A high-performance communication receiver desires a sufficient and accurate recognition of transmitted sources. In this paper, we propose a sequential decoding algorithm for the robust reception of sources with natural redundancy (NR) over the AWGN channel. To fully exploit the abundant NR in the exemplified English text sources, a causal language modeling (CLM) with a powerful Transformer decoder neural network (NN) structure is adopted for modeling the joint probability distribution. For versatility of byte-level tokenization, the UTF-8 encoding scheme is considered for the Wikipedia corpus, namely the English edition of the Wiki-40B dataset. The tree search-based M-algorithm (MA) is integrated with CLM, denoted as CLM-MA algorithm, to synthesize the a priori probability of information sequence and likelihood values of polluted symbols. Both simulation experiments and hardware platform evaluations are conducted to analyze the performance of the CLM-MA algorithm. With an adequately large M value, tremendous performance profit is achievable, especially for high-efficiency modulation levels and extremely noisy conditions. This mechanism of adopting the pre-trained NN model merely desires self-supervised learning architecture and eliminates the requirement of high-cost and accurate labels, which paves a new way for communication receiver design.

Non-orthogonal multiple access (NOMA) can be an effective solution to the limited bandwidth of light emitting diodes for visible light communication (VLC) systems to support multiuser communication. The current available works for NOMA VLC systems mainly concentrate on downlinks and the existing power allocation algorithms mainly focus on the channel state information and ignore the influence of transmitted signals. In this paper, we propose a channel and bit adaptive power control strategy for uplink NOMA VLC systems by jointly considering the channel state information and the transmission bit rate. Under this adaptive power control strategy, it is proved that the received signal at the photodiode (PD) receiver constitutes a sizeable pulse amplitude modulation constellation and low-complexity maximum likelihood detection is admitted. The simulation results indicate that our proposed adaptive power control strategy outperforms the gain ratio power allocation scheme, fixed power allocation scheme, and time division multiple access scheme.

In this paper, we study energy-efficient precoding techniques in multiuser multiple-input single-output (MISO) visible light communication (VLC) systems. Under the dual constraints of illumination and communication, an optimal precoding design is proposed for a 4×2 multiuser MISO VLC system by utilizing the properties of Farey sequence in number theory. It is proved that the received signals constitute a sizeable pulse amplitude modulation constellation and thanks to this nice constellation structure, low-complexity maximum likelihood detection is admitted for signal detection. Simulation results indicate that our proposed optimal precoding design outperforms zero-forcing and time division multiple access schemes.

High-speed information transmission system demands more powerful communication receivers. In this paper, we integrate deep learning algorithms into constructing waveform level receiver, which is capable of harnessing natural redundancy (NR) in raw message sources. Owing to end-to-end learning paradigm of neural network (NN), the proposed NN receiver can accomplish joint symbol timing synchronization and demodulation based on oversampled waveform sequences directly. The prevalent bidirectional LSTM (BiLSTM) and Transformer structures, suitable for excavating sequential correlation of complex sources and waveform sequences, are considered as the backbone of NN receivers. Under the cases of clean label and noisy label, we conceive two novel training algorithms and interpret their principles in theory. The clean label bits are accessible from original source encoding schemes, while noisy label bits are available from the decision results of canonical receivers with independently noised waveform sequences. When noisy labels possess sufficiently small error rates, optimized NN receiver is competitive with that adopting the accurate labels. As for Markov sources and natural language text sources, simulation results show that the proposed NN receivers’ performances are superior to the classical receivers without a priori knowledge, especially when high spectral efficiency modulation schemes are encountered and random noise is significant.

In this paper, we propose an optimized cooperative finite-alphabet relaying strategy for two-way relay visible light communication (VLC) systems, in which the relay node has its own information to be transmitted. In the multiple access (MAC) stage, for fixed transmission bit rate of each user, an optimal power control strategy is developed to manage the nonnegative finite-alphabet multiuser interference. Under this strategy, it is proved that the received signal constitutes an equally-spaced pulse amplitude modulation constellation, which admits lowcomplexity maximum likelihood detection. In addition, for given overall transmission bit rate of MAC stage, we derive a closedform solution for optimal bit loading to further improve the energy-efficiency of MAC stage. In the broadcast stage, owing to the fact that each buffer-aided user node knows the signals transmitted to the relay node in the MAC stage, we design a buffer-aided optimal encoding constellation which can obtain significant performance gains. Intended for this transmitted constellation, we develop two low-complexity detection algorithms. Both analytical results and computer simulations demonstrate that our proposed design has substantial performance advantage over the currently available time orthogonal transmission scheme for this application.

Pre-trained Models (PTMs) have reached the state-of-the-art (SOTA) on many Natural Language Processing (NLP) tasks and Computer Vision (CV) tasks, and are called the foundation models of artificial intelligence (AI) systems. In this paper, we introduce PTMs into communication receiver design, which is the first attempt to apply PTMs to the communications field. The powerful capability of PTMs to capture knowledge from massive data enables the PTMs-based receivers to utilize the natural redundancy (NR) that widely exists in the transmitted sources to obtain high performance gains. Intended for uncompressed Chinese text sources, we design a high-performance receiver based on the Bidirectional Encoder Representation from Transformers (BERT) model in the NLP field. We achieve an approximate maximum of posterior marginals (MPM) estimation by obtaining the conditional distribution of the input data from the pre-trained BERT model, and the performance of the approximate MPM estimation can be improved by fine-tuning the BERT model with self-supervised learning. Simulation results demonstrate that the performance of our designed PTMs-based receiver significantly outperforms the classical receiver.