Distributed nonlinear regression using in-network processing with multiple Gaussian kernels

Ban Sok Shin, Henning Paul, Masahiro Yukawa, Armin Dekorsy

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

In this paper, we propose the use of multiple Gaussian kernels for distributed nonlinear regression or system identification tasks by a network of nodes. By employing multiple kernels in the estimation process we increase the degree of freedom and thus, the ability to reconstruct nonlinear functions. For this, we extend the so-called KDiCE algorithm, which allows a distributed regression of nonlinear functions but uses a single kernel only, to multiple kernels. We corroborate our proposed scheme by numerical evaluations for the reconstruction of nonlinear functions both static and time-varying. We achieve performance gains for both cases, in particular for the tracking of a time-varying nonlinear function.

Original languageEnglish
Title of host publication18th IEEE International Workshop on Signal Processing Advances in Wireless Communications, SPAWC 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1-5
Number of pages5
ISBN (Electronic)9781509030088
DOIs
Publication statusPublished - 2017 Dec 19
Event18th IEEE International Workshop on Signal Processing Advances in Wireless Communications, SPAWC 2017 - Sapporo, Japan
Duration: 2017 Jul 32017 Jul 6

Publication series

NameIEEE Workshop on Signal Processing Advances in Wireless Communications, SPAWC
Volume2017-July

Other

Other18th IEEE International Workshop on Signal Processing Advances in Wireless Communications, SPAWC 2017
CountryJapan
CitySapporo
Period17/7/317/7/6

Keywords

  • Distributed regression
  • In-network processing
  • Kernel least-squares
  • Multiple kernels

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Computer Science Applications
  • Information Systems

Fingerprint Dive into the research topics of 'Distributed nonlinear regression using in-network processing with multiple Gaussian kernels'. Together they form a unique fingerprint.

Cite this