Search Results (641)

Aircraft skin defect recognition is a safety-critical visual inspection task in which lightweight models must maintain high diagnostic accuracy while suppressing false alarms caused by complex surface textures, illumination variations, and weak defect patterns. This study proposes HQCA-Net, a simulation-based hybrid quantum-classical channel attention network for reliable aircraft skin defect recognition. The core component, termed Residual Quantum Channel Attention (RQCA), embeds a 10-qubit variational quantum circuit into a classical ResNet-18 backbone to perform compact and structured nonlinear feature recalibration, introducing only 30 trainable quantum-gate parameters. The quantum circuit is evaluated using state-vector simulation, and this study focuses on model-level feature recalibration, reliability, and robustness within the evaluated dataset rather than implementation on physical quantum hardware. Experiments on a six-class aircraft skin defect dataset show that HQCA-Net achieves 97.93% classification accuracy and a global false positive rate of 0.49%, outperforming ResNet-18 and classical lightweight attention mechanisms including SE, ECA, and SimAM. Additional analyses using confidence calibration, Grad-CAM visualization, Gaussian noise perturbation, few-shot training, and circuit-depth ablation further indicate that the proposed RQCA module improves feature discrimination and false-alarm suppression under compact parameter constraints. These results suggest that the hybrid quantum-classical attention module can serve as a parameter-efficient nonlinear feature recalibration strategy for reliable visual defect inspection under the tested experimental conditions. Full article

Robust Arithmetic Word Problem (AWP) solving is important for applying mathematical reasoning systems in educational scenarios, where problem statements may contain changed numerical values, paraphrased descriptions, or irrelevant distracting information. Although Large Language Models (LLMs) have shown strong potential in solving AWPs, their reasoning processes may still be sensitive to surface-form variations and perturbation-induced noise. To address this issue, this paper proposes a Scene-Aware Neuro-Symbolic solver designed to improve the robustness of AWP solving under perturbations. The proposed method extends the existing scene-aware framework by introducing perturbation-oriented mechanisms at the scene, relation, and symbolic-solving levels. A Chain-of-Scene (CoS) prompting strategy first generates candidate scenes, after which goal-guided filtering retains target-related and bridge scenes while removing distractor-induced scenes. The retained scenes are then processed by the Scene-Aware Syntax-Semantics ($S^2$) method to extract explicit and implicit relations, and relation consistency checking is applied to remove locally plausible but globally irrelevant relations. Finally, the symbolic solver performs iterative equation-based reasoning over the filtered relation sets, with fallback recovery activated when standard solving does not produce a target-compatible answer. Experiments on AGG, MAWPS, and GSM8K show an average accuracy of 92.8% on clean datasets. On GSM-Perturb and AWP-Perturb, the solver achieves perturbed accuracies of 80.8% and 87.5%, with robustness drops of 8.3% and 6.8%, respectively. Ablation results show that scene filtering and relation consistency checking are the main contributors to reducing perturbation-induced errors. These findings suggest that combining LLM-based scene understanding with symbolic relation reasoning is a promising direction for improving the robustness and interpretability of AWP solvers in the evaluated perturbation settings. Full article

Multivariate time-series anomaly detection on physical sensor networks faces three challenges that generic deep learning models inadequately addressed: heterogeneous sensor reliability, context-dependent anomaly scoring, and inactionable binary outputs lacking per sensor attribution. We propose an uncertainty-aware Temporal Convolutional Network (TCN) framework built on two tightly integrated uncertainty-driven components: (i) an Adaptive Uncertainty-Aware Attention (AUAA) mechanism that gates temporal attention weights by per sensor predictive uncertainty obtained from Monte Carlo dropout; and (ii) a Dynamic Weight Adapter that learns context-sensitive blending of reconstruction error and uncertainty via a GRU over weight history. The architecture also includes an exploratory per sensor attribution head, which we audit rather than claim: a controlled-perturbation test shows it is not yet causally faithful. We complement the empirical architecture with two distribution-free theoretical results: a Chebyshev-type false-positive bound on the hybrid anomaly score, and a Monte Carlo posterior moment convergence result at rate $O\left(M^{-1/2}\right)$. Evaluated on four-month indoor air quality sensor data, the Full Enhanced model achieves $R^2=0.9988$ and MSE $1.65\times {10}^{-4}$, a $25.2\%$ MSE reduction over the Base TCN ($R^2=0.9984$, MSE $2.20\times {10}^{-4}$). Because the IAQ stream is unlabeled, the primary quantitative detection evaluation uses the labeled Skoltech Anomaly Benchmark (SKAB), a publicly available industrial water-circulation corpus disjoint from the IAQ training distribution; it yields an 8.8 × F1 advantage ($0.477$ vs. $0.054$) and a 14.4 × recall advantage ($0.418$ vs. $0.029$) for the proposed model configuration over the Base TCN at a validation-calibrated threshold applied without retuning. Against twelve established detectors under a unified protocol, the proposed model attains the best F1 and recall, while the strongest reconstruction baselines retain higher precision and a marginally higher ROC-AUC, a recall-driven trade-off. Ablation isolates each component’s contribution, the detector degrades gracefully under channel masking and noise, and the distribution-free false-positive bound is empirically respected. The framework retains a low inference cost ($0.16$ ms per window at $M=20$ Monte Carlo samples, including the uncertainty pass). Full article

