Search Results (334)

Accurate lithologic maps derived from satellite imagery underpin structural interpretation, mineral exploration, and geohazard assessment. However, automated mapping in complex terranes remains challenging because spectrally similar units, narrow anisotropic bodies, and ambiguous contacts can degrade boundary fidelity. In this study, we propose SegNeXt-HFCA, a hierarchical multiscale fusion network with coordinate attention for lithologic segmentation from a Sentinel-2/DEM feature stack. The model builds on SegNeXt and introduces a hierarchical multiscale encoder with coordinate attention to jointly capture fine textures and scene-level structure. It further adopts a class-frequency-aware hybrid loss that combines boundary-weighted online hard-example mining cross-entropy with Lovász-Softmax to better handle long-tailed classes and ambiguous contacts. In addition, we employ a robust training and inference scheme, including entropy-guided patch sampling, exponential moving average of parameters, test-time augmentation, and a DenseCRF-based post-refinement. Two study areas in the Beishan orogen, northwestern China (Huitongshan and Xingxingxia), are used to evaluate the method with a unified 10-channel Sentinel-2/DEM feature stack. Compared with U-NetFormer, PSPNet, DeepLabV3+, DANet, LGMSFNet, SegFormer, BiSeNetV2, and the SegNeXt backbone, SegNeXt-HFCA improves mean intersection-over-union (mIoU) by about 3.8% in Huitongshan and 2.6% in Xingxingxia, respectively, and increases mean pixel accuracy by approximately 3–4%. Qualitative analyses show that the proposed framework better preserves thin-unit continuity, clarifies lithologic contacts, and reduces salt-and-pepper noise, yielding geologically more plausible maps. These results demonstrate that hierarchical multiscale fusion with coordinate attention, together with class- and boundary-aware optimization, provides a practical route to robust lithologic mapping in structurally complex regions. Full article

To reduce reliability testing time, experiments are often terminated at a predetermined time, producing right-censored lifetime data. Alternatively, when test samples are inspected at fixed intervals, failures are only observed within these intervals, resulting in interval-censored lifetime data. Although quality control methods for right-censored data are well established, relatively little attention has been given to interval-censored observations. Motivated by the success of residual control charts based on convolutional neural network (CNN) for right-censored data, this study extends the chart for monitoring normally distributed interval-censored lifetime data. Simulation results based on average run length (ARL) indicate that the proposed method outperforms the traditional exponentially weighted moving average (EWMA) chart in detecting decreases in mean lifetime. The findings also highlight the practical benefits of employing high- or low-order autoregressive CNN models depending on the magnitude of process shifts. Full article

Background: Patient-based real-time quality control (PBRTQC) enables continuous analytical monitoring using routine patient results; however, the performance of classical statistical process control (SPC) algorithms varies across analytes, and standardized evaluation and optimization strategies remain limited. To address this gap, this study compared three SPC algorithms—moving average (MA), moving quantile (MQ), and exponentially weighted moving average (EWMA)—within a unified preprocessing framework and proposed a composite performance metric for parameter optimization. Methods: Routine patient results from six laboratory analytes were analyzed using a standardized “transform–truncate–alarm” PBRTQC workflow. Simulated systematic biases were introduced for model training, and algorithm-specific parameters were optimized using a composite metric integrating sensitivity, false-positive rate (FPR), and detection delay. Performance was subsequently evaluated on an independent validation dataset. Results: For most analytes, all three SPC algorithms demonstrated robust PBRTQC performance, achieving high sensitivity (generally ≥0.85), very low false-positive rates (<0.002), and rapid detection of systematic bias. EWMA showed more balanced performance for thyroid-stimulating hormone (TSH), with improved sensitivity and shorter detection delay compared with MA and MQ. The proposed composite metric effectively facilitated clinically meaningful parameter optimization across algorithms. Conclusions: Under a unified preprocessing framework, classical SPC algorithms provided reliable PBRTQC performance across multiple analytes, with EWMA offering advantages for more variable measurements. The proposed composite metric supports standardized, practical, and analyte-adaptive PBRTQC implementation in clinical laboratories. Full article

