Journal of Multiscale Materials Informatics

Variational quantum algorithm for forecasting drugs for corrosion inhibitor

2024-08-23T07:18:17+00:00

This study explores the development and evaluation of a Variational Quantum Algorithm (VQA) for predicting a drug as a corrosion inhibitor, highlighting its advantages over traditional regression models. The VQA leverages quantum-enhanced feature mapping and optimization techniques to capture complex, non-linear relationships within the data. Comparative analysis with AutoRegressive with exogenous inputs (ARX) and Gradient Boosting (GB) models demonstrate the superior performance of VQA across key metrics, including Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and Mean Absolute Deviation (MAD). The VQA achieved the lowest RMSE (4.40), MAE (3.33), and MAD (3.17) values, indicating enhanced predictive accuracy and stability. These results underscore the potential of quantum machine learning techniques in advancing predictive modeling capabilities, offering significant improvements in accuracy and consistency over classical methods. The findings suggest that VQA is a promising approach for applications requiring high precision and reliability, paving the way for broader adoption of quantum-enhanced models in material science and beyond.

Quantum support vector regression for predicting corrosion inhibition of drugs

2024-08-23T08:14:22+00:00

This study evaluates the performance of Quantum Support Vector Regression (QSVR) in predicting material properties using limited data. Experimental results show that the QSVR model consistently produces superior prediction accuracy compared to previous conventional regression models. This improvement is especially evident in the prediction accuracy for small and complex datasets, where QSVR can better capture non-linear patterns. The superiority of QSVR in processing data with a quantum approach provides great potential in developing predictive models in materials science and computational chemistry.

Enhancing School Waste Management with EcoViber Using the Waterfall Approach

2024-07-03T20:39:27+00:00

The research focuses on the development and implementation of the EcoViber application to address plastic waste management in school environments, specifically at SDN Perdopo 02. The study aims to tackle the issue of plastic waste accumulation through technological solutions, enhancing environmental awareness and operational efficiency. The application employs the waterfall method for development and features data collection, visualization, and educational tools to promote transparency and accountability. Comprehensive observations and interviews with seven teachers revealed significant improvements in waste management, with approximately 54.95 kg of plastic waste collected from January to April 2024. The findings highlight the practical implications of EcoViber in fostering a culture of environmental stewardship among school stakeholders. Despite its success, the study acknowledges potential biases in data reporting and the limited generalizability of results due to the focus on a single school. Future research should explore diverse settings and refine methodologies to enhance the scalability and long-term impact of EcoViber. Overall, the study demonstrates EcoViber's value as an innovative and effective solution for sustainable plastic waste management in educational settings.

Investigation of an amino acid compound as a corrosion inhibitor via ensemble learning

2024-06-28T03:45:53+00:00

In this study, we evaluate the performance of various machine learning models, including Random Forest (RF), Bagging (BAG), AdaBoost (ADA), Artificial Neural Network (ANN), and Support Vector Machine (SVM), using metrics such as R², Root Mean Squared Error (RMSE), and Mean Absolute Error (MAE). The results indicate that AdaBoost (ADA) achieves the highest performance with an R² of 0.999, RMSE of 2.32, and MAE of 2.24, making it the most accurate model with the smallest prediction errors. Bagging (BAG) also performs exceptionally well, with an R2 of 0.996, RMSE of 3.09, and MAE of 2.92. The Artificial Neural Network (ANN) exhibits a high R2 of 0.999, though RMSE and MAE values are not provided. Random Forest (RF) and Support Vector Machine (SVM) show good performance with R² values of 0.982 and 0.970, respectively, but are outperformed by the ensemble methods. The findings underscore the superiority of ensemble techniques, particularly AdaBoost, in achieving high predictive accuracy and minimal errors in this context.

XGBoost performance in predicting corrosion inhibition efficiency of Benzimidazole Compounds

2024-06-28T01:23:39+00:00

In this study, we compare the performance of the XGBoost model with a Support Vector Machine (SVM) model from the literature in predicting a given task. Performance metrics such as the coefficient of determination (R2), root mean squared error (RMSE), and mean absolute error (MAE) were utilized to evaluate and compare the models. The XGBoost model achieved an R² of 0.99, an RMSE of 2.54, and an MAE of 1.96, significantly outperforming the SVM model, which recorded an R² of 0.96 and an RMSE of 6.79. The scatter plot for the XGBoost model further illustrated its superior performance, showing a tight clustering of points around the ideal line (y = x), indicating high accuracy and low prediction errors. These findings suggest that the XGBoost model is highly effective for the given prediction task, likely due to its ability to capture complex patterns and interactions within the data.

Quantum Support Vector Machine for Classification Task: A Review

2024-06-26T07:32:55+00:00

Quantum computing has emerged as a promising technology capable of solving complex computational problems more efficiently than classical computers. Among the various quantum algorithms developed, the Quantum Support Vector Machine (QSVM) has gained significant attention for its potential to enhance machine learning tasks, particularly classification. This review paper explores the theoretical foundations, methodologies, and potential advantages of QSVM for classification tasks. We discuss the quantum computing principles underpinning QSVM, compare them with classical support vector machines, and review recent advancements and applications. Finally, we highlight the challenges and prospects of QSVM in the context of quantum machine learning.