rate at a receiver speed of 3 m/s. Full article

Background: Ultra-low-dose (ULD) chest CT can reduce radiation exposure but may compromise image quality. We evaluated image-domain generative adversarial network (GAN)-based denoising at low-dose (LD) and ULD levels, focusing on ULD-AiR versus LD-ADMIRE S3. Methods: In this single-center retrospective paired study, 262 participants underwent LD and ULD chest CT on the same scanner. Images reconstructed with Advanced Modeled Iterative Reconstruction at strength 3 (ADMIRE S3) were post-processed with AiR Denoising v1.0, yielding four series. Objective metrics, including signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR), and 5-point subjective ratings were compared within dose levels and between ULD-AiR and LD-ADMIRE S3. Exploratory regression assessed associations of ULD-to-LD SNR log-ratios with the volume CT dose index (CTDI_vol) log-ratio and anthropometric variables. Results: The median paired reduction in estimated effective dose from LD to ULD CT was 46.5%. Within each dose level, AiR reduced image noise and increased SNR, CNR, and subjective scores. Compared with LD-ADMIRE S3, ULD-AiR showed lower image noise and higher SNR/CNR in the lung, aorta, and muscle; liver findings were less consistent, whereas vertebral metrics were less favorable. Lung-parenchyma scores did not differ significantly, mediastinal soft-tissue scores favored ULD-AiR, and overall image-noise scores favored LD-ADMIRE S3. Exploratory regression identified CTDI_vol log-ratio associations with aortic and muscle SNR log-ratios; some anthropometric associations were sensitive to an influential observation. Conclusions: Image-domain GAN denoising improved several objective and subjective image-quality metrics at both dose levels. With a median paired reduction of 46.5% in estimated effective dose, ULD-AiR showed tissue- and endpoint-specific image-quality differences relative to LD-ADMIRE S3. These findings do not establish diagnostic or screening equivalence. Full article

Background: Forty-hertz sensory stimulation has emerged as a potential approach for modulating neural activity relevant to Alzheimer’s disease. However, electrophysiological changes following non-flickering 40 Hz light stimulation in older adults remain unclear. This study investigated whether a single-session intervention of non-flickering 40 Hz light stimulation would be associated with increased resting-state 40 Hz oscillations in cognitively normal older adults. Methods: In this uncontrolled single-arm pilot study, 16 cognitively normal older adults underwent a 60 min session of non-flickering 40 Hz light stimulation. Resting-state EEG was recorded immediately before and after stimulation. Relative power within 38–42 Hz was analyzed across six predefined scalp regions and the whole-brain measure using one-tailed Wilcoxon signed-rank tests with Benjamini–Hochberg false discovery rate (FDR) correction. Exploratory real-time EEG recordings during stimulation were available in 10 participants. Results: After FDR correction, resting-state 38–42 Hz relative power was higher post-stimulation in the central (FDR = 0.045, effect size = 0.555) and right temporal (FDR = 0.014, effect size = 0.724) regions. In the absolute-power sensitivity analysis, only the right temporal increase remained significant after FDR correction (FDR = 0.042). Exploratory during-stimulation analysis showed a nominally increased 38–42 Hz signal-to-noise ratio in the right temporal region (p = 0.026). One participant reported very mild fatigue; no other adverse responses were reported. Conclusions: This pilot study suggests regional increases in resting-state 38–42 Hz activity after non-flickering 40 Hz light stimulation, with additional absolute-power support for the right temporal finding. These findings remain preliminary given the uncontrolled design and small sample. Full article

