TUHH Open Research
Help
  • Log In
    New user? Click here to register.Have you forgotten your password?
  • English
  • Deutsch
  • Communities & Collections
  • Publications
  • Research Data
  • People
  • Institutions
  • Projects
  • Statistics
  1. Home
  2. TUHH
  3. Publication References
  4. Modeling electrically long interconnects using physics-informed delayed gaussian processes
 
Options

Modeling electrically long interconnects using physics-informed delayed gaussian processes

Publikationstyp
Journal Article
Date Issued
2023-12-01
Sprache
English
Author(s)
Garbuglia, Federico
Reuschel, Torsten  
Theoretische Elektrotechnik E-18  
Schuster, Christian  
Theoretische Elektrotechnik E-18  
Deschrijver, Dirk  
Dhaene, Tom
Spina, Domenico  
TORE-URI
https://hdl.handle.net/11420/44275
Journal
IEEE transactions on electromagnetic compatibility  
Volume
65
Issue
6
Start Page
1715
End Page
1723
Citation
IEEE Transactions on Electromagnetic Compatibility 65 (6): 1715-1723 (2023-12)
Publisher DOI
10.1109/TEMC.2023.3317917
Scopus ID
2-s2.0-85173004790
Publisher
IEEE
This work presents a machine learning technique to model wide-band scattering parameters (S-parameters) of interconnects in the frequency domain using a new Gaussian processes (GP) model. Standard GPs with a general-purpose kernel typically assume high smoothness and therefore are not suitable to model S-parameters that are highly dynamic and oscillating due to propagation delays. The new delayed Gaussian process (<inline-formula><tex-math notation="LaTeX">$\tau$</tex-math></inline-formula>GP) model employs a physics-informed kernel consisting of periodic components, whose fundamental frequencies are interpreted as tunable propagation delays. Then, the model hyperparameters are tuned using a combination of maximum marginal likelihood estimation (MMLE) and delay estimation using Gabor transform. The delay estimation allows one to automatically identify the optimal fundamental frequencies for the kernel, thus increasing the numerical stability of the hyperparameters tuning process. The resulting delayed Gaussian process model accurately predicts the S-parameter values at desired frequency points in the training interval. Two application examples demonstrate the increased accuracy of the new technique, compared to standard Gaussian processes, vector fitting (VF), and delayed vector fitting (DVF) rational models.
Subjects
Computational modeling
Data models
Delay estimation
Estimation
Gabor transform
Gaussian processes (GP)
interconnects
Kernel
kernels
machine learning (ML)
Propagation delay
Scattering parameters
S-parameters
Transforms
MLE@TUHH
DDC Class
004: Computer Sciences
TUHH
Weiterführende Links
  • Contact
  • Send Feedback
  • Cookie settings
  • Privacy policy
  • Impress
DSpace Software

Built with DSpace-CRIS software - Extension maintained and optimized by 4Science
Design by effective webwork GmbH

  • Deutsche NationalbibliothekDeutsche Nationalbibliothek
  • ORCiD Member OrganizationORCiD Member Organization
  • DataCiteDataCite
  • Re3DataRe3Data
  • OpenDOAROpenDOAR
  • OpenAireOpenAire
  • BASE Bielefeld Academic Search EngineBASE Bielefeld Academic Search Engine
Feedback