Ensuring secure and efficient multi-user (MU) transmission is critical for vehicular communication systems. Chaos-based modulation schemes have garnered considerable interest due to their benefits in physical layer security. However, most existing MU chaotic communication systems, particularly those based on non-coherent detection, suffer from low spectral efficiency due to reference signal transmission, and limited user connectivity under orthogonal multiple access (OMA). While non-orthogonal schemes, such as sparse code multiple access (SCMA)-based DCSK, have been explored, they face high computational complexity and inflexible scalability due to their fixed codebook designs. This paper proposes a deep learning-assisted power domain non-orthogonal multiple access chaos shift keying (DL-NOMA-CSK) system for vehicular communications. A deep neural network (DNN)-based demodulator is designed to learn intrinsic chaotic signal characteristics during offline training, thereby eliminating the need for chaotic synchronization or reference signal transmission. The demodulator employs a dual-domain feature extraction architecture that jointly processes the time-domain and frequency-domain information of chaotic signals, enhancing feature learning under dynamic channels. The DNN is integrated into the successive interference cancellation (SIC) framework to mitigate error propagation issues. Theoretical analysis and extensive simulations demonstrate that the proposed system achieves superior performance in terms of spectral efficiency (SE), energy efficiency (EE), bit error rate (BER), security, and robustness, while maintaining lower computational complexity compared to traditional MU-DCSK and existing DL-aided schemes. These advantages validate its practical viability for secure vehicular communications.

The advent of artificial intelligence (AI)-native wireless communication is fundamentally reshaping the design paradigm of next-generation (NextG) systems, where intelligent air interfaces are expected to operate adaptively and efficiently in highly dynamic environments. Conventional orthogonal frequency division multiplexing (OFDM) systems rely heavily on pilots and the cyclic prefix (CP), resulting in significant overhead and reduced spectral efficiency. To address these limitations, we propose an adaptive end-to-end (E2E) transceiver architecture tailored for pilot-free and CP-free wireless systems. The architecture combines AI-driven constellation shaping and a neural receiver through joint training. To enhance robustness against mismatched or time-varying channel conditions, we introduce a lightweight channel adapter (CA) module, which enables rapid adaptation with minimal computational overhead by updating only the CA parameters. Additionally, we present a framework that is scalable to multiple modulation orders within a unified model, significantly reducing model storage requirements. Moreover, to tackle the high peak-to-average power ratio (PAPR) inherent to OFDM, we incorporate constrained E2E training, achieving compliance with PAPR targets without additional transmission overhead. Extensive simulations demonstrate that the proposed framework delivers superior bit error rate (BER), throughput, and resilience across diverse channel scenarios, highlighting its potential for AI-native NextG.

--In this paper, we propose a deep unfolding neural network-based MIMO detector that incorporates complex-valued computations using Wirtinger calculus. The method, referred as Dynamic Partially Shrinkage Thresholding (DPST), enables efficient, interpretable, and low-complexity MIMO signal detection. Unlike prior approaches that rely on real-valued approximations, our method operates natively in the complex domain, aligning with the fundamental nature of signal processing tasks. The proposed algorithm requires only a small number of trainable parameters, allowing for simplified training. Numerical results demonstrate that the proposed method achieves superior detection performance with fewer iterations and lower computational complexity, making it a practical solution for next-generation massive MIMO systems.

Reconfigurable intelligent surface (RIS) is an emerging technology that is used to improve the system performance in beyond 5G systems. In this letter, we propose a novel convolutional neural network (CNN)-based autoencoder to jointly optimize the transmitter, the receiver, and the RIS of a RIS-assisted communication system. The proposed system jointly optimizes the sub-tasks of the transmitter, the receiver, and the RIS such as encoding/decoding, channel estimation, phase optimization, and modulation/demodulation. Numerically we have shown that the bit error rate (BER) performance of the CNN-based autoencoder system is better than the theoretical BER performance of the RIS-assisted communication systems.

This paper presents a novel auto-encoder based end-to-end channel encoding and decoding. It integrates deep reinforcement learning (DRL) and graph neural networks (GNN) in code design by modeling the generation of code parity-check matrices as a Markov Decision Process (MDP), to optimize key coding performance metrics such as error-rates and code algebraic properties. An edge-weighted GNN (EW-GNN) decoder is proposed, which operates on the Tanner graph with an iterative message-passing structure. Once trained on a single linear block code, the EW-GNN decoder can be directly used to decode other linear block codes of different code lengths and code rates. An iterative joint training of the DRL-based code designer and the EW-GNN decoder is performed to optimize the end-end encoding and decoding process. Simulation results show the proposed auto-encoder significantly surpasses several traditional coding schemes at short block lengths, including low-density parity-check (LDPC) codes with the belief propagation (BP) decoding and the maximum-likelihood decoding (MLD), and BCH with BP decoding, offering superior error-correction capabilities while maintaining low decoding complexity.

