Search Results (9,290)

As digital transformation accelerates across Europe, cloud computing plays an increasingly central role in modernizing public services and private enterprises. Yet adoption rates vary markedly among EU member states, reflecting deeper structural differences in digital capacity. This study employs explainable machine learning to uncover the drivers of national cloud adoption across 27 EU countries using harmonized panel datasets spanning 2014–2021 and 2014–2024. A methodological pipeline combining Random Forests (RF), XGBoost, Support Vector Machines (SVM), and Elastic Net regression is implemented, with model tuning conducted via nested cross-validation. Among individual models, Elastic Net and SVM delivered superior predictive performance, while a stacked ensemble achieved the best overall accuracy (MAE = 0.214, R² = 0.948). The most interpretable model, a standardized RF with country fixed effects, attained MAE = 0.321, and R² = 0.864, making it well-suited for policy analysis. Variable importance analysis reveals that the density of ICT specialists is the strongest predictor of adoption, followed by broadband access and higher education. Fixed-effect modeling confirms significant national heterogeneity, with countries like Finland and Luxembourg consistently leading adoption, while Bulgaria and Romania exhibit structural barriers. Partial dependence and SHAP analyses reveal nonlinear complementarities between digital skills and infrastructure. A hierarchical clustering of countries reveals three distinct digital maturity profiles, offering tailored policy pathways. These results directly support the EU Digital Decade’s strategic targets and provide actionable insights for advancing inclusive and resilient digital transformation across the Union. Full article

House price prediction is crucial in real estate for informed decision-making. This paper presents an automated prediction system that combines genetic algorithms (GA) for feature optimization and Analysis of Variance (ANOVA) for statistical analysis. We apply and compare five ensemble machine learning (ML) models, namely Extreme Gradient Boosting Regression (XGBR), random forest regression (RFR), Categorical Boosting Regression (CBR), Adaptive Boosting Regression (ADBR), and Gradient Boosted Decision Trees Regression (GBDTR), on a comprehensive dataset. We used a dataset with 1000 samples with eight features and a secondary dataset for external validation with 3865 samples. Our integrated approach identifies Categorical Boosting with GA (CBRGA) as the best performer, achieving an R² of 0.9973 and outperforming existing state-of-the-art methods. ANOVA-based analysis further enhances model interpretability and performance by isolating key factors such as square footage and lot size. To ensure robustness and transparency, we conduct 10-fold cross-validation and employ explainable AI techniques such as Shapley Additive Explanations (SHAP) and Local Interpretable Model-Agnostic Explanations (LIME), providing insights into model decision-making and feature importance. Full article

Abies nephrolepis and Picea jezoensis are native Pinaceae trees distributed in high mountainous regions of Northeast Asia (typically above ~1000 m a.s.l. on the Korean peninsula, northeastern China, Sakhalin, and the Russian Far East) and southern boreal forests, vulnerable to climate change and human disturbances, necessitating accurate habitat identification for effective conservation. While protected areas (PAs) are essential, merely expanding existing ones often fail to protect populations under human pressure and climate change. Using species distribution models with current and projected climate data, we mapped potential habitats across Northeast Asia. Spatial clustering analyses integrated with PA and land cover data helped identify optimal sites and priorities for new conservation areas. Ensemble species distribution models indicated extensive suitable habitats, especially in southern Sikhote-Alin, influenced by maritime-continental climates. Specific climate variables strongly affected habitat suitability for both species. The Kamchatka peninsula consistently emerged as an optimal habitat under future climate scenarios. Our study highlights essential environmental characteristics shaping the habitats of these species, reinforcing the importance of strategically enhancing existing PAs, and establishing new ones. These insights inform proactive conservation strategies for current and future challenges, by focusing on climate refugia and future habitat stability. Full article

This study investigates the impact of data distribution and bootstrap resampling on the anomaly detection performance of the Isolation Forest (iForest) algorithm in statistical process control. Although iForest has received attention for its multivariate and ensemble-based nature, its performance under non-normal data distributions and varying bootstrap settings remains underexplored. To address this gap, a comprehensive simulation was performed across 18 scenarios involving log-normal, gamma, and t-distributions with different mean shift levels and bootstrap configurations. The results show that iForest substantially outperforms the conventional Hotelling’s T² control chart, especially in non-Gaussian settings and under small-to-medium process shifts. Enabling bootstrap resampling led to marginal improvements across classification metrics, including accuracy, precision, recall, F1-score, and average run length (ARL)₁. However, a key limitation of iForest was its reduced sensitivity to subtle process changes, such as a 1σ mean shift, highlighting an area for future enhancement. Full article

Concrete in cold areas is often subjected to a freeze–thaw cycle period, and a harsh environment will seriously damage the structure of concrete and shorten its life. The frost resistance of concrete is primarily evaluated by relative dynamic elastic modulus and mass loss rate. To predict the frost resistance of concrete more accurately, based on the four ensemble learning models of random forest (RF), adaptive boosting (AdaBoost), categorical boosting (CatBoost), and extreme gradient boosting (XGBoost), this paper optimises the ensemble learning models by using a dynamic multi-stage optimisation algorithm (DMSOA). These models are trained using 7090 datasets, which use nine features as input variables; relative dynamic elastic modulus (RDEM) and mass loss rate (MLR) as prediction indices; and six indices of the coefficient of determination (R²), mean square error (MSE), root mean square error (RMSE), mean absolute error (MAE), correlation coefficient (CC), and standard deviation ratio (SDR) are selected to evaluate the models. The results show that the DMSOA-CatBoost model exhibits the best prediction performance. The R² of RDEM and MLR are 0.864 and 0.885, respectively, which are 6.40% and 11.15% higher than those of the original CatBoost model. Moreover, the model performs better in error control, with significantly lower MSE, RMSE, and MAE and stronger generalization ability. Additionally, compared with the two mainstream optimisation algorithms (SCA and AOA), DMSOA-CatBoost also has obvious advantages in prediction accuracy and stability. Related work in this paper has a certain significance for improving the durability and quality of concrete, which is conducive to predicting the performance of concrete in cold conditions faster and more accurately to optimise the concrete mix ratio whilst saving on engineering cost. Full article

Precisely predicting photovoltaic (PV) output is crucial for reliable grid integration; so far, most models rely on site-specific sensor data or treat large meteorological datasets as black boxes. This study proposes an explainable machine-learning framework that simultaneously ranks the most informative weather parameters and reveals their physical relevance to PV generation. Starting from 27 local and plant-level variables recorded at 15 min resolution for a 1 MW array in Çanakkale region, Türkiye (1 August 2022–3 August 2024), we apply a three-stage feature-selection pipeline: (i) variance filtering, (ii) hierarchical correlation clustering with Ward linkage, and (iii) a meta-heuristic optimizer that maximizes a neural-network R² while penalizing poor or redundant inputs. The resulting subset, dominated by apparent temperature and diffuse, direct, global-tilted, and terrestrial irradiance, reduces dimensionality without significantly degrading accuracy. Feature importance is then quantified through two complementary aspects: (a) tree-based permutation scores extracted from a set of ensemble models and (b) information gain computed over random feature combinations. Both views converge on shortwave, direct, and global-tilted irradiance as the primary drivers of active power. Using only the selected features, the best model attains an average R² ≅ 0.91 on unseen data. By utilizing transparent feature-reduction techniques and explainable importance metrics, the proposed approach delivers compact, more generalized, and reliable PV forecasts that generalize to sites lacking embedded sensor networks, and it provides actionable insights for plant siting, sensor prioritization, and grid-operation strategies. Full article

The analysis of anomalous diffusion characteristics within single-particle tracking data is a key problem in several applied-science domains, including biosignal processing, bioinformatics, and biotechnology. This task becomes particularly challenging in the presence of short trajectories, localization errors, and non-ergodicity, features that are common in real experimental data. To address these limitations, this work proposes an approach that improves the robustness and accuracy of estimating the anomalous diffusion exponent α, even for very short trajectories of up to 10 points. The approach includes an ensemble-based variance estimation of the exponent α, along with a bias correction based on time–ensemble averaged mean squared displacement, which reduces the systematic bias. These components integrate well into neural network architectures and are suitable for analyzing experimental trajectories in biotechnology and bioprocess engineering applications. Full article

This article focuses on the story of a pirogue shipwreck that occurred in early September 2024, less than two miles from the coast of Mbour, about 200 km south of Dakar. It traces an ethnographic account of that tragic event through the lenses of different voices, standpoints, and testimonies from the survivors, the relatives and friends of the victims, and those involved in the organization of both the aborted ocean crossing and the rescue operations in various ways. By situating this extreme story of “potential migrants” among other accounts of migrants who disappeared at sea and of missing pirogues, the focus shifts to the different weights and possibilities of movement when dealing with disappearance and death, the unknown and known facts, addressing that which remains unknown even within this unambiguous and tragic event. Faced with the dense plot of ties at the core of that failed escape, we suggest that the reasons for the shipwreck are excess demand and solidarity, in terms of the impossibility of denying passage onboard the boat to friends, relatives, and neighbors. “On est ensemble” is therefore a way to recognize that there is no clear distinction or distance between captain and passengers, survivors and the dead, or victims and spectators, since in Mbour, everyone perfectly understands both the reasons and the risks, and the reason for the risks, of any illegal attempt to cross sea and land borders towards Europe. Full article