We develop a systematic framework for incorporating perturbative correction terms into classical finite difference schemes for Allen–Cahn type stochastic partial differential equations. Three distinct correction approaches are introduced, conceptually motivated by perturbative quantum field theory, quantum coherent state evolution, and WKB (Wentzel–Kramers–Brillouin) barrier penetration theory. These quantum-inspired perturbative method (QIPM) corrections function as classical perturbations executing entirely on conventional hardware; quantum-mechanical formalism serves only as a design principle for constructing specific functional forms of correction terms. The primary novelty of this work lies in (i) a generic convergence-preservation theorem establishing sufficient conditions on correction magnitude for any perturbative correction to maintain the base scheme’s accuracy order, and (ii) a systematic translation methodology from quantum-mechanical analogies to explicit, implementable finite difference corrections with rigorous parameter bounds. Through convergence analysis, we demonstrate that appropriately parametrized corrections preserve the accuracy of the underlying numerical scheme, provided the solution possesses sufficient regularity and the parabolic scaling constraint $\Delta t=\mathcal{O}\left(h^2\right)$ holds. Numerical experiments on a spatially discretized domain over a finite time horizon using spatially correlated noise reveal that the anharmonic oscillator correction achieves exceptional accuracy with modest computational overhead, while the amplitude encoding correction provides intermediate accuracy with negligible timing cost. The tunneling-inspired correction exhibits higher error for smooth initial conditions, indicating strong problem-dependence. While these methods enhance accuracy in specific scenarios, genuine speedups on classical hardware are not achieved. The primary value lies in establishing systematic methodologies for perturbative correction design and developing theoretical foundations for future hybrid computational approaches. Full article

Accurate remaining useful life (RUL) prediction of rolling bearings was essential for condition-based maintenance because bearing service degradation was primarily governed by progressive rolling-contact fatigue at the rollingelement–raceway interface, whereas vibration signals provided measurable responses to this degradation rather than being its physical cause. However, reliable RUL prediction remained challenging because vibration measurements were noisy, nonlinear, stage-dependent, and sensitive to operating-condition shifts. In this study, a health-indicator-guided temporal-attention framework was developed for bearing RUL prediction using public run-to-failure vibration datasets. The novelty of this work lay in integrating degradation-consistent health indicator construction, sliding-window life-cycle representation, and HI-guided temporal attention into a unified and interpretable prediction framework. First, degradation-sensitive vibration features were extracted and fused into a compact health indicator (HI) to represent the progressive deterioration trend. Then, sliding-window sequences were generated and processed by a Transformer-based temporal-attention network, through which long-range temporal dependencies were captured and higher weights were assigned to informative degradation segments near stage transitions and late-life acceleration. Experiments on the XJTU-SY and IMS datasets showed that the proposed method improved prediction stability, reduced late-life error amplification, and achieved better performance than baseline variants without HI or temporal attention. Ablation analysis confirmed that HI construction mitigated cross-stage drift, whereas temporal attention enhanced transition sensitivity during accelerated degradation. Robustness and cross-domain tests further indicated that the method maintained acceptable degradation-following behavior under noise perturbations and operating-condition changes, although explicit domain-adaptation mechanisms were still required for strongly shifted target domains. Full article

This paper presents a control design framework that systematically translates nonlinear equilibrium operability analysis into frequency-domain robust synthesis for continuous microbial electrolysis cells (MEC). Since MEC operation is threatened by washout and highly variable influent conditions, analytical local conditions for the existence and local stability of normal operating conditions (NOC) and washout equilibria are first established. Departing from these nonlinear properties, the model is linearized within the locally validated NOC region, and a parametric sensitivity screening is used to identify dominant uncertainty sources ($\alpha$, ${\mu }_{max}$, $K_d$). These are embedded into an unstructured multiplicative uncertainty weight, enabling the synthesis of nominal and robust $H_{\infty }$ controllers that explicitly account for actuator effort, disturbance rejection, and measurement noise. Controller order reduction via balanced truncation is performed while preserving closed-loop local robustness properties. As a benchmark, an internal model control proportional–integral (IMC-PI) controller is derived, and its single tuning parameter is selected by solving a univariate multi-objective optimization that balances integral absolute error and maximum control effort, yielding a Pareto-optimal compromise. Numerical simulations under simultaneous inlet disturbances, parametric variations, measurement noise, and actuator saturation show that the reduced-order robust $H_{\infty }$ controller outperforms the optimized IMC-PI in the tracking–effort trade-off, while the nominal $H_{\infty }$ controller satisfies an a posteriori robust stability test for the linearized dynamics. The proposed framework provides a systematic path from nonlinear operability analysis to implementable robust control, demonstrating that high-order $H_{\infty }$ designs can be reduced to low-order transfer functions suitable for standard industrial control hardware while preserving local stability properties against realistic process perturbations. Full article

Existing chaos-based color image encryption algorithms still face several challenges, including insufficient dynamical complexity of low-dimensional chaotic maps, residual boundary regularity caused by fixed block partitioning, and limited diffusion among RGB channels. To address these issues, this paper proposes a color image encryption algorithm based on a three-dimensional sine-bilinear fully coupled chaotic map (3D-SBFCM). The proposed map integrates sinusoidal modulation, linear coupling, and bilinear cross-coupling within a mod-1 mapping framework, thereby improving the complexity and pseudorandomness of the generated chaotic sequences. In addition, a residual-feasibility-constrained dynamic rectangular partitioning mechanism is developed to generate reversible non-uniform image blocks and reduce the structural regularity associated with fixed-size partitioning. Based on this partitioning structure, inter-block permutation among same-size blocks and intra-block two-dimensional permutation are performed to weaken both global and local spatial correlations. Plaintext-related initialization, dynamic S-box substitution, and forward-backward cross-channel diffusion are further incorporated into the overall permutation-diffusion framework to enhance plaintext sensitivity, nonlinear confusion, and perturbation propagation across RGB channels. Experimental results demonstrate that the proposed algorithm effectively conceals the statistical characteristics of plaintext images, with information entropy values higher than 7.999 for all color channels and NPCR/UACI values close to their theoretical expectations. The algorithm also shows satisfactory robustness against cropping and noise attacks. These results indicate that the proposed method provides an effective and secure solution for color image encryption. Full article

Accurate prediction of electrical fire risk is important for early warning, but real-world monitoring data are often affected by sensor noise, transient anomalies, and non-Gaussian interference. This study proposes an HL-Transformer that incorporates an HL-Pooling layer based on the Hodges–Lehmann estimator into the Transformer feature aggregation process. The HL-Pooling layer replaces conventional mean- or max-based pooling by using the median of pairwise averages, aiming to suppress abnormal perturbations while preserving temporal information. Experiments were conducted on a real-world electrical fire monitoring dataset and the public ETTh1 dataset, with additional robustness tests under different outlier ratios and intensities. The results show that, within the same Transformer backbone, HL-Transformer reduced the MSE by 75.4% compared with the Max-Pooling variant and achieved an R² of 0.879 on the electrical fire risk prediction task. Under injected outliers, the HL-Pooling layer showed more stable error trends, and its transfer to TCN, CNN-LSTM, and 1D-CNN models further improved predictive performance. These findings indicate that HL-Pooling is a robust and portable alternative to conventional pooling for time-series forecasting in noisy monitoring environments. Full article

High-fidelity ship dynamics models are essential for the reliable operation of maritime autonomous systems. However, existing Markov-based maneuvering models and purely data-driven predictors struggle to capture hydrodynamic memory and degrade under non-ideal sensing. To address these challenges, this paper proposes a novel approach for robust ship motion prediction, the Non-Markovian Memory-Augmented Environment-Perceived and Physics-Informed Network (NMA-EPIN). This method explicitly models long-term hydrodynamic dependencies through a memory-augmented architecture. Within NMA-EPIN, a Control-Physics-Informed Neural Network (CPINN) paradigm enforces velocity–position kinematic consistency and control-logic alignment as soft constraints, suppressing cumulative drift under degraded observations. Experiments on a high-fidelity simulated dataset show that NMA-EPIN attains an average coefficient of determination $R^2=0.977$ under nominal conditions, effectively eliminating the position drift observed in baselines. Under extreme compound perturbations (50% sensor noise, packet loss, and delays), NMA-EPIN retains $R^2\approx 0.91$, which significantly outperforms the baselines. Full article

