|Signal compression by discrete recurrent neural networks
|Signal processing -- Digital techniques
Neural networks (Computer science)
Hong Kong Polytechnic University -- Dissertations
Department of Applied Mathematics
|vii, 158 leaves : ill. ; 31 cm
|The importance and demands for signal compression have been increasing abruptly, especially with the growing popularity of Internet access and personal entertainment. The speed and the ratio of compressing signal are the main concern when judging the compression algorithm. At present, two of the most popular algorithms are Fast Fourier Transform and Wavelet Transform which represent the signals as linear sum of the basic functions, by retaining a finite number of integration coefficients to achieve the goal of compression. The newest focus is on Fractal compression which try to seek the similarities in the signals such that compression can be achieved. In this project, we try to seek an algorithm which compress signals in a totally different way than the ones mentioned above. We use recurrent neural network to carry out the compression process. Signal samples were obtained from some chemical experiments such that the network can be tested without losing of generality.
|All rights reserved
Files in This Item:
|For All Users (off-campus access for PolyU Staff & Students only)
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: