Search Results (6,740)

Forecasting financial time series (FTS) is essential for analyzing and understanding the dynamics of financial markets. Traditional recurrent neural network (RNN) models often suffer from low prediction accuracy on non-stationary and abruptly changing data, as their gating mechanisms struggle to capture evolving trends in FTS. This paper introduces variational mode decomposition (VMD) and multifractal analysis to enhance the gating mechanism of the gated recurrent unit (GRU). By quantifying the changing characteristics of FTS, the proposed model dynamically adjusts the gating weights. In addition, a state fusion strategy is employed to improve the utilization efficiency of historical information. Experiments are conducted using daily data of the SSE 50, CSI 300, and CSI 1000 indices, spanning from 4 January 2002, to 26 December 2025. The results demonstrate that, compared to traditional models, the proposed model better captures the evolving characteristics of FTS and achieves higher prediction accuracy. Full article

Financial time series forecasting remains a challenging task due to the high non-stationarity and concept drift inherent to market data. Existing deep learning models, such as LSTMs and transformers, typically employ static weights after training, limiting their ability to adapt to rapid market regime shifts (e.g., from trends to reversals). To bridge this gap between static parameters and dynamic environments, we propose a novel framework named Game-Theoretic HyperNetwork (GTH-Net), which introduces a context-aware meta-learning mechanism to achieve adaptive forecasting. Specifically, we first introduce an Evolutionary Game-Theoretic Correction Module (E-GTCM) to explicitly extract latent buying and selling pressure based on market microstructure priors through an iterative gated evolution process. Subsequently, we propose a HyperNetwork-based fusion mechanism that treats the extracted game state as a meta-context to dynamically generate the weights of the forecasting head. This allows the model to automatically switch its prediction rules in response to shifting market regimes. Extensive experiments on real-world stock datasets demonstrate that GTH-Net significantly outperforms baselines in terms of machine learning predictive accuracy and simulated financial profitability. Furthermore, ablation studies and parameter analysis confirm that the dynamic weight generation mechanism effectively captures market reversals caused by overcrowded trades. Full article

With the rapid development in data mining and learning analytics, integrating predictive analytics into educational data has become increasingly critical for supporting students’ learning trajectories. In many schooling systems, the academic tracks (such as Liberal Arts or Science) and the performance of junior high school students can substantially shape their subsequent university pathways and career planning. Despite the long-term impact of these decisions, academic track selections and the evaluation of students’ potential are often made without systematic and evidence-based guidance. Predictive computer applications can assist, but the training of accurate models and the selection of adequate features remain key challenges. This paper details our process of engineering such an application comprising two tasks based on 1357 real-world junior high school academic performance records. The first task applies a classification approach to predict students’ academic track orientation, while the second task employs a multi-output regression model to forecast students’ future academic performance in senior high school. Our approach shows that the stacking ensemble model achieved a classification accuracy of 85.76%, whereas the Bi-LSTM model with multi-head attention attained an overall R² exceeding 82% in performance forecasting; both models demonstrated strong and reliable predictive capability. Moreover, the proposed approach provides inherent interpretability by decomposing predictions at the subject level. Feature importance analysis reveals how different academic subjects contribute variably to both academic track decisions and future academic performance, offering actionable insights for academic counselling and future study planning. By bridging predictive modelling with students’ educational and career planning needs, this study advances the practical application of educational data mining and provides support for evidence-based academic guidance and future career choices in real-world contexts. Full article

Accurate energy forecasting is essential for maintaining power system reliability, integrating renewable generation, and ensuring market stability. Although machine learning has improved forecasting accuracy, its operational deployment depends on Machine Learning Operations (MLOps) platforms that automate and scale the entire lifecycle of energy data pipelines. However, the capabilities of existing MLOps platforms for energy forecasting have not been systematically compared. This study adopts a PRISMA-informed review process to identify relevant end-to-end MLOps platforms for energy forecasting and then maps their documented capabilities using an established energy forecasting pipeline lifecycle as the reference structure. A total of 256 records were screened across vendor documentation, open-source repositories, and academic literature, of which 13 MLOps platforms were selected for comparative capability analysis. Platform capabilities are organised and presented across an end-to-end lifecycle covering project setup and governance, data ingestion and management, model development and experimentation, deployment and serving, and monitoring and feedback. Commercial platforms such as Amazon SageMaker and Google Vertex AI generally provide stronger end-to-end integration and production readiness, while open-source platforms such as Kubeflow and ClearML offer modular flexibility that typically requires additional integration effort to achieve end-to-end operation. The mapping identifies four priority areas where platform support remains limited, namely (i) governance workflow automation, (ii) automated data quality validation, (iii) feature management, and (iv) deployment and monitoring support under nonstationary conditions. These findings indicate that platform selection for energy forecasting should be treated as a lifecycle capability decision, balancing end-to-end integration, operational assurance, and long-term flexibility. Full article

