Blind Channel Estimation and Joint Symbol Detection with Data-Driven Factor Graphs

2024-01-23

arXiv.org

AI Summary

This paper addresses blind joint channel estimation and symbol detection for time-varying linear intersymbol interference (ISI) channels without pilot symbols. Method: We propose an EM-BP joint iterative framework that integrates factor graph modeling, expectation-maximization (EM), and belief propagation (BP). Key innovations include a data-driven momentum-enhanced BP update rule and a learnable EM parameter scheduling strategy, both optimized offline via small-sample training. Contribution/Results: Compared to conventional coherent BP detection, the proposed method achieves superior bit error rate (BER) performance at high signal-to-noise ratios (SNRs) while significantly reducing computational complexity. Numerical experiments demonstrate robust blind detection capability and an excellent trade-off between performance and complexity.

Technology Category

• Intelligent Robots: State Estimation
• Machine Learning: Neuro-Symbolic Learning
• Search and Optimization: Learning to Search

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

We investigate the application of the factor graph framework for blind joint channel estimation and symbol detection on time-variant linear inter-symbol interference channels. In particular, we consider the expectation maximization (EM) algorithm for maximum likelihood estimation, which typically suffers from high complexity as it requires the computation of the symbol-wise posterior distributions in every iteration. We address this issue by efficiently approximating the posteriors using the belief propagation (BP) algorithm on a suitable factor graph. By interweaving the iterations of BP and EM, the detection complexity can be further reduced to a single BP iteration per EM step. In addition, we propose a data-driven version of our algorithm that introduces momentum in the BP updates and learns a suitable EM parameter update schedule, thereby significantly improving the performance-complexity tradeoff with a few offline training samples. Our numerical experiments demonstrate the excellent performance of the proposed blind detector and show that it even outperforms coherent BP detection in high signal-to-noise scenarios.

Problem

• Channel Estimation
• Signal Reconstruction
• Blind Signal Processing

Innovation

• Factor Graphs
• Expectation Maximization Algorithm
• Belief Propagation