20 May 2022 in IEEE Transactions on Cognitive Communications and Networking
In this work, the Transformer Network (TRN) is applied to the automatic modulation classification (AMC) problem for the first time. Different from the other deep networks, the TRN can incorporate the global information of each sample sequence and exploit the information that is semantically relevant for classification. In order to illustrate the performance of the proposed model, it is compared with four other deep models and two traditional methods. Simulation results show that the proposed one has a higher classification accuracy especially at low signal to noise ratios (SNRs), and the number of training parameters of the proposed model is less than those of the other deep models, which makes it more suitable for practical applications.
23 October 2023 in IEEE Internet of Things Journal
Radar intrapulse signal modulation classification is an important work for the electronic countermeasure and there are mainly two categories of algorithms. The deep learning-based algorithms usually outperform the traditional feature extraction-based ones, but they may rely on massive labeled samples for training, which limits their practical applications. To solve this problem, the SS-LWCNN model which combines the semisupervised learning (SI-SL) with virtual adversarial training (VAT) and the light weight technology is proposed. VAT provides the proposed model with robustness to the local perturbation of samples, which improves the classification accuracy with limited labeled samples provided. The light weight technology greatly reduces the complexity of the model, which increases the speed of classification. As demonstrated by the simulation results, in the condition of limited labeled samples are available, the SS-LWCNN model obtains greater classification accuracy compared to the other models. As tested by both the white Gaussian noise and the impulsive noise affected signals data sets, the SS-LWCNN model shows stronger robustness than the comparable models. Furthermore, the SS-LWCNN model contains much fewer training parameters and less floating point operations (FLOPs) than the other models.