We propose a fully nonparametric empirical autoregressive copula framework for univariate time series, designed to capture nonlinear and asymmetric serial dependence while exactly preserving the empirical marginal distribution. The method decouples marginal behavior from temporal dependence by (i) constructing a shape-preserving empirical marginal via monotone interpolation and mapping observations to the unit interval, and (ii) estimating the lag–lead dependence through a nonparametric conditional AR(1) copula density on ${(0,1)}^2$. To ensure stable estimation near the boundaries, we employ reflection-based kernel methods that mitigate edge effects and yield well-behaved conditional densities on the unit support. Forecasts are obtained from the implied conditional predictive density: we compute point forecasts either as conditional modes (maximum a posteriori) on the copula scale or as conditional means, and then back-transform exactly using the empirical quantile function, guaranteeing marginal fidelity and support-respecting predictions. Empirically, we evaluate the approach on three CBOE volatility indices (VIX, VXD, and RVX) and benchmark it against linear ARMA models, copula-based parametric competitors, and state-space/heteroskedasticity baselines (Local level, TVP–AR, and ARMA–GARCH). The results highlight that modeling the full conditional transition density nonparametrically can deliver competitive—often best or near-best—forecast accuracy across horizons, particularly in the presence of pronounced volatility regimes and asymmetric adjustments. Full article

Accurate yaw alignment is critical for maximizing power capture in horizontal-axis wind turbines, as even moderate yaw misalignment leads to significant aerodynamic losses, increased actuator usage, and accelerated mechanical wear. This research paper proposes a hybrid smart yaw control system for small-scale wind turbines that combines real-time measurements with short-term wind direction prediction to improve alignment accuracy, operational reliability, and energy efficiency under realistic operating conditions. The system integrates four wind direction information sources, such as physical wind vane sensing, live online weather data, forecast data, and a data-driven prediction module within a structured priority framework (VANE → LIVE → FORECAST → AI), to ensure continuous yaw control during sensor or communication unavailability. The prediction module is based on a long short-term memory (LSTM) neural network trained in MATLAB using live data from an online platform, with sine–cosine encoding employed to address the circular nature of directional data. The yaw controller incorporates a ±15° deadband, dwell-time logic, shortest-path rotation, and cable-safe constraints to reduce unnecessary actuation while maintaining effective alignment. The proposed system is validated through MATLAB/Simulink simulations and real-time microcontroller-based experiments using a stepper motor-driven nacelle. Compared with conventional vane-based yaw control, the hybrid AI-assisted approach reduces the average yaw error by approximately 35–45%, maintains a yaw error within ±15° for more than 90% of the operating time, increases average electrical power output by 3–5%, and reduces yaw motor energy consumption by 10–15%, while decreasing corrective yaw actuation events by 30–40%. These results demonstrate that integrating an LSTM-based wind direction predictor with multi-source wind data provides a robust, low-cost, and practically deployable yaw control solution that enhances energy capture and mechanical durability in small-scale wind turbines. Full article

Short-term forecasting of solar radiation is essential for the efficient operation of solar energy systems. This study presents a neural network-based approach for short-term solar radiation forecasting using a hybrid framework that integrates temporal characteristics with weather-based features. The proposed model combines a Gated Recurrent Unit (GRU) to capture short-term temporal dynamics, a Transformer Encoder, and a Multilayer Perceptron (MLP) to integrate these representations for final prediction. Key meteorological variables, including temperature, humidity, and wind speed, are incorporated along with engineered time-related features such as lagged values, rolling statistics, and cyclical time-of-day encodings. The results demonstrate that the hybrid model effectively integrates sequential learning and feature interaction, leading to improved forecasting accuracy. The proposed approach achieves a test Mean Absolute Error (MAE) of 0.056, Root Mean Square Error (RMSE) of 0.086, and coefficient of determination (R²) of 0.92, outperforming benchmark models such as AutoRegressive Integrated Moving Average (ARIMA), Long Short-Term Memory (LSTM), GRU, and Extreme Gradient Boosting (XGBoost). The model maintains stable performance across cross-validation folds, multiple forecasting horizons, and varying weather conditions. These findings indicate that the proposed framework provides a reliable and practical solution for accurate short-term solar radiation forecasting, supporting real-time solar energy management and renewable energy system optimization. Full article

Typhoon track prediction is an important research direction in weather forecasting. Although deep learning methods have achieved some progress in this field, challenges remain, including insufficient fusion of meteorological features, limited capability in modeling temporal and spatial evolution, and high computational cost of some models. To address these issues, this paper proposes a dual-path, multi-modal typhoon track prediction model that incorporates a gated axial Transformer to enhance the modeling of deep structural features in the meteorological environment. Numerical experimental results show that the proposed model achieves higher prediction accuracy than comparative methods in typhoon track prediction tasks across multiple time scales, demonstrating the effectiveness of the approach. Full article

The transition to smart cities is accelerating distributed wind and solar deployment. However, their intermittency challenges grid operation, thereby making accurate machine-learning-based prediction of wind speed and global horizontal irradiance (GHI) crucial. This study presents a cost-effective approach that enhances prediction accuracy by extracting additional features from timestamp records for deep learning models used to forecast GHI and wind speed. Unlike conventional methods that require onsite meteorological measurements, the proposed approach uses only date and time information as inputs to multivariate deep neural networks, including recurrent neural networks, gated recurrent units, long short-term memory (LSTM), bidirectional LSTM, and convolutional neural networks. For wind speed prediction, the proposed configuration achieves R² up to 0.9987, with RMSE as low as 0.067 m/s for 3 d ahead forecasting, outperforming univariate baselines and matching models. For GHI forecasting, the time-based configuration attains R² values above 0.9994 in 12 h ahead predictions, with the RMSE reduced to approximately 4.47 W/m², representing a substantial improvement over univariate models. The proposed framework maintains strong performance, particularly under clear and sunny conditions. These results demonstrate that timestamp-engineered features can deliver forecasting accuracy comparable to conventional multivariate meteorological models while significantly reducing infrastructure requirements, making the approach well-suited for scalable smart city energy management. Full article

Against the backdrop of climate change, forest fires increasingly undermine ecosystem stability and reshape species distributions in Heilongjiang Province. Therefore, quantifying the drivers of fire occurrence and conducting long-term fire risk forecasting holds critical value for regional ecological security. Centered on the forested regions of Heilongjiang Province, this study systematically assessed the relative contributions of multi-source factors—including topography, vegetation, and meteorological conditions—to fire occurrence and compared the predictive performance of three models: Deep Neural Network with Residual Connections (ResDNN), Artificial Neural Network (ANN), and Support Vector Machine (SVM). Modeling results based on historical fire records indicated that the ResDNN model achieved the highest accuracy (85.6%). Owing to its robust nonlinear mapping capability, it performed better in capturing complex feature interactions than ANN and SVM. These results demonstrate its strong applicability to forest fire prediction in Heilongjiang Province. Building on these findings, the study employed the best-performing ResDNN model in conjunction with CMIP6 multi-model climate projections to simulate and map the spatiotemporal probability of forest fire occurrence from 2030 to 2070. The results provide an intuitive representation of long-term fire-risk trajectories under future climate scenarios and offer scientific support for regional fire prevention, monitoring, early-warning systems, and forest management under climate change. Full article

Deep learning (DL) techniques have significantly advanced wind power forecasting by enhancing accuracy. However, these DL models are vulnerable to adversarial attacks, which can lead to severely inaccurate forecasts. Existing studies in wind power forecasting have rarely addressed the stealthiness and effectiveness of adversarial attacks simultaneously, nor have they investigated defense strategies against multiple perturbation strengths or in black-box scenarios. To this end, we propose an attack algorithm for wind power forecasting, i.e., the momentum iterative fast gradient sign method (MI-FGSM). This algorithm generates adversarial samples by incorporating momentum into the iterative process and adding perturbations to the input samples along the gradient direction. To defend against such attacks under varying perturbation strengths, a defense model called multi-level iterative denoising autoencoder (MLI-DAE) is proposed. MLI-DAE is trained using adversarial samples with multiple perturbation levels to effectively restore attacked inputs to their clean forms. Experimental results under both white-box and black-box scenarios demonstrate that MI-FGSM induces significantly larger forecast errors with smaller perturbation magnitudes compared to FGSM. Furthermore, our proposed MLI-DAE effectively defends against multi-level perturbations without compromising the original forecast accuracy. Full article

