Modulation Classification via Gibbs Sampling Based on a Latent Dirichlet Bayesian Network

TL;DR

This paper introduces a Bayesian modulation classification method using Gibbs sampling on a latent Dirichlet Bayesian network, improving convergence and performance over existing techniques in frequency-selective fading channels.

Contribution

It presents a novel Bayesian framework employing a latent Dirichlet Bayesian network with Gibbs sampling, addressing convergence issues in modulation classification.

Findings

Improved convergence over traditional Gibbs sampling methods.

Enhanced classification accuracy in frequency-selective fading channels.

Generalizes and outperforms current state-of-the-art techniques.

Abstract

A novel Bayesian modulation classification scheme is proposed for a single-antenna system over frequency-selective fading channels. The method is based on Gibbs sampling as applied to a latent Dirichlet Bayesian network (BN). The use of the proposed latent Dirichlet BN provides a systematic solution to the convergence problem encountered by the conventional Gibbs sampling approach for modulation classification. The method generalizes, and is shown to improve upon, the state of the art.