摘要：Automatic modulation recognition (AMR) plays an essential role in wireless communication systems. Our paper proposes a novel multi-stream neural network (MSNN) to extract the features in parallel from the amplitude, phase, frequency, and raw data of the modulated signal. The framework integrates convolutional neural networks (CNN) and bidirectional gated recurrent units (Bi-GRU) to extract features more effectively from the spatial and temporal characteristics with the assistance of two different attention mechanisms, convolutional block attention module (CBAM) and multi-head self-attention (MHSA). Simulation experiments show that the performance of our proposed algorithm is better than that of other state-of-the-art (SOTA) recognition algorithms on four widely used DeepSig datasets. The recognition accuracy of our proposed model exceeds 99% (18 dB), 93% (16 dB), 95% (20 dB), and 97% (20 dB) respectively on the datasets RML2016.04C, RML2016.10A, RML2016.10B, and RML2018.01A.(c) 2022 Elsevier Inc. All rights reserved.

关键字：Automatic modulation recognition; Deep learning; Multi -stream; Attention mechanism

ISSN号：1051-2004

卷、期、页：卷: 130

发表日期：2022-10-01

影响因子：3.381000

期刊分区（SCI为中科院分区）：三区

发表期刊名称：DIGITAL SIGNAL PROCESSING

通讯作者：王旭,张宇浩,李洋,吴世伟

第一作者：刘得军

论文类型：期刊论文

论文概要：王旭,刘得军,张宇浩,李洋,吴世伟，A spatiotemporal multi-stream learning framework based on attention mechanism for automatic modulation recognition，DIGITAL SIGNAL PROCESSING，2022，卷: 130

论文题目：A spatiotemporal multi-stream learning framework based on attention mechanism for automatic modulation recognition