Search Results (7,766)

This paper presents a computationally efficient deep learning framework for accurate direction-of-arrival (DoA) estimation in portable radar applications. Leveraging a MobileNet architecture, the proposed model directly processes raw in-phase and quadrature-phase (IQ) data, enabling more effective learning of both spatial and temporal features. This direct input approach enhances DoA estimation accuracy, particularly under challenging conditions such as low signal-to-noise ratio (SNR) and limited snapshot scenarios. A unified training strategy is adopted for both single-source and multi-source target detection, ensuring consistency and robustness. Comprehensive simulation experiments demonstrate the proposed model’s competitive and robust performance across various conditions, including different SNR levels, closely spaced targets, and random off-grid angles. It also shows that our method achieves performance comparable to or better than recent deep learning approaches in several challenging scenarios, establishing its potential for resource-constrained environments where only low snapshot data are available. The proposed IQ-MobNet DoA estimation model achieves this competitive performance with substantially lower computational complexity, requiring only 0.24 million parameters and 0.42 million Floating Point Operations (FLOPs), representing a reduction of over 96% compared to the recent neural network models. To ensure practical applicability, the proposed IQ-MobNet framework is validated using real-world measured data, confirming its robustness beyond simulated environments. Full article

To address the challenges of severe optical attenuation and dynamic feature extraction for moving target depth retrieval in complex underwater remote sensing environments, this paper proposes a dynamic target depth estimation method based on multi-source data fusion. Taking optical RGB imagery and neuromorphic vision (NeuroIV) data as joint inputs, the proposed method constructs a three-channel feature extraction and fusion network. By leveraging a hypergraph structure, it establishes association weights between dynamic (temporal) and static (spatial) nodes to capture spatiotemporal correlations. To efficiently process the high-dimensional multi-modal data, the traditional dot-product attention is replaced with element-wise multiplication, significantly reducing computational complexity. Furthermore, a lightweight deformable attention pyramid (DAP) and diffusion model is introduced to refine depth image edges, effectively suppressing discontinuities and abruptness in the estimation results. Compared to single-modality optical imagery, the fused multi-modal data yields a superior signal-to-noise ratio and foreground contrast, achieving an improvement of over 20% in the MAE index. These results validate the effectiveness and superiority of the proposed multi-modal fusion strategy for dynamic target observation and depth retrieval in aquatic environments. Full article

In outdoor road environments, vehicle acoustic source direction-of-arrival (DOA) estimation is challenged by a low signal-to-noise ratio (SNR), dynamic-noise interference, and stringent real-time requirements. Under such conditions, conventional methods often struggle to achieve an effective balance among estimation accuracy, computational efficiency, and robustness against noise. To address this issue, this paper proposes a DOA estimation method that integrates a dynamic-pruning strategy with an adaptive subspace tracking mechanism. The proposed approach reduces computational complexity while enhancing algorithmic stability in complex and time-varying noise environments. Extensive experiments conducted on simulated data, the LOCATA dataset, and real-world outdoor road measurements demonstrate that the proposed method achieves comparable or superior DOA accuracy relative to conventional approaches, while significantly reducing computational cost. Furthermore, it exhibits stronger stability and robustness in real-world static and dynamic vehicle localization scenarios. Our method achieves a more favorable trade-off among multiple performance metrics. The results show that this method has good engineering application potential in complex outdoor environments, and can provide a practical solution for real-world vehicle monitoring. Full article

Detecting weak radar targets in complex sea conditions is inherently challenging due to non-stationary sea clutter and sea spikes. Furthermore, traditional dictionary learning algorithms for clutter suppression suffer from high computational complexity. To address these issues, this paper proposes an efficient sea clutter suppression method cascading Block Coordinate Descent (BCD)-accelerated dictionary learning with Tunable Q-factor Wavelet Transform (TQWT) denoising. During dictionary learning, a BCD strategy replaces global Singular Value Decomposition (SVD) with analytical optimization. Combined with an adaptive soft-thresholding operator, this enables low-complexity joint optimization of dictionary atoms and sparse coefficients, drastically reducing training time. Subsequently, a batch-adaptive Orthogonal Matching Pursuit (OMP) algorithm featuring Gram matrix precomputation and a dual-stop mechanism achieves efficient reconstruction and preliminary cancellation of clutter components. Finally, TQWT is applied to filter out residual non-stationary clutter and noise by leveraging its narrowband feature representation and shift invariance. Experiments on measured radar data from the IPIX database and datasets published by the Journal of Radars demonstrate that the proposed method significantly outperforms traditional K-SVD-based algorithms. Specifically, it improves the average signal-to-clutter-plus-noise ratio (SCNR) by 17.48 dB and requires a total execution time of only 7.99 s, achieving a highly favorable trade-off between suppression performance and computational efficiency. Full article

