Search Results (8,764)

This study forecasts inbound tourism demand for the United Kingdom, using monthly data from February 1989 to February 2020. In the empirical analysis, we evaluate and compare the performance of five machine learning models (decision trees, random forests, XGBoost, and support vector regression with the RBF and linear kernels) against a more traditional linear SARIMA regression model. Forecasting performance metrics included MSE, RMSE, MAE, R², and MAPE. The SVR RBF kernel model achieves the highest accuracy, with an MAPE of 0.014% on the training set. To enhance model interpretability, feature importance analysis is applied to identify the most influential predictors of tourist arrivals. This research offers significant policy implications, aiding government policymakers and private industry stakeholders in optimizing their planning and decisions, deploying better long-term business strategies and tourism-related services, and optimizing the allocation of public and private resources to support the tourism sector. Full article

Accurate prediction of syngas composition is essential for process design, optimization, and scale-up, yet it remains challenging due to interactions among operating conditions, biomass properties, and chemical reactions. This study used a database of 450 experimental observations spanning a wide range of biomass feedstocks and operating conditions to compare the predictive performance of Aspen Plus simulations and Machine Learning models in estimating the concentrations of CO, CO₂, H₂, and CH₄ in syngas. Aspen Plus was used to simulate the 4 stages of the biomass gasification process under different operating conditions, with special focus on the three reactor modules (RPlug, RGibbs, and REquil) modeling the last two stages. In parallel, Machine Learning models using four regression algorithms (XGBoost, Support Vector Machines, Random Forest and Artificial Neural Networks), with different preprocessing and data-splitting strategies, were evaluated for predicting syngas composition. The best Machine Learning models achieved R² values of 0.753 (CO), 0.866 (CO₂), 0.879 (H₂) and 0.734 (CH₄) on the test set. These results outperformed the Aspen Plus approach and highlight the potential of Machine Learning models as complementary or alternative tools for modelling biomass gasification. Shapley Additive Explanation analysis identified the most influential input variables, revealing key roles for the steam-to-biomass ratio and the equivalence ratio in predicting syngas composition. This study demonstrates that existing Aspen Plus simulation models require further development to improve performance metrics across a wide range of biomass feedstocks and operating conditions. Full article

This research paper demonstrates how to manage Caputo fractional neutral integro-differential equations which include both integral and nonlinear elements through a unified framework that models dynamic systems with memory-based dynamics. The research establishes sufficient conditions for controllability through fixed point theory in a Banach space framework which requires particular assumptions while the study focuses on the ${\mathfrak{K}}_1<1$ condition which leads to the existence of a controllable solution. The proposed criteria are demonstrated through a numerical example which tests the theoretical results. The real-world case study uses artificial neural network (ANN) technology to predict Litecoin prices through the application of the fractional controllability model which analyzes historical financial data. The hybrid framework enables precise forecasting of nonlinear time series because it combines fractional calculus mathematical principles with ANN learning abilities. The proposed method demonstrates its predictive efficiency. The method shows robust performance through experimental results using cross-validation and performance metrics. The proposed model demonstrates competitive performance while providing additional advantages such as incorporation of memory effects and theoretical controllability. The research establishes a novel connection between fractional dynamical systems and machine learning which serves as an essential tool for studying complicated systems in theoretical research and practical applications. Full article

Accurate wind speed forecasting is critical for reliable wind-power integration, yet it remains challenging due to the strongly non-stationary and inherently multi-scale nature of atmospheric processes. While deep learning models—such as LSTM, GRU, and Transformer architectures—achieve competitive short- and medium-term performance, they frequently suffer from spectral bias, hyperparameter sensitivity, and reduced generalization under heterogeneous operating regimes. To address these limitations, we propose a multi-scale spectral–recurrent framework, termed RFF-RNN, which integrates multi-band Random Fourier Feature (RFF) encodings with parameterizable recurrent backbones. A key innovation of our approach is the deliberate relaxation of strict shift-invariance constraints; by jointly optimizing spectral frequencies, phase biases, and bandwidth scales alongside the neural weights, the framework dynamically shapes a fully data-driven spectral embedding. To ensure robust adaptation, we employ a two-stage optimization strategy combining gradient-based inner-loop learning with outer-loop Bayesian hyperparameter tuning. Our extensive evaluations on a controlled synthetic benchmark and six geographically diverse real-world wind datasets (spanning the USA, China, and the Netherlands) demonstrate the superiority of the proposed framework. Statistical validation via the Friedman test confirms that RFF-enhanced models—particularly RFF-GRU and RFF-LSTM—systematically outperform standard recurrent networks and state-of-the-art Transformer architectures (Autoformer and FEDformer). The proposed approach yields significantly lower error metrics (MAE and RMSE) and higher explained variance ($R^2$), while exhibiting remarkable resilience against error accumulation at extended forecasting horizons. Full article