Traditional communications focus on regular and orthogonal signal waveforms for simplified signal processing and improved spectral efficiency. In contrast, the next-generation communications would aim for irregular and non-orthogonal signal waveforms to introduce new capabilities. This work proposes a spectrally efficient irregular Sinc (irSinc) shaping technique, revisiting the traditional Sinc back to 1924, with the aim of enhancing performance in industrial Internet of things (IIoT). In time-critical IIoT applications, low-latency and time-jitter tolerance are two critical factors that significantly impact the performance and reliability. Recognizing the inevitability of latency and jitter in practice, this work aims to propose a waveform technique to mitigate these effects via reducing latency and enhancing the system robustness under time jitter effects. The utilization of irSinc yields a signal with increased spectral efficiency without sacrificing error performance. Integrating the irSinc in a two-stage framework, a single-carrier non-orthogonal frequency shaping (SC-NOFS) waveform is developed, showcasing perfect compatibility with 5G standards, enabling the direct integration of irSinc in existing industrial IoT setups. Through 5G standard signal configuration, our signal achieves faster data transmission within the same spectral bandwidth. Hardware experiments validate an 18% saving in timing resources, leading to either reduced latency or enhanced jitter tolerance.

A deep autoencoder (DAE)-based structure for endto-end communication over the two-user Z-interference channel (ZIC) with finite-alphabet inputs is designed in this paper. The proposed structure jointly optimizes the two encoder/decoder pairs and generates interference-aware constellations that dynamically adapt their shape based on interference intensity to minimize the bit error rate (BER). An in-phase/quadrature-phase (I/Q) power allocation layer is introduced in the DAE to guarantee an average power constraint and enable the architecture to generate constellations with nonuniform shapes. This brings further gain compared to standard uniform constellations such as quadrature amplitude modulation. The proposed structure is then extended to work with imperfect channel state information (CSI). The CSI imperfection due to both the estimation and quantization errors are examined. The performance of the DAEZIC is compared with two baseline methods, i.e., standard and rotated constellations. The proposed structure significantly enhances the performance of the ZIC both for the perfect and imperfect CSI. Simulation results show that the improvement is achieved in all interference regimes (weak, moderate, and strong) and consistently increases with the signal-to-noise ratio (SNR). For example, more than an order of magnitude BER reduction is obtained with respect to the most competitive conventional method at weak interference when SNR>15dB and two bits per symbol are transmitted. The improvements reach about two orders of magnitude when quantization error exists, indicating that the DAE-ZIC is more robust to the interference compared to the conventional methods.

Equalization is an important task at the receiver side of a digital wireless communication system, which is traditionally conducted with model-based estimation methods. Among the numerous options for model-based equalization, iterative soft interference cancellation (SIC) is a well-performing approach since error propagation caused by hard decision data symbol estimation during the iterative estimation procedure is avoided. However, the model-based method suffers from high computational complexity and performance degradation due to required approximations. In this work, we propose a novel neural network (NN-)based equalization approach, referred to as SICNN, which is designed by deep unfolding of a model-based iterative SIC method, eliminating the main disadvantages of its model-based counterpart. We present different variants of SICNN. SICNNv1 is very similar to the model-based method, and is specifically tailored for single carrier frequency domain equalization systems, which is the communication system we regard in this work. The second variant, SICNNv2, is more universal, and is applicable as an equalizer in any communication system with a block-based data transmission scheme. We highlight the pros and cons of both variants. Moreover, for both SICNNv1 and SICNNv2 we present a version with a highly reduced number of learnable parameters. We compare the achieved bit error ratio performance of the proposed NN-based equalizers with state-of-the-art model-based and NN-based approaches, highlighting the superiority of SICNNv1 over all other methods. Also, we present a thorough complexity analysis of the proposed NN-based equalization approaches, and we investigate the influence of the training set size on the performance of NN-based equalizers.

In this work, two machine learning (ML)-based structures for joint detection-channel estimation in OFDM systems are proposed and extensively characterized. Both ML architectures, namely Deep Neural Network (DNN) and Extreme Learning Machine (ELM), are developed to provide improved data detection performance and compared with the conventional matched filter (MF) detector equipped with the minimum mean square error (MMSE) and least square (LS) channel estimators. The bit-error-rate (BER) performance vs computational complexity trade-off is analyzed, demonstrating the superiority of the proposed DNN-OFDM and ELM-OFDM detectors methodologies. The conventional orthogonal frequency-division multiplexing (OFDM) system is a multicarrier scheme widely utilized in communication systems due to its capacity to combat frequency-selective fading in wireless channels. This work was partly supported by the National Council for Scientific and Technological Development (CNPq) of Brazil under Grants 310681/2019-7, and in part by the CAPES (Financial code 001), and by State University of Londrina (UEL), PR, Brazil.

The intensity-modulated directly detected (IM/DD) links are the primary candidates for such short-reach interconnects [1]. However, the IM/DD links with square-law photodetection (PD) convert chromatic dispersion (CD) into a nonlinear inter-symbol interference (ISI) accumulated during the propagation in fiber. To mitigate the ISI, recurrent neural networks (RNNs) with sliding window input have been proposed in [2], achieving substantial bit-error-rate (BER) performance. However, the RNNs incorporate high computational complexity (CC) in terms of real multiplications per equalized symbol (RMPS) and are challenging to train [3]. Therefore, reservoir computing (RC), a special type of RNN, has been introduced in [4,5] to compensate for fiber-induced impairments, while keeping computational and training complexity low. In [6], it was shown that introducing a sliding window at the input boosts the RC performance for time series prediction tasks. Usually, in NNs-based digital signal processing blocks, the equalization is performed sequentially symbol by symbol [7]. However, it was experimentally demonstrated in [3] that feedforward NN-based multi-symbol equalization achieved considerable CC relaxation without losing in BER. In this work, we inherit the idea of using a sliding window at the input of the RC and propose a multi-symbol RC equalizer to decrease CC without impairing performance.