Author: Chan, Chong-fun
Title: Soft decision decoding using neural networks
Degree: M.Sc.
Year: 2000
Subject: Coding theory
Decoders (Electronics)
Neural networks (Computer science)
Hong Kong Polytechnic University -- Dissertations
Department: Multi-disciplinary Studies
Department of Electronic and Information Engineering
Pages: v, 92 leaves : ill. ; 30 cm
Language: English
Abstract: The advantage of soft decision decoding over the hard decision decoding is well known. Soft decision decoding of convolutional codes using Viterbi algorithm has low complexity, but it is not true for block codes. The neural network is used to aid the implementation of soft decision decoder of block codes. The concept and algorithm for training a network is presented. In this dissertation, a decoder which first implements the hard decision decoding of block codes, second, a procedure (called Decision Maker) tests to see if that result matches the result of soft decision decoding and third the neural network is used to implement the soft decision decoding if a match is not found. The advantage of the test procedure is that if the hard decision decoding result is good enough then the computation effort is greatly reduced. The generalization capability and storage capability of neural network are exploited to aid the soft decision decoder of block codes. Backpropagation networks are successfully trained for the binary Hamming (7,4) code and (9,5) code. Simulation results show that the performance of the decoder with Decision Maker and neural network approaches that of the maximum likelihood decoder over a wide range of signal to noise rations.
Rights: All rights reserved
Access: restricted access

Files in This Item:
File Description SizeFormat 
b15383568.pdfFor All Users (off-campus access for PolyU Staff & Students only)2.88 MBAdobe PDFView/Open

Copyright Undertaking

As a bona fide Library user, I declare that:

  1. I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
  2. I will use the Database for the purpose of my research or private study only and not for circulation or further reproduction or any other purpose.
  3. I agree to indemnify and hold the University harmless from and against any loss, damage, cost, liability or expenses arising from copyright infringement or unauthorized usage.

By downloading any item(s) listed above, you acknowledge that you have read and understood the copyright undertaking as stated above, and agree to be bound by all of its terms.

Show full item record

Please use this identifier to cite or link to this item: