Modulation scheme recognition using convolutional neural network

• Main Authors: Qianwen Zhang, Zhan Xu, Peiyue Zhang
• Format: Article
• Language: English
• Published: Wiley 2019-10-01
• Series: The Journal of Engineering
• Subjects: computer vision; fourier transforms; neural nets; learning (artificial intelligence); image recognition; image classification; feature extraction; modulation scheme recognition; recognition methods; authors; signal-to-noise ratios; optimisation functions; activation function; automatic recognition; image recognition problem; complex modulation recognition problem; different complex signal spectrograms; image dataset; powerful image feature extraction ability; cnn-based modulation recognition model; computer vision problems; extremely powerful machine-learning tool; convolutional neural network
• Online Access: https://digital-library.theiet.org/content/journals/10.1049/joe.2018.9188

Convolutional neural network (CNN) is an extremely powerful machine-learning tool, especially when dealing with computer vision problems. Here, the authors present a CNN-based modulation recognition model. In order to fully elaborate the powerful image feature extraction ability of CNN, the authors have created an image dataset of different complex signal spectrograms using short-time Fourier transform (STFT). In this case, the complex modulation recognition problem is converted to an image recognition problem. To study the accuracy of automatic recognition of signal spectrograms, the authors have applied two approaches recently developed for image classification. The first approach is to optimise activation functions. Experiments show that best performance can be achieved when using sigmoid as activation function. The second approach is using optimisation functions. At last, the authors compared the recognition accuracy under different signal-to-noise ratios (SNRs). The result shows that authors’ model achieves higher recognition accuracy under low SNR and stronger generalisation ability than other recognition methods.