Investigasi Model Machine Learning Regresi Pada Senyawa Obat Sebagai Inhibitor Korosi DOI Open Access

Muhammad Reesa Rosyid,

Lubna Mawaddah,

Muhamad Akrom

et al.

Jurnal Algoritma, Journal Year: 2024, Volume and Issue: 21(1), P. 332 - 342

Published: July 29, 2024

Korosi merupakan tantangan signifikan bagi daya tahan material, yang seringkali menyebabkan kerugian ekonomi besar. Penelitian ini memanfaatkan teknik Machine Learning (ML) untuk memprediksi efektivitas senyawa obat sebagai inhibitor korosi. Kami menggunakan lima algoritma ML menonjol: Regresi Linear, Support Vector Machines (SVM), K-Nearest Neighbors (KNN), Random Forest, dan XGBoost. Model-model dilatih dievaluasi dataset terdiri dari 14 fitur molekuler dengan efisiensi inhibisi korosi (IE%) variabel target. Hasil pelatihan model awal mengidentifikasi Forest XGBoost berkinerja terbaik berdasarkan metrik seperti Mean Squared Error (MSE), Root (RMSE), Absolute (MAE), R-squared (R²). Penyetelan hiperparameter lebih lanjut GridSearchCV menunjukkan bahwa XGBoost, setelah penyetelan, secara mengungguli lainnya, mencapai kesalahan terendah nilai R² tertinggi, akurasi prediktif superior aplikasi ini. Temuan menegaskan potensi ML, khususnya dalam meningkatkan pemodelan korosi, sehingga memberikan wawasan berharga bidang ilmu

A Novel Quantum-Enhanced Model Cascading Approach Based on Support Vector Machine in Blood-Brain Barrier Permeability Prediction DOI
Muhamad Akrom, Supriadi Rustad,

T. Sutojo

et al.

Materials Today Communications, Journal Year: 2025, Volume and Issue: unknown, P. 112341 - 112341

Published: March 1, 2025

Language: Английский

Citations

0
Predicting lattice constant in ABX3 perovskite via quantum machine learning DOI
Muhamad Akrom, Supriadi Rustad, Pulung Nurtantio Andono

et al.

Computational Materials Science, Journal Year: 2025, Volume and Issue: 253, P. 113865 - 113865

Published: April 7, 2025

Language: Английский

Citations

0
Machine learning for pyrimidine corrosion inhibitor small dataset DOI
Wise Herowati, Wahyu Aji Eko Prabowo, Muhamad Akrom

et al.

Theoretical Chemistry Accounts, Journal Year: 2024, Volume and Issue: 143(8)

Published: Aug. 1, 2024

Language: Английский

Citations

3
Development of a Machine Learning Model to Predict the Corrosion Inhibition Ability of Benzimidazole Compounds DOI Creative Commons

Aprilyani Nur Safitri,

Gustina Alfa Trisnapradika,

Achmad Wahid Kurniawan

et al.

Journal of Multiscale Materials Informatics, Journal Year: 2024, Volume and Issue: 1(1), P. 16 - 21

Published: April 29, 2024

The purpose of this study is to use quantitative structure-property relationship (QSPR)-based machine learning (ML) examine the corrosion inhibition capabilities benzimidazole compounds. primary difficulty in ML development creating a model with high degree precision so that predictions are correct and pertinent material's actual attributes. We assess comparison between extra trees regressor (EXT) as an ensemble decision tree (DT) basic model. It was discovered EXT had better predictive performance predicting compounds based on coefficient determination (R2) root mean square error (RMSE) metrics compared DT This method provides fresh viewpoint capacity models forecast potent inhibitors.

Language: Английский

Citations

1
A Machine Learning Model for Evaluation of the Corrosion Inhibition Capacity of Quinoxaline Compounds DOI Creative Commons
Noor Ageng Setiyanto, Harun Al Azies,

Usman Sudibyo

et al.

