Automatic modulation recognition based on CNN and GRU
Fugang Liu, Ziwei Zhang, Ruolin Zhou
Abstract
Based on a comparative analysis of the Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) networks, we optimize the structure of the GRU network and propose a new modulation recognition method based on feature extraction and a deep learning algorithm. High-order cumulant, Signal-to-Noise Ratio (SNR), instantaneous feature, and the cyclic spectrum of signals are extracted firstly, and then input into the Convolutional Neural Network (CNN) and the parallel network of GRU for recognition. Eight modulation modes of communication signals are recognized automatically. Simulation results show that the proposed method can achieve high recognition rate at low SNR.
Topics & Concepts
Computer scienceConvolutional neural networkArtificial intelligenceFeature extractionPattern recognition (psychology)Modulation (music)Feature (linguistics)Speech recognitionRecurrent neural networkDeep learningNoise (video)Artificial neural networkImage (mathematics)PhilosophyLinguisticsAestheticsWireless Signal Modulation ClassificationSpider Taxonomy and Behavior Studies