Automatic modulation recognition (AMR) of radio signals is becoming increasingly important due to its key role in wireless communication system management, monitoring, and control. In this paper, we propose an end-to-end AMR framework based on deep learning (DL), named CCNN-Atten. First, the complex-valued convolutional neural network (CCNN) extracts the features of the radio signal, and the feature calibration (FC) module selectively enhances the important features and suppresses irrelevant features. Then, a temporal context capture (TCC) module uses a modified multi-head attention mechanism (MHA) to capture the temporal dependence in the extracted features. The improved MHA mechanism, as a kind of self-attention mechanism, deploys causal convolutions to encode the temporal information of the input features and captures their local temporal relationship. In addition, due to the limited hardware resources in the real scenarios, we also considered a good compromise between recognition accuracy and computational complexity. Experiments were performed with the RadioML2016.10B, RadioML2016.10A, and RadioML2018.01A datasets, demonstrating the ability of the proposed CCNN-Atten to learn more robust features than other state-of-the-art (SOTA) techniques with 1 ~ 10% higher accuracy and a lower computational complexity than the SOTA models. The experimental results also show that CCNN-Atten achieves outstanding performance in dealing with radio signals with a lower sampling rate and small signal observation window.

In this paper, a frequency diverse array-based directional modulation with artificial noise synthesis scheme is proposed to enhance the physical layer security of wireless communications. We aim to optimize the secrecy performance by jointly optimizing the frequency offsets, the beamforming vector, and the artificial-noise projection matrix (ANPM). Specifically, we address the physical layer security problems for known locations of proximal eavesdropper (Eve) and legitimate user (LU). The beamforming vector and frequency offsets are designed to preserve the signal power at LU. The ANPM is calculated to minimize the effect of AN on LU. Furthermore, we extend our approach to the case of multi-LUs with unknown Eve locations. Being different from the case of a single LU, the frequency offsets across array antennas are optimized to equally allocate transmitted power to each LU. The numerical results show that the proposed method can provide a higher secrecy performance than conventional DM methods. In the case of multi-LUs with unknown Eve locations, the proposed method can provide a high secrecy capacity while achieving almost equal achievable capacity to each LU.

A novel sparse reconstruction method is developed for direction of arrival (DOA) estimation in the presence of unknown mutual coupling of uniform linear arrays (ULAs). In the proposed method, a sparse representation for single measurement vector (SMV) is first derived. Then, it is shown that the problem size can be reduced by a linear transformation to eliminate the redundant components in the SMV. Finally, by taking advantage of the banded symmetric Toeplitz structure of the mutual coupling matrix (MCM), a reweighted ℓ₁-norm minimization subject to an error-constrained ℓ₂-norm is introduced to determine the DOA estimates without mutual coupling compensation, further enhancing the sparsity and providing a robustness against the noise. Simulation results demonstrate the superiority of the proposed method over its state-of-the-art counterparts.

Fog-cloud computing is one of cores techniques in wireless networks, where fog and cloud nodes provide high-speed and large-scale computing services to mobile users through a collaborative method. For the conventional fog-cloud computing schemes, the computing abilities of nodes and the computation task offloading methods are the main factors affecting the latency and energy consumption. However, when computing abilities of nodes reach saturation, the latency and energy consumption caused by task data transmission are approximate to those caused by computation. In order to reduce latency and energy consumption of data transmission and computation, this paper proposes an opportunistic access fog-cloud computing network (OFCN), where each mobile user selects fog node through opportunistic access method. Then, we formulate an optimization problem, considering both resource allocation and computation offloading under the constraints of users’ quality of service (QoS) requirements. Due to the difficulty of solving, we divide the original problem into four suboptimal problems and develop an iterative algorithm to approach the global optimal solution. Numerical results show that the proposed OFCN can achieve lower latency and energy consumption than the conventional fog-cloud computing networks.

In this paper, we aim to address the physical layer security problem for proximal legitimate user (LU) and eavesdropper (Eve) in the case of close-located LU and Eve, where conventional directional modulation (DM) methods may fail to provide efficient secure performance. In order to handle this problem, an optimal frequency offsets of frequency diverse array-based DM with artificial noise (AN) scheme is proposed. We maximize the secrecy capacity by optimizing the frequency offsets and designing AN projection matrix. The optimization problem of the frequency offsets is solved by a block successive upper-bound minimization method to iteratively obtain stationary convergence solutions. By elaborately calculating frequency offsets across array antennas, we can decouple the angle-range correlation and maximize recreational secrecy capacity, resulting in the improvement of the security performance of wireless communications. Numerical results show that the proposed method can provide a higher secrecy capacity than conventional DM schemes with the changes of bandwidth, power allocation factor, and power for the case of proximal LU and Eve. In addition, the proposed scheme is suitable for the case of multi-Eves.

In this paper, a novel multi-beam transmission scheme is proposed to enhance physical layer (PHY) security. This scheme utilizes index modulation (IM) based on frequency diverse array (FDA) beamforming with cooperative legitimate users (LUs). By leveraging IM based on FDA, the indices associated with multiple LUs are directly used as additional sources to transmit information. Using this scheme, the confidential messages can be retrieved only if all the index information and the corresponding symbols are obtained. This adds an extra level of PHY security hence reduces the possibility of information interception by eavesdroppers (Eves). Here instead of maximizing the secrecy rate, we propose a minimum message transmission power criterion to design the FDA beamforming vector, subject to prescribed minimum received power at each of the LUs, in addition to the orthogonality constraints of the remaining LUs. This provides a reliable and accurate transmission assurance for the LUs to obtain the corresponding messages under minimum message transmission power. To further deteriorate the quality of the received signals at Eves, we also add artificial noise (AN). Moreover, by elaborating the time-variant characteristics, we provide a new and more accurate perspective for the range-time dimension secure transmission. Numerical simulations confirm the effectiveness of the proposed scheme.