Search Results (92)

Accurate forecasting of aggregated demand response (DR) potential is critical for load aggregators, yet remains challenging under severe data scarcity and domain shift conditions. This paper proposes a domain-adaptive transfer learning framework based on an ensemble of Random Vector Functional-Link (RVFL) neural networks for DR potential prediction without requiring any labeled target-domain data. By integrating domain adaptation layers and Maximum Mean Discrepancy (MMD) regularization, the proposed method explicitly reduces marginal feature distribution discrepancies between source and target domains, enabling effective knowledge transfer across heterogeneous operating scenarios. Compared with deep learning architectures, the RVFL-based framework offers favorable theoretical and practical properties for this application, including closed-form least-squares training, reduced risk of overfitting under limited data, and stable generalization under distribution shifts due to its direct-link structure and randomized hidden representations. These characteristics lead to significantly lower computational complexity and training cost than gradient-based deep models, while maintaining strong predictive capability. Case studies using real-world residential consumption data from the Pecan Street dataset demonstrate that the proposed approach consistently outperforms benchmark methods, including SVR, RF, and LSTM, across both intra-year and cross-year transfer scenarios. Reliable prediction accuracy is achieved even when only 10% of source-domain data are available, indicating strong data efficiency and scalability for practical aggregator deployment in day-ahead DR planning. Full article

Heating, ventilation, and air conditioning (HVAC) systems account for a significant portion of building energy consumption and play a crucial role in maintaining indoor comfort. However, hidden faults in air-handling units (AHUs) often lead to energy waste and degraded performance, highlighting the importance of reliable fault detection and diagnosis (FDD). This study proposes a simulation-driven FDD framework that integrates a standardized prototype dataset and an independent evaluation dataset generated from a calibrated EnergyPlus model representing a target facility, enabling controlled experimentation and transfer evaluation within simulation environments. Training data were generated from the DOE EnergyPlus Medium Office prototype model, while evaluation data were obtained from a calibrated building-specific EnergyPlus model of a research facility operated by Company H in Korea. Three representative fault scenarios—outdoor air damper stuck closed, cooling coil fouling (65% capacity), and air filter fouling (30% pressure drop)—were systematically implemented. A Deep Belief Network (DBN) classifier was developed and optimized through a two-stage hyperparameter tuning strategy, resulting in a three-layer architecture (256–128–64 nodes) with dropout and regularization for robustness. The optimized DBN achieved diagnostic accuracies of 92.4% for the damper fault, 98.7% for coil fouling, and 95.9% for filter fouling. These results confirm the effectiveness of combining simulation-based dataset generation with advanced deep learning methods for HVAC fault diagnosis. The results indicate that a DBN trained on a standardized EnergyPlus prototype can transfer to a second, independently calibrated EnergyPlus building model when AHU topology, control logic, and monitored variables are aligned. This study should be interpreted as a simulation-based proof-of-concept, motivating future validation with field BMS data and more diverse fault scenarios. Full article

Thermal and nuclear power systems require materials capable of sustaining high mechanical and thermal loads over prolonged service durations. Among these, 9Cr heat-resistant steels are particularly attractive due to their superior mechanical strength and extended creep rupture life, making them suitable for extreme environments. In this study, multiple machine learning models were explored to predict the creep rupture life of 9Cr heat-resistant steels. A comprehensive dataset of 913 samples, compiled from experimental results and literature, included eight input variables—covering chemical composition, stress, and temperature—and one output variable, the creep rupture life. The optimized artificial neural network (ANN) model achieved the highest predictive accuracy with a regularization coefficient of 0.01, 10,000 training iterations, and five hidden layers with 30 neurons per layer, attaining an R² of 0.9718 for the test dataset. Beyond accurate prediction, single- and two-variable sensitivity analyses were used to elucidate statistically meaningful trends and interactions among the input parameters governing creep rupture life. The analyses indicated that among all variables, test conditions—particularly the test temperature—exert a pronounced negative effect on creep life, significantly reducing durability at elevated temperatures. Additionally, an optimization module enables identification of input conditions to achieve desired creep life, while the Index of Relative Importance (I_RI) and quantitative effect analysis enhance interpretability. This framework represents a robust and reliable tool for long-term creep life assessment and the design of 9Cr steels for high-temperature applications. Full article

