Search Results (210)

Examining pedestrian crossing violations at high-risk road midblock crossings has become essential, particularly in high-speed corridors, as a result of accidents at crossings resulting in fatalities. Hence, this article investigates such behavior in Alexandria, Egypt, as a credible case study in a developing country. According to our research methodology, a comprehensive dataset of over 2400 field-observed video recordings was used for real-life data collection. Machine learning (ML) models, such as CatBoost and gradient boosting (GB), were employed to predict crossing decisions. The models showed that risky behavior is strongly influenced by waiting time, crossing time, and the number of crossing attempts. The highest predictive performance was achieved by CatBoost and gradient boosting, indicating strong interpersonal influence within small groups engaging in unsafe road-crossing behavior. In the same context, the Shapley additive explanation (SHAP) values for these variables were 3, 2, and 0.60, respectively. Subsequently, based on SHAP sensitivity analysis, the results show that pedestrian crossing time (s) had the highest tendency to push the model towards class 1 (e.g., crossing illegally), while total time (s) and age group (40–60 Y) had a significant negative influence on model prediction converging to class 0 (e.g., crossing illegally). The results also showed that shorter exposure times increase the likelihood of crossing illegally. This research work is among the few studies that employ a behavior-based approach to understanding pedestrian behavior at midblock crossings. This study offers actionable insights and valuable information for urban designers and transportation planners when considering the design of midblock crossings. Full article

Despite the agricultural sector’s consistently high injury rates, formal reporting is often limited, leading to sparse national datasets that hinder effective safety interventions. To address this, our study introduces a comprehensive framework leveraging advanced ensemble machine learning (ML) models to predict and interpret the severity of agricultural injuries. We use a unique, manually curated dataset of over 2400 agricultural incidents from AgInjuryNews, a public repository of news reports detailing incidents across the United States. We evaluated six ensemble models, including Gradient Boosting (GB), eXtreme Grading Boosting (XGB), Light Gradient Boosting Machine (LightGBM), Adaptive Boosting (AdaBoost), Histogram-based Gradient Boosting Regression Trees (HistGBRT), and Random Forest (RF), for their accuracy in classifying injury outcomes as fatal or non-fatal. A key contribution of our work is the novel integration of explainable artificial intelligence (XAI), specifically SHapley Additive exPlanations (SHAP), to overcome the “black-box” nature of complex ensemble models. The models demonstrated strong predictive performance, with most achieving an accuracy of approximately 0.71 and an F1-score of 0.81. Through global SHAP analysis, we identified key factors influencing injury severity across the dataset, such as the presence of helmet use, victim age, and the type of injury agent. Additionally, our application of local SHAP analysis revealed how specific variables like location and the victim’s role can have varying impacts depending on the context of the incident. These findings provide actionable, context-aware insights for developing targeted policy and safety interventions for a range of stakeholders, from first responders to policymakers, offering a powerful tool for a more proactive approach to agricultural safety. Full article

The use of resource-constrained Low-Power and Lossy Networks (LLNs), where the IPv6 Routing Protocol for LLNs (RPL) is the de facto routing standard, has increased due to the Internet of Things’ (IoT) explosive growth. Because of the dynamic nature of IoT deployments and the lack of in-protocol security, RPL is still quite susceptible to routing-layer attacks like Blackhole, Lowered Rank, version number manipulation, and Flooding despite its lightweight architecture. Lightweight, data-driven intrusion detection methods are necessary since traditional cryptographic countermeasures are frequently unfeasible for LLNs. However, the lack of RPL-specific control-plane semantics in current cybersecurity datasets restricts the use of machine learning (ML) for practical anomaly identification. In order to close this gap, this work models both static and mobile networks under benign and adversarial settings by creating a novel, large-scale multiclass RPL attack dataset using Contiki-NG’s Cooja simulator. To record detailed packet-level and control-plane activity including DODAG Information Object (DIO), DODAG Information Solicitation (DIS), and Destination Advertisement Object (DAO) message statistics along with forwarding and dropping patterns and objective-function fluctuations, a protocol-aware feature extraction pipeline is developed. This dataset is used to evaluate fifteen classifiers, including Logistic Regression (LR), Support Vector Machine (SVM), Decision Tree (DT), k-Nearest Neighbors (KNN), Random Forest (RF), Extra Trees (ET), Gradient Boosting (GB), AdaBoost (AB), and XGBoost (XGB) and several ensemble strategies like soft/hard voting, stacking, and bagging, as part of a comprehensive ML-based detection system. Numerous tests show that ensemble approaches offer better generalization and prediction performance. With overfitting gaps less than 0.006 and low cross-validation variance, the Soft Voting Classifier obtains the greatest accuracy of 99.47%, closely followed by XGBoost with 99.45% and Random Forest with 99.44%. Full article

