Adaptive Period Estimation For Sparse Point Processes

Hans-Peter Bernhard, Andreas Springer

Publikation: Konferenzband/Beitrag in Buch/BerichtKonferenzartikelBegutachtung

Abstract

In this paper, adaptive period estimation for time varying sparse point processes is addressed. Sparsity results from signal loss, which reduces the number of samples available for period estimation. We discuss bounds and minima of the mean square error of fundamental period estimation suitable in these situations. A ruleset is derived to determine the optimum memory length which achieves the minimum estimation error. The used low complex adaptive algorithm operates with variable memory length N to fit optimally for the recorded time varying process. The algorithm is of complexity 3O(N), in addition to that the overall complexity is reduced to 3O(1), if a recursive implementation is applied. This algorithm is the optimal implementation candidate to keep synchronicity in industrial wireless sensor networks operating in harsh and time varying environments.
OriginalspracheEnglisch
Titel2018 IEEE Statistical Signal Processing Workshop (SSP)
Herausgeber (Verlag)IEEE Computer Society
Seiten593-597
Seitenumfang5
ISBN (Print)978-1-5386-1572-0
DOIs
PublikationsstatusVeröffentlicht - 13 Juni 2018
Extern publiziertJa
Veranstaltung2018 IEEE Statistical Signal Processing Workshop (SSP) - Freiburg im Breisgau, Germany
Dauer: 10 Juni 201813 Juni 2018

Publikationsreihe

Name2018 IEEE Statistical Signal Processing Workshop (SSP)

Konferenz

Konferenz2018 IEEE Statistical Signal Processing Workshop (SSP)
Zeitraum10/06/1813/06/18

Fingerprint

Untersuchen Sie die Forschungsthemen von „Adaptive Period Estimation For Sparse Point Processes“. Zusammen bilden sie einen einzigartigen Fingerprint.

Dieses zitieren