Search Results (15,397)

Flow-field parameters of bow shocks in high-altitude rarefied flow are fundamental for seeker radiation noise evaluation and thermal-protection design. The conventional direct simulation Monte Carlo (DSMC) method is computationally expensive, making it difficult to achieve real-time prediction and massive sample generation of flow-field parameters. This paper presented a surrogate model adopting a convolutional neural network (CNN) to rapidly predict bow-shock reactive flow-field parameters. A blunt body with a nose radius of 0.1–1.0 m was investigated. The Latin hypercube sampling methodwas used to construct a sample space spanning altitudes of 80–150 km and Mach numbers of 15–35. DSMC-calculated data was segmented into training and test sets at a ratio of 4:1 and verified by the bow-shock ultraviolet experiments. An encoder–decoder CNN with a parallel decoder strategy was established to develop a bow-shock reactive flow surrogate model (CNN-BS) and conduct error evaluation. The results show that the mean absolute percentage errors for temperature, velocity, pressure, and nitric oxide number density are below 8%, with coefficients of determination close to 1. The average prediction time is 0.5 s, enabling online data generation. The CNN-BS model provides efficient support for radiation-noise evaluation and thermal-protection design of hypersonic blunt bodies. Full article

Microseismic monitoring is essential for the early warning of mine dynamic disasters; however, weak signal characteristics and strong environmental noise often lead to missed detections and false alarms. To address these challenges, this study proposes an optimized U-Net model for multi-class microseismic signal recognition under low-signal-to-noise-ratio conditions. The method combines Short-Time Fourier Transform, a U-Net encoder–decoder architecture, residual learning, and squeeze-and-excitation attention modules to enhance weak feature extraction and noise suppression. A multi-source dataset containing microseismic, knocking, blasting, noise, and earthquake signals was constructed using both field-measured data and public seismic datasets. Experimental results show that the proposed model achieved an overall validation accuracy of 99.25% and excellent recall performance for microseismic events. Under extreme noise conditions with a signal-to-noise ratio of −5 dB, the model still maintained a microseismic recognition accuracy of 98.25%. Comparative experiments further demonstrate that the integration of Short-Time Fourier Transform and residual attention modules significantly improves robustness and weak-signal discrimination capability. The proposed method provides an effective approach for intelligent microseismic monitoring and mine dynamic disaster early warning. Full article

Flood-induced scour remains one of the leading causes of bridge failure, yet the chain linking flood hazard to bridge decisions is still commonly treated as a sequence of disconnected tasks. This review examines that chain using uncertainty as a unifying interpretive framework, synthesizing the recent literature on non-stationary flood hazard assessment, bridge-scale hydraulics, scour processes and predictive models, scour monitoring, monitoring-informed forecasting, structural vulnerability, and risk-informed decision-making. The review synthesizes the state of the art across all these stages of the chain, highlighting how the dominant uncertainty changes along it: climate and hydrologic variability upstream; model-form, sediment, and parameter uncertainty in scour prediction; measurement noise and inverse-inference uncertainty in monitoring; and threshold and consequence uncertainty in closure, retrofit, and network-level decisions. Although major advances have been achieved in probabilistic modelling, machine learning, hybrid physics-informed methods, and multimodal sensing, most published frameworks still transfer deterministic outputs from one stage to the next. As a result, uncertainty is rarely propagated consistently to the decision level. The main value of this review lies in making the chain’s weak interfaces explicit, in showing how uncertainty propagation can serve as a unifying framework across otherwise disconnected literatures, and in identifying which methodological directions are most promising for connecting prediction, monitoring, and decision support into a coherent end-to-end probabilistic chain supporting climate-resilient bridge management. Full article