Accurate environmental prediction is crucial for ecological monitoring and disaster early warnings, but it remains challenging due to the spatiotemporal complexity of dynamic wireless sensor networks (WSNs). To this end, we propose a novel hybrid model that integrates a convolutional neural network (CNN), bidirectional long short-term memory (BiLSTM), and a black-winged kite algorithm (BKA). The CNN first extracts spatial features from multi-node sensor data to capture local environmental patterns. Subsequently, the BKA optimizes key CNN hyperparameters (learning rate, hidden layers, and regularization coefficients) to enhance the robustness of feature representation to noise and missing data. Subsequently, the BiLSTM processes the optimization features to model bidirectional long-term time dependencies (e.g., circadian rhythms, seasonal trends) to achieve accurate environmental predictions. Evaluation of the BKA-optimized CNN-BiLSTM model shows that our framework reduces prediction error by 19.3% to 32.7% compared to other models, achieving 89.4% accuracy in predicting extreme weather events. The synergy between BKA-driven CNN optimization and BiLSTM temporal dynamics modeling significantly improves the reliability of environmental prediction in resource-constrained sensor networks. Full article

Geochemical data from mine tailings are layered, compositional, and noisy, complicating automated domaining. This study introduces a continuity-aware workflow the Geostatistical k-means Recurrent Neural Network (GkRNN) that links compositional preprocessing and geostatistical continuity to sequence learning, allowing depth order and lateral context to influence final domain labels. The workflow begins with a centered log-ratio (CLR) transform, followed by construction of a spectral embedding derived from kernelized direct and cross variograms. Clustering is carried out in this embedded space, and depth sequences are regularized with a hidden Markov model (HMM) model and a long short-term memory (LSTM) network. When applied to a multivariate set of tailing drillholes, stratigraphically coherent zones were obtained, depthwise proportions were stabilized, and vertical as well as lateral semivariograms remained consistent with laminated material. Compared with k-means and Gaussian Mixture baselines, over-segmentation was reduced and the intended layered architecture was recovered in most drillholes. The result is a reproducible domaining workflow that enables clearer grade estimation and more transparent risk evaluation. Full article

Crown width (CW) is a critical metric for characterizing tree-canopy dimensions; however, its direct measurement remains labor-intensive and is often impractical in inaccessible crowns. Consequently, CW is frequently derived from projections, which are susceptible to multiple sources of imprecision, including canopy density, crown irregularity, terrain heterogeneity, and the observer’s vantage point, especially in structurally complex natural forests. While deep neural network (DNN) models show substantial potential for CW prediction, their performance in heterogeneous forests remains uncertain. We developed DNN models integrated with a Height Threshold Method (HTM) to predict individual-tree CW in the natural mixed forests of Northern China, dominated by Larix principis-rupprechtii and Picea asperata. Our study further compared the relative importance of feature engineering versus model architectural complexity in predictive accuracy and identified the key ecological variables governing CW. The model performance was evaluated through the coefficient of determination (R²), mean square error (MSE), mean absolute error (MAE), and mean absolute percentage error (MAPE). Field surveys of 34 representative sample plots produced 1884 individual-tree records. The main results were as follows: (1) all DNNs avoided overfitting, and were statistical stable under ten-fold cross-validation; (2) the optimized DNN3-2 model (tuned hidden layer count, neurons/hidden layer, L₂ regularization, and dropout) achieved peak performance, explaining 69% of CW variance with residuals with stable variance and excellent coverage properties; (3) tree size, neighborhood competition, species identity, and site quality were the most important predictors; and (4) stand parameters calculated from competitive neighborhoods defined by the HTM, particularly mean stand crowding, Simpson’s index (1-D), and Shannon’s index (H′), significantly improved prediction accuracy. By integrating DNN with the HTM, our approach allows for accurate prediction of individual-tree CW in natural mixed forests of Northern China, dominated by Larix principis-rupprechtii and Picea asperata. Full article

