Stacking Machine Learning Models using Factor Analysis to Predict the Output Laser Power

Machine learning is an intensively evolving field of artificial intelligence with applications in all areas where data from observations and experiments are accumulated. In this study, for the first time, a new approach is developed to combine the predictions of several diverse machine learning models based on the stacked generalization paradigm. A new framework for stacking the models using exploratory factor analysis has been proposed. The approach is demonstrated for predicting the output laser electric power of a copper bromide vapor laser. The achieved results show the superiority of the constructed stacked model compared to the single base models.