Soiling in photovoltaic systems is a recurring problem that reduces energy generation and demands efficient operation and maintenance (O&M) strategies. In this context, this paper proposes a machine learning-based approach to identify dirt levels and generate cleaning alerts using operational and weather data. Initially, the models were evaluated with a decision threshold ranging from 0.5 to 0.7, using only operational features. Subsequently, the inclusion of weather features was tested, which improved the models’ performance and enabled the selection of the best models for the exhaustive features search step. The models analyzed in this step were Extra Trees, Histogram-based Gradient Boosting, Extreme Gradient Boosting, and Random Forest. Exhaustive analysis further improved model performance, as indicated by global metrics and ROC curves. The Extra Trees model with a threshold of 0.5 showed the best performance and was selected as the final configuration, achieving an accuracy of 0.9884 and an AUC-ROC of 0.9957. Finally, the selected model was applied to determine daily soiling levels and trigger alerts based on temporal persistence, indicating its potential to support predictive O&M decisions and cleaning actions in PV systems. Full article

Hydrogen production is gaining increasing importance as a key component of the transition toward carbon-neutral energy systems. In this study, the prediction of hydrogen generation in membraneless alkaline water electrolyzers (MAWEs) is investigated using deep-learning-based time-series modeling. A single-input modeling framework is adopted, where only the system current is used as the input variable. Experimental current signals obtained from long-duration tests conducted at electrolyte concentrations between 5 and 35 g KOH (7200 s per experiment) are employed as the model inputs, while mass-based hydrogen production (in grams) is used as the output variable. Two recurrent neural network architectures, namely Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU), are implemented, and their predictive performance is comparatively evaluated using RMSE, MAE, and R² metrics. In addition to deep learning models, classical approaches including Linear Regression, ARIMA, and Naïve Forecast are also considered for comparison. The results show that both models are capable of accurately reproducing the hydrogen-production dynamics across the entire concentration range. In particular, the prediction accuracy improves notably at medium and high electrolyte concentrations, where the coefficient of determination (R²) approaches 0.98. The residual distributions remain narrow and symmetric around zero, indicating the absence of systematic estimation bias. The results also show that classical models can achieve comparable performance under stable operating conditions, while deep learning models provide advantages in capturing nonlinear and dynamic behavior. While LSTM and GRU exhibit comparable accuracy, each architecture provides complementary advantages under different operating conditions. These findings indicate that deep-learning-based time-series modeling constitutes a lightweight and reliable framework for prediction and control applications in MAWE systems. Overall, this study demonstrates the applicability of data-driven models for the dynamic characterization of membraneless water electrolysis. Full article

Brain tumor classification from magnetic resonance imaging, which is also known as MRI, plays a sensitive role in computer-assisted diagnosis systems. In recent years, deep learning models have achieved high classification accuracy. However, their sensitivity to adversarial perturbations has become an important reliability concern in medical applications. This study suggests a robust brain tumor classification framework that combines non-negative matrix factorization (NNMF or NMF), lightweight convolutional neural networks (CNNs), and diffusion-based feature purification. Initially, MRI images are preprocessed and converted into a non-negative data matrix, from which compact and interpretable NNMF feature representations are extracted. Statistical metrics, including AUC, Cohen’s d, and p-values, are used to rank and choose the most discriminative components. Then, a lightweight CNN classifier is trained directly on the selected feature groups. To improve adversarial robustness, a diffusion-based feature-space purification module is introduced. A forward noise method followed by a learned denoiser network is used before classification. System performance is estimated using both clean accuracy and robust accuracy under powerful adversarial attacks created by AutoAttack. The experimental results show that the proposed framework achieves competitive classification performance while significantly enhancing robustness against adversarial perturbations. The findings presuppose that combining interpretable NNMF-based representations with a lightweight deep approach and diffusion-based defense technique supplies an effective and reliable solution for medical image classification under adversarial conditions. Full article