Non-cooperative sensing using signals of opportunity traditionally requires an explicit reference signal for target detection and localization. This paper introduces a reference-free sensing framework in which target geometry is inferred directly from the received waveform rather than by comparison with an acquired or reconstructed illuminator signal. The proposed framework is implemented using the Ranging, Detection, Imaging, Communications, Approach, and Landing (RaDICAL) architecture, which combines a hybrid Dish–Sparse Uniform Circular Array (SUCA) receiver with Starlink downlink transmissions as spaceborne illuminators of opportunity. Deterministic Multifrequency Dither (DMD) applied across the SUCA elements transforms spatial diversity into unique composite waveform signatures. A unified electromagnetic and signal-processing model is developed that combines spherical-wave propagation, parabolic focusing, deterministic multifrequency modulation, and QR-based waveform-domain hypothesis testing for direct target localization. Numerical simulations together with link-budget analysis demonstrate the feasibility of the proposed approach. Single-dwell detection of 0 dBsm targets is achieved at physical signal-to-noise ratios near 0 dB, while near-unity detection probability is obtained above 10 dB SNR under controlled false-alarm conditions. The results demonstrate that commercial Starlink LEO communication satellites can serve as practical illuminators of opportunity for reference-free non-cooperative sensing without requiring acquisition or reconstruction of the transmitted illuminator waveform. Full article

Background/Objectives: Single-pass triple-rule-out computed tomography (CT) angiography (TRO-CTA) must compromise among differing pulmonary, coronary, and aortic contrast-transit times. Wide-area detector CT (WAD-CT) and dual-source CT (DSCT) offer different coverage, temporal resolution, and dose profiles, but direct comparative evidence for a sequential single-bolus strategy is limited in selected emergency patients with overlapping concern for acute coronary syndrome, pulmonary embolism, or acute aortic syndrome. We compared territory-specific image quality and radiation dose; diagnostic accuracy was not assessed. Methods: This retrospective study included 114 adults (WAD-CT, n = 60; DSCT, n = 54). After test-bolus timing, one weight-based diagnostic bolus was used for sequential pulmonary, electrocardiography-synchronized coronary, and non-gated aortic acquisitions. Attenuation, noise, signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), blinded dual-reader quality scores, and radiation dose were compared by territory. Results: Mean overall scores across the two readers were ≥3 for every examination in all phases. WAD-CT showed higher pulmonary trunk SNR (19.5 ± 8.9 vs. 14.3 ± 3.8; p = 0.002), higher ascending aortic SNR (24.9 ± 11.4 vs. 14.2 ± 3.0; p < 0.001), lower coronary and aortic noise, and 38.1% lower total estimated dose (6.40 ± 1.72 vs. 10.34 ± 6.91 mSv; p < 0.001). DSCT showed higher right coronary attenuation (671.8 ± 186.7 vs. 466.4 ± 128.9 Hounsfield units; p < 0.001), no significant difference in right coronary SNR (p = 0.681), and less aortic-root pulsation artifact (p < 0.001). Pulmonary- and coronary-phase overall scores were comparable. Conclusions: Both protocols provided acceptable territory-level image quality from one diagnostic bolus. WAD-CT provided lower coronary and aortic noise and estimated radiation dose, whereas DSCT provided higher coronary attenuation and less aortic-root pulsation artifact. Diagnostic accuracy and performance in subsegmental pulmonary arteries and distal or small coronary branches remain unestablished. Full article

