Search Results (773)

This study proposes a novel anti-resonant fiber sensing structure based on a composite “egg-shaped” configuration with surface plasmon resonance (SPR) effect. By designing a novel anti-resonant structure consisting of a semicircle and a semi-ellipse and coating its inner surface with a gold film, the optimal structural parameters are determined through three sets of simulation experiments using temperature sensitivity as the criterion. The optimal sensing structure was applied to the simulated detection and analysis of cancer cells, aiming to provide value and reference for the application of high-sensitivity optical fiber sensor in the field of cancer cell detection. Simulation results show that the proposed sensing structure achieves a maximum temperature sensitivity (TS) of 3.86 nm/°C. For the detection of six different types of cancer cells, the maximum wavelength sensitivity (WS), optimal resolution (R), maximum figure of merit (FOM), maximum signal-to-noise ratio (SNR), and best limit of detection (LOD) reach 12,142.86 nm/RIU, 8.24 × 10⁻⁶, 3035.72 RIU⁻¹, 65.50, and 0.94 nm, respectively. Owing to its unique detection mechanism, the proposed sensing structure exhibits label-free characteristics and demonstrates balanced and excellent performance across all metrics for both temperature and cancer cell detection, showing broad application prospects and great potential in the fields of environmental monitoring and medical prevention and treatment. Full article

An abundant gear fault modulation signal is closely related to the gear fault type, especially to the gear fault severity. However, the modulation signal simultaneously includes coupled frequency modulation and amplitude modulation, which hinders the precise modulation separation and modulation-based gear fault severity assessment. Therefore, a new modulation separation method is proposed, which incorporates a rotation speed extraction technique based on the extreme value search, frequency modulation mechanism and Fourier series fitting. The rotational speed induced by the gear fault is first calculated by the extreme value search, which is then combined with a frequency modulation mechanism to solve the frequency modulation signal with the Fourier series fitting. Based on the vibration modulation signal model and Fourier series fitting, amplitude modulation is finally obtained. Simulation verifies the superiority of the proposed method in aspects of effectiveness and anti-noise performance compared with other modulation separation methods. The maximum relative errors of frequency modulation and amplitude modulation parameters under a signal-to-noise ratio of 0 dB are 2.9125% and 4.1143%, respectively. Two modulation intensity indicators regarding fault-induced frequency modulation and amplitude modulation signals are presented to assess gear faults. Experiment results also demonstrate the effectiveness of the proposed method in the severity assessment of misalignment and tooth breakage. Therefore, the research provides a new technique for gear fault severity assessment based on the frequency modulation or amplitude modulation signal. Full article

In the multi-class recognition task for unmanned aerial vehicle (UAV) radio frequency (RF) signals, noise interference and complex backgrounds can significantly degrade recognition performance. The stability and accuracy of existing recognition methods often fail to meet the requirements of practical applications. To enhance the stability and accuracy of UAV RF signal recognition, especially to mitigate performance degradation in complex backgrounds, a UAV RF signal classification method, MD-Net, is proposed that integrates Adaptive Time-Frequency Masking and a dual-network architecture. First, an Adaptive Time-Frequency Masking mechanism is constructed. By analyzing the energy distribution of RF signals in the time-frequency domain, the masking region is automatically determined, ensuring that the training data maintains a diverse distribution across different interference scenarios. This significantly improves the model’s anti-interference performance and discriminative stability in complex environments. Subsequently, a dual-branch recognition network architecture is designed, integrating a multi-layer perceptron (MLP) and a long short-term memory (LSTM) network. The MLP extracts static amplitude features from the signals, while the LSTM learns time-series features. These two feature types are then fused to achieve complementary characteristics, ultimately enabling accurate classification of UAV RF signals. Extensive comparative experiments conducted on the DroneRF dataset demonstrate that the MD-Net model achieves an average recognition accuracy of 85.58%, an improvement of 5.27 percentage points over the baseline model. The experimental results show that Adaptive Time-Frequency Masking can effectively enhance the model’s adaptability to real-world interference environments, while the dual-network fusion mechanism fully integrates static amplitude and time-series features, providing a feasible and highly reliable technical approach for UAV RF signal recognition. Full article

