A Puncturing Algorithm for Mixing 2-Kernel and 3-Kernel Polar Codes

In this paper, a puncturing algorithm for mixing 2-kernel and 3-kernel polar codes is presented. The puncturing sequence is generated based on the capacity of channels and the upper bound of minimum block error probability for successive cancellation (SC) decoding. We use the capacity-zero puncturing model, the decoding algorithm of mother codes can still be adopted. An improved greedy algorithm of computing the maximization of the minimum distance is proposed to select the information set. The maximum number of punctured bits is limited to \([1,{{2}^{n-2}})\) when the length of subcodes \(M\in (2^{n-2}*3,2^n)\). Simulation results show that the block error rate based on the mixing kernels is better than that based on 2-kernel.