Browsing by Author "Nkouatchah, Telex Magloire Ngatched."

Now showing 1 - 2 of 2

Compound codes based on irregular graphs and their iterative decoding.
(2004) Nkouatchah, Telex Magloire Ngatched.; Takawira, Fambirai.
Low-density parity-check (LDPC) codes form a Shannon limit approaching class of linear block codes. With iterative decoding based on their Tanner graphs, they can achieve outstanding performance. Since their rediscovery in late 1990's, the design, construction, and decoding of LDPC codes as well as their generalization have become one of the focal research points. This thesis takes a few more steps in these directions. The first significant contribution of this thesis is the introduction of a new class of codes called Generalized Irregular Low-Density (GILD) parity-check codes, which are adapted from the previously known class of Generalized Low-Density (GLD) codes. GILD codes are generalization of irregular LDPC codes, and are shown to outperform GLD codes. In addition, GILD codes have a significant advantage over GLD codes in terms of encoding and decoding complexity. They are also able to match and even beat LDPC codes for small block lengths. The second significant contribution of this thesis is the proposition of several decoding algorithms. Two new decoding algolithms for LDPC codes are introduced. In principle and complexity these algorithms can be grouped with bit flipping algorithms. Two soft-input soft-output (SISO) decoding algorithms for linear block codes are also proposed. The first algorithm is based on Maximum a Posteriori Probability (MAP) decoding of low-weight subtrellis centered around a generated candidate codeword. The second algorithm modifies and utilizes the improved Kaneko's decoding algorithm for soft-input hard-output decoding. These hard outputs are converted to soft-decisions using reliability calculations. Simulation results indicate that the proposed algorithms provide a significant improvement in error performance over Chase-based algorithm and achieve practically optimal performance with a significant reduction in decoding complexity. An analytical expression for the union bound on the bit error probability of linear codes on the Gilbert-Elliott (GE) channel model is also derived. This analytical result is shown to be accurate in establishing the decoder performance in the range where obtaining sufficient data from simulation is impractical.
Performance of turbo-coded DS-CDMA systems in fading and burst channels.
(2001) Nkouatchah, Telex Magloire Ngatched.; Takawira, Fambirai.
Turbo codes are a class of forward error correction (FEC) codes that offer energy efficiencies close to the limits predicted by information theory. The features of turbo codes include parallel code concatenation, recursive convolutional encoding, nonuniform interleaving, and an associated iterative decoding algorithm. The excellent performance of turbo codes explains why much of the current research is focused on applying turbo codes to different systems. This dissertation first outlines a new simple criterion for stopping the iterative process of the turbo decoder for each individual frame immediately after the bits are correctly estimated and thus prevents unnecessary computations and decoding delay. The dissertation then considers the performance of turbo coded DS-CDMA systems. The performance analysis begins with simulation results for turbo coded DS-CDMA over a multi-path Rayleigh fading channel. The channel is then modeled using the Gilbert-Elliott channel model and analytical expressions for the performance of the system are derived. The influence of various parameters such as the Doppler frequency, the signal-to-noise ratio threshold on the system performance are analyzed and investigated.