Glioblastoma multiforme (GBM) remains one of the most aggressive primary brain tumors with poor prognosis despite multimodal therapy. Photodynamic therapy (PDT) using indocyanine green (ICG) is an emerging adjuvant approach aimed at eliminating residual tumor cells after resection. While ICG-PDT exerts cytotoxic effects, its impact on molecular pathways regulating programmed cell death in glioma cells is not fully understood. In this study, T98G and U-118MG glioblastoma cells were divided into four groups: untreated control, light-only (10 min broadband irradiation), ICG-only (15 min incubation), and ICG-PDT (15 min ICG + 10 min broadband irradiation). Relative mRNA expression of apoptosis-related genes (BAX, BCL2, CASP3, FAS) and ferroptosis-related genes (GPX4, ACSL4, SLC7A11, GCH1) was quantified 24 h post-treatment by RT-qPCR using the 2^−ΔΔCt method. ICG-PDT significantly reduced cell viability to 67.79% ± 3.39% (vs. 86.66% ± 4.33% in control), confirming effective phototoxicity. No statistically significant differences in mRNA levels were observed for any of the investigated genes across the groups (one-way ANOVA and Kruskal–Wallis, all p > 0.05). The largest non-significant deviation was a mild decrease in GPX4 (fold change 0.87) in the ICG-PDT group. Fluctuations in GCH1 were accompanied by high variance, likely reflecting technical noise rather than a true biological trend. The mRNA BAX/BCL2 ratio remained stable (~30) across all conditions. In contrast, the U-118MG line showed greater transcriptional sensitivity, with statistically significant decreases in CASP3 (p = 0.012) and ACSL4 (p = 0.031) expression, along with downward trends in BCL2 and GPX4 following ICG-PDT. ICG-PDT does not induce significant transcriptional changes in the analyzed genes T98G at the 24 h time point under the applied experimental conditions. In U-118MG cells, moderate transcriptional engagement of both apoptotic and ferroptotic routes was observed. Further studies at the protein and functional levels, across multiple time points and models, are warranted to fully elucidate the mechanisms of ICG-PDT in glioblastoma. Full article

Background: Breast cancer remains a leading cause of cancer-related mortality, and reliable computational decision support is increasingly viewed as a complement to expert pathological assessment rather than a replacement for it. Variational quantum classifiers (VQCs) and Quantum Support Vector Machines (QSVMs) have recently been promoted as candidate models for medical classification, yet most published comparisons rely on internal hold-out validation alone and report only a single point estimate of discrimination, omitting calibration, decision-analytic value, and explainability—three ingredients that any clinically credible model must furnish. Methods: We assembled a complete quantum–classical machine learning pipeline and evaluated it under a deliberately stringent protocol designed to expose, rather than conceal, the limitations of current Noisy Intermediate-Scale Quantum (NISQ)-era models. The analytical hypothesis was conservative and stated in advance; in light of saturated classical baselines on this benchmark, we did not anticipate a quantum advantage in raw discrimination, and we framed the study as a methodological probe rather than as a competition. Using the Wisconsin Diagnostic Breast Cancer (WDBC) dataset (n = 569) for development and an independent Wisconsin Original (WBC) cohort (n = 683) for external validation, we benchmarked five classical learners (XGBoost, LightGBM, CatBoost, RandomForest, RBF-SVM), two quantum models (an eight-qubit VQC implemented in PennyLane and a ZZ-feature-map QSVM implemented in Qiskit), and a stacked hybrid ensemble. The evaluation framework combined Optuna-driven hyperparameter optimisation, internal–external cross-validation, and external validation on the independent WBC cohort. Robustness and interpretability were then probed through circuit depth and embedding rotation ablation, depolarising noise stress tests, learning curve and feature stability analysis, decision curve analysis, and dual SHAP-based explanations covering both a direct tree-based explanation and a quantum surrogate. Reporting followed the TRIPOD + AI guideline. Results: On the internal test partition, RBF-SVM achieved the highest discrimination (AUC = 0.998), with XGBoost, LightGBM, CatBoost, the hybrid ensemble, and the VQC clustering between 0.992 and 0.996; the QSVM with a ZZ-fidelity kernel underperformed substantially (AUC = 0.727). Pairwise tests for correlated ROC curves indicated that most differences among top models were not statistically significant. On the external WBC cohort, model rankings reorganised, as RBF-SVM (AUC = 0.986, 95% CI 0.946–0.997), RandomForest (0.985, 95% CI 0.945–0.996), VQC (0.983, 95% CI 0.942–0.995), and the hybrid ensemble (0.982, 95% CI 0.941–0.995) all retained near-ceiling discrimination with extensively overlapping confidence intervals. Ablation analysis demonstrated that the choice of embedding rotation is decisive—Z-rotation embeddings collapsed VQC performance to chance levels (AUC ≈ 0.50), whereas X- and Y-rotations preserved it. Depolarising noise up to p = 0.10 had a negligible effect on the VQC, and SHAP analyses converged on worst concave points, mean concave points, and worst area as the dominant predictors across both classical and quantum models. Decision curve analysis showed positive net benefit for both classical and hybrid models across the clinically meaningful threshold range, exceeding both the treat-all and treat-none reference strategies throughout. Conclusions: In the present regime, the principal contribution of QML is not raw discrimination—modern classical learners are already at the data ceiling—but the construction of a rigorous, reproducible, externally validated, and interpretable benchmarking framework in which quantum models can be fairly compared with their classical counterparts. Because evaluation was confined to curated benchmark datasets rather than real-world clinical populations, the interpretability and net benefit findings reported here should be read as benchmark-level evidence and not as a demonstration of readiness for clinical deployment. Full article