Deep learning (DL)-based percussion methods in concrete-filled steel-tube (CFST) void detection have gained much attention. However, the detection signal contains a large amount of noise, which affects the accuracy of qualitative and quantitative analyses of the subsequent detection results. To improve the signal-to-noise ratio (SNR) during percussion detection, this study proposes a CFST void detection method using the good point set and vibrational snow ablation optimizer (GVSAO) algorithm and dual-channel parallel convolutional neural networks (CNNs). The proposed method employs the gram angle field (GAF) to transform percussive sound signals into images. It then constructs a dual-channel parallel CNN structure, where the GAF is decomposed into the following two maps: the gram angle sum field (GASF) and the gram angle difference field (GADF). These maps are simultaneously fed into the CNN for training. The outputs from the two channels are concatenated and fused. Finally, the GVSAO algorithm was used for model optimization to improve convergence speed and recognition accuracy. Both the temporal and spatial characteristics of the knocking sound signal are fully preserved, while the interference of different construction noises is effectively avoided. Validation experiments were conducted on CFST specimens with different heights of voids (0, 50, 100, and 150 mm) under different pressure loads. The original sample dataset and the signal-enhanced dataset were obtained by adding background noise with different SNRs. The test results show that the prediction accuracies on the original signal dataset are consistently above 98.74%. Among them, the accuracy achieves 100% at pressure loads of 0 and 50 tons. Additionally, the prediction accuracies on the signal-enhanced dataset are all above 97.2%, indicating that the model maintains a high level of classification performance. This suggests that the model can effectively suppress noise and exhibits excellent robustness. Full article

A reconfigurable intelligent surface (RIS) is a promising technology for beyond-fifth-generation (B5G) and sixth-generation (6G) wireless communications, but its passive reflection and two-hop double-fading structure make cascaded channel estimation challenging. Conventional convolutional neural network (CNN) estimators require many trainable parameters, while a single shallow parameterized quantum circuit (PQC) may have limited feature representation. Deep quantum circuits can also suffer from noise and barren-plateau effects on noisy intermediate-scale quantum (NISQ) devices. To address these issues, this paper proposes a multi-filter quantum convolutional neural network (MF-QCNN) for cascaded channel estimation in RIS-assisted multi-user uplink systems. The proposed model uses multiple independent shallow PQC filters in parallel, concatenates their measured features, and estimates the cascaded channel through a compact classical dense head, with the total trainable-parameter count scaling as $182F+696$ for F parallel filters. Simulation results, compared with a single-filter quantum convolutional neural network (QCNN), CNN, and multilayer perceptron (MLP) baselines, show that at a signal-to-noise ratio (SNR) of 20 dB, the 3-filter MF-QCNN reduces the normalized mean squared error (NMSE) by approximately 22.9, 8.1, and 4.6 dB relative to the single-filter QCNN, CNN, and MLP baselines, respectively, while using only about 19.3% of the CNN trainable parameters. Under zero-forcing (ZF) precoding, it achieves the highest achievable sum rate among the learning-based estimators; at SNR = 30 dB, it improves the achievable sum rate by approximately 17.4% and 12.8% over the CNN and MLP baselines, respectively. These simulation results suggest that the parallel shallow-PQC design can serve as a compact quantum-aided estimator for RIS channel estimation and may provide a useful basis for future studies on AI-native transceiver design in B5G/6G networks. Full article

