Search Results (1,113)

The post-pandemic evolution of education involving mechatronics and machine learning has shifted the demand for robotic hardware from centralized laboratories to accessible laboratories in home environments. This paper presents a portable three-wheeled holonomic robotic platform designed for remote research and home office experimentation. The proposed system utilizes a modular design and low-cost philosophy comprising a custom embedded control system driven by an ESP32-WROOM microcontroller, which manages a closed-loop PID velocity controller using Hall effect feedback from three DC micromotors. In contrast, external nodes allow the reception, conditioning, and classification of 8-channel surface electromyography (sEMG) data sampled at 500 Hz. To address the non-stationarity and stochastic noise in raw sEMG signals, this study implements a hybrid Deep Learning (DL) architecture that complements 2D Convolutional Neural Networks (CNN) for spatial feature extraction with Long Short-Term Memory (LSTM) networks for temporal context awareness. This model decodes the neuromuscular intent of the user into real-time holonomic velocity vectors, achieving validation accuracies of 80.51% for horizontal movement, 84.86% for vertical translation, and 99.56% for the Fist/no-Fist state. By synthesizing advanced AI-based teleoperation with a portable design, this study establishes a scalable framework for the next generation of “laboratory-at-home” educational tools and research regardless of physical location. Full article

The assessment of non-stationarity in the rainfall process is still a major research topic in the field of applied hydrology. The water cycle is affected by several characteristics of this process: rainfall volume, wet weather duration, their mutual association, and the annual number of events. The method used to sample rainfall variables from the time series may or may not suitably account for their variability. Herein, the rainfall process is analyzed using a bivariate event-based approach, with reference to two rainfall time series recorded at short time steps in different Italian climates. Trends are also estimated. Full article

This study presents a methodology for forecasting municipal water consumption to support efficient resource management. Using monthly data from 2018 to 2022 for the municipality of Vouzela, Portugal, three forecasting approaches were evaluated: SARIMA, Holt–Winters, and TimeGPT. Data preparation included logarithmic transformation and stationarity assessment using the KPSS test, ensuring appropriate conditions for statistical modelling. The SARIMA model was selected automatically based on the Akaike Information Criterion (AIC), while the Holt–Winters method was fitted with additive components and a Box–Cox transformation. In addition, TimeGPT was employed as a state-of-the-art foundation model for time series forecasting. The three methods were used to predict water consumption for the 12 months of 2023, and their performance was assessed using MAE, MSE, RMSE and MAPE. Results indicate that although all methods perform adequately, Holt–Winters and TimeGPT better capture recent consumption dynamics, providing more accurate forecasts in several periods. Overall, this study shows that combining classical statistical models with advanced forecasting techniques offers local authorities reliable and computationally accessible tools to support water supply planning and sustainability. Full article

Predicting financial stock returns remains challenging due to their inherent nonlinearity, non-stationarity, and sensitivity to market microstructure noise. Existing approaches typically rely on either econometric filtering techniques or deep learning models in isolation, limiting their ability to jointly capture latent dynamics and complex temporal dependencies. This study proposes a hybrid Extended Kalman Filter–Long Short-Term Memory (EKF–LSTM) framework that integrates nonlinear state-space filtering with deep sequential learning. The EKF component performs nonlinear state estimation and denoises to extract latent signals from noisy observations, while the LSTM network models nonlinear temporal dependencies in the filtered series. The proposed framework is evaluated using data from multiple international markets, including China, the United States, and Europe, providing cross-market evidence of model robustness. Empirical results show that the EKF–LSTM model consistently outperforms benchmark models (ARIMA, standalone EKF, LSTM, and GRU) across standard statistical metrics, including RMSE, MAE, and mean directional accuracy (MDA). In addition, the model delivers economically meaningful improvements under a long-only trading strategy, achieving higher risk-adjusted returns and lower maximum drawdowns relative to benchmark strategies. Diebold–Mariano tests further confirm that these performance gains are statistically significant. Overall, the findings demonstrate that integrating nonlinear state-space filtering with deep learning provides a robust and effective framework for financial time-series forecasting. However, the results should be interpreted with caution due to the limited sample size and the simplifying assumptions underlying the trading strategy. Full article

