Title :
Chaotic transmission strategies employing artificial neural networks
Author :
Muller, Andreas ; Elmirghani, Jaafar M H
Author_Institution :
Sch. of Eng., Northumbria Univ., Newcastle, UK
Abstract :
Two novel chaotic coding and decoding methods based on artificial neural networks (ANNs) are reported which employ the unimodal logistic map (LM) as an example. Coding is carried out by either modulating the LM or by generating the chaotic sequence with ANNs. In simulations speech has been coded and the resulting SNR/sub sig/ for the decoded speech has been evaluated. The results demonstrate that the two proposed methods offer a SNR/sub sig/ improvement of 4 and 20 dB over the SNR/sub sig/ obtained by using the LMS for decoding.
Keywords :
chaos; decoding; feedforward neural nets; least mean squares methods; recurrent neural nets; speech coding; LMS; SNR; artificial neural networks; chaotic coding; chaotic decoding; chaotic sequence generation; chaotic transmission; decoded speech; dynamic feedback; modulation; radial basis function; speech coding; speech simulation; unimodal logistic map; Artificial neural networks; Chaos; Chaotic communication; Decoding; Demodulation; Least squares approximation; Logistics; Modulation coding; Noise reduction; Speech analysis;
Journal_Title :
Communications Letters, IEEE
DOI :
10.1109/4234.709444
