Genetic Algorithms for Turbo Codes

This paper proposes a scheme for introducing genetic algorithms (GA) into the turbo code structure to enable the systematic data to be discarded at the encoder and reconstructed at the decoder. The scheme enables code rates of frac12 to be achieved without puncturing the parity data. The paper also shows that the speed of convergence of GAs, when implemented in the proposed structure, can be used to reduce the computational overhead involved in the turbo decoder