Search Results (539)

Wind turbine SCADA anomaly detectors are commonly calibrated using data from the same asset or development period, whereas deployment requires transfer across turbines with different operating distributions. This mismatch can produce optimistic thresholds, excessive false alarms, and misleading generalization estimates. This study proposes UC-RCF, an uncertainty-calibrated residual conformal framework integrating nonlinear multi-output normal behavior modeling, embargoed blocked cross-fitting, uncertainty-normalized residuals, operating support assessment, channel-wise conformal evidence, reflected cumulative criticality, and cross-asset alarm calibration. Evaluation followed a nested leave-one-turbine-out, asset-disjoint protocol on CARE v6, comprising 95 monitoring cases from 36 turbines across three wind farms, including 45 anomalous and 50 normal cases. UC-RCF achieved a pooled outer-fold CARE score of 0.5903, fault coverage of 0.3920, weighted earliness of 0.2423, event-level reliability of 0.5760, and normal-case accuracy of 0.8706. It detected 25 anomalous cases and generated alarms in 18 normal cases. A farm-stratified paired turbine-cluster bootstrap estimated a CARE improvement of 0.0349 over the initial full configuration, with a 95% percentile interval of 0.0055–0.0671 and a bootstrap probability of improvement of 0.991. These estimates remain exploratory because the effective resampling units comprise only 36 physical turbines from three wind farms. Mahalanobis monitoring achieved a higher CARE score of 0.6012, detecting 21 anomalous cases while generating alarms in nine normal cases. UC-RCF therefore provided broader fault coverage and four additional anomalous-case detections but incurred a higher false-alarm burden, demonstrating a sensitivity–reliability trade-off rather than universal detector dominance. Ablation analysis identified farm-normalized residual magnitude as the strongest case-level discriminator, with a receiver operating characteristic area under the curve of 0.854. Heteroscedastic uncertainty scaling and operating support adjustment did not consistently improve CARE or raw discrimination; the auxiliary framework components instead provide mechanisms for uncertainty characterization, score comparability, temporal persistence, and calibration auditing. At the CARE-optimal nominal case-level false-alarm budget of $\alpha =0.30$, the empirical normal-case false-alarm rate was 0.36. Because temporal dependence and cross-asset distribution shift can violate exchangeability, $\alpha$ is interpreted as an operational calibration target rather than a theoretically guaranteed case-level error bound. Overall, UC-RCF provides an interpretable and auditable framework for investigating residual evidence, operating support shift, temporal persistence, and calibration reliability under cross-asset deployment. Full article

Dual-parameter photonic sensors are usually reported through a nominal sensitivity and one detection limit, without stating which statistic that limit is or whether it survives transfer between devices. This computational study supplies that evaluation for one structure, a 36-layer one-dimensional multilayer read in transmission, whose Zak-phase-distinct TiO₂/SiO₂ photonic-crystal sections enclose a 600 nm analyte cavity and a 500 nm thermo-optic reference cavity, each carrying a 5 nm ITO/5 nm TiO₂ nanolaminate insert. Two coupled interface resonances at 1517 and 1651 nm, with loaded Q of 232 and 208 and refractive-index (RI) sensitivities of 90.71 and 329.41 nm/RIU, are inverted by a bounded nonlinear calibration to $2.43\times {10}^{-5}$ RIU and $0.155$$°\mathrm{C}$; the temperature channel reports the device temperature. Probability-of-detection limits at 1% false alarm and 95% detection are $4.36\times {10}^{-5}$ RIU and $0.123$$°\mathrm{C}$; they are set by the calibration standards and the wavelength reference, not by the linewidth. Transferring one calibration between devices worsens them 81-fold and 203-fold; a three-point per-device correction removes 84–93% of that loss. A trivial control matched on wavelength, Q, transmission, thickness and RI sensitivity shows no topological robustness advantage. Applied to the design itself, the same evaluation shows that the modes are cavity-selected, that hyperbolicity brings no benefit, and that the nanolaminate-free stack is preferred. Full article

Representative severe-weather events and high-reflectivity radar echo samples are relatively scarce in inland Western China, limiting the local training of deep learning-based extrapolation models. To examine the applicability and limitations of cross-regional transfer learning under limited target-domain data availability, this study adopts a source-domain pretraining and target-domain fine-tuning strategy. Using East China as the source domain and northwestern Xinjiang as the target domain, we conduct a unified comparison across three representative architectures: PredRNN, SimVP, and Earthformer. SimVP is further employed to examine the effects of target-domain data volume and module-wise transferability. In the evaluated experiments, transfer learning improved the Critical Success Index, Probability of Detection, and Fractions Skill Score at both 60- and 120-min lead times across the selected reflectivity thresholds, although changes in the False Alarm Ratio varied by architecture and threshold. The three case studies provided complementary evidence of improved echo-structure preservation. For SimVP, transfer gains are more pronounced when target-domain data are limited and generally diminish as more local training data become available. This finding suggests that pretraining can improve the use of limited target-domain data, while the continued accumulation of representative local severe-weather observations remains necessary. Within the tested SimVP freezing configurations, module-wise analysis further shows that the Encoder parameters responsible for spatial feature extraction exhibit relatively strong cross-regional reusability, whereas updating the Translator responsible for latent-space spatiotemporal evolution while keeping the Encoder frozen improves forecast performance. These module-level findings are specific to the evaluated SimVP setting. Overall, the results support the practical applicability of transfer learning in the studied East China-to-Xinjiang scenario. The transfer gains are jointly influenced by differences in meteorology and radar observations, and their broader applicability remains to be tested in future studies across different regions and model architectures. Full article

This paper presents a target detection method for active sonar based on weighted neighbourhood relative entropy (WNRE), using tools from information geometry. The method segments the matched-filter output of each echo by a sliding window, estimates the probability density of every window by kernel density estimation, and forms the detection statistic from the Jensen–Shannon divergence between each window and its Gaussian-weighted neighbourhood, so that no pre-stored noise template or prior knowledge of the noise distribution is required. Semi-physical experiments on deep-sea active sonar data from the South China Sea show that the weighted Jensen–Shannon divergence (W-JS) detector reaches P_d = 0.985 at P_fa = 0.01 at an input SNR of 9 dB on the deep-sea near-Gaussian convergent zone background, where it requires about 2.7 dB less input SNR than the CA-CFAR detector to attain P_d = 0.5. The method is most effective in near-Gaussian, locally stationary convergent-zone backgrounds; in strongly reverberant and non-stationary regions its advantage diminishes, where energy-based constant false-alarm-rate (CFAR) detectors regain competitiveness. Operating at the window level rather than point-by-point, and at the same per-decision false-alarm probability, it yields fewer expected false-alarm events per scan cycle than conventional point-by-point detectors. Full article

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

In recent years, the use of UAVs has become increasingly widespread, and the public safety risks posed by unauthorized UAV flights have become increasingly prominent, creating an urgent need for effective detection and identification of UAV targets. However, such targets are small in size, have low contrast, and exhibit an extremely low signal-to-noise ratio; conventional detection methods generally suffer from insufficient feature discrimination, missed detections, and false alarms in complex backgrounds. To address these challenges, this paper proposes a Frequency-Guided Cross-scale Refinement Network (FGCR-Net). Based on an encoder-decoder architecture, this network achieves end-to-end collaborative optimization through cross-layer feature fusion, side-channel prediction refinement, and frequency-domain background suppression. First, a multi-path selective cross-layer fusion module (SCFM) is designed. This module employs coordinated modeling via both channel and spatial paths, supplemented by adaptive weighting with learnable coefficients, to perform differentiated selective fusion of the encoder’s fine-grained features and the decoder’s semantic features, thereby bridging the semantic gap at jump connections; Second, we designed a Cross-Scale Adaptive Fusion Enhancement Attention Module (CAFEM), which cascades multi-receptive-field hollow convolutions, strip pooling, and a bidirectional semantic guidance mechanism to perform cross-scale refinement on the side outputs of each decoder layer, thereby alleviating the issues of blurred boundaries and false alarms caused by inconsistent quality of multi-scale prediction maps and insufficient cross-layer consistency; finally, we design a Frequency-Guided Semantic Enhancement Module (FGSEM), which uses the Fast Fourier Transform (FFT) to decouple encoder features into the frequency domain. By leveraging low-frequency energy to predict the background confidence map and applying spatially selective suppression to high-frequency components, this module distinguishes, from a frequency-domain perspective, the high-frequency responses of complex backgrounds and targets that are highly similar in the spatial domain. Experiments on MSDS-UAV, a self-built multi-scenario UAV dataset for small targets, demonstrate that our method consistently outperforms existing state-of-the-art methods across multiple performance metrics, with Pixel Accuracy, Mean Intersection over Union, and Probability of Detection reaching 92.76%, 70.91%, and 92.69%, respectively; Compared to the baseline model, these three metrics improved by 1.90, 3.20, and 3.76 percentage points, respectively, fully validating the effectiveness and superiority of the proposed method. Full article