Traditional Android malware detection systems struggle to adapt to evolving threats without sacrificing performance on legacy families. To address this, we present ProtoMal, a dual-branch continual learning framework that achieves a fine-grained balance between stability and plasticity. The framework utilizes a frozen old branch for knowledge preservation and a trainable new branch for novel threat acquisition. A key contribution is our robust median-based prototype learning mechanism, which leverages centroids and outlier filtering to handle the high intra-class variability and label noise inherent in malware datasets. Experimental results across three large-scale benchmarks AMD, VirusShare, and VirusShareYears demonstrate that ProtoMal significantly curtails performance degradation and achieves highly competitive average accuracy. Most notably, the proposed framework demonstrates highly competitive model stability and yields robust anti-forgetting capabilities alongside current state-of-the-art incremental learning paradigms, maintaining particular resilience under severe concept drift. Full article

With the advancement of wireless communication technologies, especially the emergence of mobile communication technologies such as satellite internet and sensor networks, the rapid proliferation of communication facilities has given rise to challenges such as the scarcity of spectrum bandwidth resources, heightened channel interference, and increased noise. Consequently, traditional image source coding technologies urgently require further improvements in their compression ratio and anti-interference capability. Targeting image transmission scenarios characterized by low signal-to-noise ratios and constrained channel bandwidths, this paper proposes an image semantic coding method based on the pre-trained Stable Diffusion model, producing a zero-shot universal image compressor. This compressor leverages the denoising network of the Stable Diffusion model, with feedback from channel SNR, to further enhance the adaptability of transmitted data to channel interference. Additionally, by designing quantization and entropy coding methods for feature tensors in the semantic space, the compression ratio of the image coding process is further improved. Simulation results demonstrate that the proposed method not only achieves superior compression performance but also ensures relatively high similarity between the decoded reconstructed image and the original. Notably, it delivers a significant improvement in the perceptual similarity of human visual quality. Furthermore, the method can adapt to Gaussian noise channels, Rician fading channels, and Rayleigh fading channels with low SNR, exhibiting broad application prospects in the field of wireless communication coding methods, where the electromagnetic environment is growing increasingly complex. Full article

The automated detection of deep-sea polymetallic nodules is critical for processing large volumes of benthic imagery. However, its scalability faces challenges from cross-expedition covariate shifts, such as changes in lighting, altitude, and camera payloads, which lower zero-shot model performance. While semi-supervised pseudo-labelling presents a potential alternative to time-consuming re-annotation, simple implementations can quickly lead to confirmation bias. This study identifies two primary sources of this degradation: spatial noise from tiling fragmentation at tile borders and an architecture-agnostic interior false positive floor caused by semantic domain shift. This work proposes using a multi-model ensemble for pseudo-labelling to reduce the noise impact. Using a spatial border filter and confidence stratification, three architecturally distinct teacher models (YOLOv8, Faster R-CNN, and DINO) are employed to determine a reliable and domain-invariant subspace. Under a strict anti-leakage Leave-One-Partition-Out protocol, the proposed approach surpasses the supervised fine-tuning baseline at 100-tile pseudo-label budget across four random seeds (macro mAP_50:95 of $0.4745\pm 0.0042$ versus $0.4467\pm 0.0079$), with gains concentrated in the most domain-shifted fold. Beyond this budget, our findings highlight two important adaptation trends: a pool-size degradation trend where excessive pseudo-label volume actively degrades generalisation, and the observation that the fine-tuned models reduce pseudo-label fidelity despite higher precision, providing evidence for the advantage of using frozen source checkpoints for cross-domain adaptation. Full article

