• Complex
  • Title
  • Keyword
  • Abstract
  • Scholars
  • Journal
  • ISSN
  • Conference
搜索

Author:

Liu, J. (Liu, J..) | Feng, F. (Feng, F..) | Na, W. (Na, W..) | Liu, W. (Liu, W..) | Lin, Z. (Lin, Z..) | Ma, K. (Ma, K..) | Zhang, Q.-J. (Zhang, Q.-J..)

Indexed by:

EI Scopus

Abstract:

Neuro-transfer function (neuro-TF) approaches are diffusely applied in the field of parametric modeling technology, the coefficient of the rational transfer function become more responsive to dealing with higher order problems; The sensitivity of the pole-residue transfer function keeps at a low level, but the problems of noncontinuity and non-smooth of the poles/residues will appear when the geometric dimension changes greatly. This paper applies a hybrid neuro-TF to parameterized model of a fifth-order waveguide filter to address the above problem. From the results, this method of hybrid neuro-TF can obtain better improvement in accuracy than other methods. © 2023 IEEE.

Keyword:

hybrid-based transfer function parametric extraction neural networks Waveguide filter parameterized modeling

Author Community:

  • [ 1 ] [Liu J.]Tianjin University, School of Microelectronics, Tianjin, China
  • [ 2 ] [Feng F.]Tianjin University, School of Microelectronics, Tianjin, China
  • [ 3 ] [Na W.]Beijing University of Technology, School of Information and Technology, Beijing, China
  • [ 4 ] [Liu W.]Shaanxi University of Science and Technology, College of Electrical and Information Engineering, Xian, China
  • [ 5 ] [Lin Z.]Tianjin Chengjian University, School of Control and Mechanical Engineering, Tianjin, China
  • [ 6 ] [Ma K.]Tianjin University, School of Microelectronics, Tianjin, China
  • [ 7 ] [Zhang Q.-J.]Carleton University, Department of Electronics, Ottawa, K1S5B6, ON, Canada

Reprint Author's Address:

Email:

Show more details

Related Keywords:

Source :

Year: 2023

Language: English

Cited Count:

WoS CC Cited Count:

SCOPUS Cited Count:

ESI Highly Cited Papers on the List: 0 Unfold All

WanFang Cited Count:

Chinese Cited Count:

30 Days PV: 1

Affiliated Colleges:

Online/Total:812/10615521
Address:BJUT Library(100 Pingleyuan,Chaoyang District,Beijing 100124, China Post Code:100124) Contact Us:010-67392185
Copyright:BJUT Library Technical Support:Beijing Aegean Software Co., Ltd.