Search Results (2,547)

The Consensual Assessment Technique (CAT) is a gold standard of creativity assessment which provides valid product-based creativity scores that are contextually grounded (stemming from raters with unique expertise, culturally and historically situated). However, its implementation is often demanding (raters’ burden, complex rating designs). This study investigates whether machine learning can effectively simulate expert-panel judgments of creativity using minimal training data. Using a dataset of 411 short stories, we compared the performance of Random Forest (RF), Gradient Boosted Trees, and Decision Tree models, based on story length and Divergent Semantic Integration, to predict expert CAT ratings by (1) identifying the optimal algorithm and (2) the minimum training sample size required for reliable prediction. Results indicate that RF consistently outperformed other algorithms, achieving high correlations with CAT scores (r = 0.80) using as few as 25 training stories. Furthermore, RF demonstrated superior accuracy and lower reliance on story length compared to LLM-based scoring models. These findings provide a robust proof-of-concept for using simulated expert panels as a scalable alternative to (decontextualized) automated assessment methods, while reducing human raters’ burden and the logistical constraints of complex rating designs. Extension of this work to different contexts, creativity tasks and domains are necessary to gauge its generalizability. Full article

This study investigates the feasibility of acoustic signal analysis for the assessment of weld bead quality in the shielded metal arc welding (SMAW) process. The work focuses on comparing time-domain acoustic signals and time–frequency spectrogram representations for the classification of welds as accepted or rejected according to standard welding inspection criteria. Two key acoustic descriptors, the fundamental frequency (F₀) and the harmonics-to-noise ratio (HNR), were extracted and analyzed to evaluate statistical differences between the two weld quality classes. Statistical tests, including Anderson–Darling, Levene, ANOVA, and Kruskal–Wallis (α = 0.05), revealed significant differences between accepted and rejected welds. Accepted welds exhibited a bimodal HNR distribution associated with transient arc instability at the beginning and end of the bead, whereas rejected welds showed more uniform acoustic behavior throughout the process. Subsequently, the acoustic data were represented using both audio signals and spectrograms and used as inputs for ten supervised machine learning models, including Support Vector Classifier (SVC), Logistic Regression (LR), k-Nearest Neighbors (KNN), Decision Tree (DT), Random Forest (RF), Extra Trees (ET), Gradient Boosting (GB), and Naïve Bayes (NB). The results demonstrate that spectrogram-based representations significantly outperform time-domain signals, achieving accuracies of 0.95–0.96, ROC-AUC values above 0.95, and false positive and false negative rates below 6%. These findings indicate that, while scalar acoustic descriptors provide statistically significant insight into weld quality, time–frequency representations combined with machine learning enable a more robust and reliable framework for automated non-destructive evaluation, particularly in manual SMAW processes under realistic operating conditions. Full article

The Welded Bead Bending Test (WBBT) assesses steel structures intended for construction in Germany in accordance with ZTV-ING Part 4 or DBS 918 002-02, as specified in Stahl-Eisen-Prüfblatt (SEP) 1390. Test outcomes are classified as passed (p) if the minimum bending angle $\alpha \ge {60}^{\circ }$ is achieved without fracture, not passed (n.p.) if fracture occurs beforehand, and invalid if no crack propagates into the base material. This study evaluates eight supervised machine learning models for classification regarding their suitability for predicting WBBT results: Decision Tree Classifier (DT), Random Forest Classifier (RF), Histogram-based Gradient Boosting Classifier (HGBC), k-Nearest-Neighbour (KNN), Bagging Classifiers based on DT (BCDT) and RF (BCRF), Generalized Learning Vector Quantizer (GLVQ), and Generalized Matrix Learning Vector Quantizer (GMLVQ). An industrial dataset of approximately 3600 samples was compiled in collaboration with Chemnitzer Werkstoff und Oberflächentechnik GmbH (CEWUS). Evaluation metrics included Balanced Accuracy, Recall, Specificity, computation time, and prediction stability. BCDT and BCRF achieved the highest Balanced Accuracy (70.6% and 70.3%, respectively), with BCRF excelling in Specificity (82.5%), thereby reliably detecting the n.p. class. GLVQ and GMLVQ demonstrated superior stability (maximum variability between training and testing dataset 0.14% and 3.17%, respectively), while BCRF and GMLVQ required the longest training times (BCRF: 10 s–20 s; GMLVQ: up to 80 s). KNN proved least suitable for WBBT outcome prediction. Full article

Extreme class imbalance is a persistent obstacle for machine learning-driven intrusion detection, as rare but high-impact cyberattacks occur far less frequently than benign traffic in training data. In many real-world cybersecurity datasets, this imbalance becomes extreme, with certain attack types containing a handful of samples, effectively placing the problem in a few-shot learning regime. This paper presents a controlled benchmarking study of Generative Adversarial Network (GAN) objectives for synthesizing minority-class cyberattack data. Using the UWF-ZeekData22 network traffic dataset, each MITRE ATT&CK tactic is framed as a separate binary detection task, and tactic-specific GANs are trained solely on minority samples to generate synthetic attack records. Four widely used GAN variants—Vanilla GAN, Conditional GAN (cGAN), Wasserstein GAN (WGAN), and Wasserstein GAN with Gradient Penalty (WGAN-GP)—are compared under unified training steps and fixed augmentation conditions. The utility of generated data is assessed by evaluating downstream detection performance using five traditional classifiers: Logistic Regression, Support Vector Machine, k-Nearest Neighbors, Decision Tree, and Random Forest. The results indicate that GAN augmentation generally strengthens minority-class detection across tactics and models, reducing false negatives and improving recall consistency, while not systematically harming majority-class performance. However, the effectiveness of each GAN objective varies significantly with data sparsity. Specifically, simpler adversarial objectives often outperform more complex architectures by preserving discriminative feature structure, while heavily regularized models may overly smooth minority-class distributions and reduce separability. Wasserstein-based objectives provide improved training stability, but additional regularization does not consistently translate to better detection performance. Overall, the results demonstrate that in extreme-imbalance settings, GAN effectiveness is governed more by data sparsity and structure preservation than by architectural complexity. These findings establish class-specific generative augmentation as a practical strategy for intrusion detection and provide empirical guidance for selecting appropriate GAN objectives for tabular cybersecurity data under highly imbalanced conditions. Full article

Accurate prediction of compost maturity is vital for ensuring quality, safety, minimum substrate weight loss and agronomic performance of compost products. In this study, eight supervised machine learning (ML) classification models including Random Forest, Logistic Regression, Decision Tree, Gaussian and Multinomial Naive Bayes, K-Nearest Neighbors, Support Vector Machine, and AdaBoost were systematically evaluated for their ability to predict compost maturity using three key indicators: cation exchange capacity (CEC), carbon to nitrogen ratio (C/N), and humic acid (HA) content. A dataset comprising 756 samples (4 composting/vermicomposting systems × 7 treatments × 9 time points × 3 replicates) was generated. To reduce replicate-induced variability and ensure robust machine learning analysis, triplicates were averaged at each time point, resulting in 252 effective observations used for model development. Pearson correlation and heatmap analysis indicated strong interdependencies among CEC, HA, total nitrogen (TN) and organic matter (OM) content, confirming their collective utility in compost maturity classification. Model performance was assessed based on classification metrics (accuracy, precision, recall, F₁-score) and regression-based error indicators, including mean absolute error (MAE), mean squared error (MSE), root mean squared error (RMSE), and coefficient of determination (R²). Ensemble models, particularly RF and AdaBoost, showed the highest predictive accuracy (up to 0.98) and lowest error rates (e.g., MAE < 0.05, RMSE < 0.1, R² > 0.95) when predicting CEC and C/N-based maturity classes. HA-based predictions showed slightly lower precision and higher variance across models. Full article

