A Deep Learning Based Decoder for Concatenated Coding over Deletion Channels

TL;DR

A deep learning-based decoder designed for concatenated coding schemes over a deletion/substitution channel that uses Bidirectional Gated Recurrent Units (BI-GRUs) as log-likelihood ratio (LLR) estimators and outer code decoders for estimating the message bits.

Abstract

In this paper, we introduce a deep learning-based decoder designed for concatenated coding schemes over a deletion/substitution channel. Specifically, we focus on serially concatenated codes, where the outer code is either a convolutional or a low-density parity-check (LDPC) code, and the inner code is a marker code. We utilize Bidirectional Gated Recurrent Units (BI-GRUs) as log-likelihood ratio (LLR) estimators and outer code decoders for estimating the message bits. Our results indicate that decoders powered by BI-GRUs perform comparably in terms of error rates with the MAP detection of the marker code. We also find that a single network can work well for a wide range of channel parameters. In addition, it is possible to use a single BI-GRU based network to estimate the message bits via one-shot decoding when the outer code is a convolutional code.

Figures (8)

• Figure 1: Insertion of marker bits into the LDPC or convolutional coded bits. This case is for when $N_c = 5$, $N_m = 2$, $k/n = 0.5$, $r = 5/14$ and the two-bit marker of $[0,1]$.
• Figure 2: The block diagram for the first setup.
• Figure 3: The block diagram for the second setup.
• Figure 4: BER/FER as a function of the deletion probability for the first setup with BI-GRU as an estimator when $N_c = 5$.
• Figure 5: BER/FER as a function of the deletion probability for the first setup with BI-GRU as an estimator when $N_c = 10$..