Full metadata record
| DC Field | Value | Language |
|---|---|---|
| dc.contributor | Multi-disciplinary Studies | en_US |
| dc.creator | Wong, Yiu-wah | - |
| dc.identifier.uri | https://theses.lib.polyu.edu.hk/handle/200/4233 | - |
| dc.language | English | en_US |
| dc.publisher | Hong Kong Polytechnic University | - |
| dc.rights | All rights reserved | en_US |
| dc.title | Neural network aided soft decision decoding of block codes | en_US |
| dcterms.abstract | Block decoding algorithms and convolutional decoding algorithms have been devised to operate with hard or soft decisions. However, soft-decision decoding is generally not used with block codes because it is considerably more difficult than hard-decision decoding to implement. Therefore, block codes are usually implemented with hard-decision decoders. Due to the complexity of block code soft-decision decoder, the implementation the block code soft-decision decoder based on neural network techniques will be attempted. There are many applications of neural networks in the area of soft decision decoding. In [5], the work presented assures us that we can use backpropagation as the training method for implementing soft decision decoder of block codes. In this dissertation, the concept of neural network aided soft decision decoding (NND) for block codes is presented. The architecture and algorithm for training a network by backpropagation has been investigated. The best suited modification that can be made to the training algorithm and meets the needs of soft decision decoder is implemented. The modifications involve changes to momentum parameter μ, steepness parameter σ and size of hidden neurons. Simulations have been performed that realize the theory and demonstrate the ability of neural networks to act as soft-decision decoder for block codes. Experimental results show that the performance of the neural network aided soft-decision decoder approaches that of maximum likelihood decoder. On the other hand, smaller steepness parameter and larger momentum parameter can reduce the training time. According to the simulation results, the training time can be reduced dramatically to a much smaller number of epochs from the required number of epoch with an acceptable performance. | en_US |
| dcterms.extent | vi, 99 leaves : ill. ; 31 cm | en_US |
| dcterms.isPartOf | PolyU Electronic Theses | en_US |
| dcterms.issued | 1997 | en_US |
| dcterms.educationalLevel | All Master | en_US |
| dcterms.educationalLevel | M.Sc. | en_US |
| dcterms.LCSH | Data transmission systems | en_US |
| dcterms.LCSH | Coding theory | en_US |
| dcterms.LCSH | Decoders (Electronics) | en_US |
| dcterms.LCSH | Neural networks (Computer science) | en_US |
| dcterms.LCSH | Hong Kong Polytechnic University -- Dissertations | en_US |
| dcterms.accessRights | restricted access | en_US |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| b12505067.pdf | For All Users (off-campus access for PolyU Staff & Students only) | 3.04 MB | Adobe PDF | View/Open |
Copyright Undertaking
As a bona fide Library user, I declare that:
- I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
- 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.
- 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.
Please use this identifier to cite or link to this item:
https://theses.lib.polyu.edu.hk/handle/200/4233