Lung cancer (LC) remains a leading cause of cancer mortality worldwide, where accurate and early identification of gene mutations such as epidermal growth factor receptor (EGFR) is critical for precision treatment. However, machine learning-based radiomics approaches often face challenges due to the small and imbalanced nature of the datasets. This study proposes a comprehensive framework based on Generic Sparse Regularized Autoencoders with Kullback–Leibler divergence (GSRA-KL) to generate high-quality synthetic radiomics data and overcome these limitations. A systematic approach generated 63 synthetic radiomics datasets by tuning a novel kl_weight regularization hyperparameter across three hidden-layer sizes, optimized using Optuna for computational efficiency. A rigorous assessment was conducted to evaluate the impact of hyperparameter tuning across 63 synthetic datasets, with a focus on the EGFR gene mutation. This evaluation utilized resemblance-dimension scores (RDS), novel utility-dimension scores (UDS), and t-SNE visualizations to ensure the validation of data quality, revealing that GSRA-KL achieves excellent performance (RDS > 0.45, UDS > 0.7), especially when class distribution is balanced, while remaining competitive with the Tabular Variational Autoencoder (TVAE). Additionally, a comprehensive statistical correlation analysis demonstrated strong and significant monotonic relationships among resemblance-based performance metrics up to moderate scaling (≤1.0*), confirming the robustness and stability of inter-metric associations under varying configurations. Complementary computational cost evaluation further indicated that moderate kl_weight values yield an optimal balance between reconstruction accuracy and resource utilization, with Spearman correlations revealing improved reconstruction quality (MSE $\rho =-0.78$, $p<0.001$) at reduced computational overhead. The ablation-style analysis confirmed that including the KL divergence term meaningfully enhances the generative capacity of GSRA-KL over its baseline counterpart. Furthermore, the GSRA-KL framework achieved substantial improvements in computational efficiency compared to prior PSO-based optimization methods, resulting in reduced memory usage and training time. Overall, GSRA-KL represents an incremental yet practical advancement for augmenting small and imbalanced high-dimensional radiomics datasets, showing promise for improved mutation prediction and downstream precision oncology studies. Full article

Water inrush and mud burst disasters pose severe challenges to the safe and efficient construction of underground engineering. Water inflow prediction is closely related to drainage design, disaster prevention and control, and the safety of the surrounding ecological environment. Thus, assessing the water inflow accurately is of importance. This study proposes a Bayesian Optimization-Long Short-Term Memory (BOA-LSTM) recurrent neural network for predicting tunnel water inflow. The model is based on four input parameters, namely tunnel depth (H), groundwater level (h), rock quality designation (RQD), and water-richness (W), with water inflow (WI) as the single-output variable. The model first processes and analyzes the data, quantitatively characterizing the correlations between input parameters. The tunnel water inflow is predicted using the long short-term memory (LSTM) recurrent neural network, and the Bayesian optimization algorithm (BOA) is employed to select the hyperparameters of the LSTM, primarily including the number of hidden layer units, initial learning rate, and L2 regularization coefficient. The modeling process incorporates a five-fold cross-validation strategy for dataset partitioning, which effectively mitigates overfitting risks and enhances the model’s generalization capability. After a comprehensive comparison among a series of machine learning models, including a long short-term memory recurrent neural network (LSTM), random forest (RF), back propagation neural network (BP), extreme learning machine (ELM), radial basis function neural network (RBFNN), least squares support vector machine (LIBSVM), and convolutional neural network (CNN), BOA-LSTM performed excellently. The proposed BOA-LSTM model substantially surpasses the standard LSTM and other comparative models in tunnel water inflow prediction, demonstrating superior performance in both accuracy and generalization. Hence, it provides a reference basis for tunnel engineering water inflow prediction. Full article

Elucidating drug response mechanisms in human melanoma is crucial for improving treatment outcomes. Moreover, the existing tools intended to provide deeper insight into melanoma drug resistance have notable limitations. Therefore, we propose a deep learning (DL)-based approach that works as follows. First, we processed two single-cell datasets related to human melanoma from the GEO (GSE108383_A375 and GSE108383_451Lu) database and trained a fully connected neural network with five adapted methods (L1-Regularization, DeepLIFT, SHAP, IG, and LRP). We then identified 100 genes by ranking all genes from the highest to the lowest based on the sum of absolute values for corresponding weights across all neurons in the first hidden layer. From a biological perspective, compared to existing bioinformatics tools, the presented DL-based methods identified a higher number of expressed genes in four well-established melanoma cell lines: MALME-3M, MDA-MB435, SK-MEL-28, and SK-MEL-5. Furthermore, we identified FDA-approved melanoma drugs (e.g., Vemurafenib and Dabrafenib), critical genes such as ARAF, SOX10, DCT, and AXL, and key TFs including MITF and TFAP2A. From a classification perspective, we utilized five-fold cross-validation and provided gene sets using all the abovementioned methods to three randomly selected machine learning algorithms, namely, support vector machines, random forests, and neural networks with different hyperparameters. The results demonstrate that the integrated gradients (IG) method adapted in our DL approach contributed to 2.2% and 0.5% overall performance improvements over the best-performing baselines when using A375 and 451Lu cell line datasets. Additional comparison against no gene selection demonstrated that IG is the only method to generate statistically significant results, with 14.4% and 11.7% overall performance improvements. Full article