As new energy vehicles and energy storage systems become more common, safety accidents caused by lithium-ion batteries overheating have become more of a concern. Early detection based on distinctive gases (such as H₂ and CO) can give an earlier warning than typical monitoring methods like temperature, voltage, or impedance. Nonetheless, attaining high-precision identification in intricate mixed-gas settings continues to be difficult because of the considerable cross-sensitivity of metal oxide semiconductor (MOS) gas sensors. This research presents an ISA-LSTM-TCN multi-task learning model utilizing an enhanced spatial attention mechanism for the swift identification and concentration forecasting of distinctive gases during lithium-ion battery thermal runaway. The model improves key feature extraction and anti-noise performance by combining the long-term temporal modeling ability of the Long Short-Term Memory (LSTM) network with the multi-scale feature extraction ability of the Temporal Convolutional Network (TCN). It also adds an Improved Spatial Attention (ISA) module with a residual multiplication structure. Moreover, in a multi-task learning framework, joint optimization of gas categorization and concentration regression is facilitated using a hard parameter-sharing method. Tests using a built MOS sensor array dataset show that the model is 99.23% accurate at classifying gases and that the $R^2$ values for predicting H₂ and CO concentrations are 0.9510 and 0.8400, respectively. Tests on public datasets and in different noisy environments show that the model is even better at generalizing and is more robust. The results show that the suggested method allows for quick, accurate detection of thermal runaway gases. This makes it an effective and smart way to monitor battery safety warning systems. Full article

Aiming at the challenges of class imbalance, tiny defect scales, and complex brushed background interference in the surface defect detection of electrical commutators, this paper proposes a high-precision and lightweight improved instance segmentation algorithm named WG-YOLOv11. Firstly, to overcome the barrier of highly imbalanced positive and negative samples in actual industrial data collection, a Balanced Defect Synthesis (BDS) data augmentation strategy is introduced to effectively enrich the morphological diversity of tiny defects. Secondly, a Wavelet Transform Convolution (WTConv) module is collaboratively integrated into the feature extraction network to expand the receptive field while preserving the high-frequency edge details of hairline cracks. Thirdly, a Group CBAM Enhancer (GCE) module is introduced to filter out high-reflection and brushed background noise through grouped attention and weight re-calibration mechanisms. Finally, addressing the difficulty of pixel-level alignment for tiny defects, an $\alpha$-IoU loss function is utilized to improve the high-precision segmentation and localization capabilities by dynamically adjusting the gradient distribution. Comprehensive evaluations are conducted on two real-world electrical commutator surface defect datasets: KolektorSDD2 and KolektorSDD. Experimental results show that on the KolektorSDD2 dataset, compared to the YOLOv11 baseline, the Mask mAP@50 of WG-YOLOv11 increases from 85.2% to 89.2%, and the stringent metric Mask mAP@50:95 improves from 52.7% to 56.9%. Additional computational analysis on the same dataset validates that the proposed method maintains high efficiency, matching the baseline computational cost without compromising real-time inference speed. Furthermore, evaluations on the public MSD dataset confirm the model’s cross-domain generalization capabilities. The proposed framework effectively achieves a balance between detection accuracy, anti-interference robustness, and a lightweight architecture. Full article

Bi-temporal change detection (CD) in remote sensing (RS) aims to map image pairs at different times into a shared feature space to discriminate variant regions effectively. However, factors such as cloud interference may disrupt the feature distribution of RS images and cause pseudo-change problems. Existing public change detection datasets also pay less attention to such pseudo-change phenomena. To address the pseudo-change problems of CD applications, we propose a Domain Adversarial Anti-Interference Change Detection Network (DAAINet), which uses ResNet to extract multi-scale features from the original input images. Semantic features are then obtained and fed into a subsequent graph convolution module after soft clustering, by introducing a domain adversarial structure to align the feature space in RS images. In the graph convolution module, the association of node context is utilized to predict the adjacency relationship between objects. We collected data and constructed a real-world dataset called “Cloud Interference Change Detection” (CICD), which focuses on real bi-temporal remote sensing image data containing cloud interference and includes pseudo-changes caused by factors such as the presence of temporary objects and illumination changes. Experimental results demonstrate that our method is more robust and efficient compared to other state-of-the-art methods on two public CD datasets, and achieves state-of-the-art performance on the noise-corrupted CICD dataset, surpassing prior methods by up to 5.67%p in IoU and 1.42%p in recall. Full article

