A High-Quality Data Acquisition Method for Machine-Learning-Based Design and Analysis of Electromagnetic Structures

Abstract

Electromagnetic structures play a significant role in wireless communication, radar detection, medical imaging, etc. Machine learning has been increasingly applied to facilitate the design and analysis of electromagnetic structures. Data acquisition is a major bottleneck. Conventional methods blindly sweep geometric parameters on a uniform grid and acquire corresponding responses via simulation. Acquired data have unstable quality due to inconsistent informativeness of responses, leading to a low ratio of model performance to data amount. This paper proposes a high-quality data acquisition method to increase the ratio of model performance to data amount. It anticipates and generates high-quality data by analyzing distribution of existing data iteratively. Comparative analysis of four implementations proves, the proposed method reduces required data amount by around 40 % for the same model performance, hence saves around 40 % simulation and computing resources. The proposed method benefits machine learning applications of metasurfaces, antennas, and many other microwave structures.