Distributed wavelet de-noising for sensor networks

Raymond Wagner, Véronique Delouille, Richard Baraniuk

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

17 Scopus citations


Wireless sensor networks provide a natural application area for distributed data processing algorithms. Power consumption for communication between sensor network nodes typically dominates over that for local data processing, so it is often more efficient to process data in the network than it is to send data to a remote, central collection point for analysis. Distributed wavelet analysis represents one such technique, whereby local collaboration among nodes de-correlates measurements, yielding a sparser data set with fewer significant values. This sparsity can then be leveraged to suppress errors in nodes' measurements, which are typically gathered by inexpensive sensors subject to measurement noise. In this paper, we briefly review the details of a distributed wavelet processing protocol for sensor networks based on the theory of lifting, and we develop a suite of wavelet de-noising protocols for distributed de-noising of measurements. We illustrate the effectiveness of the system with a series of numeric examples.

Original languageEnglish (US)
Title of host publicationProceedings of the 45th IEEE Conference on Decision and Control 2006, CDC
PublisherInstitute of Electrical and Electronics Engineers Inc.
Number of pages7
ISBN (Print)1424401712, 9781424401710
StatePublished - 2006
Event45th IEEE Conference on Decision and Control 2006, CDC - San Diego, CA, United States
Duration: Dec 13 2006Dec 15 2006

Publication series

NameProceedings of the IEEE Conference on Decision and Control
ISSN (Print)0743-1546
ISSN (Electronic)2576-2370


Other45th IEEE Conference on Decision and Control 2006, CDC
Country/TerritoryUnited States
CitySan Diego, CA

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Modeling and Simulation
  • Control and Optimization


Dive into the research topics of 'Distributed wavelet de-noising for sensor networks'. Together they form a unique fingerprint.

Cite this