Part I of this two-part documentation of the ECMWF ensemble (ECEPS) new tropical cyclone track and intensity forecasting challenges during the 2024 western North Pacific season described four typhoons that started well to the south of an unfavorable external environment north of 20° N. In this Part II, five other 2024 season typhoons that formed and intensified near and north of 20° N are documented. One change is that the Cooperative Institute for Meteorological Satellite Studies ADT + AIDT intensities derived from the Himawari-9 satellite were utilized for initialization and validation of the ECEPS intensity forecasts. Our first objective of providing earlier track and intensity forecast guidance than the Joint Typhoon Warning Center (JTWC) five-day forecasts was achieved for all five typhoons, although the track forecast spread was large for the early forecasts. For Marie (06 W) and Ampil (08 W) that formed near 25° N, 140° E in the middle of the unfavorable external environment, the ECEPS intensity forecasts accurately predicted the ADT + AIDT intensities with the exception that the rapid intensification of Ampil over the Kuroshio ocean current was underpredicted. Shanshan (11 W) was a challenging forecast as it intensified to a typhoon while being quasi-stationary near 17° N, 142° E before turning to the north to cross 20° N into the unfavorable external environment. While the ECEPS provided accurate guidance as to the timing and the longitude of the 20° N crossing, the later recurvature near Japan timing was a day early and 4 degrees longitude to the east. The ECEPS provided early, accurate track forecasts of Jebi’s (19 W) threat to mainland Japan. However, the ECEPS was predicting extratropical transition with V_max ~35 kt when the JTWC was interpreting Jebi’s remnants as a tropical cyclone. The ECEPS predicted well the unusual southward track of Krathon (20 W) out of the unfavorable environment to intensify while quasi-stationary near 18.5° N, 125.6° E. However, the rapid intensification as Krathon moved westward along 20° N was underpredicted. Full article

Artificial Intelligence (AI) and computer-aided diagnosis (CAD) have revolutionised various aspects of modern life, particularly in the medical domain. These technologies enable efficient solutions for complex challenges, such as accurately segmenting brain tumour regions, which significantly aid medical professionals in monitoring and treating patients. This research focuses on segmenting glioma brain tumour lesions in MRI images by analysing them at the pixel level. The aim is to develop a deep learning-based approach that enables ensemble learning to achieve precise and consistent segmentation of brain tumours. While many studies have explored ensemble learning techniques in this area, most rely on aggregation functions like the Weighted Arithmetic Mean (WAM) without accounting for the interdependencies between classifier subsets. To address this limitation, the Choquet integral is employed for ensemble learning, along with a novel evaluation framework for fuzzy measures. This framework integrates coalition game theory, information theory, and Lambda fuzzy approximation. Three distinct fuzzy measure sets are computed using different weighting strategies informed by these theories. Based on these measures, three Choquet integrals are calculated for segmenting different components of brain lesions, and their outputs are subsequently combined. The BraTS-2020 online validation dataset is used to validate the proposed approach. Results demonstrate superior performance compared with several recent methods, achieving Dice Similarity Coefficients of 0.896, 0.851, and 0.792 and 95% Hausdorff distances of 5.96 mm, 6.65 mm, and 20.74 mm for the whole tumour, tumour core, and enhancing tumour core, respectively. Full article

Duck egg quality classification is critical in farms, hatcheries, and salted egg processing plants, where cracked eggs must be identified before further processing or distribution. However, duck eggs present a unique challenge due to their white eggshells, which make cracks difficult to detect visually. In current practice, human inspectors use standard white light for crack detection, and many researchers have focused primarily on improving detection algorithms without addressing lighting limitations. Therefore, this paper presents duck egg crack detection using an adaptive convolutional neural network (CNN) model ensemble with multi-light channels. We began by developing a portable crack detection system capable of controlling various light sources to determine the optimal lighting conditions for crack visibility. A total of 23,904 images were collected and evenly distributed across four lighting channels (red, green, blue, and white), with 1494 images per channel. The dataset was then split into 836 images for training, 209 images for validation, and 449 images for testing per lighting condition. To enhance image quality prior to model training, several image pre-processing techniques were applied, including normalization, histogram equalization (HE), and contrast-limited adaptive histogram equalization (CLAHE). The Adaptive MobileNetV2 was employed to evaluate the performance of crack detection under different lighting and pre-processing conditions. The results indicated that, under red lighting, the model achieved 100.00% accuracy, precision, recall, and F1-score across almost all pre-processing methods. Under green lighting, the highest accuracy of 99.80% was achieved using the image normalization method. For blue lighting, the model reached 100.00% accuracy with the HE method. Under white lighting, the highest accuracy of 99.83% was achieved using both the original and HE methods. Full article

