Search

It is a promising technology to replace traditional transceiver design with neural network (NN)-based autoencoder to realize end-to-end communication. The joint optimization of multiple blocks helps the communication system to achieve better performance. However, this approach needs a differentiable channel modeling to train both NNs at the transceiver. For a non-differentiable channel in a real scenario, gradient backpropagation cannot be performed. In this paper, we propose a Kalman-based autoencoder framework to achieve gradient estimation and backpropagation by adding a control layer at the last layer of the encoder NN, which combines the rich feature representations learned by the NN with the Bayesian filter method based on Extended Kalman Filter (EKF) and Cubature Kalman Filter (CKF). According to simulation results, the proposed framework has a fast convergence rate and strong robustness in both additive white Gaussian noise (AWGN) and Rayleigh block fading (RBF) of perturbation scenarios.

In this letter, we construct rate compatible polar codes via polarizing matrix extension, to support efficient adaptive incremental redundancy hybrid automatic repeat request (IR-HARQ) protocol. We show that an arbitrary number of incremental coded bits can be generated by extending the polarizing matrix, such that multiple retransmissions are aggregated to produce a longer polar code with extra coding gain. This coding gain is maximized by selecting the most reliable bit channels in the extended codes, rather than the shorter codes, as information bits. Naturally, some information bits are transferred from the shorter part to the extended part for higher bit channel reliability. One-to-one parity-checking between the two parts lends itself well to the above purpose during the construction of the longer code. Simulation results demonstrate consistent coding gain over the chase combining HARQ scheme.

This paper investigates the impact of pilot sequences on the digital self-interference cancellation (SIC) in full-duplex systems. Nonlinearity may be introduced to the self-interference (SI) signal by the circuits, especially the high power amplifier, which needs to be modeled and estimated for SIC. Applying the parallel Hammerstein model, the nonlinearity and the multipath channels are jointly estimated based on pilot sequence. By implementing the Pseudo-Noise (PN) and Zadoff-Chu (ZC) sequences, we evaluate the estimation accuracy and SIC performance. In addition, the impact of the power misalignment between the pilot and the data is studied. The results suggest that the SI can be almost completely removed with both PN and ZC sequences when the transmit power is low. However, with high transmit power where the nonlinearity effect is more severe, the PN sequence outperforms the ZC sequence due to their different nonlinearity behaviors. Then, by comparing different power level settings, we show that the best strategy for digital cancellation is to set the transmit powers of the pilot and the data be approximately the same.

A special permutation group of polar codes based on $N$ /4-cyclic shift is designed and analyzed for practical use. A permutation-transformation equivalence is firstly introduced to transfer the effect of permutation on the codeword side to the uncoded side. Then, we introduce the $N$ /4-cyclic shift permutation and analyze the conditions under which it can permute a codeword to another for polar codes that even do not fully respect partial order. We also reveal that the value assignment of frozen bits should follow specific rules related to the permutation pattern. Finally, a novel polar-specific implicit indication method is presented by applying the $N$ /4-cyclic shift permutation group to the practical wireless communication scenarios such as Physical Broadcasting Channel (PBCH) of a cellular network, which significantly simplifies the detection algorithm.

In this paper, we propose a comprehensive Polar coding solution that integrates reliability calculation, rate matching and parity-check coding. Judging a channel coding design from the industry's viewpoint, there are two primary concerns: (i) low-complexity implementation in application-specific integrated circuit (ASIC), and (ii) superior \& stable performance under a wide range of code lengths and rates. The former provides cost- \& power-efficiency which are vital to any commercial system; the latter ensures flexible and robust services. Our design respects both criteria. It demonstrates better performance than existing schemes in literature, but requires only a fraction of implementation cost. With easily-reproducible code construction for arbitrary code rates and lengths, we are able to report "1-bit" fine-granularity simulation results for thousands of cases. The released results can serve as a baseline for future optimization of Polar codes., The work was first disclosed in 2016 as a technical contribution to 3GPP and accepted by IEEE ICC 2018. Part of the proposed design has been adopted by 3GPP as the Polar coding standards for 5G