High-performance deep learning models require extensive computational resources and datasets, making their ownership protection a pressing concern. To address this challenge, we focus on advancing model security through robust watermarking mechanisms. In this work, we propose a novel deep neural network watermarking method that embeds ownership information directly within the image feature space. Unlike existing approaches that often suffer from low embedding success rates and significant performance degradation, our method leverages convolutional kernels with orthogonal preferences to extract multiperspective features, which are then linearly mapped at the output layer for watermark embedding. Furthermore, we introduce an orthogonal regularization constraint into the loss function to increase the watermark robustness. This constraint enforces orthogonality in both convolutional and fully connected layer weights, suppresses redundancy in hidden layer representations, and minimizes interference between the watermark and the model’s original feature space. Through these innovations, we significantly improve the embedding reliability and preserve model integrity. Experimental results obtained on ResNet-18 and ResNet-101 demonstrate a 100% watermark detection rate with less than 1% performance impact, underscoring the practical security value of our approach. Comparative analysis further validates that our method achieves superior harmlessness and effectiveness relative to state-of-the-art techniques. These contributions highlight the role of our work in strengthening intellectual property protection and the trustworthy deployment of deep learning models. Full article

This paper proposes a new accelerated fixed-point algorithm based on a double-inertial extrapolation technique for solving structured variational inclusion and convex bilevel optimization problems. The underlying framework leverages fixed-point theory and operator splitting methods to address inclusion problems of the form $0\in (A+B)(x)$, where A is a cocoercive operator and B is a maximally monotone operator defined on a real Hilbert space. The algorithm incorporates two inertial terms and a relaxation step via a contractive mapping, resulting in improved convergence properties and numerical stability. Under mild conditions of step sizes and inertial parameters, we establish strong convergence of the proposed algorithm to a point in the solution set that satisfies a variational inequality with respect to a contractive mapping. Beyond theoretical development, we demonstrate the practical effectiveness of the proposed algorithm by applying it to data classification tasks using Deep Extreme Learning Machines (DELMs). In particular, the training processes of Two-Hidden-Layer ELM (TELM) models is reformulated as convex regularized optimization problems, enabling robust learning without requiring direct matrix inversions. Experimental results on benchmark and real-world medical datasets, including breast cancer and hypertension prediction, confirm the superior performance of our approach in terms of evaluation metrics and convergence. This work unifies and extends existing inertial-type forward–backward schemes, offering a versatile and theoretically grounded optimization tool for both fundamental research and practical applications in machine learning and data science. Full article

This paper introduces a novel adversarial learning framework for reconstructing hidden layers in historical palimpsests. Recovering text hidden in historical palimpsests is complicated by various artifacts, such as ink diffusion, degradation of the writing substrate, and interference between overlapping layers. To address these challenges, the authors of this paper combine a synthetic data generator grounded in physical modeling with three generative architectures: a baseline VAE, an improved variant with stronger regularization, and a U-Net-based GAN that incorporates residual pathways and a mixed loss strategy. The synthetic data engine aims to emulate key degradation effects—such as ink bleeding, the irregularity of parchment fibers, and multispectral layer interactions—using stochastic approximations of underlying physical processes. The quantitative results suggest that the U-Net-based GAN architecture outperforms the VAE-based models by a notable margin, particularly in scenarios with heavy degradation or overlapping ink layers. By relying on synthetic training data, the proposed method facilitates the non-invasive recovery of lost text in culturally important documents, and does so without requiring costly or specialized imaging setups. Full article

