Transfer Learning for the Behavior Prediction of Microwave Structures

Jiteng Ma; Shuping Dang; Peizheng Li; Gavin T Watkins; Kevin A Morris; Mark A Beach

doi:10.1109/LMWC.2022.3214467

Transfer Learning for the Behavior Prediction of Microwave Structures

Jiteng Ma, Shuping Dang, Peizheng Li, Gavin T Watkins, Kevin A Morris, Mark A Beach

Research output: Contribution to journal › Article (Academic Journal) › peer-review

6 Citations (Scopus)

96 Downloads (Pure)

Abstract

Microwave structures behavior prediction is an
important research topic in radio frequency (RF) design. In
recent years, deep-learning-based techniques have been widely
implemented to study microwaves, and they are envisaged to revolutionize this arduous and time-consuming work. However, empirical data collection and neural network training are two significant challenges of applying deep learning techniques to practical RF modeling and design problems. To this end, this
letter investigates a transfer-learning-based approach to improve the accuracy and efficiency of predicting microwave structure behaviors. Through experimental comparisons, we validate that the proposed approach can reduce the amount of data required for training while shortening the neural network training time for the behavior prediction of microwave structures.

Original language	English
Pages (from-to)	1-4
Number of pages	4
Journal	IEEE Microwave and Wireless Components Letters
DOIs	https://doi.org/10.1109/LMWC.2022.3214467
Publication status	Published - 26 Oct 2022

Bibliographical note

Publisher Copyright:
IEEE

Access to Document

10.1109/LMWC.2022.3214467

Full-text PDF (accepted manuscript)
This is the accepted author manuscript (AAM). The final published version (version of record) is available online via IEEE at https://ieeexplore.ieee.org/document/9930869. Please refer to any applicable terms of use of the publisher.
Accepted author manuscript, 853 KB

Handle.net

Persistent link

SWAN (Secure Wireless Agile Networks) EPSRC Prosperity Partnership
Beach, M. A. (Principal Investigator), Sandell, M. (Co-Principal Investigator), Hilton, G. (Co-Investigator), Austin, A. C. M. (Co-Investigator), Armour, S. M. D. (Co-Investigator), Haine, J. L. (Collaborator), Wales, S. W. (Collaborator), Luke, J. (Collaborator), Rogoyski, A. (Collaborator), Zhu, Z. (Collaborator), Watkins, G. T. (Collaborator), Kalokidou, V. (Researcher), Cappello, T. (Co-Investigator), Arabi, E. (Researcher), Nair, M. (Researcher), Ma, J. (Student), Wilson, S. (Student), Ozan, S. H. O. (Student), Prior, R. E. (Administrator), Xenos, E. (Student), Kayal, S. (Student), Chin, W. H. (Co-Principal Investigator) & Morris, K. A. (Co-Investigator)
1/02/20 → 31/01/25
Project: Research, Parent

Efficient Digital Power Amplifier and Learning-Based Microwave Structure Design for Future Wireless Communication Systems
Ma, J. (Author), Beach, M. (Supervisor) & Morris, K. (Supervisor), 18 Jun 2024
Student thesis: Doctoral Thesis › Doctor of Philosophy (PhD)

File

Cite this

@article{1e07516fcb0d4f618ed3b86d77e05454,

title = "Transfer Learning for the Behavior Prediction of Microwave Structures",

abstract = "Microwave structures behavior prediction is an important research topic in radio frequency (RF) design. In recent years, deep-learning-based techniques have been widely implemented to study microwaves, and they are envisaged to revolutionize this arduous and time-consuming work. However, empirical data collection and neural network training are two significant challenges of applying deep learning techniques to practical RF modeling and design problems. To this end, this letter investigates a transfer-learning-based approach to improve the accuracy and efficiency of predicting microwave structure behaviors. Through experimental comparisons, we validate that the proposed approach can reduce the amount of data required for training while shortening the neural network training time for the behavior prediction of microwave structures.",

author = "Jiteng Ma and Shuping Dang and Peizheng Li and Watkins, \{Gavin T\} and Morris, \{Kevin A\} and Beach, \{Mark A\}",

note = "Publisher Copyright: IEEE",

year = "2022",

month = oct,

day = "26",

doi = "10.1109/LMWC.2022.3214467",

language = "English",

pages = "1--4",

journal = "IEEE Microwave and Wireless Components Letters",

issn = "1531-1309",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

}

TY - JOUR

T1 - Transfer Learning for the Behavior Prediction of Microwave Structures

AU - Ma, Jiteng

AU - Dang, Shuping

AU - Li, Peizheng

AU - Watkins, Gavin T

AU - Morris, Kevin A

AU - Beach, Mark A

N1 - Publisher Copyright: IEEE

PY - 2022/10/26

Y1 - 2022/10/26

N2 - Microwave structures behavior prediction is an important research topic in radio frequency (RF) design. In recent years, deep-learning-based techniques have been widely implemented to study microwaves, and they are envisaged to revolutionize this arduous and time-consuming work. However, empirical data collection and neural network training are two significant challenges of applying deep learning techniques to practical RF modeling and design problems. To this end, this letter investigates a transfer-learning-based approach to improve the accuracy and efficiency of predicting microwave structure behaviors. Through experimental comparisons, we validate that the proposed approach can reduce the amount of data required for training while shortening the neural network training time for the behavior prediction of microwave structures.

AB - Microwave structures behavior prediction is an important research topic in radio frequency (RF) design. In recent years, deep-learning-based techniques have been widely implemented to study microwaves, and they are envisaged to revolutionize this arduous and time-consuming work. However, empirical data collection and neural network training are two significant challenges of applying deep learning techniques to practical RF modeling and design problems. To this end, this letter investigates a transfer-learning-based approach to improve the accuracy and efficiency of predicting microwave structure behaviors. Through experimental comparisons, we validate that the proposed approach can reduce the amount of data required for training while shortening the neural network training time for the behavior prediction of microwave structures.

U2 - 10.1109/LMWC.2022.3214467

DO - 10.1109/LMWC.2022.3214467

M3 - Article (Academic Journal)

SN - 1531-1309

SP - 1

EP - 4

JO - IEEE Microwave and Wireless Components Letters

JF - IEEE Microwave and Wireless Components Letters

ER -

Transfer Learning for the Behavior Prediction of Microwave Structures

Abstract

Bibliographical note

Access to Document

Handle.net

Fingerprint

Projects

SWAN (Secure Wireless Agile Networks) EPSRC Prosperity Partnership

Student theses

Efficient Digital Power Amplifier and Learning-Based Microwave Structure Design for Future Wireless Communication Systems

Cite this