The performance of deep learning-based hydrological forecasting is highly sensitive to input quality, yet existing studies lack a systematic framework to evaluate the impact of high-frequency noise based on hydrological characteristics. To address this, we propose a frequency-based framework to assess the robustness of LSTM runoff prediction models. We define three hydrologically meaningful noise types—long-term trend, short-term event, and transient interference—and employ a synthetic noise injection strategy on the CAMELS dataset. Furthermore, we introduce an adaptive exponentially weighted moving average (AEWMA) algorithm that dynamically adjusts smoothing based on local signal variability. Results from dual-domain evaluation (time and frequency) indicate that model accuracy deteriorates significantly when high-frequency noise exceeds 30% of the total signal energy. Moderate adaptive smoothing (e.g., $\alpha =0.9\&0.6$) effectively preserves hydrological signals while mitigating performance loss, whereas aggressive smoothing suppresses meaningful variations. This study underscores the necessity of noise-type-specific preprocessing and suggests spectral energy ratios as quantitative thresholds for adaptive data quality control in hydrological modeling workflows. Full article

Stock price prediction is a core challenge in quantitative finance. While machine learning has advanced the modeling of complex financial time series, existing methods often rely on single-target predictions, underutilize multidimensional market information, and are disconnected from practical trading systems. To address these gaps, this research develops a hybrid machine learning framework for flexible target forecasting and systematic trading of major American technology stocks. The framework integrates Ensemble Models (AdaBoost, Decision Tree, LightGBM, Random Forest, XGBoost) with Fusion Models (Voting, Stacking, Blending) and introduces a Transfer Learning method enhanced by Dynamic Time Warping to facilitate knowledge sharing across assets, improving robustness. Focusing on ten key stocks, we forecast three distinct momentum indicators: next-day Closing Price Difference, Moving Average Difference, and Exponential Moving Average Difference. Empirical results demonstrate that the proposed Transfer Learning approach achieves superior predictive performance and trading simulations confirm that strategies based on these predicted momentum signals generate substantial returns. This research demonstrates that the proposed hybrid machine learning framework can mitigate the high information entropy inherent in financial markets, offering a systematic and practical method for integrating machine learning with quantitative trading. Full article

This work presents a lightweight and interpretable framework for the early warning of voltage stability degradation in distribution networks, based on fractal and spectral features from flow measurements. We propose a Fast Voltage Stability Index (FVSI), which combines four independent indicators: the Detrended Fluctuation Analysis (DFA) exponent α (a proxy for long-term correlation), the width of the multifractal spectrum Δα, the slope of the spectral density β in the low-frequency range, and the $c_2$ curvature of multiscale structure functions. The indicators are calculated in sliding windows on per-node series of voltage in per unit Vpu and reactive power Q, standardized against an adaptive rolling/first-N baseline, and anomalies over time are accumulated using the Exponentially Weighted Moving Average (EWMA) and Cumulative SUM (CUSUM). A full online pipeline is implemented with robust preprocessing, automatic scaling, thresholding, and visualizations at the system level with an overview and heat maps and at the node level and panel graphs. Based on the standard IEEE 13-node scheme, we demonstrate that the Fractal Voltage Stability Index (FVSI_Fr) responds sensitively before reaching limit states by increasing α, widening Δα, a more negative $c_2$, and increasing β, locating the most vulnerable nodes and intervals. The approach is of low computational complexity, robust to noise and gaps, and compatible with real-time Phasor Measurement Unit (PMU)/Supervisory Control and Data Acquisition (SCADA) streams. The results suggest that FVSI_Fr is a useful operational signal for preventive actions (Q-support, load management/Photovoltaic System (PV)). Future work includes the calibration of weights and thresholds based on data and validation based on long field series. Full article

