Abstract
In this paper, we investigate the application of Machine Learning (ML) methods in Electromagnetics (EM) design through an illustrative example. Particularly, we show how ML techniques can significantly reduce the need for costly and resource hungry consuming full wave EM simulations by calculating accurate surrogate models using manageable count of EM full wave simulations. Three machine learning methods that are more suitable for antenna and EM applications, i.e., modified linear regression, Gaussian process and Support Vector Regression are applied to a particular problem and accurate models with only few percent prediction error are obtained using a small dataset. More interestingly, we show the surrogate models can successfully predict for the unseen data with only few percent degradation in accuracy.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
