TY - GEN
T1 - Performance Optimization of a Slot Antenna using Bayesian Optimization
AU - Yamamoto, Shunsuke
AU - Takegami, Kohei
AU - Kanaya, Haruichi
N1 - Funding Information:
This work was partially supported by the Cabinet Office (CAO), Cross-ministerial Strategic Innovation Promotion Program (SIP), “An intelligent knowledge processing infrastructure, integrating physical and virtual domains” (NEDO) (JPNP18014), SCOPE (JP19501002), and KAKENHI (JP21K04177) JSPS.
Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - This paper presents the performance optimization of a slot antenna using Bayesian Optimization (BO). BO is an optimization technique that can obtain accurate results in a short time with a small amount of data. Two slot antennas with a simple structure for 5GHz-band are designed. The one is the reference slot antenna, which is designed by EM simulation without BO, and the other is the optimized slot antenna which is optimized using BO from the reference slot antenna. One design parameter is optimized to ensure that the optimal solution is obtained. Both the reference slot antenna and the optimized slot antenna are fabricated and tested. EM simulated and measured results have good agreement. As a consequence, the optimized slot antenna provided better antenna characteristics such as reflection coefficient than those of the reference slot antenna. Compared with another optimization technique which is the parametric analysis of the EM simulator, BO achieved reducing the number of EM simulations drastically to find the optimal value.
AB - This paper presents the performance optimization of a slot antenna using Bayesian Optimization (BO). BO is an optimization technique that can obtain accurate results in a short time with a small amount of data. Two slot antennas with a simple structure for 5GHz-band are designed. The one is the reference slot antenna, which is designed by EM simulation without BO, and the other is the optimized slot antenna which is optimized using BO from the reference slot antenna. One design parameter is optimized to ensure that the optimal solution is obtained. Both the reference slot antenna and the optimized slot antenna are fabricated and tested. EM simulated and measured results have good agreement. As a consequence, the optimized slot antenna provided better antenna characteristics such as reflection coefficient than those of the reference slot antenna. Compared with another optimization technique which is the parametric analysis of the EM simulator, BO achieved reducing the number of EM simulations drastically to find the optimal value.
UR - http://www.scopus.com/inward/record.url?scp=85126818553&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85126818553&partnerID=8YFLogxK
U2 - 10.1109/RWS53089.2022.9719898
DO - 10.1109/RWS53089.2022.9719898
M3 - Conference contribution
AN - SCOPUS:85126818553
T3 - IEEE Radio and Wireless Symposium, RWS
SP - 153
EP - 155
BT - 2022 IEEE Radio and Wireless Symposium, RWS 2022
PB - IEEE Computer Society
T2 - 2022 IEEE Radio and Wireless Symposium, RWS 2022
Y2 - 16 January 2022 through 19 January 2022
ER -