This study employed machine learning to investigate the mechanical behavior of one-part geopolymer (OPG)-stabilized soil subjected to acid erosion. Based on the unconfined compressive strength (UCS) data of acid-eroded OPG-stabilized soil, eight machine learning models, namely, Adaptive Boosting (AdaBoost), Decision Tree (DT), Extra Trees (ET), Gradient Boosting (GB), Light Gradient Boosting Machine (LightGBM), Random Forest (RF), Support Vector Machine (SVM), and eXtreme Gradient Boosting (XGBoost), along with hyper-parameter optimization by Genetic Algorithm (GA), were used to predict the degradation of the UCS of OPG-stabilized soils under different durations of acid erosion. The results showed that GA-SVM (R² = 0.9960, MAE = 0.0289) and GA-XGBoost (R² = 0.9961, MAE = 0.0282) achieved the highest prediction accuracy. SHAP analysis further revealed that solution pH was the dominant factor influencing UCS, followed by the FA/GGBFS ratio, acid-erosion duration, and finally, acid type. The 2D PDP combined with SEM images showed that the microstructure of samples eroded by HNO₃ was marginally denser than that of samples eroded by H₂SO₄, yielding a slightly higher UCS. At an FA/GGBFS ratio of 0.25, abundant silica and hydration products formed a dense matrix and markedly improved acid resistance. Further increases in FA content reduced hydration products and caused a sharp drop in UCS. Extending the erosion period from 0 to 120 days and decreasing the pH from 4 to 2 enlarged the pore network and diminished hydration products, resulting in the greatest UCS reduction. The results of the study provide a new idea for applying the ML model in geoengineering to predict the UCS performance of geopolymer-stabilized soils under acidic erosion. Full article

The growing demand for sustainable pavement materials has driven increased interest in asphalt mixtures incorporating recycled crumb rubber (CR). While CR modification enhances mechanical performance and durability, its often increases initial production costs and energy demand. This study develops an integrated framework that combines machine learning (ML) and economic analysis to identify the optimal balance between performance and cost in CR-modified asphalt overlay mixtures. An experimental dataset of conventional and CR-modified mixtures was used to train and validate multiple ML algorithms, including Random Forest (RF), Gradient Boosting (GB), Artificial Neural Networks (ANNs), and Support Vector Regression (SVR). The RF and ANN models exhibited superior predictive accuracy (R² > 0.98) for key performance indicators such as Marshall stability, tensile strength ratio, rutting resistance, and resilient modulus. A Cost–Performance Index (CPI) integrating life-cycle cost analysis was developed to quantify trade-offs between performance and economic efficiency. Environmental life-cycle assessment indicated net greenhouse gas reductions of approximately 96 kg CO₂-eq per ton of mixture despite higher production-phase emissions. Optimization results indicated that a CR content of approximately 15% and an asphalt binder content of 4.8–5.0% achieve the best performance–cost balance. The study demonstrates that ML-driven optimization provides a powerful, data-based approach for guiding sustainable pavement design and promoting the circular economy in road construction. Full article

