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 and other different networks on IQ features AP features. conclude that two are complementary under high low SNR. Therefore, we use probabilistic principal component analysis (PPCA) fuse features, propose convolution feature fusion (FF-Onedimcnn). Simulation results show overall rate model improved by about 10%, compared with automatic modulation classification models, our lowest complexity highest accuracy.