This study examines how assessments of coastal extreme sea levels depend on the separability and reconstructability of the astronomical tide in hourly sea-level records. Using a global tide-gauge network, it proposes an ensemble-learning correction framework that integrates a physical-baseline threshold with multi-criteria consistency testing to determine whether machine-learning enhancement is genuinely effective across stations and time windows. The analysis uses hourly records from 528 UHSLC tide gauges, with 31-day short sequences used to reconstruct 180-day sea-level variability. Taking the physical tidal model as the baseline, residuals are corrected using Extremely Randomized Trees, Random Forest, and Gradient Boosting. To avoid false improvement driven solely by error reduction, a hierarchical decision framework is established. Baseline model quality is first screened using NSE and the coefficient of determination, after which mathematical artefacts are identified through diagnostics of peak suppression and variance shrinkage. A five-level classification is then derived from the convergent evidence of twelve performance metrics and four statistical significance tests. The results show a consistent global pattern across all three algorithms. Approximately 57% of stations meet the criterion for genuine improvement, whereas about 42% are associated with an unreliable physical baseline, indicating that the dominant source of failure arises not from the ensemble-learning algorithms themselves, but from spatially varying limitations in the underlying physical baseline. Spatially, the credibility of machine-learning correction is strongly conditioned by baseline quality: stations with effective correction are more continuous along the eastern North Atlantic and European coasts, whereas stations with ineffective correction are more concentrated in the Gulf of Mexico, the Caribbean, and the marginal seas and archipelagic regions of the western Pacific. These results indicate that the observed spatial heterogeneity primarily reflects geographically varying physical and dynamical conditions that control baseline reliability and residual learnability, rather than a standalone difference in the intrinsic capability of ensemble learning itself. Full article

Introduction: Drug side effects are a relevant problem for patient safety and public health, and traditional methods have limitations in capturing complex patterns between clinical and pharmacological variables. Objective: To evaluate machine learning models to probabilistically predict multiple side effects associated with drug use. Materials and methods: A cross-sectional computational study was carried out with data from 1000 medications that included clinical condition, dosage and duration of treatment. Random Forest, Decision Tree, Support Vector Classifier and KNN were trained and optimized using Grid Search and an 80:20 split for training and testing. Chi-square tests and Principal Component Analysis were applied to explore associations and overlap between categories. Results: Significant associations were found between side effects and clinical condition (p < 0.05) and the drug administered (p < 0.05). The PCA showed a high overlap between categories, which justified a probabilistic approach. Tree-based models showed better performance (accuracy ≈ 0.35). Conclusions: Prediction of side effects is a multifactorial and non-deterministic problem; probabilistic machine learning models allow for estimating several plausible adverse events and can support clinical decision-making and pharmacovigilance. Full article

Background/Objectives: Tablet development requires simultaneous optimization of multiple quality attributes under limited experimental budgets, yet formulation–property relationships are highly nonlinear in mixture systems. To support pre-formulation decision-making prior to extensive tablet prototyping, this study proposes an AI framework that organizes formulation and process data together with raw-material property records into a reusable database, and enriches conventional composition/process features with physically motivated mixture descriptors derived from raw-material properties and formulation/process settings. Methods: Mixture-level scalar descriptors are constructed by composition-weighted aggregation of material properties, and particle size distribution (PSD) is incorporated via a compact set of summary statistics computed from composition-weighted mixture PSDs. Three feature sets are compared: (i) Materials + Processes (MP), (ii) MP with scalar Descriptors (MPD), and (iii) MPD with PSD summaries (MPDD). Five target properties are modeled: hardness, disintegration time, flow function, cohesion, and thickness. We train and evaluate Random Forest, Extra Trees Regressor, Lasso, Partial Least Squares, Support Vector Regression, and a multi-branch neural network that processes the three feature blocks separately and concatenates them for prediction. For interpolation assessment, repeated Train/Dev/Test splitting (5:3:2) across multiple random seeds is used, and the effect of feature augmentation is quantified by paired RMSE improvements with bootstrap confidence intervals and paired Wilcoxon signed-rank tests. To assess robustness under practical formulation updates, rolling-origin time-series splits are employed and Applicability Domain indicators are computed to characterize out-of-distribution coverage. Results: Across interpolation evaluations, mixture-descriptor augmentation (MPD/MPDD) improves hardness and disintegration time in most settings, whereas gains for flow function are smaller and cohesion/thickness show mixed effects under limited sample sizes. Conclusions: Under extrapolation-oriented evaluation, the descriptors can improve hardness but may degrade disintegration-time prediction under covariate shift, emphasizing the need for careful descriptor selection and dimensionality control when deploying pre-formulation predictors. Full article