This paper proposes a multi-sensor fusion autonomous navigation method integrating a nine-axis IMU, the Leishen C16 mechanical LiDAR, and the LakiBeam1L single-line LiDAR, aimed at addressing issues such as track slippage and positioning drift that commonly occur in tracked chassis operating under continuously changing conditions on hilly slopes and farmland. IMU-derived slope and attitude information is used as a terrain prior and incorporated into adaptive ground segmentation, slope-cross-slope path cost modeling, and velocity regulation. Leishen C16 LiDAR point clouds are used for NDT scan-to-map localization and spatial obstacle representation, while the LakiBeam1L LiDAR establishes a velocity-dependent near-field safety zone for dynamic obstacle triggering and local avoidance. Python simulations were conducted in simple, general, and complex environments under five slope conditions, forming 15 environment-slope combinations. Three representative scenarios were further validated in ROS/Gazebo. To strengthen statistical reliability, 10 repeated trials were performed for each environment-slope-algorithm combination, and additional stress tests included obstacle-position perturbation, sensor noise perturbation, initial-pose perturbation, dynamic obstacle speed perturbation, and variable slope/local undulation perturbation. An isolated no-LakiBeam1L ablation, significance tests, IMU perturbation tests, planning-weight sensitivity analysis, and stronger-baseline comparison were also added. In the repeated-trial dataset, the proposed method improved the arrival rate from 23.3% to 94.7%, reduced tracking RMSE by 61.46%, reduced localization RMSE by 60.62%, and increased obstacle recall by 26.32%. Under mixed perturbations, the arrival rate of the proposed method was 81.3%, compared with 29.3% for the baseline. These results indicate improved simulation-level stability and perception reliability, while the applicability to real hilly farmland still requires hardware and field validation. Full article

Acoustic emission (AE) source localization provides important spatial information for damage characterization and fracture evolution analysis in construction materials, while its accuracy and applicability are strongly dependent on sensor network design. This study proposes an optimization framework for selecting an effective six-sensor network for velocity-free AE source localization in construction materials. The source coordinates are determined by solving a nonlinear inverse problem using the Levenberg–Marquardt algorithm, and candidate sensor subsets are evaluated by combining location error metrics with the number of effective localization results to quantify the effective monitoring range for damage characterization. The framework is investigated through numerical simulations and pencil-lead break tests on a 600 mm × 600 mm ceramic tile. Among different six-sensor configurations, the best-performing layouts place four sensors at the outer corners and two sensors at the horizontal or vertical inner corners. A benchmark comparison with the Fisher-information-based optimized sensor network and sensitivity analyses further show that the optimized sensor network maintains higher effective monitoring ranges under arrival-time noise, velocity uncertainty, and sensor coordinate perturbations. The proposed approach provides a useful reference for robust and cost-effective AE sensor network design in damage monitoring, fracture characterization, and nondestructive evaluation of construction materials. Full article

Strong differential privacy often collapses utility in transformer-based time-series forecasting because noise is injected directly into high-dimensional gradients (e.g., DP-SGD), severely corrupting the optimization process. We introduce Low-Dimensional Feature-Path Privacy for Transformers (LDPT), which enforces privacy by routing calibrated perturbations through a low-dimensional feature bottleneck ($D=16$) that is independent of the model parameter count. LDPT implements noise via classically simulated quantum channels (Lindblad/depolarizing dynamics) and finite-shot POVM measurements, providing an auditable mapping from privacy budget $\epsilon$ to perturbation magnitude while keeping the transformer gradients clean. Across the ETT datasets and multiple prediction horizons, LDPT substantially preserves forecasting utility under its native local $\epsilon$-QDP guarantee. At a nominal per-pass $\epsilon =0.1$, LDPT limits MSE degradation to under 6%. In contrast, DP-SGD with global $(\epsilon ,\delta )$-DP applied to the identical transformer architecture suffers over 100% MSE degradation. Because these methods operate under different privacy definitions (local $\epsilon$-QDP vs. global $(\epsilon ,\delta )$-DP), this comparison illustrates the impact of noise placement rather than equivalent privacy protection. To isolate the effect of the calibration mechanism, we further evaluate a classical Gaussian mechanism on the same feature-path bottleneck, which requires orders-of-magnitude larger noise and severely degrades utility. Membership inference attacks confirm that LDPT does not amplify membership leakage beyond the non-private baseline. These results demonstrate that decoupling privacy noise from optimization through low-dimensional feature-path placement and tight channel-based calibration is critical for practical privacy-preserving transformer forecasting. Full article

