Login | Register

A multistage scheduled decoder for short block length low-density parity-check codes

Title:

A multistage scheduled decoder for short block length low-density parity-check codes

Elhami-Khorasani, Nazanin (2007) A multistage scheduled decoder for short block length low-density parity-check codes. Masters thesis, Concordia University.

[img]
Preview
Text (application/pdf)
MR28914.pdf - Accepted Version
4MB

Abstract

Recent advances in coding theory have uncovered the previously forgotten power of Low-Density Parity-Check (LDPC) codes. Their popularity can be related to their relatively simple iterative decoders and their potential to achieve high performance close to shannon limit. These make them an attractive candidate for error correcting application in communication systems. In this thesis, we focus our research on the iterative decoding algorithms for Low-Density Parity-Check codes and present an improved decoding algorithm. First, the graph structure of LDPC codes is studied and a graph-based search algorithm to find the shortest closed walk and shortest cycle for each node of the graph is proposed. Then, the Deterministic schedule is applied on nodes of the graph with the objective of preserving the optimality of the algorithms. Finally, Hybrid Switch-Type technique is applied on the improved algorithms to provide a desirable complexity/performance trade-off. Hybrid Technique and Deterministic schedule are combined for decoding regular and irregular LDPC codes. The performance and complexity of the decoder is studied for Sum-Product and Gallager A algorithms. The result is a flexible decoder for any available LDPC code and any combination of decoding algorithms based on the communication systems need. In this technique, we benefit the high performance of soft-decision algorithms and low complexity of hard-decision algorithms by changing the decoding rule after a few iterations. Hence, a desirable performance can be obtained with less average number of soft iterations. Moreover, all the nodes do not update messages in each iteration. As a result, the total number of computations is reduced considerably

Divisions:Concordia University > Gina Cody School of Engineering and Computer Science > Electrical and Computer Engineering
Item Type:Thesis (Masters)
Authors:Elhami-Khorasani, Nazanin
Pagination:xvi, 86 leaves : ill. ; 29 cm.
Institution:Concordia University
Degree Name:M.A. Sc.
Program:Electrical and Computer Engineering
Date:2007
Thesis Supervisor(s):Shayan, Yousef R.
ID Code:975270
Deposited By: Concordia University Library
Deposited On:22 Jan 2013 16:05
Last Modified:18 Jan 2018 17:40
Related URLs:
All items in Spectrum are protected by copyright, with all rights reserved. The use of items is governed by Spectrum's terms of access.

Repository Staff Only: item control page

Downloads per month over past year

Back to top Back to top