Traditional linear models in urban informatics struggle to capture the complex, non-linear spatial non-stationarity inherent in metropolitan housing markets. To overcome these constraints, this study introduces a data-driven computational framework integrating a Spatio-Temporal Graph Convolutional Network (STGCN) with gradient-based Explainable Artificial Intelligence (XAI) and Geographically Weighted Regression (GWR). This framework is empirically tested using 217,598 apartment transactions in Busan, the Republic of Korea, augmented with high-resolution micro-demographic grids and Digital Elevation Model (DEM) topographical data. Utilizing unsupervised K-Means clustering, the region is spatially stratified into a dense Urban Core and a dispersed Suburban Periphery. The STGCN demonstrates overwhelming predictive superiority ($R^2=0.802$) over the traditional Spatial Error Model ($R^2=0.437$). Crucially, gradient-based XAI and localized GWR coefficients successfully unspool the deep learning “black box,” visualizing hyper-localized economic realities that global linear models obscure. The analysis expose stark regional market segmentation driven by environmental topography, mathematically quantifying non-linear dynamics such as coastal high-floor premiums, severe mountainous altitude penalties, and latent urban reconstruction premiums. Ultimately, this research bridges the gap between predictive computational power and spatial economic interpretability, offering a robust informatics framework for equitable urban planning. Full article

To address the challenges of strong volatility, pronounced non-stationarity, and the inability of single models to simultaneously capture local dynamics and global dependencies in photovoltaic (PV) power series under complex weather conditions, this study proposes a short-term PV power forecasting framework that integrates weather-based clustering, signal decomposition, parameter optimization, and hybrid neural networks. First, a density-based clustering algorithm, namely Density-Based Spatial Clustering of Applications with Noise (DBSCAN), is employed to partition historical samples into distinct weather regimes, thereby mitigating the impact of heterogeneous meteorological conditions on model stability. Second, to handle the strong non-stationarity of PV power series, Variational Mode Decomposition (VMD) is introduced to decompose the original signal into multiple intrinsic components. The Crested Porcupine Optimizer (CPO) is further utilized to adaptively optimize key VMD parameters, including the number of modes and the penalty factor, thereby improving decomposition quality. Finally, a hybrid LSTM–Transformer forecasting model is constructed to jointly capture local temporal dynamics and long-range dependencies. The Newton–Raphson-Based Optimizer (NRBO) is employed to optimize critical hyperparameters, including the learning rate, regularization coefficient, and the number of hidden units, thereby enhancing model performance. The proposed method is validated using real-world data from a PV power station in Alice Springs, Australia. Experimental results demonstrate that, compared with the LSTM–Transformer baseline, the proposed model achieves reductions in RMSE of 0.086, 0.082, and 0.097 kW, and reductions in MAE of 0.062, 0.082, and 0.081 kW under clear-sky, cloudy, and rainy/snowy conditions, respectively. The corresponding R² values reach 0.993, 0.968, and 0.958. These results indicate that the proposed framework exhibits strong predictive performance across different weather scenarios and provides a reliable reference for short-term PV power forecasting and grid dispatching decisions. Full article

Real-world time series forecasting is often challenging due to non-stationarity and distribution shifts, where the optimal forecasting model varies across different temporal regimes and horizons. In this work, we introduce a method called Adaptive Future-Guided Ensemble Learning (AFG-EL), a two-stage framework that performs drift-aware, sample-level routing over a heterogeneous model zoo. AFG-EL learns dynamic fusion weights from meta-features of the historical window and incorporates a future-guided training signal from a relative-future teacher or scorer, emphasizing learning on regime transitions and drift-sensitive segments. Crucially, the inference process remains strictly causal, requiring only historical data and extracted meta-features. We further use sparse routing with an entropy-based fallback mechanism to enhance stability when routing confidence is low. Our experiments on several commonly used forecasting datasets demonstrate that AFG-EL consistently outperforms strong single-model baselines, uniform averaging, and adaptive fusion baselines. Full article

Financial markets are characterized by non-stationarity, regime shifts, and complex cross-asset interactions, which challenge traditional portfolio optimization and motivate reinforcement learning (RL) for adaptive decision-making. However, many RL-based approaches remain predominantly return-centric, with risk, uncertainty, and human oversight only weakly integrated, limiting robustness and practical applicability. This review provides a critical synthesis of risk-aware and uncertainty-sensitive reinforcement learning for portfolio optimization from a human–AI collaboration perspective. We analyze major architectural paradigms—including single-agent, hierarchical, multi-agent, and modular systems—together with risk modeling strategies (e.g., reward shaping, constraint-based optimization, and downside risk measures such as CVaR) and probabilistic approaches to uncertainty estimation (e.g., Bayesian neural networks, Monte Carlo dropout, and ensembles). A structured analysis of 57 fully assessed studies reveals that only 5 (9%) explicitly couple uncertainty estimation with risk constraint mechanisms, while 38 (69%) treat risk and uncertainty as structurally independent components. We identify a central structural limitation: risk objectives are rarely conditioned on epistemic uncertainty, while uncertainty estimates seldom influence constraint mechanisms or capital allocation. This decoupling leads to fragmented frameworks that remain difficult to deploy in real financial environments. By integrating architectural design, risk modeling, uncertainty estimation, and evaluation practices, this review proposes a unified, deployment-oriented perspective for developing governance-aligned portfolio decision-support systems. Full article

