10 March 2022 in IEEE Communications Letters
A deep learning (DL)-based detector utilizing the Transformer framework is proposed for orthogonal frequency-division multiplexing with index modulation (OFDM-IM) systems, termed as TransIM. Concretely, TransIM adopts a two-step detection method. First, the neural networks with the Transformer block as the core provide soft probabilities of different transmitted symbols. Then, conventional signal detection methods are performed based on those probabilities to make final decisions. This method is verified to improve system error performance significantly, albeit at the cost of slightly increased complexity. Simulation results indicate that the proposed TransIM detector fares better than existing DL-based ones regarding bit error rate (BER) performance.
25 March 2021 in IEEE Transactions on Signal Processing
In this paper, we propose a framework to attain the integrated design of polar coding and spatial modulation (SM) such that the performance of coded SM-MIMO system can be efficiently improved. This Polar-SM framework recognizes SM and polar coding from a unified perspective of polarization by which the original SM-MIMO channel is split into a series of bit polarized subchannels under the three-stage channel transform, i.e., index-symbol→modulation→bit partitions. This paradigm exploits the underlying weak polarization effect within the SM signal, then concatenates with the binary polarization in polar coding, forming a signal-coding cascaded polarization framework. In particular, the first stage channel transform serially decomposes the original SM-MIMO channel into the index subchannel and the symbol subchannel. This mechanism follows the chain rule of mutual information, which preserves the capacity and maximizes the polarization effect. Combining with modulation and bit partitions, we prove the capacity-achieving property of Polar-SM. From the point of practicality, we propose a rate-filling method to realize a fast and low-complexity code construction of Polar-SM. Guided by the three-stage channel transform, we design a glued successive cancellation list (gSCL) decoding algorithm at the receiver to integrate SM detection and polar decoding as a collaborative ensemble. Simulation results validate the performance gain of Polar-SM over state-of-the-art polar-coded MIMO systems and LDPC-coded SM systems.
11 January 2021 in IEEE Wireless Communications Letters
The polar neural decoder has a performance improvement at the cost of additional storage and computation. In this letter, we first propose a ResNet-like BP architecture to improve the standard polar BP decoding. Each iteration inherits a portion of information from the previous iteration as additional input and passes its output to the next iteration. Second, trainable damping factors, which can be learned through deep learning techniques, are applied to determine the inheritance ratio in the ResNet-like BP. We allocate the damping factors flexibly and demonstrate the optimization of a shared constant damping factor provides the same level of performance with the individual optimization of the damping factor at each state. Moreover, we qualitatively explain the performance gain by analyzing the mutual information between the input and output of the decoder. Numerical and simulation results indicate that the ResNet-like BP decoder can effectively improve the error correction performance and accelerate convergence compared with the standard polar BP algorithm.
14 November 2023 in IEEE Transactions on Vehicular Technology
This paper studies the joint design of polar coding and orthogonal frequency division multiplexing with index modulation (OFDM-IM) to improve the system error performance. A three-stage channel transform is established based on cascaded signal-code polarization to decompose the raw OFDM-IM channel into polarized subchannels. Both multilevel coding (MLC) and bit-interleaved coded-modulation (BICM) based approaches are considered. For the transceiver implementation, a polar code construction method based on mutual information equivalence is first presented, followed by several well-designed index mapping lookup tables to ensure equal activation probabilities for each subcarrier. An index set partitioning (ISP) rule is further proposed to enhance the system polarization effect. Subsequently, the multi-stage collaborative receiver structure is described, along with a bit log-likelihood ratio (LLR) calculation method. Furthermore, the proposed polar-coded OFDM-IM framework can be extended to other OFDM-IM variants, such as OFDM-I/Q-IM. Simulation results demonstrate the superior error performance of the proposed schemes.
10 March 2021 in IEEE Communications Letters
In this letter, we concern the self-decoding capability of polar-coded hybrid automatic repeat request (Polar-HARQ) schemes. The proposed self-decoding method enables the incremental redundancy (IR) based Polar-HARQ to recover all source bits solely using the retransmission codewords. It provides an extra decoding chance when the joint decoding attempt fails. With this, the final decoding success probability increases such that the number of retransmissions can be reduced and the system latency goes down. We derive one necessary condition for the successful self-decoding, which can also guide the optimization of Polar-HARQ. Three mainstream Polar-HARQ schemes are compared from the perspective of self-decoding. Simulation results validate the analysis.
1 January 2026 in IEEE Transactions on Wireless Communications