Modulation classification method for frequency modulation signals based on the time–frequency distribution and CNN

• Published in: IET radar, sonar & navigation Vol. 12; no. 2; pp. 244 - 249
• Main Authors: Zhang, Juan, Li, Yong, Yin, Junping
• Format: Journal Article
• Language: English
• Published: The Institution of Engineering and Technology 01.02.2018
• Subjects: blind modulation classification method; CNN‐based algorithm; computer vision; computer vision area; convolutional neural network; feature extraction; feature extraction strategy; frequency modulation; frequency modulation signals; modulation classification method; neural nets; Research Article; signal modulation classification; signal recognition; time‐frequency analysis; time‐frequency distribution; time‐frequency map; modulation classification method; time-frequency map; frequency modulation signals; signal modulation classification; computer vision area; time-frequency distribution; convolutional neural network; CNN-based algorithm; signal recognition; feature extraction; time-frequency analysis; blind modulation classification method; computer vision; feature extraction strategy; frequency modulation; neural nets
• ISSN: 1751-8784; 1751-8792
• DOI: 10.1049/iet-rsn.2017.0265

Signal modulation classification is an important research subject in both military and civilian field. This study proposed a novel blind modulation classification method based on the time–frequency distribution and convolutional neural network (CNN). This is the first attempt to treat the time–frequency map as a picture and use an outstanding (CNN-based) algorithm in computer vision area for signal recognition. The combination offers a novel feature extraction strategy, to some extent, which also conforms to intuition. Simulation results show that the method proposed in this study is efficient and robust and enables a high degree of automation for extracting features, training weights and making decisions. Additionally, a remarkable performance emerges with small samples and repeated training, which distinguishes this method from many other classification methods.