Background: Monitoring training load and recovery is essential for performance optimization and injury prevention in youth football. However, predicting subjective recovery in preadolescent athletes remains challenging due to biological variability and the multidimensional nature of training responses. This exploratory study examined whether supervised machine learning (ML) models could predict Total Quality of Recovery (TQR) using integrated external load, internal load, anthropometric and maturational variables collected over one competitive microcycle. Methods: Forty male sub-elite U11 and U13 football players (age 10.3 ± 0.7 years; height 1.43 ± 0.08 m; body mass 38.6 ± 6.2 kg; BMI 18.7 ± 2.1 kg/m²) completed a microcycle comprising four training sessions (MD-4 to MD-1) and one official match (MD). A total of 158 performance-related variables were extracted, including external load (GPS-derived metrics), internal load (RPE and sRPE), heart rate indicators (U13 only), anthropometric and maturational measures, and tactical–cognitive indices (FUT-SAT). After preprocessing and aggregation at the player level, five supervised ML algorithms—K-Nearest Neighbors (KNN), Support Vector Machine (SVM), Decision Tree (DT), Random Forest (RF), and Gradient Boosting (GB)—were trained using a 70/30 train–test split and 5-fold cross-validation to classify TQR into Low, Moderate, and High categories. Results: Tree-based models (DT, GB) demonstrated the highest predictive performance, whereas linear and distance-based approaches (SVM, KNN) showed lower discriminative ability. Anthropometric and maturational factors emerged as the most influential predictors of TQR, with external and internal load contributing modestly. Predictive accuracy was moderate, reflecting the developmental variability characteristics of this age group. Conclusions: Using combined physiological, mechanical, and maturational data, these ML-based monitoring systems can simulate subjective recovery in young football players, offering potential as decision-support tools in youth sub-elite football and encouraging a more holistic and individualized approach to training and recovery management. Full article

Accurate prediction of road traffic crash severity is essential for developing data-driven safety strategies and optimizing resource allocation. This study presents a predictive modeling framework that utilizes Random Forest (RF), Gradient Boosting (GB), and K-Nearest Neighbors (KNN) to estimate segment-level frequencies of fatalities, serious injuries, and slight injuries on Hungarian roadways. The model integrates an extensive array of predictor variables, including roadway geometric design features, traffic volumes, and traffic composition metrics. To address class imbalance, each severity class was modeled using resampled datasets generated via the Synthetic Minority Over-sampling Technique (SMOTE), and model performance was optimized through grid-search cross-validation for hyperparameter optimization. For the prediction of serious- and slight-injury crash counts, the Random Forest (RF) ensemble model demonstrated the most robust performance, consistently attaining test accuracies above 0.91 and coefficient of determination (R²) values exceeding 0.95. In contrast, for fatalities count prediction, the Gradient Boosting (GB) model achieved the highest accuracy (0.95), with an R² value greater than 0.87. Feature importance analysis revealed that heavy vehicle flows consistently dominate crash severity prediction. Horizontal alignment features primarily influenced fatal crashes, while capacity utilization was more relevant for slight and serious injuries, reflecting the roles of geometric design and operational conditions in shaping crash occurrence and severity. The proposed framework demonstrates the effectiveness of machine learning approaches in capturing non-linear relationships within transportation safety data and offers a scalable, interpretable tool to support evidence-based decision-making for targeted safety interventions. Full article