Hyperspectral images (HSIs) are inevitably degraded by mixed noise, which hampers downstream interpretation. Recent graph-signal-processing denoisers encode the spatial–spectral structure of an HSI through a product graph over superpixel bodies, yet the adopted Kronecker (tensor) product graph retains only the joint spatial–spectral edges and discards the pure-spatial and pure-spectral edges—the two priors that govern HSI smoothness. We introduce a two-parameter weighted product-graph family that contains the Kronecker, Cartesian and strong products as exact special cases, and propose Weighted Strong Product Graph Laplacian Regularization (WSPGLR)—the strong-product branch with a tunable joint-edge weight β—embedded in a global low-rank plus sparse model solved by the Alternating Direction Method of Multipliers (ADMM) with singular-value-thresholding and soft-thresholding updates and a sparse conjugate-gradient (CG) solve. On three simulated cubes (Washington DC Mall, Pavia University, Indian Pines) under four mixed-noise scenarios, WSPGLR consistently improves Mean Peak Signal-to-Noise Ratio (MPSNR) and ERGAS (Erreur Relative Globale Adimensionnelle de Synthèse) over a matched Kronecker-product control in every tested case (and Mean Structural Similarity (MSSIM) in 11 of 12 settings)—up to 2.5 dB in MPSNR from the graph term alone—and an ablation shows that β governs a spatial–spectral fidelity trade-off (Spectral Angle Mapper, SAM). On the detailed urban scenes, WSPGLR attains the highest MPSNR against the external methods and matched control in seven of eight settings, whereas it trails LRTDTV on the smooth agricultural scene; with an optional scene-adaptive TV step it attains the best average rank across scene types; a Tucker-based variant further shows the low-rank block is modular and generally improves spectral fidelity. Tests on four no-reference real HSIs and 30 paired real-noise MEHSI samples extend the sensor coverage; on MEHSI, the native-domain RND framework remains substantially stronger, which delimits the scope of the proposed training-free regularizer. Full article

DC distribution networks employing a low-current grounding method offer high power supply reliability. However, when a single-pole grounding fault occurs on a feeder, the fault current characteristics are not distinct, making accurate fault identification and feeder protection challenging. Prolonged operation with the fault may cause insulation damage, potentially leading to pole–pole short-circuit faults and escalating the incident. Therefore, equipping the system with reliable and rapid feeder protection is crucial. This paper analyzes the fault current in a two-level VSC-based DC distribution system under single-pole grounding faults, clarifies the relationship between the transient current of the feeder and the line capacitive current, and further investigates the variation patterns of fault transient current and Teager-based signal-feature characteristics. Based on this, a single-pole grounding fault protection method utilizing the Teager instantaneous-current feature is proposed. The Teager energy operator is employed to extract the instantaneous current feature of each feeder, and a protection criterion is constructed using the dimensionless feature ratio between the faulty pole and the non-fault pole to identify the faulty feeder. A simulation model of the DC distribution network is built using MATLAB/Simulink. Simulation results show that the proposed protection method can adapt to various scenarios, including different line faults, fault locations, fault resistances, and noise, while demonstrating satisfactory performance. Full article

This paper presents a delay-aware observer-side voltage-source inverter (VSI) nonlinearity compensation chain for medium- and high-speed sensorless control of permanent magnet synchronous motors (PMSMs). The method reduces the observer-model voltage mismatch caused by inverter nonlinearities and is implemented with a continuous boundary-layer adaptive-gain sliding-mode observer (ASMO) and a second-order phase-locked loop (PLL). Two-point linear prediction estimates the phase current when the VSI nonlinear voltage error actually takes effect. A $C^1$-continuous cubic zero-crossing weight limits abrupt direction changes near current zero crossings, while a synchronous correlation signal derived from the estimated back electromotive force updates the equivalent distortion-voltage amplitude online. Compensation is applied only to the reconstructed ASMO input voltage, leaving the original current loop and space-vector pulse-width modulation (SVPWM) unchanged. Comparative and ablation simulations show lower characteristic back-EMF harmonics and electrical rotor-position estimation error than conventional compensation. Hardware tests under variable-speed and load-step conditions confirm improved dynamic estimation and disturbance rejection. The intended operating region is medium to high speed, where the back-EMF has sufficient signal-to-noise ratio and a nonsalient machine model is appropriate. The fixed-point realization is reported as implementation-feasibility evidence rather than as the principal contribution. Full article