This research proposes a physics-based deep learning framework, developed as a proof-of-concept based on synthetic data, for estimating the mechanical properties of layered media—namely density (ρ), Young’s modulus (E), and top layer thickness (h₁)—using synthetic seismogram images generated via Finite Element Method (FEM) simulations. The dataset, comprising 5000 simulations, incorporates physical constraints and empirical density–modulus correlations. While a ResNet-style Convolutional Neural Network (CNN) extracts density and stiffness parameters from composite time–frequency images, the estimation of h1 utilizes a direct time-domain raw-signal approach to preserve spatial resolution. A 5-fold nested cross-validation scheme with internal Bayesian Optimization ensures rigorous model evaluation, further validated by normality assessments and bootstrap confidence intervals. Performance was tested against synthetic Gaussian noise (0% to 50%) and benchmarked against classical Full Waveform Inversion (FWI). The results demonstrate high predictive accuracy for shallow properties, with R² values reaching 0.96 for Young’s modulus and 0.83 for raw-signal thickness. The neural network model requires 0.035 s per inference compared to 180 s for the FWI approach, avoiding the local minima convergence issues typical of iterative inversion. The framework exhibits resilience under moderate noise levels (up to 30%), establishing a reliable baseline for future experimental validation. Full article

Knowledge Tracing (KT) plays a pivotal role in Intelligent Tutoring Systems (ITS) by dynamically assessing learners’ evolving knowledge states. However, tracking the acquisition of English presents unique challenges. Existing KT models typically employ homogeneous, predefined forgetting mechanisms that fail to capture the highly individualized nature of linguistic memory retention. Furthermore, language assessment data is notoriously noisy, which leads models to overfit superficial performance rather than capturing true underlying linguistic competence. To address these issues, we propose a novel framework to robustly trace English language competence. First, we introduce a Learning-Profile-Driven Adaptive Forgetting mechanism. Unlike methods with shared forgetting rates, our approach constructs a dynamic and strictly causal profile from historical interactions to generate personalized cognitive parameters (e.g., individualized forgetting rates). These parameters synchronously modulate the decay of multi-level knowledge states, enabling the model to accurately capture the heterogeneous memory retention patterns of different learners. Second, we design a Masked Consistency Regularization training paradigm. By applying stochastic masking to historical responses and enforcing predictive consistency, we prevent the model from exploiting localized noise and “shortcut” learning, compelling it to mine robust and invariant language representations. Extensive experiments on real-world educational datasets demonstrate that our proposed framework significantly outperforms state-of-the-art baselines in both prediction accuracy and noise resistance, offering a robust and interpretable solution for personalized language learning. Full article

In this work, we investigate deterministic chaos in external-cavity semiconductor lasers with delayed optical self-feedback. A noise-free quadrature-based delay differential model is used to isolate the intrinsic nonlinear dynamics produced by phase-sensitive delayed reinjection and carrier–photon interactions. Sensitivity to initial conditions is quantified by computing the leading Lyapunov exponents through a variational approach that integrates the base delay differential equations together with their delayed variational equations using a fourth-order Runge–Kutta method of steps and periodic QR orthonormalization. High-resolution Lyapunov maps are constructed in the $({\log }_{10}C,{\varphi }_f)$ parameter space for different pump ratios and selected short-feedback delays. The delay values are interpreted through the reference-normalized ratio ${\tau }_f/T_{R,\mathrm{ref}}$, where $T_{R,\mathrm{ref}}\approx 131.9\mathrm{ps}$ is a fixed reference timescale derived from a reference solitary-laser operating point. The results show that both the spatial organization of positive-${\lambda }_1$ regions and the mean positive Lyapunov exponent are strongly affected by feedback delay, feedback phase, feedback strength, and pump ratio. Within the selected short-delay set, delayed self-feedback produces broader, more connected, and more strongly unstable chaotic regions as the external-cavity memory time increases toward the fixed reference timescale, particularly at larger pump ratios. These findings show that short external-cavity self-feedback can support robust deterministic chaotic regimes relevant to compact and integrated photonic implementations. The proposed framework provides a reproducible deterministic reference for identifying and interpreting feedback-induced chaos in short-delay external-cavity semiconductor lasers, while stochastic effects such as spontaneous-emission and Langevin noise are left for future robustness studies. Full article

