With the recently explosive growth of deep learning, automatic modulation recognition has undergone rapid development. Most of the newly proposed methods are dependent on large numbers of labeled samples. We are committed to using fewer labeled samples to perform automatic modulation recognition in the cognitive radio domain. Here, a semi-supervised learning method based on adversarial training is proposed which is called signal classifier generative adversarial network. Most of the prior methods based on this technology involve computer vision applications. However, we improve the existing network structure of a generative adversarial network by adding the encoder network and a signal spatial transform module, allowing our framework to address radio signal processing tasks more efficiently. These two technical improvements effectively avoid nonconvergence and mode collapse problems caused by the complexity of the radio signals. The results of simulations show that compared with well-known deep learning methods, our method improves the classification accuracy on a synthetic radio frequency dataset by 0.1% to 12%. In addition, we verify the advantages of our method in a semi-supervised scenario and obtain a significant increase in accuracy compared with traditional semi-supervised learning methods.

In wireless sensor networks (WSNs), sensor readings have spatiotemporal correlation, and wireless links are unreliable. To balance the energy-performance trade-off and reduce the impact of packet loss, a novel approach is proposed that combines Kronecker compressed sensing (KCS) and cluster topology to exploit spatial and temporal correlations simultaneously. The head nodes generate sparse sub-measurement matrices based on gathered data to avoid measuring nodes that cannot successfully transmit readings. The sink constructs those matrices as a block diagonal matrix (BDM) to utilize the spatial correlation among clusters. Numerical results show that this scheme effectively balances the energy-performance trade-off and maintains a high reconstruction accuracy with packet loss.

Recently, automatic modulation recognition has been an important research topic in wireless communication. Due to the application of deep learning, it is prospective of using convolution neural networks on raw in-phase and quadrature signals in developing automatic modulation recognition methods. However, the errors introduced during signal reception and processing will greatly deteriorate the classification performance, which affects the practical application of such methods. Therefore, we first analyze and quantify the errors introduced by signal detection and isolation in noncooperative communication through a baseline convolution neural network. In response to these errors, we then design a signal spatial transformer module based on the attention model to eliminate errors by a priori learning of signal structure. By cascading a signal spatial transformer module in front of the baseline classification network, we propose a method that can adaptively resample the signal capture to adjust time drift, symbol rate, and clock recovery. Besides, it can also automatically add a perturbation on the signal carrier to correct frequency offset. By applying this improved model to automatic modulation recognition, we obtain a significant improvement in classification performance compared with several existing methods. Our method significantly improves the prospect of the application of automatic modulation recognition based on deep learning under nonideal synchronization.

Reliability and energy efficiency are two key considerations when designing a compressive sensing (CS)-based data-gathering scheme. Most researchers assume there is no packets loss, thus, they focus only on reducing the energy consumption in wireless sensor networks (WSNs) while setting reliability concerns aside. To balance the performance–energy trade-off in lossy WSNs, a distributed data storage (DDS) and gathering scheme based on CS (CS-DDSG) is introduced, which combines CS and DDS. CS-DDSG utilizes broadcast properties to resist the impact of packet loss rates. Neighboring nodes receive packets with process constraints imposed to decrease the volume of both transmissions and receptions. The mobile sink randomly queries nodes and constructs a measurement matrix based on received data with the purpose of avoiding measuring the lossy nodes. Additionally, we demonstrate how this measurement matrix satisfies the restricted isometry property. To analyze the efficiency of the proposed scheme, an expression that reflects the total number of transmissions and receptions is formulated via random geometric graph theory. Simulation results indicate that our scheme achieves high precision for unreliable links and reduces the number of transmissions, receptions and fusions. Thus, our proposed CS-DDSG approach effectively balances energy consumption and reconstruction accuracy.