Accurate estimation of flow discharge, Q, through hydraulic structures such as spillways and gates is of great importance in water resources engineering. Each hydraulic structure, due to its unique characteristics, requires a specific and comprehensive study. In this regard, the present study innovatively focuses on predicting Q through Rectangular Top-Hinged Gates (RTHGs) using advanced Gradient Boosting (GB) models. The GB models evaluated in this study include Categorical Boosting (CatBoost), Histogram-based Gradient Boosting (HistGBoost), Light Gradient Boosting Machine (LightGBoost), Natural Gradient Boosting (NGBoost), and Extreme Gradient Boosting (XGBoost). One of the essential factors in developing artificial intelligence models is the accurate and proper tuning of their hyperparameters. Therefore, four powerful metaheuristic algorithms—Covariance Matrix Adaptation Evolution Strategy (CMA-ES), Sparrow Search Algorithm (SSA), Particle Swarm Optimization (PSO), and Genetic Algorithm (GA)—were evaluated and compared for hyperparameter tuning, using LightGBoost as the baseline model. An assessment of error metrics, convergence speed, stability, and computational cost revealed that SSA achieved the best performance for the hyperparameter optimization of GB models. Consequently, hybrid models combining GB algorithms with SSA were developed to predict Q through RTHGs. Random split was used to divide the dataset into two sets, with 70% for training and 30% for testing. Prediction uncertainty was quantified via Confidence Intervals (CI) and the R-Factor index. CatBoost-SSA produced the most accurate prediction performance among the models (R² = 0.999 training, 0.984 testing), and NGBoost-SSA provided the lowest uncertainty (CI = 0.616, R-Factor = 3.596). The SHapley Additive exPlanations (SHAP) method identified h/B (upstream water depth to channel width ratio) and channel slope, S, as the most influential predictors. Overall, this study confirms the effectiveness of SSA-optimized boosting models for reliable and interpretable hydraulic modeling, offering a robust tool for the design and operation of gated flow control systems. Full article

Background: Muscle injuries are among the main problems in professional soccer, affecting player availability and team performance. Countermovement jump (CMJ) variables have been proposed as indicators of injury risk and for detecting strength imbalances, although their use is less explored than isokinetic assessments. Unlike previous studies based solely on linear statistics, this research integrates biomechanical data with machine learning approaches, providing a novel perspective for injury prediction in elite soccer. Objective: To examine the association between CMJ variables and muscle injury risk during a competitive season, considering injury incidence and effective playing minutes. It was hypothesized that specific CMJ asymmetries would be associated with a higher injury risk, and that machine learning algorithms could accurately classify players according to their injury status. Methods: Forty-one professional soccer players (18 women, 23 men) from national league teams (Chile) were assessed during preseason using force platforms. Non-contact muscle injuries and playing minutes were recorded over 10 months after the CMJ evaluations. Analyses included two-way ANOVA (sex × injury status) and machine learning algorithms (Logistic Regression, Decision Tree, K-Nearest Neighbors [KNN], Random Forest, Gradient Boosting [GB]). Results: Significant sex differences were observed in most variables (p < 0.05 and η_p² > 0.11), except peak force and peak power asymmetry. For injury status, only peak force asymmetry differed, while sex × injury interactions were found in peak power and left peak power. KNN (Accuracy = 87% and CI 95% = 71% to 96%) and GB (Accuracy = 84% and CI 95% = 68% to 94%) achieved the best classification performance between injured and non-injured players. Conclusions: CMJ did not show consistent statistical differences between injured and non-injured groups. However, machine learning models, particularly KNN and GB, demonstrated high predictive accuracy, suggesting that injuries are a complex phenomenon characterized by non-linear patterns. These findings highlight the potential of combining CMJ with machine learning approaches for functional monitoring and early detection of injury risk, though validation in larger cohorts is required before establishing clinical thresholds and preventive applications. Full article

