A protograph low-density parity-check (P-LDPC) code-based lossy coding system is proposed for compressing the Gaussian mixture model source, as a particular case of shipping transportation systems. The compression performance is benchmarked against the rate-distortion bounds for this source. Some effective methods are developed to improve both the encoder and the decoder to reduce the compression distortion. Experimental results demonstrate that the proposed methods achieve good performance while maintaining low complexity.

A lossy source coding system based on the protograph low-density parity-check (P-LDPC) code is proposed for Gaussian source compression. In the proposed system, the conventional belief propagation (BP) algorithm is modified to be a concatenated BP-inverse BP (BP-$i$BP) for encoding and decoding, where the$i$BP is constructed by a fully-connected layer of a neural network. Compared to the existing approximate message passing algorithm, the proposed BP-$i$BP realizes a float-to-bit compression with low complexity for arbitrary Gaussian sources. The BP-$i$BP is implemented based on the linking relation of the protograph; therefore, it is necessary to optimally design the protograph to obtain better rate-distortion function (RDF) performance. Regarding the coding optimal procedure, a mutual information iteration convergence (MIIC) algorithm is designed as the optimal criterion to determine the source P-LDPC code with minimum distortion. Inspired by the plane construction of quantum stabilizer code, a lattice topological splicing (LTS) algorithm is proposed for regularly building the protograph to reduce the code searching complexity. By using the MIIC and the LTS algorithms, the BP-$i$BP based on the designed P-LDPC code maintains good distortion performance close to the RDF limit.

The joint source channel coding (JSCC) system is sensitive to the changing channel characteristics, because the optimally designed source-channel code pair always needs to be redesigned when the transmission environment is updated. A solution is to seek a common code pair for variable channels. Channel model 3 (CM3) is a variable on-body channel following the Weibull distribution, which is analyzed in four conditions due to varying shape factors, namely with exponential, Rayleigh, log-normal and normal distributions. The JSCC system is considered in this paper based on double protograph low-density parity-check (DP-LDPC) code pair over the variable CM3 channel. Firstly, four DP-LDPC code pairs are searched by the conventional differential evolution (DE) algorithm with four distributions of the Weibull model, respectively. However, these four code pairs only present good bit-error ratio performance in their own distribution, and have error floors in the other three. To resolve the problem, an artificial intelligence method based on principle component analysis (PCA) algorithm is designed to extract the common code pair. It is demonstrated that the common code pair performs well in noise-varying and practical-parameter transmissions. Instead of four DE code pairs, the designed one PCA code pair provides a strong technical support to low-complexity manufacturing such as eHealthcare.