Ground reaction forces (GRFs) are essential for assessing running biomechanics, and the combination of wearable sensors and machine learning offers an accessible alternative for estimating GRFs outside controlled environments. This scoping review summarized current methods used to predict GRFs during running. A structured search (2019–2025) identified 36 studies, from which 37% did not report participant’s training status, and 59% of all participants were males. Treadmill running was assessed in 58% of studies, which included larger samples (median N = 28) and more steps/participant (median = 65) than overground studies (median N = 14; median = 32). Deep learning models, particularly LSTM and Bi-LSTM networks, were the most applied techniques, though presenting similar accuracies compared to classical regression methods. Vertical GRF predictions were the most accurate, while mediolateral GRF predictions remain challenging. GRF-derived variables such as peak forces, impact peaks, and impulses were predicted more accurately than region-dependent metrics like loading rates. Notably, no study validated treadmill-trained models on overground running, limiting real-world generalizability. Future work should prioritize larger, sex-balanced cohorts, improving prediction of mediolateral GRFs and loading rates, and explore validating treadmill-based models in overground conditions. In conclusion, although machine learning shows promise for GRF predictions, key methodological gaps must be addressed to enable robust, real-world applications. Full article

Background: This study investigates the impact of anatomically constrained preprocessing and deep learning architecture selection on benign versus malignant breast lesion classification in contrast-enhanced mammography (CEM), with the goal of improving robustness and clinical reliability across heterogeneous data sources. Methods: In this retrospective multicenter study, CEM images from 300 patients (314 lesions) were combined with 1003 publicly available CEM images, yielding a total of 1120 breast cases. Automatic breast segmentation was performed using the LIBRA framework to generate breast-mask images. Eleven deep learning models, including classical convolutional neural networks, attention-based networks, hybrid convolutional neural networks (CNNs), Transformer architectures, and mammography-specific models, were trained and evaluated using both original DICOM images and breast-mask inputs. Performance was assessed using accuracy, balanced accuracy, sensitivity, specificity, AUROC, and AUPRC on cross-validation and independent test sets. Hyperparameter optimization was conducted for the best-performing architecture. Results: Models trained on breast-mask images consistently outperformed those trained on original DICOM images across all architectures and metrics, with AUROC improvements ranging from +0.06 to +0.21. Among all models, ResNet50 trained on breast-mask images achieved the best performance (AUROC = 0.931; AUPRC = 0.933; balanced accuracy = 0.834), further improved after optimization (balanced accuracy = 0.886; sensitivity = 0.842; specificity = 0.930). Classical CNN architectures demonstrated performance comparable to or exceeding that of more complex hybrid CNN–Transformer models when anatomically focused preprocessing and rigorous optimization were applied. Conclusions: Anatomically constrained preprocessing through breast-mask segmentation substantially enhances deep learning performance and stability in CEM-based breast lesion classification. These findings indicate that input representation quality and training optimization are critical determinants of clinically relevant performance, often outweighing architectural complexity, and may support more reliable AI-assisted decision support in CEM workflows. Full article

The running reliability of rolling bearings depends on the effective lubrication state, and poor lubrication will induce abnormal vibration. Therefore, vibration-based fault diagnosis is an important means to evaluate the health of bearings through vibration characteristics. However, the lack of fault samples in actual working conditions seriously restricts the generalization ability and accuracy of an intelligent diagnosis model. A novel few-shot diagnosis method integrating multi-layer feature fusion and adaptive similarity measurement is proposed. This method adopts a meta-learning framework to simulate sample scarcity through numerous N-way K-shot diagnostic tasks. An efficient feature extractor with a cross-task feature stitching mechanism is designed to fuse features from support and query sets. To overcome the limitation of fixed-distance metrics in existing meta-learners, a learnable similarity scheduler adaptively generates optimal pseudo-distance functions. In particular, a multi-layer feature fusion strategy is introduced to compute adaptive similarities at multiple network depths, which significantly enhances feature robustness against operational variations. Experimental results demonstrate the method achieves stable diagnostic accuracy above 90% under extremely few-shot conditions and maintains over 90% accuracy when transferring from laboratory-simulated faults to natural operational faults, validating its strong potential for practical industrial applications where annotated fault data is scarce. Full article