Road traffic accidents at intersections pose a persistent challenge in Riyadh, Saudi Arabia, contributing significantly to public health burdens and economic losses. Traditional statistical approaches often fail to capture the complex, non-linear interactions among geometric design, traffic parameters, and accident severity. This study develops a multi-methodological machine learning framework to predict intersection accident severity using the Equivalent Property Damage Only (EPDO) metric. Historical data (2017–2023) from Riyadh Municipality for 150 high-risk intersections were analyzed, incorporating predictors such as service road distance (SRD), U-turn distance (UTD), median width (MW), peak hour volume (PHV), heavy vehicle percentage (HV%), and injury/frequency counts. Six algorithms, i.e., Decision Tree, Random Forest, Gradient Boosting, Support Vector Machine, Linear Regression, and Artificial Neural Network, were compared using a 70/30 train–test split and k-fold cross-validation in this study. The Gradient Boosting model achieved superior performance (R² = 0.89 with MSE = 63.43 and RMSE = 7.96) and was selected for final deployment. SHAP feature importance analysis revealed minor injuries (MIs), serious injuries (SRIs), and fatalities (FAs) as the most important dominant predictors, with geometric factors (UTD, MW) and traffic composition (HV%) providing actionable infrastructure insights. The model ranked intersections and identified the “Jeddah Road with Taif Road” (predicted EPDO = 137.22) as the highest-risk location. Evidence-based recommendations include enforcing the minimum 300 m U-turn buffers with staggering service road exits ≥150 m and restricting heavy vehicles during peak hours. The scalable framework developed in this study supports the data-driven prioritization of safety interventions and aligns with sustainable urban mobility goals and offers transferability to other metropolitan contexts worldwide. Full article

Major depressive disorder (MDD) is a prevalent mental health condition that inflicts a high burden on individuals and healthcare systems. There is a clinical need to detect MDD relapse practically and effectively to improve treatment outcomes for patients. To address this, we developed a smart monitoring system using an Artificial Intelligence (AI) approach to estimate MDD severity and relapse risk from patients’ smartphone behavioral data (i.e., digital phenotyping). Thirty-five MDD patients were recruited from the Institute of Mental Health in Singapore, who installed the smartphone study app Sallie. Their symptoms were quantified using the Hamilton Depression Rating Scale (HAMD-17) at the start of the trial, and every 30 days after over 3 months. The app collected behavioral data such as activity, activity type, and GPS location used to train AI models such as logistic regression, decision trees, and random forest classifiers. We found that passive data collection continued for most participants (up to 79% retention rate) after 3 months. We also used five-fold cross-validation to predict HAMD-17 severity ranging from two to four classes and the relapse status, achieving 91%, 88%, and 78% accuracies for two to four classes, respectively, and a relapse prediction accuracy of 86% whereby four patients relapsed during the study. Additionally, anxiety factors within the HAMD-17 were significantly predicted (Pearson correlation coefficient = 0.78, p = 1.67 × 10⁻¹⁴). These results demonstrate the promise of using smartphone behavioral data to estimate depressive symptoms and identify early indicators of relapse. Full article

