p-Index From 2021 - 2026
4.564
P-Index
Claim Missing Document
Check
Articles

Found 1 Documents
Search
Journal : Journal of Geoscience, Engineering, Environment, and Technology

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 A. Syarifuddin, A. Syarifuddin Abbas, Ardiman Sudjiany Ahdani, Luthfiyah Ahmad Riva’i, Fuad Ahmad Yani Aimmah, Aisy Wildatil Akhir, Muhammad Akmal Indra Amalia, Irfa Nur Amang Sudarsono, Amang Andi Paida, Andi Anggita, Anggita Arif Widodo Arifin, Moh Aziz Asriani Asriani, Asriani Asyofi, Muhammad Nur Haris Asyrofi, Muhammad Nur Haris Azizah, Rini Azizan, Fanni Azwardi Azwardi Bangga , Abdul Taufik Bin Ikhwat, Mohamad Azwan Binti Mohd. Nasir, Fadhillah Christanto Syam Custer, Johny Dadet Pramadihanto Eko Prayitno Eko Prayitno Eko Prayitono Ekoprayitno, Ekoprayitno Fahmuddin S, Muhammad Faisal Ananda Faisal Ananda Fatchiatuzahro, Fatchiatuzahro Fitriani Fitriani Fitriani, Siti Hendra Saputra Idrus, Aderiza Cahya Ayu Restia Jannah, Muzlifatul Khairusuhada, Khairusuhada Latuf, Lingkan Haifa M Udin Harun Al Rasyid, M Udin Harun Maemonah, Maemonah Mahmud, Saifuddin Masturah, Rahmah Ma’arif, M. Samsul Milla Marlina Assegaf Mohammad WIJAYA Muhammad Arman Muhammad Danial Muhammad Rusdi dan Afritha Amelia - Nabila, Gina Nor Anisa Nordin, Mohd Nur Azmi Nuraeni, Erni Nurlina Nurlina Nurrahman - Pamenang, M. Unggul Riyanti, Agus Rizal Mz, Syamsul Rosmida, Rosmida Roziqin, M. Choirur Ruliana Saiful Falah, Saiful Samsul Huda Sarah, Huria May Sesilia Seli Shapie, Sinatu Sadiah Siswoyo, Eko Siti Rohani Sulfasyah Sulfasyah, Sulfasyah Syaari Utari, Ni’matul Aliyah Fajri W., Andri Permana Widodo, Edi Wahyu Wina Rachmawan, Irene Erlyn Zaidi Bin Othman Zain, Andicha Zulfahmi Zulfahmi