Objective: Existing deep learning (DL) studies on brain metastasis have largely focused on algorithm or reader performance in controlled settings, whereas its role in routine teleradiology quality support remains unestablished. We evaluated the report-level impact of DL assistance on brain metastasis interpretation in a real-world teleradiology workflow using dual-sequence MRI. Materials and Methods: In this retrospective study, 600 patients who underwent contrast-enhanced dual-sequence brain MRI during two consecutive 3-month periods before (pre-DL, n = 286) and after (post-DL, n = 314) DL integration into teleradiology workflow were analyzed. Ten board-certified teleradiologists interpreted all the cases with or without DL-generated overlays. Report-level diagnostic metrics were assessed against a consensus reference standard established by faculty neuroradiologists. Subsequently, exploratory case-level stratified sensitivity analyses were performed for metastasis-positive examinations based on lesion multiplicity and the largest lesion size. Teleradiologists’ perceptions were assessed using a post-interpretation survey. Results: Compared with the pre-DL group, the post-DL group showed higher sensitivity (77.7% vs. 90.8%, p < 0.001), specificity (82.3% vs. 90.8%, p = 0.002), accuracy (80.8% vs. 90.8%, p < 0.001), positive predictive value (68.2% vs. 85.7%, p < 0.001), and negative predictive value (88.3% vs. 94.2%, p = 0.011). False-positive and false-negative rates were lower after DL implementation (11.9% vs. 5.7%, p = 0.009; 7.3% vs. 3.5%, p = 0.045). Sensitivity gains were most pronounced for cases with single metastasis (74.6% vs. 91.2%, p = 0.007) and with the largest lesion ≤ 5 mm (74.3% vs. 92.0%, p = 0.004), whereas sensitivity was similar for multiple metastases and for cases with a largest lesion > 5 mm. Survey responses suggested favorable usability and diagnostic support. Conclusions: In this real-world teleradiology workflow, DL implementation was associated with higher report-level diagnostic metrics and fewer false interpretations. DL assistance may help support quality control for brain metastasis interpretation, particularly in more subtle and diagnostically challenging cases, although radiologist judgment remains essential for subtle or borderline lesions. Full article

Background/Objectives: Cancer remains one of the leading global health burdens, mainly because of the lack of specificity and off-target toxicity associated with conventional therapeutic approaches. To move toward more efficient anticancer drug discovery, we have developed an advanced machine-learning-based architecture that allows for predictive modeling of anticancer small molecules. Methods: A total of 3600 compounds with experimentally validated IC₅₀ values were systematically processed to derive a comprehensive suite of molecular representations comprising 2D physicochemical descriptors, structural fingerprints, and hybrid descriptor sets generated via the Mordred and PaDEL frameworks. A total of six machine learning algorithms—Random Forest (RF), Extreme Gradient Boosting (XGB), Gradient Boosting (GB), Extra-Trees classifier (ET), Adaptive Boosting (AdaBoost), and Light Gradient Boosting Machine (LightGBM)—were trained and benchmarked via a rigorous model evaluation protocol incorporating 10-fold cross-validation along with multiple performance metrics. Ensemble voting strategies were also examined to assess potential performance. Result: Of all configurations, the XGB-Hybrid architecture emerged as the most robust and generalizable classifier with an AUC of 0.88 and accuracy of 79.11% on the independent test set. To ensure interpretability and mechanistic insight, SHAP-based feature analysis was conducted, by which feature contributions could be quantified and the molecular determinants most influential for anticancer activity discrimination were revealed. Altogether, the current study establishes an XGB-Hybrid framework as technically rigorous, interpretable, and high-performance predictive modeling with the ability to accelerate early-stage anticancer small molecule identification. Conclusions: The study has brought into focus the transformational effect of machine learning in modern computational oncology and rational drug design pipelines. Full article