This study aims to investigate the effect of manufacturing parameters on the mechanical properties of PC-ABS samples produced by the Fused Deposition Modeling (FDM) additive manufacturing method and to model these relationships using machine learning methods. In the study, the parameters of printing speed, infill density, and raster angle were determined according to the Taguchi L16 experimental design, and tensile, bending, and impact tests were performed on the produced samples. Experimental results showed that the infill density parameter resulted in an increase in tensile strength of approximately 62% (from 25.10 MPa to 40.71 MPa) and an increase in flexural strength of approximately 46% (from 45.13 MPa to 66.13 MPa). Furthermore, an improvement in impact energy of approximately 45% (from 1.698 J to 2.467 J) was achieved under optimum printing speed conditions. Mechanistic properties were predicted using Decision Tree, Random Forest, K-Nearest Neighbors, and Multilayer Perceptron models with a dataset generated from experimental data. Comparing the model performances, the Random Forest algorithm was found to provide the highest prediction performance with accuracy in the R² range of 0.94–0.99 and RMSE values below 0.5, demonstrating strong generalization capabilities. The results showed that infill density is the most decisive parameter on both tensile and flexural strength, and that printing speed has a significant effect, especially on impact energy. ANOVA analyses revealed that all main parameters have statistically significant effects on mechanical properties. In the performance comparison of the machine learning models, the Random Forest algorithm provided the highest prediction accuracy, demonstrating that mechanical properties can be reliably predicted. In conclusion, it has been shown that the mechanical performance of PC-ABS parts produced by the FDM method can be optimized by using the correct selection of production parameters and machine learning-based modeling approaches. Full article

Topsoil features within a depth of 0–10 cm are vital for making soil management decisions that affect crop production. However, the use of these soil features to predict soil organic carbon (SOC) at 10–20 cm requires further investigation. The study aims to predict SOC at 10–20 cm using total nitrogen (total N), pH, cation exchange capacity (CEC), and SOC at 0–10 cm and select a suitable model for predicting SOC. This study was conducted using data from a long-term tillage, winter wheat (Triticum aestivum L.)-fallow experiment established in autumn 1970. Treatments included moldboard plow, stubble mulch, no-till, and native sod, each replicated three times. Soil samples were collected from each plot at depths of 0–10 cm and 10–20 cm in April of 2010 and 2011. Models were fit using ordinary least squares (OLS), least absolute shrinkage and selection operator (LASSO), random forests, and Bayesian additive regression trees (BART). Using root mean square error (RMSE), SOC was predicted with an accuracy of 1.44 g kg⁻¹ or relative RMSE (rRMSE) of 13.5%. This was achieved with the OLS model that used total N, pH, and CEC as predictors. The good performance of the OLS model over more flexible machine learning approaches suggests that the information predictors provide about the response variable (SOC) is approximately linear. As the agricultural dataset was small (n = 24), the less complex model reduced the chances of overfitting while keeping the variance relatively low. Random forests and BART had an rRMSE greater than 21%. Statistical models could be used to estimate SOC at 10–20 cm and reduce destructive soil analysis methods. Full article

Leaf Area Index (LAI) is a fundamental parameter for characterizing the growth of tea (Camellia sinensis L.). However, in rugged mountainous regions, the combined effects of topographic relief and canopy structural heterogeneity severely constrain the accuracy of UAV-based multispectral LAI retrieval. This study develops an integrated framework combining topographic correction with interpretable machine learning to improve LAI estimation. We utilized a UAV multispectral dataset collected during the peak growing season from a typical tea-growing region in Fujian Province, China (altitude range: 58–186 m), comprising a total of 90 samples. Three topographic correction methods, including Sun–Canopy–Sensor (SCS), SCS with C correction (SCS+C), and Minnaert+SCS, were evaluated in combination with Linear Regression (LR), Decision Tree (DT), Random Forest (RF), and Extreme Gradient Boosting (XGBoost) models. Results indicated that the SCS+C algorithm outperformed other methods by effectively accounting for direct and diffuse radiation components, thereby reducing topographic dependence while maintaining radiometric consistency across heterogeneous surfaces. The XGBoost model combined with SCS+C correction achieved the highest performance (R² = 0.8930, RMSE = 0.6676, nRMSE = 7.93%, MAE = 0.4936, Bias = −0.0836). SHapley Additive exPlanations (SHAP) analysis revealed a structure-dominated retrieval mechanism, in which red-band textural features (Correlation_R) exhibited higher importance than conventional vegetation indices. Compared with previous studies that primarily focus on either topographic correction or model development, this study provides quantitative insights into the underlying retrieval mechanisms. This framework improves the precision of tea LAI retrieval in complex terrains and provides a robust methodological basis for digital management in mountainous agriculture. Full article

