End-to-End PSK Signals Demodulation Using Convolutional Neural Network

Demodulation techniques are of central importance for achieving intelligent receiving. Improvement in demodulation performance enhances the overall a communication system correspondingly. However, conventional demodulators require dedicated hardware platforms leading to high implementation costs and time-consuming development. This work proposes unified architecture end-to-end automatic demodulated modulated signals. The proposed demodulator utilizes residual unit fully convolutional network (R-FCN) extract time-domain feature signal determine transmitted symbols realize received signal. Simulations show that method has better compared existing methods. It is further demonstrated when signal-to-noise ratios (SNR) exceed 2dB, exhibits similar symbol-unsynchronized data demodulators.