Signal Codes
Information Theory
2016-11-18 v1 math.IT
Abstract
Motivated by signal processing, we present a new class of channel codes, called signal codes, for continuous-alphabet channels. Signal codes are lattice codes whose encoding is done by convolving an integer information sequence with a fixed filter pattern. Decoding is based on the bidirectional sequential stack decoder, which can be implemented efficiently using the heap data structure. Error analysis and simulation results indicate that signal codes can achieve low error rate at approximately 1dB from channel capacity.
Cite
@article{arxiv.0806.4773,
title = {Signal Codes},
author = {Ofir Shalvi and Naftali Sommer and Meir Feder},
journal= {arXiv preprint arXiv:0806.4773},
year = {2016}
}
Comments
Submitted to IEEE Transactions on Information Theory