Radio Modulation Classification Using STFT Spectrogram and CNN

Radio modulation classification is significant in wireless communication. Conventional methods require expert knowledge for feature designing which is difficult to adapt to the complex non-cooperative radio environment. In this paper, a novel scheme with short-time-Fourier-transformation (STFT) and convolutional neural network (CNN) is provides. Signal intra-pulse sequences are first transformed into gray-scaled STFT spectrograms, followed with bi-cubic interpolations, to compress to a fixed image size. Therefore, the classification of radio modulations is equivalent to the spectrogram image recognition problem. Then a CNN is designed to automatically utilize intra-pulse feature extraction and classification. A dataset of 16 different modulation types is provided for experiment, the results demonstrate that our method achieve a significantly improvement than a conventional method, with the classification accuracy increased from 74.3% to 99.0%. The experimental results also indicate that our method can distinguish individuals of the same modulation type.