Multiple-source DOA (Direction of Arrival) estimation is vital for array processing, radar, and integrated sensing and communications, yet classical subspace methods degrade under low signal-to-noise ratios and snapshot-starved conditions due to inaccurate sample covariance matrices. To address this, we propose a Toeplitz-enhanced neural network (TENN-DOA) for DOA estimation, a hybrid physics-informed framework for uniform linear arrays that combines the array signal processing prior with a lightweight learning-based regressor. The front end explicitly enforces the Hermitian–Toeplitz structure and fuses the projected matrix with the sample covariance via an analytically derived optimal shrinkage coefficient, yielding a robust covariance estimate. This enhanced representation is mapped onto an overcomplete angular dictionary, producing a feature sequence structurally coupled with the array manifold. A pooling-free one-dimensional convolutional neural network with decreasing kernel sizes starts with large kernels to capture the broad spectral envelope from grid mismatch, and then regresses to a pseudo spatial spectrum under multi-hot supervision for grid-point estimates. The Monte Carlo simulation results show that under the conditions of low signal-to-noise ratio, limited snapshots and the simulated ideal uniform linear array scenario, TENN-DOA achieves a higher resolution probability and lower root mean square error compared with MUSIC, TLS-ESPRIT and the deep learning-based baseline algorithm DA-MUSIC. Full article

Conventional static MRI sequences routinely used in veterinary medicine provide limited information regarding joint motion and kinematics. Therefore, this study aimed to compare the diagnostic utility of static and kinematic MRI for the evaluation of the feline TMJ in cadavers and for the detection of TMJ dislocation using a low-field (0.25 T) MRI system. In addition, TMJ inclination angles were measured in both intact and experimentally dislocated joints at maximal interincisal opening (MIO) and in the closed-mouth position. Static MRI examinations were performed using T1-weighted (T1W), T2-weighted (T2W), and three-dimensional (3D) sequences acquired in both the closed-mouth and MIO positions. kMRI was performed using a 2D HYCE S sequence during repetitive mandibular opening and closing movements. Subsequently, TMJ dislocation was experimentally induced in a subset of cadavers, which were then rescanned using the same imaging protocol. Inclination angle measurements were analyzed using linear mixed-effects models. Compared with static MRI, kMRI demonstrated lower image quality, primarily due to motion artifacts and a reduced signal-to-noise ratio (SNR). TMJ inclination angles were significantly affected by both mouth position (p < 0.001) and dislocation status (p = 0.005). Mouth position had the greatest influence on inclination angles, with significantly larger values observed during maximal mouth opening than in the closed-mouth position. Furthermore, the left TMJ exhibited significantly greater inclination angles than the right TMJ (p = 0.012). Experimentally induced dislocation significantly altered TMJ inclination angles, indicating measurable biomechanical changes associated with joint instability. Full article

Magnetic anomaly detection (MAD) is a core technology for the detection of ferromagnetic targets, yet traditional methods such as the Orthogonal basis function (OBF) detector suffer from severe performance degradation in low signal-to-noise ratio (SNR) and Gaussian colored noise environments. To address this issue, this paper proposes a novel neural network architecture based on manual feature extraction, namely the Partitioned Classification Network with 42 features (PCN-42). First, a total of 42 magnetic anomaly features belonging to three categories, i.e., time–frequency features, statistical features, and magnetic moment features, are extracted from magnetic measurement data. Subsequently, each category of features is processed independently by parallel sub-networks followed by feature fusion. Finally, the performance of the proposed method for magnetic anomaly signal detection is verified under colored noise simulation conditions combined with measured geomagnetic noise. In the experiments, the target is modeled as a magnetic dipole with moment 200 $\mathrm{A}\cdot {\mathrm{m}}^2$, closest point of approach (CPA) ranges from 300 to 800 m, and noise conditions span Gaussian colored noise ($\alpha$ = 0.5, 0.8, 1.0) plus measured geomagnetic background. Simulation results demonstrate that compared with the OBF detector, the detection probability of the PCN-42 detector is improved by 45–75 percentage points, reaching over 80% in different magnetic moment directions and approximately 90% at CPA = 450 m. Experiments with measured noise further validate the effectiveness of the proposed method. This method significantly improves the detection probability of magnetic anomaly signals in colored noise environments. MAD serves a broad range of civilian purposes, including mineral exploration, buried pipeline monitoring, archeological prospection, and humanitarian unexploded ordnance (UXO) clearance. Full article

