Optimal Channel-Aware Bayesian Estimation with 1-Bit Quantization

Santosh Paudel, Hao Chen

Research output: Contribution to journalArticlepeer-review

Abstract

We address the optimal quantizer design problem for distributed Bayesian parameter estimation where each sensor quantizes its local observation into one bit and transmit it through non-ideal channels to the Fusion Center. We first develop an asymptotic performance limit (PL) as a performance bound for any quantizer design with a known prior. Aided by this PL, we derive the optimal quantizer and near optimal quantizer with set of observation models that achieves the PL, thus solve a set of optimal quantizer design problem for distributed estimation.

Original languageAmerican English
JournalElectrical and Computer Engineering Faculty Publications and Presentations
StatePublished - 1 Jan 2021

Keywords

  • Cramer-Rao lower bound
  • One-bit quantization
  • asymptotic performance limit
  • distributed Bayesian estimation
  • non-ideal channel

EGS Disciplines

  • Electrical and Computer Engineering

Fingerprint

Dive into the research topics of 'Optimal Channel-Aware Bayesian Estimation with 1-Bit Quantization'. Together they form a unique fingerprint.

Cite this