Emotional information often modulates recognition memory, but the relative roles of arousal and valence remain debated, partly because many studies rely on normative emotion categories rather than individualized affective experience. This study examined whether post-test individualized arousal and valence ratings were associated with recognition-confidence responses to emotional Chinese words and whether the learning task influenced later recognition. Forty participants studied neutral, positive, and negative words under semantic-judgment and recognition-judgment learning conditions. After a 24 h delay, they completed a six-point old/new confidence test and then rated each final-test word for valence and arousal. Linear mixed-effects models showed that individualized arousal was more consistently associated with stronger old-response confidence than individualized valence, with a nonlinear increase at higher arousal levels. Semantic-judgment learning was followed by higher old-item confidence and hit probability than recognition-judgment learning. Descriptive signal-detection summaries indicated that valence-category effects were more evident in false-alarm rates, response criterion, and d′ (sensitivity index) estimates than in the primary old-response confidence model. Because affective ratings were collected after recognition, these findings should be interpreted as associative rather than causal, and they highlight the need to distinguish recognition confidence, response bias, and memory sensitivity in emotional memory research. Full article

Drainage pipeline environments are typically characterized by darkness, high humidity, water accumulation, sediment deposition, reflective surfaces, and severe occlusions. These challenging conditions make conventional single-sensor inspection methods highly susceptible to environmental interference, resulting in false detections, missed defects, and insufficient reliability in defect confirmation. To address these challenges, this paper proposes a vision–LiDAR–ultrasonic multi-sensor fusion method for defect confirmation in drainage pipeline inspection. The three sensing streams are processed in parallel rather than using visual detection as the exclusive trigger: the vision branch performs high-recall screening of apparent defects, the LiDAR branch continuously evaluates geometric anomalies in spatially indexed point-cloud segments, and the ultrasonic branch independently evaluates wall-thickness and echo anomalies along the valid probe-contact path. Candidate regions proposed by any branch are merged through timestamp-, odometry-, and coverage-aware spatial association, after which all available visual, geometric, and acoustic evidence at each union candidate is mapped to basic probability assignments and fused using reliability-constrained Dempster–Shafer evidence theory. The five-run evaluation on the fixed 105-group test subset (18 defects and 87 non-defects) gives the proposed method an Accuracy of 97.7 ± 0.5%, Precision of 93.4 ± 2.2%, Recall of 93.3 ± 2.5%, F1-score of 93.3 ± 1.5%, and false-alarm rate of 1.4 ± 0.5%. Under the same test protocol, the vision-only baseline gives an F1-score of 81.1 ± 2.4% and a false-alarm rate of 3.9 ± 0.6%. These results are calculated from the measured per-group predictions obtained in the experiments. Full article

The booming data volume of modern time-domain surveys demands fast, robust early classification of sparsely sampled light curves, as newly discovered transients typically have only a handful of observations. We compare classifiers for extremely sparse light curves (3–30 observations) on a benchmark of approximately 1.72 million segments spanning seven astrophysical classes from ZTF and ATLAS. Methods include handcrafted-feature approaches (XGBoost, feature-based Transformers) and end-to-end LSTM and Transformer models. A pre-trained end-to-end Transformer achieves test accuracy of 0.946 (macro F1 0.950), exceeding 90% accuracy with only seven observations, but falls to 0.513 without pre-training. XGBoost-Reduced (38 features, excluding LS descriptors) reaches 0.922, while XGBoost-Full (56 features) reaches 0.913. Reliability diagnostics confirm LS periods and false-alarm probabilities are unreliable on 3–30-point segments; restricting training and evaluation to ≥15 points does not reverse the full-scale preference for the Reduced catalog. On CPU, XGBoost runtime is dominated by feature extraction (ratio ≈ 16:1); adding LS descriptors increases total processing time by ∼7.8% (feature extraction by ∼7.0%) without a commensurate accuracy gain. A lightweight LSTM attains 0.847 accuracy with 0.2 M parameters. These results offer practical guidance for model selection in real-time survey pipelines. Full article