In today’s increasingly interconnected digital world, cyber threats have grown in frequency and sophistication, making intrusion detection systems a critical component of modern cybersecurity frameworks. Traditional IDS methods, often based on static signatures and rule-based systems, are no longer sufficient to detect and respond to complex and evolving attacks. To address these challenges, Artificial Intelligence and machine learning have emerged as powerful tools for enhancing the accuracy, adaptability, and automation of IDS solutions. This study presents a novel, hybrid ensemble learning-based intrusion detection framework that integrates deep learning and traditional ML algorithms with explainable artificial intelligence for real-time cybersecurity applications. The proposed model combines an Artificial Neural Network and Support Vector Machine as base classifiers and employs a Random Forest as a meta-classifier to fuse predictions, improving detection performance. Recursive Feature Elimination is utilized for optimal feature selection, while SHapley Additive exPlanations (SHAP) provide both global and local interpretability of the model’s decisions. The framework is deployed using a Flask-based web interface in the Amazon Elastic Compute Cloud environment, capturing live network traffic and offering sub-second inference with visual alerts. Experimental evaluations using the NSL-KDD dataset demonstrate that the ensemble model outperforms individual classifiers, achieving a high accuracy of 99.40%, along with excellent precision, recall, and F1-score metrics. This research not only enhances detection capabilities but also bridges the trust gap in AI-powered security systems through transparency. The solution shows strong potential for application in critical domains such as finance, healthcare, industrial IoT, and government networks, where real-time and interpretable threat detection is vital. Full article

Microbially-induced calcite precipitation (MICP) has emerged as a promising bio-geotechnical technique for sustainable soil improvement, yet accurate prediction of treatment effectiveness remains challenging due to complex multi-factor interactions. This study develops an ensemble learning framework (LARO-EnML) for predicting the unconfined compressive strength (UCS) of MICP-treated sand. A comprehensive database containing 402 experimental datasets was utilised in the study, consisting of unconfined compression test results from bio-cemented sands with eight key input parameters considered. The performance evaluation demonstrates that LARO-EnML achieves superior predictive accuracy, with RMSE of 0.5449, MAE of 0.2853, R² of 0.9570, and OI of 0.9597 on the test data, significantly outperforming other models. Model interpretability analysis reveals that calcite content serves as the most influential factor, with a strong positive correlation to strength enhancement, while urease activity exhibits complex, staged influence characteristics. This research contributes to advancing the practical implementation of MICP technology in geotechnical engineering by offering both accurate predictive capability and enhanced process understanding through interpretable ML approaches. Full article

Urban commercial districts, with their unique characteristics, serve as a reflection of broader urban development patterns. However, only a handful of studies have harnessed point-of-interest (POI) data to model the intricate relationship between retail commercial space types and other factors. This paper endeavors to bridge this gap, focusing on the influence of urban development factors on retail commerce districts through the lens of POI data. Our exploration underscores how commercial zones impact the density of residential neighborhoods and the coherence of pedestrian pathways. To facilitate our investigation, we propose an ensemble clustering technique for identifying and outlining urban commercial areas, including Kernel Density Analysis (KDE), Density-based Spatial Clustering of Applications with Noise (DBSCAN), Geographically Weighted Regression (GWR). Our research uses the city of Manchester as a case study, unearthing the relationship between commercial retail catchment areas and a range of factors (retail commercial space types, land use function, walking coverage). These include land use function, walking coverage, and green park within the specified areas. As we explore the multiple impacts of different urban development factors on retail commerce models, we hope this study acts as a springboard for further exploration of the untapped potential of POI data in urban business development and planning. Full article

This study suggests a hybrid approach that combines improved feature selection and intelligent diagnosis to increase the operational safety and intelligent diagnosis capabilities of hydropower units. In order to handle the vibration data, complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) is used initially. A novel comprehensive index is constructed by combining the Pearson correlation coefficient, mutual information (MI), and Kullback–Leibler divergence (KLD) to select intrinsic mode functions (IMFs). Next, feature extraction is performed on the selected IMFs using Refined Composite Multiscale Fluctuation Dispersion Entropy (RCMFDE). Then, time and frequency domain features are screened by calculating dispersion and combined with IMF features to build a hybrid feature vector. The vector is then fed into a CNN-GRU-Attention model for intelligent diagnosis. The improved slime mold algorithm (ISMA) is employed for the first time to optimize the hyperparameters of the CNN-GRU-Attention model. The experimental results show that the classification accuracy reaches 96.79% for raw signals and 93.33% for noisy signals, significantly outperforming traditional methods. This study incorporates entropy-based feature extraction, combines hyperparameter optimization with the classification model, and addresses the limitations of single feature selection methods for non-stationary and nonlinear signals. The proposed approach provides an excellent solution for intelligent optimized diagnosis of hydropower units. Full article