Conventional optimization-driven secure relay selection relies on maximization algorithm and accurate channel state information (CSI) of both legitimate and eavesdropper channels. Particularly, estimating and collecting accurate eavesdropper CSI is a difficult task. In this paper, we exploit the benefits of machine learning in solving secure relay selection problem from a data-driven perspective. We convert secure relay selection to a multiclass-classification problem and solve it by a decision-tree-based scheme, which is composed of three phases - preparing training data, building decision tree and predicting relay selection. To meet decision tree’s requirement that input features must take discrete values, a feature extraction method is proposed to generate discrete input by quantizing the accurate CSI of legitimate and eavesdropper channels. By this means, the decision-tree-based relay selection only requires quantized CSI feedback which takes substantially fewer bits in predicting phase. For the purpose of optimizing quantization parameters and enhancing decision tree prediction, we further derive three splitting criteria, i.e. information gain, information gain ratio and Gini index. Simulation results show that if the quantization parameters are set properly, the proposed decision-tree-based scheme can achieve satisfactory performance in terms of average secrecy rate while reducing computational complexity and feedback amount.

This letter investigates the implementation of perfect interference alignment (IA) based on propagation delay (PD) for $K\times 2$ X channels where each of the $K$ source nodes sends an independent message to each of the two destination nodes. The key problem is to find a feasible PD alignment (PDA) structure to achieve the degrees of freedom (DoF), which is $2K/(K+1)$ . From the simple $K=2, 3$ to the general $K$ , we show the DoF achievability of the proposed PDA structure combined with proper time slot scheduling at the transmitter side. Moreover, the feasibility condition in Euclidean space is given. The connection to cyclic IA is further built up when $K=2$ .

Underwater acoustic communications are different from terrestrial radio communications; acoustic channel is asymmetric and has large and variable end‐to‐end propagation delays, distance‐dependent limited bandwidth, high bit error rates, and multi‐path fading. Besides, nodes’ mobility and limited battery power also cause problems for networking protocol design. Among them, routing in underwater acoustic networks is a challenging task, and many protocols have been proposed. In this chapter, we first classify the routing protocols according to application scenarios, which are classified according to the number of sinks that an underwater acoustic sensor network (UASN) may use, namely single‐sink, multi‐sink, and no‐sink. We review some typical routing strategies proposed for these application scenarios, such as cross‐layer and reinforcement learning as well as opportunistic routing. Finally, some remaining key issues are highlighted.

Propagation delay based cyclic interference alignment design is proposed for general X channels with two transmitters and K receivers. From the basic case with K=3 to the general case with arbitrary K, the transmit polynomial and the PD feature of the channels are given. The corresponding receive polynomials are deduced, which show that perfect cyclic IA has been performed in K+1 time-slots to obtain the optimal degrees of freedom 2K/(K+1). Furthermore, the feasibility analysis of node placement in the Euclidean space is provided, which demonstrates the wide application scope from underwater acoustic to terrestrial radio communications.