This paper develops an analytical treatment of vibro-acoustic wave propagation in a cylindrical waveguide containing two clamped elastic membranes and a central flexible-shell segment. The acoustic field obeys the time-harmonic Helmholtz equation, the shell motion is described by Donnell–Mushtari thin-shell theory under axisymmetric loading, and the membrane response is governed by classical membrane theory and incorporated through a tailored Galerkin scheme. The resulting coupled fluid–structure boundary-value problem is solved by the Mode-Matching Method: the acoustic potentials are expanded in orthogonal radial eigenfunctions within each subregion, and continuity of pressure, normal velocity, and structural displacement are enforced at every interface. The mirror symmetry of the configuration is exploited by an exact decomposition into symmetric and anti-symmetric sub-problems, each of which reduces to a truncated linear algebraic system of dimension $4N+4$ for the unknown modal amplitudes. Acoustic power-balance identities provide a quantitative consistency check on the numerical implementation and diagnose convergence with respect to the truncation order; structural damping is accommodated through complex-modulus substitutions for the shell and the membrane tension without altering the algebraic structure of the system. The numerical results demonstrate that the dual-membrane configuration delivers transmission-loss values exceeding $25\mathrm{dB}$ across the low-frequency band relevant to HVAC and automotive applications, with a representative plateau near $13\mathrm{dB}$ at the reference geometry, through resonance-driven modal coupling between the acoustic field and the compliant interfaces. Parametric studies identify the excitation frequency, the inner-membrane radius, the shell radius, and the chamber length as effective design parameters for tuning the attenuation. The formulation furnishes a unified and computationally efficient analytical tool for predicting and optimising noise attenuation in flexibly coupled cylindrical duct systems. Full article

In the context of the increasing demands of precision manufacturing and nanotechnology, especially for emerging fields such as Oxide oxide films in Nuclear nuclear fuel assemblies, the measurement of multi-layer inhomogeneous thin films faces significant challenges. Traditional spectroscopic interference thickness measurement techniques have limitations in handling dispersion interference, parameter coupling, and the efficient solution of nonlinear inverse problems. This study proposes a new model that integrates deep learning and physical model fitting. It constructs a theoretical model of multi-layer thin-film interference spectroscopy based on the Lorentz–Drude formula, uses a generative adversarial network (GAN) for initial structure analysis, and builds a two-layer optimization framework of “deep learning rough positioning—physical model fine fitting”. The research aims to break through the limitations of traditional methods, improve measurement accuracy and anti-noise ability, and provide a key technical support for emerging fields. Full article

In impedance imaging, the incompatibility and nonlinearity of the inverse problem lead to problems such as blurred boundaries and severe artifacts in the reconstructed images, making it difficult to meet the requirements for precise identification of multi-layer tissue structures in the legs. To this end, this paper proposes a post-processing algorithm for leg EIT that integrates the boundary attention mechanism, with a Wasserstein generative adversarial network as the training framework, cyclic residual U-Net as the generator, and the boundary attention module embedded in the RecurrentBlock. This leads to adaptive enhancement of the ability to extract organizational boundary features through a three-path fusion of spatial attention, channel attention, and learnable Laplacian edge enhancement. A leg anatomy prior constraint loss function was designed, integrating six constraints—pixel loss, edge loss, hierarchical tissue constraint, total variation regularization, structural similarity loss, and histogram matching—to guide the reconstruction results to conform to the multi-layered tissue structure features of the leg. A simulation dataset of leg sections containing multiple tissues such as skin, fat, muscle, bone, blood vessels, and nerves was constructed, and the pre-reconstructed images were obtained using the hybrid total variation regularization algorithm as the network input. The simulation results show that, under noise-free and different signal-to-noise ratio conditions, the proposed BAM-R2UNet algorithm achieves the best performance in RMSE, SSIM and PSNR metrics compared with HTV, DnCNN and standard U-Net algorithms, can remove artifacts, accurately restore the boundary and conductivity distribution of leg tissues, and has stronger anti-noise robustness. Full article