This study investigates the influence of large-scale climate modes on Mediterranean dust-transport variability using a newly developed Saharan Dust Flux Transport Index (SDFTI_base) for 2003–2024. Monthly and seasonal correlations show that NAO–SDFTI_base associations reach r = 0.35–0.55 across sub-regions, whereas ENSO–SDFTI_base correlations remain weaker (r = 0.10–0.25). Running correlations reveal pronounced non-stationarity, fluctuating between −0.4 and +0.6, while wavelet coherence exceeds 0.5 at 2–4-year periods during episodic teleconnection events. NAO exerts its strongest influence at sub-annual scales (0.15–0.5 years), whereas ENSO modulates dust transport primarily at interannual scales (1–3 years). Teleconnection strength is regionally heterogeneous: WestMed and EastMed exhibit the most persistent coupling, CentMed shows weak sensitivity, and BalBSea displays intermediate behaviour. NAO produces near-immediate dust-transport responses, while ENSO often leads dust-transport variability. These results provide a multi-scale dynamical framework linking Atlantic and Indo-Pacific climate variability to Mediterranean dust-transport pathways and highlight the importance of teleconnection-based diagnostics for regional climate assessment. Full article

Background: Diarrheal disease remains a major and persistent cause of morbidity and mortality in Rwanda, with substantial seasonal surges that strain routine services; however, transparent and operationally interpretable national forecasting has been underused for age-stratified burden. Methods: We analyzed the Rwanda Health Management Information System (HMIS) monthly diarrhea case counts (January 2015–December 2025), stratified by age group (under-five and five-and-above), and developed validated Seasonal Autoregressive Integrated Moving Average (SARIMA) forecasts for January 2026–December 2027. Stationarity was assessed using the Augmented Dickey–Fuller test and addressed through differencing. Candidate models were selected via rolling 5-fold cross-validation: Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Akaike Information Criterion (AIC), Bayesian Information Criterion (BIC), and Mean Absolute Percentage Error (MAPE) and confirmed via Ljung–Box residual diagnostics, and benchmarked against seasonal naïve, Exponential Smoothing State-Space (ETS), and Seasonal-Trend decomposition using Loess (STL) + drift reference models. Results: Rwanda recorded 6,309,098 diarrhea cases during 2015–2025, with 49.2% among under-fives; while absolute counts were higher in those aged ≥5 years, risk remained consistently higher in under-fives (91.7–229.5 per 1000) than in those ≥5 years (17.9–34.3 per 1000). Both series showed strong annual seasonality with recurrent peaks in August–November, and forecasts suggest this pattern will persist through 2026–2027. Conclusions: These findings suggest a provisional seasonal (pre-peak, peak, and post-peak) preparedness framework and age-differentiated planning signals, underscoring that burden and risk are not inter changeable across age groups. Full article

The carbon allowance price series exhibits nonlinearity, non-stationarity, and high noise due to multiple factors. Accurate forecasting is crucial to the stability of the carbon market and to resource allocation. This paper proposes a forecasting framework using multi-scale decomposition and a TCN–LSTM hybrid model. First, the original carbon allowance price series is decomposed using CEEMDAN optimized by PSO. Then, VMD performs secondary decomposition of complex components based on sample entropy. Next, transfer entropy identifies causal relationships between each component and the original series, enabling reconstruction based on causality. Finally, a TCN–LSTM model uses reconstructed sequences to forecast carbon prices. The method achieves high-precision short-term forecasts using only the carbon allowance price series, avoiding reliance on external variables. Empirical results on the Hubei carbon market show an optimal lag of 3, with R² = 0.8873, outperforming the single LSTM and TCN models and achieving a lower RMSE. The forecast using January–March 2026 data shows stable carbon prices with slight fluctuations. This study provides a reliable method for data-constrained short-term carbon price forecasting, supporting decision-making and policy assessment. Full article

