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

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

研究成果: Conference contribution

3 被引用数 (Scopus)

抄録

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.

本文言語English
ホスト出版物のタイトル18th IEEE International Workshop on Signal Processing Advances in Wireless Communications, SPAWC 2017
出版社Institute of Electrical and Electronics Engineers Inc.
ページ1-5
ページ数5
ISBN(電子版)9781509030088
DOI
出版ステータスPublished - 2017 12月 19
イベント18th IEEE International Workshop on Signal Processing Advances in Wireless Communications, SPAWC 2017 - Sapporo, Japan
継続期間: 2017 7月 32017 7月 6

出版物シリーズ

名前IEEE Workshop on Signal Processing Advances in Wireless Communications, SPAWC
2017-July

Other

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

ASJC Scopus subject areas

  • 電子工学および電気工学
  • コンピュータ サイエンスの応用
  • 情報システム

フィンガープリント

「Distributed nonlinear regression using in-network processing with multiple Gaussian kernels」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル