This study aims to develop a reliable method for predicting power plant construction costs during the early planning stages using ensemble machine learning techniques. Accurate cost predictions are essential for project feasibility, and this research highlights the strength of ensemble methods in improving prediction accuracy by combining the advantages of multiple models, offering a significant improvement over traditional approaches. This investigation employed the Random Forest (RF) algorithm to estimate the overall construction cost of a power plant. The RF algorithm was contrasted with single-learner machine learning models: Support Vector Regression (SVR) and k-Nearest Neighbors (KNN). Performance measures, comprising the coefficient of determination ($R^2$), Mean Absolute Error (MAE), and Root Mean Squared Error (RMSE), were used to evaluate and contrast the performance of the implemented models. Statistical measures demonstrated that the RF approach surpassed alternative models, demonstrating the highest coefficient of determination for testing ($R^2=0.956$) and the lowest Root Mean Square Error (RMSE = 29.27) for the testing dataset. The Shapley Additive Explanation (SHAP) technique was implemented to explain the significance and impact of predictor factors affecting power plant construction costs. The outcomes of this investigation provide crucial information for project decision-makers, allowing them to reduce discrepancies in projected costs and make informed decisions at the beginning of the construction phase.

The nature of the construction business and building projects necessitates the capacity to manage extensive and intricate data and documentation. The processes for documenting, exchanging, and updating data constitute one of the principal administrative challenges being currently confronted by the construction project management. As a consequence of the continued reliance on paper-based processes evidenced in the Iraqi businesses and construction projects, a considerable volume of documentation is likely to accumulate, thereby increasing the complexity and time required for specific data to be retrieved. In this study, the Support Vector Machine (SVM) and Building Information Modeling (BIM) models were used to document projects by employing the MATLAB-Revit software. The findings demonstrate that the project timeline is also recorded because it is related to the suggested model, which is designed to produce an effective model that mimics reality. A comparative analysis of the data pertaining to the foundations, columns, walls (24 cm and 12 cm), floors, and slabs of four multi-story buildings, was conducted. This analysis was divided into three categories: estimated, SVM-BIM, and actual documentation. The findings indicated that the proposed model demonstrated a high degree of accuracy in predicting the material quantities required in building construction. These values were found to be in close proximity to, and aligned with, the actual documentation.

The global road traffic safety situation is alarming, with millions of fatalities and injuries annually, underscoring the urgent need for improved safety measures. This study examines factors influencing highway safety, prioritizing them using the Relative Importance Index (RII). Through case evaluations, expert interviews, and a 29-criteria questionnaire grouped into road, vehicle, driver, and environmental factors, key issues were identified. The most critical factors include poorly designed roads (84.2%), malfunctioning brakes (83.4%), distracted driving (82.8%), and adverse weather (80.6%). These findings highlight the necessity of addressing fundamental road safety challenges to reduce accidents and their economic impacts. Proactive measures targeting infrastructure, vehicle maintenance, driver behavior, and environmental adaptability are essential for enhancing traffic safety worldwide.