Industrial anomaly detectors emit binary alarms, but production lines need graded dispositions. Calibrating alarms into fault probabilities requires ground truth, coming only from noisy human review treated as exact. We report a deployed closed loop on a reciprocating-compressor line (46,023 units, nine test campaigns, four fused detector legs). A stratified review of 1161 units audited a fusion-score grading and refuted its assumed monotonicity: precision was 25.2%/13.8%/26.1% for high/medium/low tiers. The cause was correlated false positives: two legs firing on shared broadband transients agreed on 480 units at 21.0% precision—detector agreement is not independent evidence—whereas one periodicity feature was monotone (27.8% → 60.0% → 100%). A blind test against seeded fault units (hardware ground truth) measured reviewer sensitivity at 0.905 and specificity at 0.421 on hard cases; Rogan–Gladen correction restored monotonicity (95% of bootstrap replicates; 83% under campaign-cluster resampling), exposed the low-tier advantage as a label-noise artifact, and re-estimated no-alarm prevalence at 4–10% versus the observed 13.3%. Corrected evidence drove a redeployed rule calibrating tiers at ≈67%/27%/17% under review budgets (≤1%/≤3%/≤9% of production). The methodology—stratified audit, seeded-fault blind testing, and evaluation-side prevalence correction—transfers to any human-verified system. Full article

Lightning poses localized risks to signaling, communication, and traction-power systems along high-speed railways, yet most nowcasting products are generated on regular grids rather than operational line segments. This study developed a grid-to-segment machine-learning framework for next-hour lightning warning along the Jinan West–Tai’an corridor. Ground-based lightning observations, hourly ERA5 fields, temporal variables, and engineered historical lightning features and spatial-neighborhood features were organized on a 0.25° grid. Data from 2014 to 2018 were used for training, 2019 for validation, and 2020 for independent testing. Grid probabilities were converted into warnings for six railway segments using 10 km buffers and maximum-probability aggregation. In 2020, the full extreme gradient-boosting (XGBoost) model, a tree-based ensemble-learning algorithm, achieved grid-level probability of detection (POD), false-alarm ratio (FAR), and critical success index (CSI) values of 0.55, 0.50, and 0.36; segment-level verification yielded 0.60, 0.39, and 0.43. To examine transfer to forecast-driven application, the trained model and threshold were fixed, and ERA5 meteorological inputs were replaced by short-lead ECMWF HRES forecasts for July 2025. POD decreased from 0.85 to 0.80 and CSI from 0.60 to 0.57, while FAR remained nearly unchanged. Under a predefined non-zero rule, HRES litota1 achieved 0.62, 0.71, and 0.25. ML-HRES therefore showed higher CSI and lower FAR than the direct litota1 baseline. Full article

Spaceborne synthetic aperture radar (SAR) needs point-like reference targets for co-registration, calibration, and absolute geolocation, but real corner reflectors (CRs) exist only at a few dedicated sites. We present a detection and three-dimensional (3D) positioning pipeline for naturally occurring corner-reflector-like (pseudo-CR) scatterers in KOMPSAT-5 stacks, combining constant false alarm rate (CFAR) detection ranked by local contrast rather than absolute power, a multi-scale template bank, multi-look range-Doppler bundle triangulation, and a per-target conditioning diagnostic vector. At the nine-CR Mongolia calibration field, all nine are recovered, with a mean horizontal error of 1.37 m and a mean 3D error of 2.01 m. At a CR-absent suburban site in Suncheon, Republic of Korea, 18 scenes yield 39,822 clusters, 26,659 of which pass the conditioning gate. Over 16 response-enriched poles retained by author adjudication, the difference to the nearest conditioning-filtered cluster averages 3.19 m horizontally and 1.45 m vertically relative to the surveyed pole base. Because part of that set was selected after inspecting preliminary responses, these are conditional nearest-cluster agreements, not verified target accuracies, and no detection probability is claimed. In an exploratory comparison on the same set, contrast ranking retains more evaluation targets than power ranking at equal budgets, 16 against 9 of 16. Removing robust weighting and pruning degrades the mean Mongolia 3D error to 7.39 m; the DEM prior is non-critical, whereas the clustering radius is consequential in the dense pole field, with the count within 20 m falling from 16 to 9 as the radius grows from 15 m to 30 m. In a leave-scene-out check, 85.8% of 254 evaluable clusters persist in a scene excluded from their solutions, against 35.2% of 270 evaluable random positions: a complete-case enrichment of 78%, or 53–82% under cross-arm worst-case imputation of the unevaluable targets; neither estimate measures catalogue precision. Limited KOMPSAT-5 stacks can therefore yield few-metre nearest-cluster agreement at selected pole locations where stable multi-scene responses form. Full article

