An Effective Method for Antenna Optimization Using Attention-based LSTM

Peng Wang, Menglin Zhai*, Demin Li, Rui Pei, Lei Zhang

*Corresponding author for this work

Research output: Chapter in Book or Report/Conference proceedingConference Proceedingpeer-review

Abstract

This paper proposes an optimization design of a dual-band antenna at GSM1800 (1.8 GHz) and ISM bands (2.45 GHz) with an Attention-base Long Short-Term Memory (ALSTM) neural network method. By taking the antenna performance indexes as the input and the corresponding geometric variables as the output, the proposed A-LSTM can improve the efficiency of machine learning-assisted optimization on antenna design. The experimental results show that the error of A-LSTM is lower than that of traditional artificial neural network (ANN), and its optimized antenna has better performance.

Original languageEnglish
Title of host publication2022 International Conference on Microwave and Millimeter Wave Technology, ICMMT 2022 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781665467520
DOIs
Publication statusPublished - 2022
Externally publishedYes
Event14th International Conference on Microwave and Millimeter Wave Technology, ICMMT 2022 - Harbin, China
Duration: 12 Aug 202215 Aug 2022

Publication series

Name2022 International Conference on Microwave and Millimeter Wave Technology, ICMMT 2022 - Proceedings

Conference

Conference14th International Conference on Microwave and Millimeter Wave Technology, ICMMT 2022
Country/TerritoryChina
CityHarbin
Period12/08/2215/08/22

Fingerprint

Dive into the research topics of 'An Effective Method for Antenna Optimization Using Attention-based LSTM'. Together they form a unique fingerprint.

Cite this