Offshore cranes equipped with active motion compensation (AMC) systems play a vital role in marine engineering tasks such as offshore wind turbine maintenance, subsea operations, and dynamic load positioning under wave-induced disturbances. These systems rely on complex hydraulic actuators whose strongly nonlinear dynamics—often described by differential-algebraic equations (DAEs)—impose significant computational burdens, particularly in real-time applications like hardware-in-the-loop (HIL) simulation, digital twins, and model predictive control. To address this bottleneck, we propose a neural network-based surrogate model that approximates the actuator dynamics with high accuracy and low computational cost. By approximately reducing the original DAE model, we obtain a lower-dimensional ordinary differential equations (ODEs) representation, which serves as the foundation for training. The surrogate model includes three hidden layers, demonstrating strong fitting capabilities for the highly nonlinear characteristics of hydraulic systems. Bayesian regularization is adopted to train the surrogate model, effectively preventing overfitting. Simulation experiments verify that the surrogate model reduces the solving time by 95.33%, and the absolute pressure errors for chambers $p_1$ and $p_2$ are controlled within 0.1001 MPa and 0.0093 MPa, respectively. This efficient and scalable surrogate modeling framework possesses significant potential for integrating high-fidelity hydraulic actuator models into real-time digital and control systems for offshore applications. Full article

Ignition delay time (IDT) is a critical parameter for evaluating the autoignition characteristics of aviation fuels. However, its accurate prediction remains challenging due to the complex coupling of temperature, pressure, and compositional factors, resulting in a high-dimensional and nonlinear problem. To address this challenge for the complex aviation kerosene RP-3, this study proposes a multi-stage hybrid optimization framework based on a five-input, one-output BP neural network. The framework—referred to as CGD-ABC-BP—integrates randomized initialization, conjugate gradient descent (CGD), the artificial bee colony (ABC) algorithm, and L2 regularization to enhance convergence stability and model robustness. The dataset includes 700 experimental and simulated samples, covering a wide range of thermodynamic conditions: 624–1700 K, 0.5–20 bar, and equivalence ratios φ = 0.5 − 2.0. To improve training efficiency, the temperature feature was linearized using a 1000/T transformation. Based on 30 independent resampling trials, the CGD-ABC-BP model with a three-hidden-layer structure of [21 17 19] achieved strong performance on internal test data: R² = 0.994 ± 0.001, MAE = 0.04 ± 0.015, MAPE = 1.4 ± 0.05%, and RMSE = 0.07 ± 0.01. These results consistently outperformed the baseline model that lacked ABC optimization. On an entirely independent external test set comprising 70 low-pressure shock tube samples, the model still exhibited strong generalization capability, achieving R² = 0.976 and MAPE = 2.18%, thereby confirming its robustness across datasets with different sources. Furthermore, permutation importance and local gradient sensitivity analysis reveal that the model can reliably identify and rank key controlling factors—such as temperature, diluent fraction, and oxidizer mole fraction—across low-temperature, NTC, and high-temperature regimes. The observed trends align well with established findings in the chemical kinetics literature. In conclusion, the proposed CGD-ABC-BP framework offers a highly accurate and interpretable data-driven approach for modeling IDT in complex aviation fuels, and it shows promising potential for practical engineering deployment. Full article

Efficient utilization of wind energy resources, including advances in weather and seasonal forecasting and climate projections, is imperative for the sustainable progress of wind power generation. Although temperature and precipitation data receive considerable attention in interannual variability and seasonal forecasting studies, there is a notable gap in exploring correlations between climate indices and wind speeds. This paper proposes the use of an ensemble of artificial neural networks to forecast wind speeds based on climate oscillation indices and assesses its performance. An initial examination indicates a correlation signal between the climate indices and wind speeds of ERA5 for the selected case study in eastern Canada. Forecasts are made for the season April–May–June (AMJ) and are based on most correlated climate indices of preceding seasons. A pointwise forecast is conducted with a 20-member ensemble, which is verified by leave-on-out cross-validation. The results obtained are analyzed in terms of root mean squared error, bias, and skill score, and they show competitive performance with state-of-the-art numerical wind predictions from SEAS5, outperforming them in several regions. A relatively simple model with a single unit in the hidden layer and a regularization rate of ${10}^{-2}$ provides promising results, especially in areas with a higher number of indices considered. This study adds to global efforts to enable more accurate forecasting by introducing a novel approach. Full article