Pressure pulsations generated by pumps impair noise behaviour, increase mechanical loading, and reduce control performance in hydraulic systems. This study investigates the use of a rotary mechanical pulsation compensator integrated into the drivetrain of an external gear pump. The aim is to attenuate pulsations directly at their source without modifying the hydraulic layout. This is accomplished by using the torque induced flow rate pulsation to cancel the external flow rate excitation, which leads to destructive interference between flow rate induced and torque induced pressure pulsations. An analytical frequency domain model of the coupled mechanical–hydraulic system is derived to determine the required stiffness and damping conditions. The theoretical results are validated experimentally at mean pressure levels of 100 bar and 170 bar, both for two different hydraulic layouts. With a resonator pipeline at the pump outlet, the first harmonic of the pressure pulsation at the compensation frequency is reduced by 10.9 bar and 18.4 bar, respectively, which corresponds to reduction rates of 93% and 98%. The required damping value depends on the operating conditions, but it is independent of the hydraulic layout. While insufficient damping increases pressure pulsations around the compensation frequency, slightly higher damping flattens the frequency characteristics of pressure pulsation and reduces the maxima around the compensation frequency. In the neighbourhood of this frequency, the proposed concept enables effective reduction of the first pressure pulsation harmonic through a structural modification of the drivetrain. Full article

Accurate distance measurement in outdoor environments remains a challenging problem for mobile augmented reality (AR) systems due to sensor noise, environmental variability, and the limitations of single-modality approaches. Existing consumer AR solutions often prioritize usability over metric robustness, leading to performance degradation in large-scale or heterogeneous outdoor scenarios. This work presents EfMAR, an adaptive framework for outdoor mobile AR-based geospatial measurements that integrates multiple sensing modalities through a structured sensor fusion architecture. EfMAR combines visual SLAM, inertial sensing, depth information, and global positioning cues to improve robustness and consistency in distance estimation across diverse outdoor conditions. Beyond implementation, the framework formalizes a reusable architectural model for adaptive multi-sensor fusion, supporting reproducibility and future comparative research. A dedicated dataset is described, comprising 584 unique real-world evaluation instances collected across representative outdoor scenarios. External literature-derived data were utilized strictly as calibration baselines for modeled operational degradation profiles, maintaining methodological transparency. Performance evaluation focuses on analyzing relative behavior, stability, and variability across sensing approaches rather than establishing absolute accuracy benchmarks. Comparative results across multiple distance ranges and environments indicate that hybrid sensor fusion strategies exhibit more stable and consistent performance trends compared to single-modality solutions, particularly in challenging urban contexts. Dispersion analysis further highlights the influence of environmental factors such as lighting conditions and spatial scale on measurement variability. Overall, the results position EfMAR as a flexible and adaptive framework designed to enhance robustness in outdoor AR-based geospatial measurement tasks. By emphasizing consistency, transparency, and architectural generalization, this work contributes a practical foundation for future research and development in mobile AR sensing for real-world outdoor applications. Full article

In Underwater Acoustic Target Recognition (UATR), accurately extracting spectral lines from time–frequency spectra in complex ocean environments faces three critical challenges: low-frequency spectral confusion, line spectrum and noise mixture, and a computational efficiency vs. performance trade-off. To address these, we propose a deep learning-integrated framework based on application-oriented integration and adaptation of established techniques tailored to the underwater acoustic domain. The framework consists of the following: (1) the Line Spectrum Separation Network (LSS-Net), which integrates a Time–Frequency Joint LSTM and a Temporal Gated Cross-Attention (TGCA) module within an encoder–decoder architecture adapted for high-resolution underwater acoustic time–frequency spectra; (2) a physics-informed signal simulation approach that realistically models Doppler frequency drift and intensity fluctuations; and (3) a Peak-Tracking Line Extractor (PTLE) algorithm that leverages underwater acoustic-specific temporal constraints. The proposed framework achieves an MOTA of 0.89 on simulated data and 0.52 on real sea trial data, outperforming existing methods by 0.06-2.14 in MOTA and significantly suppressing high-resolution background noise. Full article