In froth flotation, the features of froth images are important information to predict the concentrate grade. However, the froth structure is influenced by multiple factors, such as air flowrate, slurry level, ore properties, reagents, etc., which leads to highly complex and dynamic changes in the image features. Additionally, issues such as the immeasurability of ore properties and measurement errors pose significant uncertainties including aleatoric uncertainty (intrinsic variability from ore fluctuations and sensor noise) and epistemic uncertainty (incomplete feature representation and local data heterogeneity) and generalization challenges for prediction models. This paper proposes an uncertainty quantification regression framework based on cross-modal interaction fusion, which integrates the complementary advantages of Selective Kernel Networks (SKNet) and Vision Transformers (ViT). By designing a cross-modal interaction module, the method achieves deep fusion of local and global features, reducing epistemic uncertainty caused by incomplete feature expression in single-models. Meanwhile, by combining adaptive calibrated quantile regression—using exponential moving average (EMA) to track real-time coverage and adjust parameters dynamically—the prediction interval coverage is optimized, addressing the inability of static quantile regression to adapt to aleatoric uncertainty. And through the localized conformal prediction module, sensitivity to local data distributions is enhanced, avoiding the limitation of global conformal methods in ignoring local heterogeneity. Experimental results demonstrate that this method significantly improves the robustness of uncertainty estimation while maintaining high prediction accuracy, providing strong support for intelligent optimization and decision-making in industrial flotation processes. Full article

To address the challenges of varying scales of concrete defects, class imbalance, and hardware limitations, we propose EMAFG-RTDETR, a UAV-based concrete defect detection algorithm built upon RTDETR. In the feature extraction stage, a lightweight multi-scale attention feature extraction module (EMA-PRepFaster block) is designed, where PConv and RepConv are fused to improve the FasterNet block. At the same time, an Efficient Multi-scale Attention (EMA) module is introduced to enhance spatial feature extraction while reducing computational redundancy. For feature fusion, the Gather-and-Distribute mechanism of GOLD-YOLO is adopted to improve the fusion of multi-scale features. The introduction of Powerful-IoU v2 not only accelerates the training process but also enhances the model’s ability to capture defects of different sizes. To handle the issue of sample imbalance, a novel classification loss function, EMASVLoss, is proposed. This function adjusts classification loss values through piecewise weighting and integrates an exponential moving average mechanism for dynamic weight smoothing, improving model adaptability. Finally, the algorithm was deployed and validated on an octocopter UAV developed by our team. Experimental results demonstrate that EMAFG-RTDETR achieves a 2.5% improvement in mean Average Precision (mAP@0.5), reaching 90% on the concrete defect dataset, with reductions in both parameter size and computational cost. Moreover, the UAV equipped with the proposed algorithm can accurately detect cracks and spalling defects on concrete surfaces, validating the effectiveness of the improved model. Full article

A robust methodology for parametric fault diagnosis in photovoltaic systems is proposed, focusing on DC-DC boost converters. The methodology uses Adaptive Sliding Mode Observers (ASMO) combined with adaptive thresholding. Specifically, an observer-based scheme detects and isolates faults in passive components of the converter, achieving complete isolation in about 0.05 s, even under varying environmental conditions. In addition, a dynamic fault discrimination approach is introduced, based on adaptive thresholds derived from Exponentially Weighted Moving Average (EWMA). This minimizes false alarms caused by transient conditions. Stability and robustness are guaranteed through Lyapunov-based conditions. Simulation results under sequential and simultaneous fault scenarios confirm rapid and precise fault detection, highly specific isolation, and exceptional resilience against environmental disturbances. Full article

This paper presents OpS-EWMA-LLM (Operational State Shifts Detection using Exponential Weighted Moving Average and Labeling using Large Language Model), a hybrid framework that combines fleet-normalized statistical shift detection with LLM-assisted diagnostics to identify and interpret operational state changes across heterogeneous fleets. First, we introduce a residual-based EWMA control chart methodology that uses deviations of each component’s sensor reading from its fleet-wide expected value to detect anomalies. This statistical approach yields near-zero false negatives and flags incipient faults earlier than conventional methods, without requiring component-specific tuning. Second, we implement a pipeline that integrates an LLM with retrieval-augmented generation (RAG) architecture. Through a three-phase prompting strategy, the LLM ingests time-series anomalies, domain knowledge, and contextual information to generate human-interpretable diagnostic insights. Finaly, unlike existing approaches that treat anomaly detection and diagnosis as separate steps, we assign to each detected event a criticality label based on both statistical score of the anomaly and semantic score from the LLM analysis. These labels are stored in the OpS-Vector to extend the knowledge base of cases for future retrieval. We demonstrate the framework on SCADA data from a fleet of wind turbines: OpS-EWMA successfully identifies critical temperature deviations in various components that standard alarms missed, and the LLM (augmented with relevant documents) provides rationalized explanations for each anomaly. The framework demonstrated robust performance and outperformed baseline methods in a realistic zero-tuning deployment across thousands of heterogeneous equipment units operating under diverse conditions, without component-specific calibration. By fusing lightweight statistical process control with generative AI, the proposed solution offers a scalable, interpretable tool for condition monitoring and asset management in Industry 4.0/5.0 settings. Beyond its technical contributions, the outcome of this research is aligned with the UN Sustainable Development Goals SDG 7, SDG 9, SDG 12, SDG 13. Full article