Under high renewable energy penetration, wind power forecasting faces pronounced challenges due to strong randomness and uncertainty, making conventional point-forecast-centric paradigms insufficient for risk-aware and reliable power system scheduling. An uncertainty-aware temporal transformer framework for wind power forecasting is presented, integrating probabilistic modeling with deep temporal representation learning to jointly optimize prediction accuracy and uncertainty characterization. Crucially, rather than treating uncertainty quantification merely as a post-processing step, the central conceptual contribution lies in modularizing uncertainty directly within the attention mechanism. A probability-driven temporal attention mechanism is incorporated at the encoding stage to emphasize high-variability and high-risk time slices during feature aggregation, while a multi-quantile output and interval modeling strategy is adopted at the prediction stage to directly learn the conditional distribution of wind power, enabling simultaneous point and interval forecasts with statistical confidence. Extensive experiments on multiple public wind power datasets demonstrate that the proposed method consistently outperforms traditional statistical models, deep temporal models, and deterministic transformers, as validated by formal statistical significance testing. Specifically, the method achieves an MAE of $0.089$, an RMSE of $0.132$, and a MAPE of $10.84\%$ on the test set, corresponding to reductions of approximately $8\%$–$10\%$ relative to the deterministic transformer. In uncertainty evaluation, a PICP of $0.91$ is attained while compressing the MPIW to $0.221$ and reducing the CWC to $0.241$, indicating a favorable balance between coverage reliability and interval compactness. Compared with mainstream probabilistic forecasting methods, the model further reduces RMSE while maintaining coverage levels close to the 90% target, effectively mitigating excessive interval conservatism. Moreover, by adaptively generating heteroscedastic intervals that widen during high-volatility events and narrow under stable conditions, the model achieves a highly focused and effective capture of critical uncertainty information. Full article

This study develops a multiregional forecasting framework for road traffic accidents in Ecuador, addressing a critical limitation in existing predictive approaches that rely predominantly on point error metrics without validating the statistical assumptions underlying forecast uncertainty. Although the analysis is conducted at the provincial level, the spatial dimension is used primarily for cross-regional comparison and risk classification rather than for explicit spatial interaction modeling. Using a dataset of 27,648 monthly observations covering all 24 provinces from 2014 to 2025, the study applies the Prophet model within a Design Science Research paradigm and a CRISP-DM implementation cycle. Separate provincial models are estimated with a 24-month forecasting horizon, and methodological rigor is ensured through systematic residual diagnostics using the Shapiro–Wilk test for normality and the Ljung–Box test for temporal independence. Empirical results indicate that the Prophet-based artifact outperforms a naïve seasonal benchmark in 70.8% of the provinces, demonstrating excellent predictive accuracy in structurally stable regions such as Tungurahua (MAPE = 10.9%). At the same time, the framework enables the identification of critical emerging risks in provinces such as Santo Domingo and Cotopaxi, where projected increases exceed 49% despite acceptable point forecasts. The findings confirm that point accuracy alone does not guarantee the validity of confidence intervals and that residual validation is essential for trustworthy uncertainty quantification. Overall, the proposed approach provides a robust foundation for a predictive surveillance system capable of supporting differentiated, evidence-based road safety policies in territorially heterogeneous contexts. Full article

Artificial intelligence (AI) is increasingly reshaping esthetic and reconstructive plastic surgery by improving measurement accuracy, treatment planning, and prediction of surgical outcomes. This article provides a scientific overview of current AI applications, including automated image analysis, machine-learning-based outcome forecasting, and generative models for preoperative simulation. AI-driven three-dimensional morphometrics allow precise, reproducible quantification of facial and body structures, supporting more objective assessments of symmetry, proportion, and contour. Predictive algorithms trained on large clinical datasets can estimate postoperative results and complication risks with higher consistency than traditional subjective evaluation. Intraoperative AI tools, such as real-time image guidance and robotic assistance, show potential to increase procedural precision and reduce variability. Despite these advances, important limitations persist. Algorithmic bias, restricted data diversity, opaque model architectures, and unresolved ethical concerns regarding data privacy and esthetic standardization challenge widespread clinical adoption. Overall, AI offers a powerful framework for enhancing precision and reproducibility in esthetic surgery, but its safe and responsible integration will require rigorous validation, transparent methodology, and continued human oversight. Full article

The nonlinearity and the extreme variability of seismic signals makes the detection of earthquakes difficult. Although the conventional deep-learning models can be used to extract useful features, they cannot be used in early-warning systems due to their non-interpretability. In this study, a Bidirectional Long Short-Memory network with an attention system (Bi-LSTM-Attn) is proposed to detect seismic events using the ConvNetQuake dataset. To improve the quality of data, the entire preprocessing pipeline, such as signal filtering, segmentation, normalization, and noise reduction is employed. The model was optimized using hyperparameter tuning of sequence length, learning rates, and attention weighting to achieve the best number of true-positive detections and a minimum number of false alarms. The accuracy, precision and recall, F1-score, MSE, and ROC curves were used to assess the performance and the attention weight visualization allowed interpreting the model. It is proven through experiments that the Bi-LSTM-Attn model provides more credible and comprehensible forecasting in relation to baseline LSTM and GRU models. Making the high-accuracy classification and the transparent decision behavior, the approach will increase the level of trust to the automated seismic surveillance, as well as help to build the reliable global networks of earthquake early-warnings. Full article