Distribution drift can substantially degrade the performance of deployed machine learning models; for example, accuracy on SST-2 can fall from $88\%$ to $58\%$. Detecting such degradation is fundamentally challenging because deployment provides inputs but not labels, so the detection itself must be reference-free. We introduce DecayBench, the first reference-free, calibrated benchmark for evaluating drift detectors. DecayBench measures detector trustworthiness along five axes (calibrated, valid, timely, no-regret, adaptive), and compares ten existing detectors across ten NLP, vision, and multimodal datasets using paired-bootstrap significance testing. Evaluation on DecayBench shows that no existing detector is uniformly optimal. Motivated by this observation, we propose Alert, a label-free aggregation rule for drift detection. Unlike all competing combiners, it uses a label-free self-configuring selection rule with a no-regret guarantee. Alert has three contributions: (i) a dilution analysis yielding a self-configuring detector selection rule; (ii) a finite-sample conformal guarantee that controls the false-alarm probability on clean data at any prescribed level (e.g., $5\%$) for arbitrary score distributions; and (iii) a no-regret result: when no single detector dominates (constituents of comparable effect size, a condition checkable offline), Alert matches or beats the best constituent, being never significantly worse and sometimes better by a large margin; this holds across NLP, NLI, and vision (ResNet), with the largest gains under multimodal drift, and the proof identifies a dominant single detector (MMD on CLIP) as the only dilution exception. We prove the no-regret property and, across the benchmark, report its empirical counterpart, non-dominance under a paired bootstrap (Alert is never significantly worse than the best constituent), which at some operating points is statistically inconclusive rather than a strict win. Because Alert combines only embedding- and logit-based detector scores, it directly transfers across NLP, vision, and multimodal models. Empirically, Alert strictly improves over single-modality monitoring, increasing AUC by up to 25 points under mixed-modality drift and by approximately 50 points under cross-modal mismatch, where individual modality-specific detectors perform near chance. Alert also matches or outperforms the Fisher, Simes, Bonferroni, and median combiners, performs best under low-severity drift, and matches or surpasses early fusion (Concat-MMD) in both multimodal settings. Full article

Since heavy clutter seriously restricts the ability of radar to detect targets, it is significant to build the target detector under heavy clutter. For practical situations without the secondary data or prior knowledge of target and clutter, this paper proposes a polarization-space-time detector. First, a general radar model is constructed for multiple pulses, multiple arrays, and multiple polarizations. Based on the theory of ternary hypothesis, the secondary data free (SDF) GLRT detector is proposed, which can maintain the constant false alarm probability (CFAR) in inhomogeneous clutter. Then, this paper proposes a matrix transform operator and an adaptive detection method using sliding window. These two approaches do not need to know the steering vector of radar and the noncentral parameter of clutter in advance, so the SDF-GLRT detector can adapt to different application scenarios. In addition, this paper optimizes the polarization waveform of the radar system by constructing a projection matrix. This method yields closed-form solutions of the optimal polarization and worst polarization, rather than relying on numerical solution. Finally, the performances of the SDF-GLRT detector and three other detectors are compared by simulated and real data. The proposed SDF-GLRT maintains $P_{\mathrm{FA}}$ of $5.4\times {10}^{-3}$ and $2.6\times {10}^{-3}$ on two IPIX datasets (#54 and #310) at a design $P_{\mathrm{FA}}={10}^{-3}$, whereas the other detectors deviate to $0.0249$–$0.7405$. The optimal polarization yields a detection-probability gain of more than $0.22$ over the worst polarization at $\mathrm{SCR}=0$ dB. Full article

The rapid deployment of low-Earth-orbit mega-constellations has increased the demand for reliable and scalable orbit-anomaly monitoring. Existing methods are vulnerable to heavy-tailed measurement errors, maneuver-induced propagation drift, and the anisotropic uncertainty of short observation arcs. This study proposes an uncertainty-aware Starlink monitoring framework that combines residual-domain wavelet shrinkage with a Huber-weighted adaptive two-body extended Kalman filter to suppress non-Gaussian contamination without obscuring abrupt state changes. A linear altitude correction and a quadratic phase-time correction are introduced into Simplified General Perturbations-4 propagation to compensate for maneuver-related forecast drift. A cross-time covariance model and a joint normalized innovation squared test are further constructed for uncertainty-aware short-arc maneuver sensing, while hierarchical evidence fusion supports anomaly detection and event interpretation. Across paired experiments, the filtering chain reduces position root-mean-square error from 752.4 ± 77.7 m to 175.9 ± 9.9 m, and compensated propagation reduces the 72 h prediction error from 128.7 km to 19.6 km. The detector achieves 93.4% accuracy with a 2.7% false-alarm rate and maintains empirical short-arc false-alarm probabilities near the nominal one percent level. These results demonstrate a consistent engineering link between catalog-scale screening and uncertainty-aware short-arc maneuver sensing. Full article