This study evaluates the efficacy of quantum machine learning (QML) models in predicting stainless steel corrosion behaviour. Using two datasets, the quantum support vector classifier (QSVC) outperformed classical models, achieving accuracies of 95.46 % and 94.80 % for Dataset A and Dataset B, respectively. The QSVC excelled in identifying complex corrosion classes and demonstrated robust performance across diverse environments. This QML approach accurately predicts corrosion without experimental testing, saving significant time and cost. Future research will aim to include more environmental variables and steel types, broadening the model's applicability.
This study evaluates the efficacy of quantum machine learning (QML) models in predicting stainless steel corrosion behaviour. Using two datasets, the quantum support vector classifier (QSVC) outperformed classical models, achieving accuracies of 95.46 % and 94.80 % for Dataset A and Dataset B, respectively. The QSVC excelled in identifying complex corrosion classes and demonstrated robust performance across diverse environments. This QML approach accurately predicts corrosion without experimental testing, saving significant time and cost. Future research will aim to include more environmental variables and steel types, broadening the model's applicability.
Quantum Machine Learning (QML) has emerged as an interdisciplinary field that harnesses the potential of quantum computing to revolutionize classical machine learning paradigms. This paper presents a benchmarking study focused on four quantum classifier algorithms: Quantum Support Vector Classifier (QSVC), Variational Quantum Circuit (VQC), Quantum Neural Network Classifier (QNNC) and Pegasos Quantum Support Vector Classifier (PegasosQSVC). These quantum classifiers hold promise for unlocking quantum advantages in classification tasks. However, a systematic assessment of their performance across diverse datasets is yet to be fully explored. In this research study, we evaluate and compare the classification performance of quantum machine learning classifiers on various datasets (Breast Cancer, Diabetes, and Titanic) and compare them to a classical model. Our findings revealed that PegasosQSVC consistently maintained high performance across all datasets with the highest average accuracy, recall, and F1-score values of 0.81, 0.72, and 0.71, respectively, followed by VQC, followed by VQC, while QSVC and QNNC perform variably. Nevertheless, QSVC was found to balance performance and training time, achieving an average accuracy of 0.81 and a training time of 177 seconds. Overall, the classical model surpassed QML models as it was up to 10% higher in average accuracy.
Abstract Quantum machine learning (QML) leverages the potential of machine learning (ML) to explore the subtle patterns in huge datasets of complex nature with quantum advantages. QML accelerates materials research with active screening of chemical space, identifying novel materials for practical applications, and classifying structurally diverse materials given their measured properties. This study analyzes the performance of three efficient quantum machine learning algorithms viz., variational quantum classifier (VQC), quantum support vector classifier (QSVC), and quantum neural networks (QNN) for distinguishing transition metal chalcogenides (TMCs) from transitional metal oxides (TMOs). By employing feature selection, classical machine learning achieves 100% accuracy whereas QML achieves the highest performance of 99% and 98% for test and train data respectively on QSVC. Further, to extend the QML models for structural and functional analysis of materials that cannot be inferred directly from the formula, stability analysis, and magnetic nature analysis on 1000 and 500 materials are performed, respectively. The stability analysis achieves 78% accuracy with QSVC and the magnetic nature analysis achieves 88% with QNN establishing the competence of QML models. This study proves that QML models are remarkable in materials classification and analysis which fuels the task of materials discovery in the future.
Corrosion, caused by electrochemical reactions in corrosive environments, can degrade the quality and lifespan of materials, potentially leading to significant losses in various industrial sectors. One common strategy to reduce corrosion rates is by using corrosion inhibitors. A significant challenge in this field is the time-consuming and costly process of testing new corrosion inhibitors in the laboratory. Consequently, there is a need for more efficient and cost-effective methods to predict the effectiveness of potential corrosion inhibitors using machine learning techniques. This research addresses this problem by applying a quantum machine learning (QML) approach with quantum neural network (QNN) algorithms to evaluate the effectiveness of drug compounds as corrosion inhibitors. The study aims to optimize QNN models by investigating three different quantum circuit configurations to identify the most effective design. The results showed that Model-01, consisting of three layers, demonstrated the best performance with an MSE of 38.81, an RMSE of 6.23, and an MAE of 6.19, along with the shortest training time of 32 seconds, indicating an optimal balance between complexity and generalizability. Overall, this QML approach provides new insights into the predictive ability of QNN models in assessing the effectiveness of drug compounds as corrosion inhibitors, demonstrating the potential of quantum computing to enhance predictive accuracy and efficiency in investigating anti-corrosion materials
This study explores the performance of Quantum Support Vector Classifiers (QSVCs) and Quantum Neural Networks (QNNs) in comparison to classical models for machine learning tasks. By evaluating these models on the Iris and MNIST-PCA datasets, we find that quantum models tend to outperform classical approaches as the problem complexity increases. While QSVCs generally provide more consistent results, QNNs exhibit superior performance in higher-complexity tasks due to their increased quantum load. Additionally, we analyze the impact of hyperparameter tuning, showing that feature maps and ansatz configurations significantly influence model accuracy. We also compare the PennyLane and Qiskit frameworks, concluding that Qiskit provides better optimization and efficiency for our implementation. These findings highlight the potential of Quantum Machine Learning (QML) for complex classification problems and provide insights into model selection and optimization strategies
This study examines the potential of quantum machine learning (QML) to predict the corrosion inhibition capacity of expired pharmaceutical compounds. The investigation employs a QSPR model, using features generated from density functional theory (DFT) calculations as input. At the same time, corrosion inhibition efficiency (CIE) values obtained from experimental data serve as the target output. The VQC model demonstrates varied performance across evaluation metrics, especially with encoding and ansatz design. The model achieves fine scores in evaluation metrics, with root mean square error (RMSE) of 6.15, mean absolute error (MAE) of 5.63, and mean absolute deviation (MAD) of 5.50. The research underscores the significance of larger datasets for enhancing predictive accuracy and points to QML's potential in exploring anti-corrosion materials. Although there are some limitations, this study provides a foundational framework for using QML to predict anti-corrosive properties.
This research is the first of its kind to leverage the power of Quantum Machine Learning (QML) to perform multi-class classification of Cardiovascular Diseases (CVDs). We propose a novel approach that enables multi-class classification with Pegasos Quantum Support Vector Classifier (QSVC). The QSVC and the Pegasos QSVC significantly outperform the classical SVC by a margin of +10.76% and +9.72%, respectively. The paper further ventures into a quantum deep learning based architecture with a novel Quanvolutional Neural Network (QNN) implementation, outperforming the other models by achieving 97.31% accuracy, 97.41% precision, 97.31% recall, 97.30% F1 score, and 99.10% specificity.