Performance Evaluation and Comparison of Machine Learning Algorithms for Prediction of Electrodeposited Copper Ions

Machine learning predictions algorithms have been used in different scenarios by earlier researchers. This article found the application of these for material deposition rate copper ions through high-speed selective jet electrodeposition (HSSJED). The presented emphasizes selection best suitable machine prediction among Gaussian process regression (GPR), support vector (SVM), and linear (LR) compares them with each other algorithm which agrees experimental data. comparison performances has done taking root-mean-square error (RMSE), coefficient determination (R2), mean squared (MSE), absolute (MAE) as a basic measure same, also various graphs plotted discussed better understanding. dataset collected performing HSSJED experiment on parameters like electrolyte composition, electrode gap, applied dc potential. It that GPR are than two agree output quantitative done, results discussed.