On the decoding of convolutional codes using genetic algorithms

In this paper, we deal with decoding of convolutional codes using artificial intelligence techniques. A comparison of our decoder versus the Viterbi decoder in terms of performance and computing complexity is given. The simulation results show that the genetic algorithms based decoder (GAD) outperforms the Viterbi decoders. Furthermore the computing complexity of GAD is better for codes with large lengths. The good results obtained by GAD for systematic convolutional codes make it more attractive.

[1]  Faissal El Bouanani,et al.  Comparaison des decodeurs de Chase, l'OSD et ceux bases sur les algorithmes genetiques , 2007 .

[2]  C. Hartmann,et al.  Efficient Maximum-Likelihood Soft-Decision Decoding of Linear Block Codes Using Algorithm A* , 1993, Proceedings. IEEE International Symposium on Information Theory.

[3]  L. Hebbes,et al.  Genetic Algorithms for Turbo Codes , 2005, EUROCON 2005 - The International Conference on "Computer as a Tool".

[4]  N. Durand,et al.  Turbo codes optimization using genetic algorithms , 1999, Proceedings of the 1999 Congress on Evolutionary Computation-CEC99 (Cat. No. 99TH8406).

[5]  Yuen-Hsien Tseng,et al.  Neural Network Decoders for Linear Block Codes , 2002, Int. J. Comput. Eng. Sci..

[6]  A. Glavieux,et al.  Near Shannon limit error-correcting coding and decoding: Turbo-codes. 1 , 1993, Proceedings of ICC '93 - IEEE International Conference on Communications.

[7]  Rüdiger L. Urbanke,et al.  Modern Coding Theory , 2008 .

[8]  J. Bibb Cain,et al.  Error-Correction Coding for Digital Communications , 1981 .

[9]  Kishan G. Mehrotra,et al.  Genetic Algorithms for Soft-Decision Decoding of Linear Block Codes , 1994, Evolutionary Computation.