Yunan Zhu

Distributed underwater acoustic networks support autonomous coordination and rapid response in complex ocean environments by distributing sensing and decision-making functions to individual nodes. However, under long propagation delays, limited bandwidth, and decentralized scheduling, most existing protocols still struggle to suppress multi-hop conflicts under concurrent multi-flow transmissions while balancing end-to-end delay and energy consumption. To this end, we propose a Routing-Aware Collision-Avoidance MAC (RACA-MAC), which can cooperate with various distributed routing mechanisms. In multi-hop concurrent underwater acoustic networks, relay selection and collision avoidance are strongly coupled. Therefore, RACA-MAC formulates relay selection and transmission timing as a unified relay–timeslot decision problem. Specifically, RACA-MAC constructs a local Flow Competition Graph (FCG) from overheard scheduling announcements, transmission feedback, topology awareness, and flow identifiers to represent spatiotemporal exclusion relationships among multi-hop flows. It then combines routing candidates, seed-based transmission/reception windows, and FCG-based conflict filtering to build a feasible relay–timeslot action set. Based on this set, an absorbing Markov chain models end-to-end forwarding risks under reliability, collision, and energy constraints, while Lagrangian relaxation transforms the coupled constraints into locally computable price-aware cost functions. Consequently, each node dynamically adjusts its relay–timeslot decision under limited local information, enabling end-to-end-performance-oriented distributed multi-hop scheduling. Simulation results show that RACA-MAC improves packet delivery ratio by 20–60%, while reducing end-to-end delay and average energy consumption by up to 30% and 50%, respectively.

This paper presents a novel variant of filter bank multicarrier (FBMC) communication, which carries additional bits through mapping the real and imaginary parts of the symbol to the active time-frequency (TF) points, called FBMC with real part and imaginary part index modulation (FBMC-RIIM). Spectral efficiency is improved by doubling the index bits and the inherent interference in each index group is significantly reduced. In this paper, an efficient combination set selection strategy, which synthetically considers the average Hamming distance, average poor index number and average interference coefficient, is also designed. The BER performance comparison between the proposed and reference schemes is obtained under different index modes, spectral efficiency, modulation order and prototype filters. The enhanced performance demonstrates that the proposed scheme is a promising alternative for multicarrier transmission by outperforming the existing FBMC-IM counterpart.

Underwater acoustic channels often have to face the interference of impulsive noise, which is usually modeled by α-stable distribution in simulation experiments. To solve the problem of underwater acoustic channel estimation under impulsive noise, this paper proposes a convex combination–variable-step-size least mean p-norm algorithm. The algorithm incorporates a convex combination into the variable-step-size least mean p-norm algorithm and uses the convex combination of different convergence domains provided by changing the parameters of the Gaussian function to further improve the effect after convergence. The simulation results of channel estimation show that the convex combination–variable-step-size least mean p-norm algorithm provides a more stable, robust, and universal solution than the variable-step-size least mean p-norm algorithm.

Low energy consumption has always been one of the core issues in the routing design of underwater sensor networks. Due to the high cost and difficulty of deployment and replacement of current underwater nodes, many underwater applications require the routing protocol design to consider the network lifetime extension problem. Based on this, we designed a new routing protocol that takes into account both low energy consumption and balanced energy consumption, and achieves effective extension of the network lifetime, called adaptive power-controlled depth-based routing protocol for underwater wireless sensor networks (APCDBRP). The protocol consists of two phases: (1) the route establishment phase and (2) the data transmission phase. In the route establishment phase, the initial path is established by the sink node broadcasting beacon packets at the maximum transmission power. The receiving nodes update their routing tables based on the beacon information and forward the beacon packets. In the data transmission phase, APCDBRP introduces a novel forwarding factor that considers both energy efficiency and energy balance. It selects the optimal next hop based on high energy efficiency and relatively abundant energy, thus extending the network’s lifetime. Additionally, APCDBRP proposes a new data protection and route reconstruction mechanism to address issues such as network topology changes due to node mobility and data transmission failures. Our simulation is based on AquaSim–Next Generation, which is a specialized tool built on the NS3 platform for researching underwater networks. Simulation results demonstrate that, compared to other typical routing protocols, APCDBRP exhibits superior performance in reducing network energy consumption and extending the network’s lifetime. It also achieves a high packet delivery rate with lower energy consumption.

In recent years, research on modulated signal recognition using deep learning (DL) has achieved remarkable success, allowing automatic modulation recognition (AMR) to play a crucial role in modern communication systems. The emergence of the attention mechanism has then rapidly led to a wide range of applications in image classification and speech recognition, which proves the effectiveness of the attention mechanism. In this paper, the authors propose a network model feed‐forward Attention mechanism with Residuals networks and Long Short‐Term Memory (RLADNN) based on feed‐forward attention mechanism with Residuals networks (Resnet) and Long Short‐Term Memory (LSTM), which takes the advantage that the Attention mechanism can effectively solve some long‐term memory problems in [−20:18] signal‐to‐noise ratio (SNR) for the recognition of 11 modulated signals with different SNR, and effectively improves the recognition rate.

The orthogonal time frequency space (OTFS) modulation technique can provide reliable communication in time-varying channels. Due to the dispersive characteristics of underwater acoustic channels, this paper proposes an OTFS-IM underwater acoustic communication system based on Hamming distance optimization to reduce the impact of dispersion in underwater acoustic communication. Firstly, the OTFS-IM underwater acoustic communication system is introduced, which introduces index modulation into the Delay–Doppler (DD) domain to make the OTFS system have stronger anti-Delay–Doppler capability. In contrast, since there is index sequence redundancy in a specific index combination, a Hamming distance optimization model is used to eliminate the redundant combination in the specific index combination sequence and further improve the bit error rate performance of the system. In addition, the Hamming distance optimized OTFS-IM underwater acoustic communication system is verified by simulation analysis. The results show that the proposed Hamming distance optimized OTFS-IM can achieve more reliable bit error rate performance.

Underwater acoustic target recognition is an important supporting technology for underwater information acquisition and countermeasure. Usually, ship radiated noise is covered by the underwater acoustic background and previous deep learning methods for this task rely on clear and effective acoustic features. We propose a novel network called AMNet to alleviate the problem in this paper. It consists of a multi-branch backbone network coupled with a convolutional attention network. The proposed network is able to obtain the internal features of radiated noise from the time-frequency map of the original data. The convolutional attention network adaptively selects the effective features by weighting them against the global information of the time-frequency map to assist the multi-branch backbone network in classification recognition. Experimental results demonstrate that our model achieves an overall accuracy of 99.4% (2.4% improvement) on the ShipsEar database.

To address the problems of the high complexity and poor bit error rate (BER) performance of traditional communication systems in underwater acoustic environments, this paper incorporates the theory of deep learning into a conventional communication system and proposes data-driven underwater acoustic filter bank multicarrier (FBMC) communications based on convolutional autoencoder networks. The proposed system is globally optimized by two one-dimensional convolutional (Conv1D) modules at the transmitter and receiver, it realizes signal reconstruction through end-to-end training, it effectively avoids the inherent imaginary interference of the system, and it improves the reliability of the communication system. Furthermore, dense-block modules are constructed between Conv1D layers and are connected across layers to achieve feature reuse in the network. Simulation results show that the BER performance of the proposed method outperforms that of the conventional FBMC system with channel equalization algorithms such as least squares (LS) estimation and virtual time reversal mirrors (VTRM) under the measured channel conditions at a certain moment in the Qingjiang River.