Signal Modulation Classification Based on Deep Belief Network

Abstract

Modulation classification plays an important role in civil and military fields such as software defined radio, electronic countermeasure and intelligent demodulator. Due to the difficulty of feature extraction in traditional signal modulation classification algorithm, this paper proposes a signal modulation classification algorithm based on deep belief network. The proposed algorithm does not need to extract the signal features, and uses the I/Q data to classify signal directly. The simulation results show that the classification performance of the proposed algorithm is better than traditional machine learning algorithm, when the simulation condition is same.