Accurate irrigated cropland mapping is critical for agricultural water management and food security. Existing image-based irrigation mapping workflows primarily rely on vegetation indices and synthetic aperture radar (SAR) backscatter features, which have limited capacity to characterize the temporal evolution of irrigation processes and crop growth conditions. The AlphaEarth Foundation (AEF) model developed by Google DeepMind provides compact embeddings with temporal semantic information learned via self-supervision, yet their utility for irrigation mapping has not been systematically assessed. In this study, a comprehensive assessment of AEF embeddings for irrigated cropland mapping was performed in terms of feature separability, classification performance, and spatiotemporal transferability. Experiments were conducted in two representative irrigated regions: the Guanzhong Plain in China and Kansas in the USA. Class separability of the 64 embedding dimensions was quantified using the Jeffries–Matusita (JM) distance. Then, the AEF embeddings were compared with the Sentinel feature set (Sentinel-2 bands, normalized difference vegetation index(NDVI), enhanced vegetation index(EVI), normalized difference water index(NDWI) and Sentinel-1 vertical transmit vertical receive(VV), vertical transmit horizontal receive(VH)) using K-means clustering and supervised classifiers, including Decision Tree (DT), Random Forest (RF), Gradient Boosting Decision Trees (GBDT), Support Vector Machine (SVM), and Multi-layer Perceptron (MLP). Finally, transfer experiments across 2022 and 2024 in the Guanzhong Plain and Kansas were conducted to examine cross-year and cross-region performance. The results showed that AEF embeddings consistently provide stronger class separability in both study areas, with a maximum JM distance of 1.58 (A29). Using AEF embeddings, RF achieved overall accuracies (OA) of 0.95 in the Guanzhong Plain and 0.93 in Kansas, outperforming models based on Sentinel-1/2 bands and indices. Notably, unsupervised K-means clustering on AEF embeddings yielded OA > 0.85, indicating high intrinsic separability between irrigated and rainfed croplands. Transfer experiments further demonstrate stable temporal transfer (cross-year OA > 0.87), whereas cross-region transfer is constrained by differences in irrigation regimes, crop phenology and management practices, resulting in limited spatial generalization (OA~0.3). Overall, this study demonstrates the potential of high-information-density representations from geospatial foundation models for irrigated cropland mapping and provides methodological and technical insights to support transfer learning and operational mapping over large areas. Full article

Groundwater is the primary source of irrigation in many semi-arid hard-rock aquifer regions. Yet, its suitability assessment is often hindered by the nonlinear hydrochemical dynamics that traditional bivariate tools, such as the U.S. Salinity Laboratory (USSL) diagram, cannot adequately resolve. To overcome this limitation, we developed an explainable artificial intelligence (XAI) framework that predicts irrigation suitability categories directly from hydrochemical variables, without relying on calculated indices. Using 1872 post-monsoon groundwater samples from Telangana, India, we trained three ensemble tree-based classifiers (Random Forest, LightGBM, and XGBoost) on 11 hydrochemical variables (Na⁺, K⁺, Ca²⁺, Mg²⁺, HCO₃⁻, Cl⁻, F⁻, NO₃⁻, SO₄²⁻, pH, and total hardness). Class imbalance was addressed using the Synthetic Minority Over-sampling Technique (SMOTE), and model hyperparameters were optimized with Optuna. Among the tested models, LightGBM achieved the best performance (balanced accuracy = 0.938). Model interpretability was enabled using Shapley Additive Explanations (SHAP), supported by Piper and Gibbs diagrams, revealing a critical distinction between sodicity-driven salinity and hardness-driven mineralization, identifying calcium-saturated waters for which gypsum amendment can be chemically futile. To bridge the gap between algorithmic accuracy and operational simplicity, we distilled SHAP explanations into linear heuristics and quantified the trade-off between accuracy and simplicity. Accordingly, we proposed a tiered hydrochemical triage framework in which quantitative heuristics handled approximately 62.5% of the routine samples, while XAI resolved the complex and ambiguous cases. Overall, the proposed framework transforms classic suitability assessment tools into an adaptable, evidence-informed, proactive decision-support system for sustainable agricultural water management under increasing environmental stress. Full article