Accurate modelling of nonlinear dynamical systems remains a fundamental challenge in control engineering, particularly in applications characterized by strong nonlinearities, uncertainty, and varying operating conditions such as anti-lock braking systems (ABSs). Although neural networks are widely used for nonlinear system identification, their performance is often limited by correlated input features, poor numerical conditioning, and reliance on computationally demanding nonlinear optimization. This paper proposes a novel neural network modelling framework that integrates improved almost-orthogonal functional input transformation with a linear-in-parameters structure. The proposed approach systematically constructs a nonlinear feature space in which correlations between basis functions are explicitly controlled through a perturbation-based near-orthogonality mechanism, resulting in improved conditioning of the regression matrix and enabling stable least-squares-based parameter estimation. The method is formulated for a general class of nonlinear discrete-time systems and experimentally validated on an Inteco ABS laboratory setup, where wheel slip dynamics are identified using measured wheel speeds and braking torque. The obtained results demonstrate improved modelling accuracy, increased robustness to measurement noise, non-Gaussian disturbances, and parameter drift, as well as lower computational complexity compared with conventional multilayer perceptron and polynomial-based models. These findings suggest that structured feature generation may improve the reliability of data-driven models and indicate potential applicability of the proposed framework for real-time and control-oriented applications in complex dynamical systems. Full article

A space-based bistatic passive radar system, typically utilizing a satellite as the illuminator of opportunity and ground or aerial platforms as receivers, offers significant advantages for wide-area maritime surveillance, robust anti-jamming performance, and superior survivability. However, due to the limited transmit power and significant path loss over long-range propagation, the signal-to-noise ratio (SNR) of sea-surface targets is extremely low. To achieve effective detection and estimation, long-time integration is required, which can unfortunately induce severe range cell migration (RCM) and Doppler frequency migration (DFM) effects, resulting in integration gain loss and degraded detection performance. This article proposes a hybrid integration and parameter estimation algorithm based on the keystone transform and segmented matched filtering (KTSMF), which partitions the echoes into multiple frames and combines the keystone transform with segmented matched filters for integration. It not only effectively eliminates RCM and DFM effects in both intra-frame and inter-frame processing but also addresses Doppler ambiguity and Doppler aliasing effects, which enables a generalized processing capability for slow-moving, fast-moving, and highly maneuverable targets. Simulation results and analysis demonstrate that the proposed method achieves superior detection performance and parameter estimation accuracy compared to existing algorithms. Full article

Anti-collision detection technologies primarily rely on optical, radar, or laser sensors; however, their performance often deteriorates severely under adverse weather conditions (e.g., rain, snow, fog) or in scenarios involving visual occlusion. By contrast, magnetic anomaly detection leverages perturbations in the geomagnetic field induced by target objects (e.g., vehicles, metallic obstacles), exhibiting intrinsic all-weather operability and strong anti-interference capability. Nevertheless, conventional magnetic anomaly detection methods suffer from the limited applicability of the magnetic dipole model, which only affords coarse positioning accuracy and is predominantly suited for long-range targets. To address this limitation, this paper proposes an Extended N-th-Pole Magnetic Dipole (E-NMD) model that improves accuracy by analyzing the Lagrangian cosine term and rigorously constraining truncation errors under specific operational conditions. Experimental results demonstrate that, for steel with a relative permeability of 200, the model achieves a fitting variance of 99.87%. Furthermore, to overcome the inversion difficulties arising when the strength of short-range magnetic anomalies is comparable to sensor noise, an Adaptive Iterative Extended Kalman Filter (AI-EKF) is developed to enable robust noise suppression and precise distance estimation. Results indicate that E-NMD outperforms the traditional N-th-Pole Magnetic Dipole (NMD) model in proximal state estimation, achieving a 39.62% reduction in Root Mean Square Error (RMSE). Finally, in light of parameter uncertainty in magnetic anomaly targets under real-world conditions, a Dual-Mode Pairwise Iterative Extended Kalman Filter (DI-EKF) is introduced to jointly estimate parameters and system states, yielding an 89% reduction in RMSE compared to AI-EKF. Full article