Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal Journal of Geoscience, Engineering, Environment, and Technology
Binti Mohd. Nasir, Fadhillah
Unknown Affiliation
Earth & Planetary Sciences Engineering Environmental Science Physics

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Optimization of Machine Learning Algorithms Through Outlier Data Separation for Predicting Concrete Compressive Strength Ananda, Faisal; Saputra, Hendra; Fahmi, Nurul; Prayitno, Eko; Shapie, Sinatu Sadiah; Bin Ikhwat, Mohamad Azwan; Nordin, Mohd Nur Azmi; Zain, Andicha; Binti Mohd. Nasir, Fadhillah
Journal of Geoscience, Engineering, Environment, and Technology Vol. 10 No. 02 (2025): JGEET Vol 10 No 02 : June (2025)
Publisher : UIR PRESS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25299/jgeet.2025.10.02.21896

Abstract

This study investigates the comparative performance of ten machine learning models—Linear Regression, SVM, Neural Network, Decision Tree, Random Forest, Gradient Boosting, AdaBoost, XGBoost, LightGBM, and CatBoost—in predicting concrete compressive strength. The research emphasizes practical applications in construction, where accurate predictions can improve material design and structural reliability. Through detailed evaluation using MAE, RMSE, and R² metrics, CatBoost and Linear Regression emerged as top-performing models. A rigorous hyperparameter tuning process, employing grid search, significantly enhanced models like SVM and Neural Network, increasing their R² by over 80%. However, tuning occasionally led to reduced performance due to overfitting or unsuitable parameter selection. Outlier analysis using the Z-score method revealed nuanced effects across models: while SVM and Decision Tree benefited from outlier removal, models like Neural Network and CatBoost experienced performance degradation, indicating their reliance on diverse data patterns. These findings underscore the importance of tailored tuning and outlier handling strategies. Future work will incorporate advanced optimization techniques (e.g., Bayesian optimization) and robust cross-validation to further improve model generalization and stability.
Co-Authors Bin Ikhwat, Mohamad Azwan Eko Prayitno, Eko Faisal Ananda Hendra Saputra Nordin, Mohd Nur Azmi Nurul Fahmi Shapie, Sinatu Sadiah Zain, Andicha