Very low frequency (VLF) radio waves propagating within the Earth–ionosphere waveguide are highly sensitive to changes in lower ionospheric conditions, which are reflected in the amplitude of received transmitter signals. During the solar terminator passage, rapid changes in ionospheric conductivity modify propagation conditions and produce characteristic VLF amplitude minima associated with modal interference and mode conversion processes. In this study, we investigate the spectral characteristics of VLF amplitude variability during the sunrise transition, which spans extended time intervals along long west–east propagation paths, using signals from the NPM-PIU and NPM-PLO paths recorded in Peru under solar minimum conditions (2008–2010). One-hour intervals centered on amplitude minima are analyzed using Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) combined with the continuous wavelet transform. The analysis reveals recurrent wave-like fluctuations (WFs) with dominant periods between 2 and 6 min, whose amplitudes increase systematically within ±15 min around the amplitude minima. These fluctuations are better distinguished during the later-stage minima and exhibit enhanced occurrence during solstice months. The results indicate that the evolving modal structure of the waveguide during the sunrise transition may enhance the sensitivity of the VLF signals to small perturbations, enabling the detection of weak short-period ionospheric disturbances. Full article

The inverse problem under consideration concerns a one-dimensional parabolic equation whose thermal diffusivity takes the quadratic-in-space form $a_s\left(\tau \right){\kappa }^2+b_s\left(\tau \right)\kappa +c_s\left(\tau \right)$. The unknowns are three time-dependent coefficients $a_s\left(\tau \right),b_s\left(\tau \right),c_s\left(\tau \right)$ together with the temperature field $T(\kappa ,\tau )$. The direct problem supplies initial data, Neumann boundary conditions, and three over-determination conditions: two boundary temperatures and the spatial integral of T. We prove two theorems. The first theorem establishes the local-in-time existence of a solution under explicit regularity and sign conditions on the given data $\xi ,{\nu }_k,{\delta }_{\ell },\theta$ and compatibility at $\tau =0$. The second theorem guarantees the uniqueness of this solution. Despite uniqueness, the inverse reconstruction remains ill-posed: small perturbations in the over-specified data can cause large deviations in the recovered coefficients. For the forward model, we implement two numerical schemes: (i) a Crank–Nicolson finite difference methodology (CN-FDM) on a uniform grid and (ii) a semi-discretized Crank–Nicolson approach combined with Bell spectral collocation in space (CN–Bell). The inverse step minimizes a Tikhonov-regularized least-squares functional using MATLAB’s (R2026a) lsqnonlin. Two numerical examples (smooth and non-smooth), tested with both exact synthetic data and artificially added noise, demonstrate stable and accurate coefficient reconstructions. The framework applies directly to heat conduction and porous media flow where diffusivity varies quadratically in space. Full article

Existing noisy-label hyperspectral image classification (HSIC) methods usually address clean sample selection and representation regularization as separate problems, although the reliability of observed labels varies substantially across samples in hyperspectral data. This issue is amplified by mixed pixels, boundary ambiguity, spectral overlap, and limited labeled samples, which make hard clean samples difficult to distinguish from mislabeled ones. We therefore propose PDAM, a sample-reliability-guided training framework for noisy-label HSIC. The method first estimates feature-space class consistency by comparing each sample with the prototype of its observed class and converting this consistency into a reliability probability with a Gaussian mixture model. To reduce conservative false negatives, matched high-confidence selection is further used to recover hard but correctly labeled samples. The resulting reliability estimate then determines how strongly the observed label is trusted through target refinement and how strongly the input is perturbed through reliability-guided masking. Finally, masked reconstruction provides label-independent structural regularization so that uncertain samples can still contribute to spectral–spatial representation learning. Under the evaluated synthetic symmetric noise settings on the University of Pavia (UP), Salinas Valley (SV), and Kennedy Space Center (KSC) datasets, PDAM achieves the best OA and Kappa in most reported comparisons and improves robustness under both moderate and severe noise. At 30% noise, PDAM reaches 97.30% OA on UP, 98.13% OA on SV, and 95.37% OA on KSC. Ablation studies further support the necessity of reliability estimation, hard clean sample recovery, and reliability-guided supervision and regularization within this unified training mechanism. Full article