This study explores the use of Broad Learning Systems (BLS) to predict the corrosion inhibition efficiency (CIE) of heterocyclic compounds, addressing limitations of deep neural networks (DNNs) such as vanishing gradients and computational inefficiency. BLS prioritizes network width over depth, enabling faster learning and improved generalization. Trained on quantum chemical properties (QCPs) of 192 heterocyclic compounds, BLS outperformed multilayer perceptron neural networks (MLPNN) and random forest (RF) models, achieving lower mean absolute error (MAE: 1.41), root mean square error (RMSE: 1.79), and higher R² (0.993). Predicted CIE values for quinoxaline derivatives (95.39% and 94.05%) aligned closely with experimental data. This study demonstrates the potential of BLS as an efficient, accurate, and scalable approach for predicting corrosion inhibition capabilities, contributing to advancements in corrosion science and environmentally friendly solutions.
 
Keywords - machine learning, broad learning system, neural network, corrosion.

This study explores Quantum Convolutional Neural Network (QCNN) starting from foundational quantum operations, such as the Rx gate for encoding MNIST image data into quantum states. We implemented quantum convolutional and pooling layers using one_unitary and two_unitary circuits, enabling effective feature extraction and dimensionality reduction while preserving critical information. Expressibility analysis revealed varying capabilities across different one_unitary circuits, with Rx, Ry, and Rz combinations demonstrating promising results akin to Haar random states. The proposed QCNN model exhibited robust performance metrics (accuracy: 95.98%, precision: 94.44%, recall: 96.59%, F1-score: 0.9551, AUC: 0.9604) in classification tasks, supported by efficient convergence during optimization. Future directions include expanding QCNN applications to handle more complex datasets and optimizing architectures to enhance quantum machine learning capabilities, particularly in image processing. This study underscores the potential of QCNNs in advancing quantum computing applications in neural network architectures.
 
Keywords: MNIST, classification, CNN, expressibility

This study presents a Quantum Machine Learning (QML) architecture for perfectly classifying the Iris flower dataset. The research addresses improving classification accuracy using quantum models in machine-learning tasks. The objective is to demonstrate the effectiveness of QML approaches, specifically the Variational Quantum Circuit (VQC), Quantum Neural Network (QNN), and Quantum Support Vector Machine (QSVM), in achieving high performance on the Iris dataset. The proposed methods result in perfect classification, with all models attaining accuracy, precision, recall, and an F1-score of 1.00. The main finding is that the QML architecture successfully achieves flawless classification, contributing significantly to the field. These results underscore the potential of QML in solving complex classification problems and highlight its promise for future applications across various domains. The study concludes that QML techniques can offer transformative solutions in machine learning tasks, particularly those leveraging VQC, QNN, and QSVM.

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 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.

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.

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.

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.

This comprehensive review delves into the realm of green corrosion inhibitors for iron alloys, focusing on a thorough exploration guided by data-driven investigation, density functional theory (DFT) simulations, and experimental validation. Harnessing the potential of plant extracts, this study scrutinizes their effectiveness in mitigating corrosion in iron alloys through a multi-faceted approach. By integrating computational modeling with empirical experimentation, a deeper understanding of the inhibitive mechanisms is achieved, offering insights into their practical application. The review synthesizes findings from diverse studies, elucidating the pivotal role of DFT in predicting inhibitor behavior and optimizing their performance. Furthermore, experimental validation provides crucial validation of theoretical predictions, highlighting the synergistic relationship between simulation and real-world application. Through this journey of exploration, the review underscores the promise of green corrosion inhibitors derived from natural sources, paving the way for sustainable corrosion control practices in the realm of iron alloys.

This study investigates machine learning-based quantitative structure-property relationship (QSPR) models for predicting the thermal stability of zinc metal-organic frameworks (Zn-MOF). Utilizing a dataset comprising 151 Zn-MOF compounds with relevant molecular descriptors, ridge (R) and kernel ridge (KR) regression models were developed and evaluated. The results demonstrate that the R model outperforms the KR model in terms of prediction accuracy, with the R model exhibiting exceptional performance (R² = 0.999, RMSE = 0.0022). While achieving high accuracy, opportunities for further improvement exist through hyperparameter optimization and exploration of polynomial functions. This research underscores the potential of ML-based QSPR models in predicting the thermal stability of Zn-MOF compounds and highlights avenues for future investigation to enhance model accuracy and applicability in materials science.