This study aims to predict stock market risk and improve preparedness for potential economic crises by identifying sharp declines in stock returns using classification-based machine learning models. Using ten years of KOSPI 200 index data (2015 to 2024), a daily return series was constructed. A day was labeled a risk event (1) if its return fell below the 5th percentile of the returns observed over the preceding 100 trading days, indicating a sharp decline. Nine classification models—Logistic Regression, k-nearest Neighbor, Decision Tree, Random Forest, Linear Discriminant Analysis, Naive Bayes, Quadratic Discriminant Analysis, AdaBoost, and Gradient Boosting—were trained and validated. Among these, Logistic Regression demonstrated the strongest overall performance across multiple evaluation metrics, including accuracy, non-risk F1 score, risk F1 score, and AUC. Full article

In insurance portfolios, classifying customers without a prior history at a given company is particularly challenging due to the absence of historical behavior, extreme class imbalance, heavy-tailed loss distributions, and strict operational constraints. Traditional machine learning approaches, including the baseline methodology proposed in previous studies, typically optimize global predictive accuracy and therefore fail to capture business-critical outcomes, especially the identification of high-risk clients. This study extends the existing approach by evaluating two complementary business-aware classification strategies: (i) a balanced bagging ensemble specifically designed to handle class imbalance and maximize expected profit under explicit customer-omission constraints, and (ii) a lightweight Transformer-based architecture capable of learning richer feature representations. Both approaches incorporate the asymmetric financial cost structure of insurance and operate under operational selection limits. The empirical analysis is conducted on a proprietary large-scale auto insurance dataset comprising 51,618 customers and is complemented by validation on nine synthetic datasets to assess robustness. Model performance is evaluated using statistical tests (ANOVA, Friedman, and pair-wise comparisons) together with business-oriented metrics. The results show that both proposed approaches consistently outperform the baseline methodology (p < 0.001) in terms of profit, with the ensemble offering a better balance of performance and efficiency, while the Transformer shows stronger robustness and generalization under data perturbations. The balanced ensemble provides the most favourable trade-off between predictive performance, robustness, interpretability, and computational efficiency, making it suitable for deployment in regulated insurance environments, while the Transformer achieves competitive results and exhibits stronger generalization under data perturbations. The proposed approach aligns machine learning with actuarial portfolio optimization by explicitly integrating profit-driven objectives and operational constraints, offering two practical and scalable solutions for risk-based decision-making in real-world insurance settings. Full article

Background/Objectives: Electroanatomic mapping (EAM) provides high-resolution spatial and electrogram information, but the prognostic utility of quantitative EAM features has not been systematically evaluated with contemporary artificial intelligence (AI) methods. We investigated whether an AI analysis of quantitative EAM exports from the CARTO system enhances the prediction of major arrhythmic events (MAEs). Methods: In this retrospective, multicenter cohort study, 248 consecutive patients undergoing left ventricular EAM at four tertiary electrophysiology centers were analyzed. Numerical EAM descriptors (spatial coordinates, unipolar/bipolar voltages, local activation time, impedance) were transformed into derived metrics, including local activation heterogeneity (GR), late-potential extent (LAT), bipolar–unipolar discrepancy (VLT), and low-amplitude scar extent (Scar Areas), and were spatially normalized via spherical projection. Clinical, anamnestic, and imaging variables were integrated. Machine learning and deep learning models were trained with an 80:20 train/test split and evaluated using three-fold cross-validation. Performance metrics included area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, and precision. Results: Models incorporating both clinical and AI-processed EAM features achieved high discriminatory performance (test AUC up to 0.92; accuracy up to 0.896). Specificity was consistently high (≈0.97–0.998), whereas sensitivity remained modest (≈0.39–0.58). Among the EAM-derived features, GR was the most consistently informative predictor across algorithms and analyses; VLT, LAT, and Scar Areas also contributed substantially. Regionally, basal sub-mitral, subaortic, and posterolateral basal-to-mid zones exhibited the strongest associations with MAEs. Conclusions: AI-driven quantitative analysis of left ventricular EAM exports augments risk stratification for MAEs beyond conventional clinical and binary EAM descriptors. Reflecting local conduction heterogeneity, GR emerged as the dominant EAM predictor. Prospective validation in larger, disease-specific cohorts and real-time integration within EAM platforms are warranted. Full article