DocumentCode :
2312325
Title :
Convolutional decoders based on artificial neural networks
Author :
Berber, Stevan M. ; Kecman, Vojislav
Author_Institution :
Sch. of Eng., Auckland Univ., New Zealand
Volume :
2
fYear :
2004
fDate :
25-29 July 2004
Firstpage :
1551
Abstract :
This paper investigates new methods of decoding convolutional codes based on neural networks. The methods are compared using BER curves obtained by simulation. New algorithms, based on iterative decoding, simulated annealing and total search, are investigated and the results obtained are presented. Both the neural network decoder and the Viterbi decoder are simulated and the bit error rates are compared. It is seen that the BER curves of the neural network decoders compare well with and even outperforms that of the decoder based on Viterbi algorithm. It was shown that the novel decoding algorithm based on total search gives the results that are comparable with or better than the results obtained by using turbo decoding techniques.
Keywords :
Viterbi decoding; convolutional codes; error statistics; iterative decoding; neural nets; search problems; simulated annealing; turbo codes; BER curves; Viterbi algorithm; Viterbi decoder; artificial neural networks; bit error rates; convolutional codes; convolutional decoders; iterative decoding algorithm; neural network decoder; simulated annealing; total search algorithm; turbo decoding techniques; Artificial neural networks; Bit error rate; Convolution; Convolutional codes; Electronic mail; Iterative algorithms; Iterative decoding; Maximum likelihood decoding; Neural networks; Viterbi algorithm;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks, 2004. Proceedings. 2004 IEEE International Joint Conference on
ISSN :
1098-7576
Print_ISBN :
0-7803-8359-1
Type :
conf
DOI :
10.1109/IJCNN.2004.1380186
Filename :
1380186
Link To Document :
بازگشت