Semantic communication has emerged as a promising paradigm for next-generation wireless networks, offering substantial efficiency gains by prioritizing the transmission of task-relevant meaning over bit-level accuracy. However, while its benefits in bandwidth reduction and intelligent data representation are well established, its potential to provide intrinsic reconstruction resistance without relying on conventional cryptographic mechanisms remains largely unexplored. This paper investigates whether semantic communication system architectures themselves can contribute to intrinsic reconstruction resistance for image transmission. We propose an autoencoder-based semantic communication framework in which images are encoded into latent representations and transmitted over a wireless channel, with decoding performed using architecture-specific neural networks. Unlike traditional secure communication approaches that depend on encryption, the proposed method leverages architectural uniqueness and representation-level abstraction to limit unauthorized reconstruction. To systematically analyze this, we evaluate eight adversarial scenarios encompassing variations in encoder–decoder architecture and initialization, including both matched (worst-case) and maximum mismatched (best-case) conditions. The system is modeled using a standard Alice–Bob–Mallory framework, where an adversary attempts to reconstruct intercepted semantic representations without full architectural knowledge. Performance is evaluated using peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM) for reconstruction quality, alongside semantic accuracy measured via a convolutional neural network (CNN)-based classifier and embedding cosine similarity to assess information leakage. Experimental results demonstrate that architectural mismatches substantially degrade both visual reconstruction and semantic interpretability for unauthorized receivers, while matched configurations enable substantial recovery. It is important to emphasise that the proposed approach does not provide cryptographic confidentiality; rather, it offers architecture-dependent resistance to unauthorised semantic reconstruction under restricted adversarial assumptions. Overall, the results show that semantic communication systems can exhibit intrinsic reconstruction resistance through architecture-dependent latent-space organisation, reducing reliance on additional cryptographic overhead under restricted adversarial assumptions, while also highlighting limitations when adversaries possess full architectural and initialisation knowledge. Full article

Active magnetic bearings (AMBs) require accurate dynamic models for controller design and performance analysis, but their inherent open-loop instability makes modeling difficult under practical operating conditions. This study presents a closed-loop black-box identification method for an AMB system under decentralized control. A pseudo-random binary sequence (PRBS) excitation was injected into the closed-loop system, and the measured input–output data were used to estimate a nonparametric frequency-response model. The effects of excitation amplitude were first examined, and an excitation level of about 10–12% of the saturation current was found to provide a suitable balance among coherence, signal-to-noise ratio, and frequency-response variance. Based on the obtained frequency-domain data, ARX, output-error (OE), and state-space (SS) models were identified and compared. An initial model order range was estimated using the ARX structure and quantitative criteria, including the loss function and Bayesian information criterion. Within this candidate range, different model structures and orders were further evaluated. The 7th-order SS model showed the best overall agreement with the nonparametric frequency response and captured the dominant dynamic features more accurately. Independent time-domain validation and closed-loop reconstruction further confirmed that the selected SS model can represent the practical AMB dynamics with acceptable accuracy. Full article

In window tracking mode, stray light and detector readout noise can submerge star spot signals in star sensor images. The resulting degradation reduces centroid extraction accuracy and may even cause extraction failure, thereby preventing precise attitude determination. This study uses the self-supervised spatiotemporal denoising model ASTERIS as the baseline. ASTERIS integrates 3D spatiotemporal inputs with a global attention mechanism for joint noise modeling, thereby providing stronger denoising and restoration capability than conventional methods such as multi-frame stacking. However, ASTERIS lacks adaptive compensation for subpixel jitter in on-orbit star images and has difficulty preserving the high-frequency morphology of star spots, affecting denoising performance and centroiding accuracy. To address these limitations, this study introduces two improvements: First, frame-by-frame spatial deformable convolution is incorporated into the decoder upsampling stage to adaptively compensate for subpixel offsets, actively suppress background noise, and lower the parameter count. Second, a complex-valued frequency domain loss with a high-frequency weighted mask is designed to jointly constrain the amplitude and phase spectra, thereby preserving high-frequency star spot details. Experimental results show that, for star images with extremely low signal-to-noise ratios, the proposed method improves the peak signal-to-noise ratio by approximately 17.8 dB and reduces the centroid localization error to approximately 0.1 pixels. This performance is substantially better than that of the original ASTERIS model, which improves the peak signal-to-noise ratio by approximately 9.5 dB and yields an error of approximately 0.4 pixels, and the multi-frame stacking method, which improves the peak signal-to-noise ratio by approximately 6.0 dB and yields an error of approximately 0.5 pixels. Under the simulated strong noise conditions considered in this study, the proposed method achieves effective centroid extraction, demonstrating its potential for on-orbit star sensor data processing. Future work will further address its engineering deployment. Full article

Detecting and localizing leaks in buried pipelines typically requires direct access to the pipe, which is often impractical in real-world conditions. Although ground-surface vibration measurements offer a non-intrusive alternative, their potential for spatial leak localization remains underexplored, particularly in relation to frequency-dependent attenuation effects. This study investigates how frequency-dependent energy decay encodes spatial information in leak-induced ground vibrations. Experimental wok was conducted using an outdoor buried pipeline testbed, where surface acceleration data were collected with a movable array of piezoelectric sensors. The measurements were reorganized into L-shaped sensor trios to enable directional analysis and increase the number of spatial configurations. Energy-based features extracted from discrete frequency bands were used to represent the leak signatures, capturing both attenuation behavior and soil–pipe interaction effects. Artificial Neural Network and Random Forest models were trained to estimate leak coordinates in a local reference frame. The results demonstrate high localization accuracy at the centimeter scale and reveal consistent relationships between prediction error, distance, and signal-to-noise ratio. These findings show that frequency-dependent attenuation provides a robust basis for spatial inference, and that combining ground surface vibration measurements with lightweight machine learning models offers an effective and non-intrusive solution for leak localization in buried pipelines. Full article

High-quality X-ray pulsar observation profiles are vital for investigating both their physical properties and navigation applications. Conventional profile extraction relies on epoch folding, whose performance is constrained by observation duration and bin size, often leading to poor-quality profiles or even failure under extremely low-photon conditions. This paper proposes a novel method that directly extracts high-quality profile frequency spectra merely by statistical analysis of photon sequences followed by the reconstruction of time domain waveforms. Monte Carlo simulations and real observational data demonstrate that the proposed method exhibits higher correlation coefficients and signal-to-noise ratios than those obtained using traditional epoch folding, and also outperforms the Fourier-series-based frequency cutoff method. Moreover, comparable profile quality can be achieved using an order of magnitude fewer photons than required by epoch folding. The lower the photon count, the more significant the improvement, making the method especially suitable for small-area detectors and resource-constrained observation scenarios. Full article

Vehicle-to-Vehicle (V2V) cooperative object detection enhances environmental perception capabilities in complex traffic scenarios by sharing sensory information among vehicles, but limited transmission bandwidth and wireless channel noise can significantly affect the reliable transmission of cross-vehicle semantic features and lead to a degradation in detection performance at the receiver. Although existing semantic communication methods based on DeepJSCC can alleviate the cliff effect of traditional separated source–channel coding under low signal-to-noise ratio conditions, they typically rely on additional external autoencoder structures, which increase model complexity and the deployment burden on vehicular edge computing platforms. Meanwhile, under high compression ratios, these methods struggle to adequately preserve detection-related fine-grained information, such as object boundaries, spatial locations, and local structures. Motivated by these challenges, we develop Mamba-KGSC as a lightweight knowledge-guided semantic communication framework for robust V2V cooperative object detection. At the transmitter, Mamba-KGSC utilizes the internal time-scale parameters of the Mamba-YOLO-T backbone network to generate spatial semantic masks, realizing the sparse encoding and transmission of task-relevant features while avoiding the introduction of complex external codec networks. At the receiver, a multi-source knowledge base constraint verification module is constructed to refine the initial detection results by combining physical consistency screening with visual–physical spatial joint redundancy suppression, thereby suppressing physically inconsistent misdetections and repeated detections induced by channel noise. The experimental evaluation indicates that, under a 50% compression ratio, multiple SNR settings, and different channel models, the front-end semantic communication branch of Mamba-KGSC improves mAP@0.5:0.95 by an average of 1.90 percentage points over the DeepJSCC baseline. The multi-source knowledge base constraint verification module further reduces abnormal and duplicate candidate bounding boxes. Overall, Mamba-KGSC provides a balanced solution in terms of transmission cost, detection accuracy, model complexity, and physical consistency, offering a lightweight implementation scheme for robust V2V cooperative detection in challenging communication environments. Full article

Extended-range three-dimensional (3D) single-molecule localization microscopy (SMLM) and single-particle tracking (SPT) require precise emitter localization across cellular-scale axial distances. However, long-rangeengineered point-spread functions (PSFs) spread photons over wider camera footprints, lowering the signal-to-noise ratio (SNR) and localization precision. We numerically evaluated a physics-guided deep learning workflow for 3D localization over a 10.0 µm axial range using simulated electron-multiplying charge-coupled device (EMCCD) images. The workflow combines an analytical secondary-astigmatism phase mask, frequency-domain cross-filtering, a cross-filtering generative adversarial network (CFGAN), and coarse-to-fine fitting. The optical model and engineered PSF provide physical signal priors, cross-filtering preserves directional Fourier-domain energy, and CFGAN suppresses residual structured noise before model-based localization. In low-SNR simulations, lateral, axial, and radial root-mean-squared localization errors (RMSEs) decreased from 54.11, 96.12, and 112.79 nm without denoising to 31.14, 39.06, and 50.12 nm after CFGAN denoising—close to Cramér–Rao lower-bound (CRLB) references of 34.39, 38.94, and 51.95 nm. High-SNR RMSE values were 8.78, 12.00, and 14.96 nm, comparable to CRLB references of 10.36, 11.71, and 15.64 nm. These simulations suggest that physics-guided restoration can improve extended-range 3D SMLM precision, while experimental validation remains necessary. Full article

Aiming at core bottlenecks in weak and small target detection in radar range-Doppler (RD) spectra under low signal-to-noise ratio (SNR)—including severe performance degradation of traditional constant false alarm rate (CFAR) detectors and the inherent trade-off difficulty faced by existing deep learning methods in balancing detection accuracy, localization precision, and real-time performance—this paper proposes a progressive sub-pixel-level intelligent detection algorithm named F²DN-CCWL. The algorithm constructs a three-stage detection pipeline: global candidate screening, local fine discrimination, and weighted localization, and implements a full-stack customized design covering network architecture, soft-label training strategy, and post-processing modules. Simulation and field-measured results demonstrate that at −20 dB SNR, the proposed algorithm achieves a detection probability of 95.3%, a false alarm rate of 3.1%, an average localization error of 0.76 pixels, and a single-frame inference latency of 47.21 ms. This method offers a high-performance engineering solution for radar-based detection of low observable targets. Full article

Spaceborne spectrometers are key optical payloads for global and regional greenhouse gas (GHGs) monitoring. With the increasing demands for high-precision and high-efficiency monitoring, spectrometers are required to provide a wide swath, high spatial resolution, and high spectral resolution. However, existing spaceborne grating spectrometers still face a trade-off between swath width and spatial resolution. To address this issue, this paper presents the optical design and fabrication of an immersed-grating spectrometer for GHG monitoring. The proposed spectrometer achieves a swath width of 100 km and a spatial resolution of 3 km × 3 km while providing high spectral resolution. It operates in four channels centered at 0.76, 1.61, 2.06, and 2.30 μm, covering the O₂-A band and the main absorption bands of CO₂ and CH₄, with corresponding spectral resolutions of 0.04, 0.07, 0.09, and 0.10 nm, respectively. The four channels share a common slit, which reduces system volume and inter-channel spatial registration errors. Immersed gratings are used as the core dispersive elements, enabling high spectral resolution in a compact optical configuration. To correct the smile and anamorphic beam compression induced by high-angular-dispersion immersed gratings, a prism-based simultaneous correction method is proposed. Based on this method, the initial parameters of the dispersion module are determined, and the optical design of the spectrometer is completed. Large-sized immersed gratings with high groove density are precisely fabricated using holographic lithography and ion-beam etching, after which the spectrometer is aligned and tested. The test MTF at the Nyquist frequency of the spatial dimension exceeds 0.72, indicating good imaging quality. The test spectral resolution of the four channels is all better than the design value, and the maximum smile and trapezoidal distortion are both within one pixel. This spectrometer provides an effective technical solution for achieving wide-swath, high-spatial-resolution, and high-spectral-resolution GHG monitoring under constraints imposed by detector size, signal-to-noise ratio, and payload size and mass. Full article