Exoskeletons offer promising solutions for enhancing human mobility; however, personalizing assistance parameters to optimize physiological outcomes remains challenging. Human-in-the-loop (HIL) optimization has emerged as an effective strategy for tailoring device control, often using electromyography (EMG) as a real-time proxy for metabolic cost. This study simulates HIL optimization using surrogate models built from the average root mean square of the muscles’ activations (EMG-RMS) derived from treadmill walking trials with a robotic waist tether. Nine surrogate models were evaluated for prediction accuracy, including gradient boosting (GB), random forest, support vector regression, and Gaussian process variants. Seven global optimization algorithms were compared based on convergence time, EMG-RMS at optimum, and efficiency metrics. GB achieved the highest predictive accuracy (1.57% RAEP). Among optimizers, the gravitational search algorithm (GSA) produced the lowest EMG-RMS value (0.17 normalized units) and the fastest convergence (0.32 s), while particle swarm optimization (PSO) achieved 0.36 EMG-RMS in 1.61 s. These findings demonstrate the value of EMG-based simulation frameworks in guiding algorithm selection for HIL optimization, ultimately reducing the experimental burden in developing personalized exoskeleton assistance strategies. Full article

Accurate, timely maps of post-fire burn severity are vital for rehabilitation, hydrologic hazard assessment, and ecosystem recovery in the western United States, where large, frequent wildfires and steep environmental gradients challenge model generalization. Machine learning models, particularly tree-based regressors, are increasingly used to relate satellite-derived spectral features to ground-based severity metrics such as the Composite Burn Index (CBI). However, model generalization across spatial domains, both within and between wildfires, remains poorly characterized. In this study, we benchmarked six tree-based regression models (Decision Tree-DT, Random Forest-RF, Extra Trees-ET, Bagging, Gradient Boosting-GB, and AdaBoost-AB) for predicting wildfire severity from Landsat surface reflectance data across ten U.S. fire events. Two spatial validation strategies were applied: (i) within-fire spatial generalization via Leave-One-Cluster-Out (LOCO) and (ii) cross-fire transfer via Leave-One-Fire-Out (LOFO). Performance is assessed with R², RMSE, and MAE under identical predictors and default hyperparameters. Results indicate that, under LOCO, variance-reduction ensembles lead: RF attains R² = 0.679, MAE = 0.397, RMSE = 0.516, with ET statistically comparable (R² = 0.673, MAE = 0.393, RMSE = 0.518), and Bagging close behind (R² = 0.668, MAE = 0.402, RMSE = 0.525). Under LOFO, ET transfers best (R² = 0.616, MAE = 0.450, RMSE = 0.571), followed by GB (R² = 0.564, MAE = 0.479, RMSE = 0.606) and RF (R² = 0.543, MAE = 0.490, RMSE = 0.621). These results indicate that tree ensembles, especially ET and RF, are competitive under minimal tuning for rapid severity mapping; in practice, RF is a strong choice for an individual fire with local calibration, whereas ET is preferred when model transferability to unseen fires is paramount. Full article

Background: With the rapid emergence of novel survival models and feature selection methods, comparing them with traditional approaches is essential to define contexts of optimal performance. Methods: This study systematically evaluates nine survival models combined with nine feature selection methods for predicting the occurrence of angina pectoris using electronic health record (EHR) data from a Hungarian hospital (n = 29,655, features = 1150). Performance was assessed with the concordance index (C-index) and integrated Brier score (IBS) to compare predictive accuracy across methods. Results: Tree-based survival models, particularly gradient-boosted survival (GBS) and random survival forest (RSF), consistently outperformed conventional approaches in terms of C-index, but showed slightly worse calibration as reflected in their higher IBSs. The best-performing model was RSF, which was optimized using Bayesian hyperparameter tuning. For feature selection, tree-based methods such as Boruta and RSF-based approaches showed superior performance. We further identified clusters of feature selection methods and generated consensus feature sets. We also analyzed the internal relationships between the selected features. Survival model performance was also examined over time using the time-dependent Area Under the Curve (AUC) based on the best-performing feature set. Conclusions: Our findings highlight the substantial impact of recent methodological innovations in survival analysis, which offer significant gains in predictive accuracy and efficiency, ultimately support more robust clinical decision-making in the early identification of angina pectoris among patients with diabetes. Full article