Bearing fault diagnosis increasingly relies on multiple sensors, since compound or multi-location faults can produce signatures that are only partially captured by a single sensor. The decision-level fusion (DLF) of independently trained models offers a practical way to combine such complementary information, yet systematic comparisons across DLF techniques remain scarce, particularly for measurements from different sensor locations. This paper benchmarks six DLF strategies, i.e, Max, Average, Majority Voting, Weighted Sum, Dempster–Shafer, and Stacking, on a dual-branch one-dimensional convolutional neural network (1D-CNN) with each branch trained end-to-end on vibration signals from a distinct bearing location. On a two-sensor test bench covering seven health conditions, all methods exceed 99.7% accuracy on clean signals, while Dempster–Shafer fusion proves markedly more robust under noise, retaining up to 84% accuracy at a 5 dB signal-to-noise ratio (SNR). A conflict-coefficient analysis further provides an interpretable account of when fusion succeeds, linking performance to the confidence complementarity between branches. Full article

This paper introduces a Joint 4-channel wavelength-division multiplexed (WDM) Dual-Polarization Autoencoder (J-4WDM-DPAE) framework to address the scaling limitations of existing end-to-end learning architectures for long-haul coherent optical transmission. The proposed approach employs a unified one-dimensional residual convolutional neural network (CNN) decoder that processes all eight complex symbol streams (4 WDM channels × 2 polarizations) at the symbol rate, enabling simultaneous exploitation of inter-channel and inter-polarization correlations with low inference latency. The transceiver is trained through a fully differentiable dual-polarization Manakov split-step Fourier method (SSFM) model including span-wise amplified spontaneous emission (ASE) noise and an effective combined transmitter–local-oscillator phase-noise process, enabling co-optimization of a shared geometric constellation shaping (GCS) encoder under realistic nonlinear and linewidth constraints. Robustness is further enhanced by randomized launch powers and signal-to-noise ratio (SNR) conditions during training. Additional robustness is assessed by cross-SPS evaluation (SSFM-resolution mismatch) and SSFM convergence checks, indicating that the reported achievable-rate trends are not an artifact of the baseline SSFM discretization. Evaluations over standard single-mode fiber (SSMF) for 16-, 32-, and 64-quadrature amplitude modulation (QAM) show that at 1000 km, the learned constellations achieve generalized mutual information close to the dual-polarization limits, with pre-FEC bit-error rates remaining below an adopted threshold of $2\times {10}^{-2}$ (used as a representative soft-decision FEC operating target) up to 4000 km when the model is re-trained for each distance. Complexity analysis further indicates that the unified WDM-aware decoder provides a quantitative performance–computational trade-off compared to existing counterparts under matched link conditions. Full article

Low-altitude wireless networks (LAWNs) require reliable multi-user communication together with accurate range and velocity sensing. Communication and sensing share the same transmit power and spatial degrees of freedom (DoF), and therefore joint beamforming is required to coordinate multi-user spectral efficiency with delay-Doppler estimation accuracy. An adaptive multi-objective beamforming and power allocation framework is developed for a multiple-input multiple-output (MIMO) integrated sensing and communication (ISAC) base station. Communication performance is measured by the achievable multi-user sum spectral efficiency. Sensing performance is characterized by the Cramér–Rao lower bounds (CRLBs) for delay and Doppler frequency. A dimensionless system effectiveness integrated metric (SEIM) combines the three normalized performance components. The beamforming problem is lifted to transmit covariance matrices and treated via semidefinite relaxation (SDR) and alternating successive convex approximation (SCA) under power and per-user signal-to-interference-plus-noise ratio (SINR) constraints. An entropy-regularized weight subproblem provides a closed-form softmax update, and a damping step couples the weight update with the covariance iterations. Numerical results characterize the communication–sensing tradeoff with respect to the transmit power, array size, user loading, SINR requirements, and objective weights. Full article