To address the issue of the Geiger-mode Avalanche Photodiode (GM-APD) LiDAR’s echo being easily overwhelmed by strong noise under low signal-to-background ratio conditions, leading to degraded performance in range parameter estimation and low target restoration accuracy, this paper proposes a range parameter estimation method based on multi-scale tracking differentiator. This method eliminates the reliance on complex statistical models and spatial prior information and uses a nonlinear dynamic tracking mechanism to extract target information. Firstly, a dual-scale tracking differentiator system is constructed, where the large-scale factor captures the transient mutation characteristics of the echo signal, and the small-scale factor estimates the overall evolution trend of the signal. Secondly, the difference between the dual-scale outputs is obtained to acquire the residual signal, and nonlinear mapping enhancement is performed in combination with the photon trigger probability characteristics to deeply suppress noise and highlight the target peak. Finally, the peak threshold method is used to complete the range calculation. Simulation results show that when the SBR = 0.06, compared with typical methods such as the neighborhood kernel density method, the method in this paper is more robust, the root mean square error of the range estimation is reduced by at least 38.35%, and the target restoration degree is improved by at least 19.99%, which provides a highly efficient way for high-fidelity single-photon three-dimensional imaging and target detection under strong noise. Full article

As one of the core technologies of predictive maintenance, the development of remaining useful life (RUL) prediction is gradually transitioning from early single-mechanism modeling to a new phase characterized by the deep integration of physics-based approaches, data-driven methods, and uncertainty awareness. This paper first analyzes the fundamental challenges facing this development, such as multi-stress coupling, sensor degradation, and non-stationary noise. By comparing the core advantages and applicability boundaries of statistical models, data-driven models, and hybrid models, it constructs a capability map for RUL prediction. It further points out that current RUL prediction still faces critical capability gaps in areas such as physical consistency and uncertainty decoupling. Finally, the paper distills a new paradigm for engineering implementation, including mechanism-guided neural architecture design and digital twin-driven online parameter adaptation. The research indicates that future RUL prediction studies must transcend the competition over accuracy metrics and shift toward the coordinated development of robustness, interpretability, and decision adaptability—a trinity guided by the principles of “trustworthy AI.” Full article

Distinguishing between human-made interferences and natural background disturbances is of great significance for the safe operation of terrestrial optical cables because human-caused damage can be halted through timely intervention. To address the problem of small-sample disturbance recognition in distributed acoustic sensing (DAS) systems, this paper proposes a fused CNN–SVM classification model based on hybrid features. A convolutional neural network is employed to extract the high-level spatiotemporal features of disturbance signals, which are subsequently fused with statistical features and fed into a support vector machine for classification. Evaluated on open-source data, the proposed model achieves accuracy improvements of 9.1%, 8.7%, and 2.7% over the conventional CNN, the statistical-feature-based SVM, and the conventional CNN-SVM model, respectively. Furthermore, based on field-measured data, a dataset comprising 5664 samples was constructed, covering four typical disturbance-event types: background noise, drilling, knocking, and digging. The field classification results demonstrate that the three-layer convolutional structure of the model achieves a recognition accuracy of 98.5%. Both the ROC curves and multiple evaluation metrics indicate that the proposed three-layer fused CNN–SVM model delivers better classification performance and more balanced category recognition, offering a feasible reference for similar fiber disturbance engineering tasks. Full article

6G promises ultra-low latency, high data throughput, and seamless global connectivity. However, providing uninterrupted connectivity in remote and underserved regions remains a critical challenge for Terrestrial Networks (TNs), where the cost of deploying infrastructure is difficult to justify against sparse user density. Standardized under 3GPP Release 17, Non-Terrestrial Networks (NTNs) have emerged as a viable solution to close this digital divide. Among NTN platforms, High-Altitude Platform Stations (HAPS) occupy a strategic middle ground, as they deliver lower propagation delays than Low-Earth Orbit (LEO) satellites while achieving far broader coverage than TN-based Base Stations (BS). Despite these advantages, battery-powered Internet of Things (IoT) devices communicating via HAPS face a fundamental energy efficiency (EE) challenge: transmit power must be carefully managed to maximize data throughput while preserving battery life and minimizing packet queuing delays. To address this, we propose a Q-learning-based Reinforcement Learning (RL) framework. The RL agent observes the instantaneous battery level and queue state of the IoT device, and dynamically selects optimal power levels from a discrete action space across successive time slots. Unlike traditional heuristic algorithms, such as Round Robin (RR), Max Single-to-Noise Ratio (Max-SNR), and fixed-power allocation, which rely on static rules or greedy channel-based decisions, the proposed Q-learning agent learns adaptive, long-term optimal policies through direct interaction with the environment, without requiring explicit mathematical modeling of the channel or traffic dynamics. Extensive simulations demonstrate that the proposed framework achieves up to 40% higher average EE compared to all benchmark schemes, maintains consistently lower power consumption, and exhibits superior statistical reliability as evidenced by a right-shifted Cumulative Distribution Function (CDF) of EE. These results demonstrate Q-learning as a promising candidate for scalable, energy-aware power control of next-generation HAPS-assisted IoT deployments in 6G NTN ecosystems. Full article