Among various statistical process-control (SPC) methods, control charts are widely employed as essential instruments for monitoring and improving process quality. This study focuses on a new modified exponentially weighted moving-average (New Modified EWMA) control chart that enhances detection capability under integrated and fractionally integrated time-series processes. Special attention is given to the effect of symmetry on the chart structure and performance. The proposed chart preserves a symmetric monitoring configuration, in which the two-sided design ($\mathrm{LCL}>0$) establishes control limits that are equally spaced around the center line, enabling balanced detection of both upward and downward shifts. Conversely, the one-sided version ($\mathrm{LCL}=0$) introduces a deliberate asymmetry to increase sensitivity to upward mean shifts, which is particularly useful when downward deviations are physically implausible or less critical. The efficacy of the control chart utilizing both models is assessed through Average Run Length (ARL). Herein, the explicit formula of ARL is derived and compared to the ARL obtained from the Numerical Integral Equation (NIE) in terms of both accuracy and computational time. The accuracy of the analytical ARL expression is validated by its negligible percentage difference ($\%diff$) in comparison to the results derived using the NIE approach, and the display processing time not exceeding 3 s. To confirm the highest capability, the suggested method is compared to both the classic EWMA and the modified EWMA charts using evaluation metrics such as ARL and SDRL (standard deviation run length), as well as RMI (relative mean index) and PCI (performance comparison index). Since asset values are volatile due to positive and negative market influences, symmetry is crucial in financial monitoring. Thus, symmetric control-chart structures reduce directional bias and better portray financial market activity by balancing upward and downward movements. Finally, examination of US stock prices illustrates performance, employing a symmetrical two-sided control chart for the rapid detection of changes through the new modified EWMA, in contrast to standard EWMA and modified EWMA charts. Full article

Semi-supervised learning (SSL) is critical for medical image segmentation but often struggles with network dependency and pseudo-label error accumulation. To address these issues, we propose a fractal-dimension-guided hierarchical contrastive learning dual-student framework(FD-HCL). We extend the Mean Teacher architecture with a dual-student design and introduce an independence-aware exponential moving average (I-EMA) update mechanism to mitigate model coupling. For enhanced feature learning, we devise a hierarchical contrastive learning (HCL) mechanism guided by voxel uncertainty, spanning global, high-confidence, and low-confidence regions. We further improve structural integrity by incorporating a fractal-dimension (FD)-weighted consistency loss and integrating a novel uncertainty-aware bidirectional copy–paste (UB-CP) augmentation. Extensive experiments on the LA and BraTS 2019 datasets demonstrate the state-of-the-art performance of our framework across 10% and 20% labeled data settings. On the LA dataset with 10% labeled data, our method achieved a Dice score that outperformed the best existing approach by 0.68%. Similarly, under the 10% labeling setting on the BraTS 2019 dataset, we surpassed the state-of-the-art Dice score by 0.55%. Full article