Ultra-high-performance concrete (UHPC) is recognized for its exceptional strength and durability. However, the adoption of UHPC frequently leads to higher material and environmental costs. Accurate prediction of compressive strength is crucial for optimizing material design and reducing construction costs. In this study, a dataset of 800 samples was compiled from published articles. Four models, including random forest (RF), Gaussian Process Regression (GPR), Gradient Boosting (GB) and Artificial Neural Network (ANN), were applied. Results show that ANN and GPR achieved the best accuracy and stability. GB also performed well with good adaptability. RF captured general trends but produced larger errors in the high-strength range. Feature importance analysis highlighted curing age and cement content as the most influential factors, with a combined contribution above 65%. The water-to-binder ratio also affected strength through matrix densification. Extended evaluation with regression error characteristic (REC) curves and environmental impact index (EII) revealed the balance between performance and environmental impact. Higher compressive strength often required higher energy, CO₂, and resource use. The range of 150–250 MPa showed a better balance between performance and sustainability. This study confirms the robustness of machine learning models for strength prediction and provides guidance for green and low-carbon ultra-high-performance concrete design. Full article

This study proposes an innovative stacking ensemble learning framework for classifying faults in induction motors utilized in Electric Vehicles (EVs). Employing a comprehensive dataset comprising motor data, such as speed, torque, current, and voltage, the analysis encompasses six distinct conditions: normal operating mode, over-voltage fault, under-voltage fault, overloading fault, phase-to-phase fault, and phase-to-ground fault. The proposed model integrates Gradient Boosting (GB), K-Nearest Neighbors (KNN), Gradient Boosting (XGBoost), Support Vector Machine (SVM), Decision Tree (DT), and Random Forest (RF) algorithms in a synergistic manner. The findings reveal that the RF–GB–DT–XGBoost combination achieves a remarkable accuracy of 98.53%, significantly surpassing other methods reported in the literature. Performance is evaluated through metrics including accuracy, precision, sensitivity, and F1-score, with results analyzed in comparison to practical applications and existing studies. Validated with real-world data, this study demonstrates that the proposed model offers a groundbreaking solution for predictive maintenance systems in the EV industry, exhibiting high generalization capacity despite complex operating conditions. This approach holds transformative potential for both academic research and industrial applications. The dataset used in this study was generated using a MATLAB 2018/Simulink-based Variable Frequency Drive (VFD) model that emulates real-world EV operating conditions rather than relying solely on laboratory data. This ensures that the developed model accurately reflects practical electric vehicle environments. Full article

This paper analyzes the combined effects of acetone vapor treatment and 3D printing process parameters (layer thickness and infill rate) on the hardness and surface roughness of acrylonitrile styrene acrylate (ASA) components by using different machine learning and deep learning strategies for the first time in the technical literature. Considering the high-performance materials and aesthetic requirements of manufacturers, post-processing operations are highly critical for 3D-printed samples. ASA is a promising alternative, especially for the structural parts utilized in outdoor conditions like car outer components, electronic part housing, extreme sports equipment, and construction materials. However, it has to sustain hardness features against outer scratching, peeling, and indentations without losing its gloss. Together with the rising competitiveness in the search for a high-performance design with a perfect outer view, the combination of additive manufacturing and machine learning methods was implemented to enhance the hardness and surface quality properties for the first time in the literature. Concordantly, in this study, four different vaporizing durations (15, 45, 90, and 120 min.), three different layer thicknesses (0.1, 0.2, and 0.4 mm), and three different infill rates (25, 50, and 100%) were determined. According to both experimental and multi-way learning approaches, the results show that the support vector regressor (SVR) combined with one-dimensional convolutional neural networks (1D-CNNs) was the best approach for predictions. Gradient boosting (GB) and recurrent neural networks (RNNs) may also be preferable for low-error forecasting. Moreover, although there was a positive relationship between the layer thickness/infill rate and Shore D hardness outcomes, the highest levels were obtained at 45 min of vaporizing. Full article