TY - JOUR
T1 - Bayesian Inspired Sampling for Efficient Machine Learning Assisted Microwave Component Design
AU - Zhou, Zhao
AU - Wei, Zhaohui
AU - Ren, Jian
AU - Sun, Yu-Xiang
AU - Yin, Yingzeng
AU - Pedersen, Gert Frølund
AU - Shen, Ming
PY - 2024/2/1
Y1 - 2024/2/1
N2 - Machine learning (ML) has demonstrated significant potential in accelerating the design of microwave components owing to its great ability to approximate the projection between geometric parameters and electromagnetic (EM) responses. A well-trained ML model can predict the EM responses of a microwave component with unseen geometric parameter settings accurately, or determine the parameter settings based on desired EM constraints in a matter of milliseconds. However, this ML-based design process often requires heavy simulation to collect a large amount of training data. To mitigate this issue, this article proposes an efficient Bayesian-inspired sampling-assisted ML method for the design of microwave components. In contrast to typical ML-based design methods which use uniform and arbitrary sampling to extensively represent the entire parameter space, necessitating intensive simulation for generating training data, the proposed Bayesian-inspired sampling strategy efficiently represents the entire parameter space by recognizing and emphasizing more promising parameter settings. This is achieved by defining a Bayesian-based expression for evaluating the probability of the outcome of adding a new data sample in a specific parameter area. During each iteration of the design process, new data is always added in the area with the highest probability of beneficial outcomes. Therefore, it optimizes the distribution of training data and reduces the amount of required training data and simulations. Results from three design case studies demonstrate that the proposed method can significantly reduce the number of required data and simulation by around 40% for the same model performance. This validates that the proposed Bayesian-inspired sampling-aided ML method significantly improves overall efficiency.
AB - Machine learning (ML) has demonstrated significant potential in accelerating the design of microwave components owing to its great ability to approximate the projection between geometric parameters and electromagnetic (EM) responses. A well-trained ML model can predict the EM responses of a microwave component with unseen geometric parameter settings accurately, or determine the parameter settings based on desired EM constraints in a matter of milliseconds. However, this ML-based design process often requires heavy simulation to collect a large amount of training data. To mitigate this issue, this article proposes an efficient Bayesian-inspired sampling-assisted ML method for the design of microwave components. In contrast to typical ML-based design methods which use uniform and arbitrary sampling to extensively represent the entire parameter space, necessitating intensive simulation for generating training data, the proposed Bayesian-inspired sampling strategy efficiently represents the entire parameter space by recognizing and emphasizing more promising parameter settings. This is achieved by defining a Bayesian-based expression for evaluating the probability of the outcome of adding a new data sample in a specific parameter area. During each iteration of the design process, new data is always added in the area with the highest probability of beneficial outcomes. Therefore, it optimizes the distribution of training data and reduces the amount of required training data and simulations. Results from three design case studies demonstrate that the proposed method can significantly reduce the number of required data and simulation by around 40% for the same model performance. This validates that the proposed Bayesian-inspired sampling-aided ML method significantly improves overall efficiency.
KW - Bayes methods
KW - Bayesian
KW - Data models
KW - Microwave FET integrated circuits
KW - Microwave communication
KW - Microwave integrated circuits
KW - Microwave theory and techniques
KW - Training data
KW - machine learning (ML)
KW - microwave components
KW - sampling strategy
KW - simulation data
UR - http://www.scopus.com/inward/record.url?scp=85166772898&partnerID=8YFLogxK
U2 - 10.1109/TMTT.2023.3298194
DO - 10.1109/TMTT.2023.3298194
M3 - Journal article
SN - 0018-9480
VL - 72
SP - 996
EP - 1007
JO - I E E E Transactions on Microwave Theory and Techniques
JF - I E E E Transactions on Microwave Theory and Techniques
IS - 2
ER -