Groundwater systems in semi-arid and industrial regions are increasingly affected by climate-driven non-stationarity and anthropogenic pressure, challenging conventional forecasting approaches. This study develops and evaluates an integrated artificial intelligence framework designed to minimize piezometric head residual dispersion under non-stationary hydroclimatic conditions. The proposed methodology combines Improved Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (ICEEMDAN) and Variational Mode Decomposition (VMD) with a Slime Mould Algorithm–optimized Long Short-Term Memory (SMA–LSTM) model and a CNN–LSTM architecture, which are dynamically fused using an Adaptive Weighting Model (AWM). The framework was applied to long-term groundwater level (1994–2024), groundwater quality (2017–2023), and meteorological datasets to evaluate the predictive robustness across climatic variability regimes. The proposed ensemble achieved a mean absolute error of 0.267 m, root mean square error of 0.429 m, coefficient of determination (R²) of 0.948, and Nash–Sutcliffe efficiency of 0.938, representing substantial residual reduction compared to baseline deep learning models. Residual diagnostics confirmed minimized peak deviations and stable performance under non-stationary conditions. Scenario-based simulations driven by CMIP6 climate projections indicate increasing groundwater stress under future warming trajectories, with amplified variability and declining recharge signals. These findings demonstrate that multi-stage signal decomposition coupled with metaheuristic optimization and adaptive ensemble learning significantly enhances predictive stability and residual minimization in climate-sensitive aquifer systems. The proposed framework provides a transferable, climate-resilient decision-support tool for sustainable groundwater management in industrial and semi-arid regions. Full article

Indirect methods based on Pontryagin’s Maximum Principle (PMP) offer theoretical rigor for nonlinear optimal control but suffer from extreme sensitivity to costate initialization. Physics-Informed Neural Networks (PINNs) provide a promising data-free approach to globally approximate trajectories and overcome this initialization barrier. However, they often lack strict numerical precision due to their reliance on soft penalty constraints. To bridge this gap, this paper proposes a hybrid framework that synergizes the global search capability of a structurally modified PINN with the rigorous precision of high-order Chebyshev–Gauss–Lobatto (CGL) spectral discretization. Within this framework, we first introduce a novel neural architecture that enforces the PMP stationarity condition as a hard constraint by analytically eliminating control inputs via costates, thereby reducing the optimization search space and ensuring strict optimality during training. The neural-generated trajectories subsequently provide a high-quality warm start for a CGL pseudospectral solver, transforming the problem into a single-shot convex quadratic programming formulation. Numerical experiments on the Van der Pol oscillator and elliptic PDE optimal control problems demonstrate that this strategy effectively mitigates the initialization sensitivity of indirect methods. The results show that the proposed method achieves superior accuracy and convergence stability compared to standalone PINN solvers, providing a robust initialization-free approach for complex nonlinear optimal control. Full article

Motor imagery electroencephalography (MI-EEG) decoding remains challenging in cross-subject scenarios due to pronounced inter-subject variability and signal non-stationarity, which often lead to performance degradation on unseen subjects. Existing prototype-based and domain adaptation methods typically rely on global feature alignment or single-level class representation, limiting their ability to capture both channel-wise spatial variability and high-level semantic structure. To address these limitations, we propose a dual-stage prototype representation framework for cross-subject MI-EEG decoding. The framework models spatial and semantic variability in a hierarchical manner by introducing channel prototypes and feature prototypes, enabling more consistent representations across subjects. Furthermore, a prototype-guided pairwise similarity learning strategy is employed to enhance intra-class compactness and inter-class separability in the embedding space. To mitigate cross-subject distribution shifts, we integrate a lightweight statistical perturbation method (StyleMix) with Wasserstein-based domain alignment, helping reduce subject-specific distribution variations. Experiments on the BCI Competition IV 2a and 2b datasets show that the proposed method achieves competitive performance under the evaluated target-assisted few-shot setting, reaching average accuracies of 79.12% and 87.31%, respectively, and improving over the strongest baseline by up to 2.99 percentage points. Full article

This systematic review (PRISMA 2020) examines 89 studies—64 peer-reviewed articles and 25 arXiv preprints (2007–2026)—addressing the gap between AI research and operational predictive maintenance (PdM) deployment in complex manufacturing systems. Analyzing five thematic clusters in non-stationary and stochastic environments, we evaluated predictive performance and deployment readiness. Deep learning dominates remaining useful life (RUL) forecasting; however, 65.6% of studies employ weak or unclear validation protocols (Tier 0–1), lacking real-world robustness testing. Fault diagnosis increasingly integrates Edge-AI, yet Explainable AI (XAI) adoption remains scarce (15.6%), undermining industrial trustworthiness. No study reached operational field validation beyond temporal or cross-domain split, reflecting a systematic disconnection from deployed manufacturing systems. We introduce a novel Deployment Readiness Score (DRS) framework and identify critical barriers: data scarcity, environmental non-stationarity, computational constraints, and black-box model distrust. Recommendations include standardized temporal validation protocols, multi-site field studies, and architecture-integrated explainability. The 25 arXiv preprints (2024–2026) exhibit a mean DRS nearly three times that of the peer-reviewed corpus, signaling nascent convergence toward deployment-mature research. This review was not pre-registered. Full article