Automatic modulation classification based deep learning with mixed feature

<span lang="EN-US">The automatic modulation classification (AMC) plays an important and necessary role in the truncated wireless signal, which is used modern communications. The proposed convolution neural network (CNN) for AMC based on a method of feature expansion by integrating I/Q (time form) with r/Ɵ (polar order to take advantage two things: first, helps increase features; second that converting polar form accuracy higher due diversity form. CNN consists six blocks. Each block contains symmetric asymmetric filters, as well max average pooling filters. This paper uses DeepSig: RadioML dataset 24 classes. has outperformed many recent papers terms types, up 96.06 at SNR=20 dB.</span>