In order to solve high encoding complexities of irregu-lar low-density parity-check (LDPC) codes, a deterministic con-struction of irregular LDPC codes with low encoding complexities is proposed. The encoding algorithms are designed, whose com-plexities are linear equations of code length. The construction and encoding algorithms are derived from the effectively encoding characteristics of repeat-accumulate (RA) codes and masking technique. First, the new construction modifies parity-check ma-trices of RA codes to eliminate error floors of RA codes. Second, the new constructed parity-check matrices are based on Vander-monde matrices; this deterministic algebraic structure is easy for hardware implementation. Theoretic analysis and experimental results show that, at a bit-error rate of 10 × 10- 4, the new codes with lower encoding complexities outperform Mackay's random LDPC codes by 0.4-0.6 dB over an additive white Gauss noise (AWGN) channel.
This paper presents a matrix permuting approach to the construction of Low-Density Parity-Check (LDPC) code. It investigates the structure of the sparse parity-check matrix defined by Gallager. It is discovered that the problem of constructing the sparse parity-check matrix requires an algorithm that is efficient in search environments and also is able to work with constraint satisfaction problem. The definition of Q-matrix is given, and it is found that the queen algorithm enables to search the Q-matrix. With properly permuting Q-matrix as sub-matrix, the sparse parity-check matrix which satisfied constraint condition is created, and the good regular-LDPC code that is called the Q-matrix LDPC code is generated. The result of this paper is significant not only for designing low complexity encoder, improving performance and reducing complexity of iterative decoding arithmetic, but also for building practical system of encodable and decodable LDPC code.
