Automatic modulation recognition (AMR) is an essential and challenging topic in the development of the cognitive radio (CR), and it is a cornerstone of CR adaptive modulation and demodulation capabilities to sense and learn environments and make corresponding adjustments. AMR is essentially a classification problem, and deep learning achieves outstanding performances in various classification tasks. So, this paper proposes a deep learning-based method, combined with two convolutional neural networks (CNNs) trained on different datasets, to achieve higher-accuracy AMR. A CNN is trained on samples composed of in-phase and quadrature component signals, otherwise known as in-phase and quadrature (IQ) samples, to distinguish modulation modes that are relatively easy to identify. We adopt dropout instead of pooling operation to achieve higher recognition accuracy. A CNN based on constellation diagrams is also designed to recognize modulation modes that are difficult to distinguish in the former CNN, such as 16QAM and 64QAM, demonstrating the ability to classify QAM signals even in scenarios with a low signal-to-noise ratio.

Automatic modulation classification (AMC) is an promising technology for non-cooperative communication systems in both military and civilian scenarios. Recently, deep learning (DL) based AMC methods have been proposed with outstanding performances. However, both high computing cost and large model sizes are the biggest hinders for deployment of the conventional DL based methods, particularly in the application of internet-of-things (IoT) networks and unmanned aerial vehicle (UAV)-aided systems. In this correspondence, a novel DL based lightweight AMC (LightAMC) method is proposed with smaller model sizes and faster computational speed. We first introduce a scaling factor for each neuron in convolutional neural network (CNN) and enforce scaling factors sparsity via compressive sensing. It can give an assist to screen out redundant neurons and then these neurons are pruned. Experimental results show that the proposed LightAMC method can effectively reduce model sizes and accelerate computation with the slight performance loss.

The Internet of Things (IoT) has attracted significant attentions in the fifth generation (5G) mobile networks and the smart cities. However, considering the large numbers of connectivity demands, it is vital to improve the spectrum efficiency (SE) of the IoT with an affordable power consumption. To improve the SE, the non-orthogonal multiple access (NOMA) technology is newly proposed through accommodating multiple users in the same spectrums. As a result, in this paper, an energy efficient resource allocation (RA) problem is introduced for the NOMA based heterogeneous IoT. At firstly, we assume the successive interference cancelation (SIC) is imperfect for practical implementations. Then, based on the analyzing method for cognitive radio (CR) networks, we present a stepwise RA scheme for the mobile users (MUs) and the IoT users (IoTUs) with the mutual interference management. Thirdly, we propose a deep recurrent neural network (RNN) based algorithm to solve the problem optimally and rapidly. Moreover, a priorities and rate demands based user scheduling method is supplemented, to coordinate the access of the heterogeneous users with the limited radio resource. At last, the simulation results verify that the deep learning based scheme is able to provide optimal RA results for the NOMA heterogeneous IoT with fast convergence and low computational complexity. Compared with the conventional OFDMA system, the NOMA system with imperfect SIC yields better performance on the SE and the scale of connectivity, at the cost of high power consumption and low EE.

Heterogeneous network (HetNet) with energy harvesting is a promising technique to provide perpetual power supplies and ubiquitous coverage as well as high data rate for next-generation wireless communications. In this paper, we consider a robust power allocation and power splitting (PS) problem for downlink simultaneous wireless information and power transfer (SWIPT)-enabled HetNets. The robust energy-efficiency (EE) maximization problem of femtocell users (FUs) is formulated under the outage-probability interference power constraint of macrocell user (MU), the maximum allowable transmission power of FU and the EE-based outage constraint of each FU. The originally fractional optimization problem with the probabilistic constraint is NP-hard and difficult to solve. Without knowing the distribution of uncertain parameters, a min-max probability machine approach is firstly introduced to convert the semi-infinite optimization problem into a deterministic one which is transformed into a deterministic convex one by using the Dinkelbach method and the quadratic transformation approach. An iterative power allocation and PS scheme is obtained based on convex optimization methods. Finally, the effectiveness of the proposed algorithm is demonstrated by simulation results from the perspective of EE and robustness.

This paper aims to improve spectrum efficiency (SE) for the unmanned aerial vehicle (UAV) relayed cellular uplinks, through distinguishing both line of sight (LoS) and non-line of sight (NLoS) links. Meanwhile, aiming to accommodate the air-to-ground (A2G) cooperative non-orthogonal multiple access (NOMA) based cellular users (CUs) with a high energy efficiency (EE), a joint resource allocation (RA) problem is further considered for the UAV and the CUs. To solve the problem, firstly an access-priority based receiver determination (RD) method is derived. According to the RD result, heuristic user association (UA) strategies are given. Then, based on the UA result, transmission powers of the CUs and the UAV are initialized based on their quality of service (QoS) demands. Further, the subchannels are assigned to the associated CUs and the UAV with the reweighted message-passing algorithm. At last, the transmission power of the CUs and the UAV is jointly fine-tuned with the proposed access control schemes. Compared with the traditional orthogonal frequency division multiple access (OFDMA) scheme and the traditional ground-to-ground (G2G) NOMA scheme, simulation results confirm that the UAV aided NOMA with the proposed joint RA scheme yields better performances in terms of the SE, the EE and the access ratio of the CUs.