Journal of Multiscale Materials Informatics, Journal Year: 2024, Volume and Issue: 1(1), P. 10 - 15

Published: April 29, 2024

Investigating potential corrosion inhibitors via empirical research is a labor- and resource-intensive process. In this work, we evaluated various linear non-linear algorithms as predictive models for inhibition efficiency (CIE) values using machine learning (ML) paradigm based on the quantitative structure-property relationship (QSPR) model. quinoxaline compound dataset, our analysis showed that XGBoost model performed best predictor of other ensemble-based models. The coefficient determination (R2), mean absolute percentage error (MAPE), root squared (RMSE) metrics were used to objectively assess superiority. To sum up, study offers fresh viewpoint effectiveness in determining ability organic compounds like suppress iron surfaces.

Language: Английский

Citations

1
Ensemble Learning Model in Predicting Corrosion Inhibition Capability of Pyridazine Compounds DOI Creative Commons

Dian Arif Rachman,

Muhamad Akrom

Journal of Multiscale Materials Informatics, Journal Year: 2024, Volume and Issue: 1(1), P. 38 - 43

Published: April 29, 2024

Empirical studies of possible compound corrosion inhibitors require a lot money, time, and resources. Therefore, we used machine learning (ML) paradigm based on quantitative structure-property relationship (QSPR) models to evaluate ensemble algorithms as predictors inhibition efficiency (CIE) values. Our investigation reveals that the gradient boosting (GB) regressor model outperforms other ensemble-based models. This advantage is evaluated objectively using metrics root mean square error (RMSE), absolute (MAE), coefficient determination (R2). In summary, our research provides new perspective how well in particular ensembles work identify organic molecules such pyridazine have potential prevent surfaces metals iron its alloys.

Language: Английский

Citations

1
Harnessing Quantum SVR on Quantum Turing Machine for Drug Compounds Corrosion Inhibitors Analysis DOI Open Access

Akbar Priyo Santosa,

Muhammad Reesa,

Lubna Mawaddah

et al.

Advance Sustainable Science Engineering and Technology, Journal Year: 2024, Volume and Issue: 6(3), P. 02403013 - 02403013

Published: July 27, 2024

Corrosion is an issue that has a significant impact on the oil and gas industry, resulting in losses. This worth investigating because corrosion contributes to large part of total annual costs production companies worldwide, can cause serious problems for environment will society. The use inhibitors one way prevent quite effective. study experimental aims implement machine learning (ML) efficiency inhibitors. In this study, Quantum Support Vector Regression (QSVR) algorithm ML approach used considering increasingly developing quantum computing technology with aim producing better evaluation matrix values ​​than classical algorithm. From experiments carried out, it was found QSVR combination (TrainableFidelityQuantumKernel, ZZFeatureMap/ PauliFeatureMap, linear entanglement) obtained Root Mean Square Error (RMSE) model training time value 6,19 92 compared other models experiment which be considered predicting success research provide new insights ability computer algorithms increase predict inhibitors, especially industrial scale.

Language: Английский

Citations

1
Quantum machine learning for corrosion resistance in stainless steel DOI Creative Commons
Muhamad Akrom, Supriadi Rustad,

T. Sutojo

et al.

Deleted Journal, Journal Year: 2024, Volume and Issue: 3, P. 100013 - 100013

Published: Aug. 23, 2024

Language: Английский

Citations

1
Robust Machine Learning for Predicting Thermal Stability of Metal-Organic Framework DOI
Harun Al Azies, Muhamad Akrom, Supriadi Rustad

et al.

Chemistry Africa, Journal Year: 2024, Volume and Issue: unknown

Published: Sept. 30, 2024

Language: Английский

Citations

1
A machine learning approach for forecasting the efficacy of pyridazine corrosion inhibitors DOI
Gustina Alfa Trisnapradika,

Muhamad Akrom,

Supriadi Rustad

et al.

Theoretical Chemistry Accounts, Journal Year: 2024, Volume and Issue: 144(1)

Published: Dec. 5, 2024

Language: Английский

Citations

1