The current application of the production data exponentially weighted moving average (EWMA) model can detect PRRSV outbreaks earlier than that of processing fluid (PF) testing; however, its advantages have not been fully reported. This study aimed to analyze various production parameters, including abortion, off-feed, low appetite, and dead sows, on a daily basis following a PRRSV outbreak in an II-vx sow farm. The EWMA method was employed and the results were compared with the early detection of positive PF results. Differences in daily abnormal indicators across the three PRRSV status periods were analyzed. Additionally, this study evaluated the PRRSV detection rates in different sample types (AF, OS, and TBS) from aborted sows and compared the detection rates of different sample combinations using statistical tests. The 187-day study revealed that the first true positive (TP) alarm point for daily abortion sows occurred on day 107 and for off-feed sows on day 110. In contrast, the first RT-qPCR-positive result for PF was obtained on Day 122. The average values of daily abortions and off-feed sows in status I-A were significantly higher than those in status II-vx and I-B. Conversely, the average value of low appetite in status I-A was significantly lower than that in statuses II-vx and I-B. No significant differences were observed in the daily number of dead sows among the three groups. The RT-PCR detection rates varied significantly (p < 0.01) among the different sample types (AF, 43.04%; TBS, 65.82%; and OS, 74.68%), with amniotic fluid (AF) showing the lowest detection rate. Combining AF and oropharyngeal swabs (OS) samples yielded a higher detection rate than combining AF and TBS samples. Using the EWMA to monitor the daily number of aborted sows was effective for the early detection of PRRSV outbreaks. Full article

Fractional-order models (FOMs) have been recognized as superior tools for capturing the complex electrochemical dynamics of lithium-ion batteries, outperforming integer-order models in accuracy, robustness, and adaptability. Parameter identification (PI) is essential for FOMs, as its accuracy directly affects the model’s ability to predict battery behavior and estimate critical states such as state of charge (SOC) and state of health (SOH). In this study, a hybrid deep learning approach has been introduced for FOM PI, representing the first application of deep learning in this domain. A simulation platform was developed to generate datasets using Sobol and Monte Carlo sampling methods. Five deep learning models were constructed: long short-term memory (LSTM), gated recurrent unit (GRU), one-dimensional convolutional neural network (1DCNN), and hybrid models combining 1DCNN with LSTM and GRU. Hyperparameters were optimized using Optuna, and enhancements such as Huber loss for robustness to outliers, stochastic weight averaging, and exponential moving average for training stability were incorporated. The primary contribution lies in the hybrid architectures, which integrate convolutional feature extraction with recurrent temporal modeling, outperforming standalone models. On a test set of 1000 samples, the improved 1DCNN + GRU model achieved an overall root mean square error (RMSE) of 0.2223 and a mean absolute percentage error (MAPE) of 0.27%, representing nearly a 50% reduction in RMSE compared to its baseline. This performance surpasses that of the improved LSTM model, which yielded a MAPE of 9.50%, as evidenced by tighter scatter plot alignments along the diagonal and reduced error dispersion in box plots. Terminal voltage prediction was validated with an average RMSE of 0.002059 and mean absolute error (MAE) of 0.001387, demonstrating high-fidelity dynamic reconstruction. By advancing data-driven PI, this framework is well-positioned to enable real-time integration into battery management systems. Full article

Forecasting stock prices remains a central challenge in financial modelling, as markets are influenced by market sentiment, firm-level fundamentals and complex interactions between macroeconomic and microeconomic factors, for example. This study evaluates the predictive performance of both classical statistical models and advanced attention-based deep learning architectures for daily stock price forecasting. Using a dataset of major U.S. equities and Exchange Traded Funds (ETFs) covering 2012–2024, we compare traditional statistical approaches, Seasonal Autoregressive Integrated Moving Average (SARIMA) and Exponential Smoothing (ES) in the Error, Trend, Seasonal (ETS) framework, with deep learning architectures such as the Temporal Fusion Transformer (TFT), and a novel hybrid model, the TFT-Graph Neural Network (TFT-GNN), which incorporates relational information between assets. All models are assessed under consistent experimental conditions in terms of forecast accuracy, computational efficiency, and interpretability. Our results indicate that while statistical models offer strong baselines with high stability and low computational cost, the TFT outperforms them in capturing short-term nonlinear dependencies. The hybrid TFT-GNN achieves the highest overall predictive accuracy, demonstrating that relational signals derived from inter-asset connections provide meaningful enhancements beyond traditional temporal and technical indicators. These findings highlight the advantages of integrating relational learning into temporal forecasting frameworks and emphasise the continued relevance of statistical models as interpretable and efficient benchmarks for evaluating deep learning approaches in high-frequency financial prediction. Full article