Automatic Modulation Classification Based on One-Dimensional Convolution Feature Fusion Network

Abstract

Deep learning method has been gradually applied to Automatic Modulation Classification (AMC) because of its excellent performance. In this paper, a lightweight one-dimensional convolutional neural network module (OnedimCNN) is proposed. We explore the recognition effects of this module and other different neural networks on IQ features and AP features. We conclude that the two features are complementary under high and low SNR. Therefore, we use this module and probabilistic principal component analysis (PPCA) to fuse the two features, and propose a one-dimensional convolution feature fusion network (FF-Onedimcnn). Simulation results show that the overall recognition rate of this model is improved by about 10%, and compared with other automatic modulation classification (AMC) network models, our model has the lowest complexity and the highest accuracy.