计算机科学 ›› 2023, Vol. 50 ›› Issue (11A): 220900007-7.doi: 10.11896/jsjkx.220900007
杨小蒙1,2, 张涛1, 庄建军2, 乔晓强1, 杜奕航1
YANG Xiaomeng1,2, ZHANG Tao1, ZHUANG Jianjun2, QIAO Xiaoqiang1, DU Yihang1
摘要： 针对现有的调制分类算法大多忽略了不同特征之间的互补性和特征融合的问题,提出了一种利用深度学习模型进行特征融合的方法。该方法试图融合调制信号的时序特征和空间特征,以获得差异性更加明显的识别特征。首先,获取调制信号的A/P信号和I/Q信号;然后,搭建卷积长短时记忆模块与复数密集残差卷积模块分别提取A/P信号的时序特征和I/Q信号的空间特征并将之进行融合,获取融合互补的识别特征;最后,将识别特征输入分类网络,得到识别结果。实验结果表明,基于开源数据集,当信噪比大于5 dB时,识别率达到了93.25%,与基于单一特征识别相比,识别准确率高出3%～11%;利用实际采集数据进行分类识别,进一步证实了所提特征提取模型与融合策略的有效性。
中图分类号:
| [1]ZENG Y,ZHANG M,HAN F,et al.Spectrum Analysis andConvolutional Neural Network for Automatic Modulation Re-cognition[J].IEEE Wireless Communication Letters,2019,8(3):929-932. [2]WANG Y,LIU M,YANG J,et al.Data-Driven Deep Learning for Automatic Modulation Recognition in Cognitive Radios[J].IEEE Transactions on Vehicular Technology,2019,68(4):4074-4077. [3]HAZZA A,SHOAIB M,ALSHEBEILI S A,et al.An overview of feature-based methods for digital modulation classification[C]//2013 1st InternationalConference on Communications,Signal Processing,and their Applications(ICCSPA).IEEE,2013:1-6. [4]ZENG C Z,JIA X.Modulation recognition method of communication signals based on correlation characteristics[C]//IEEE International Conference on Signal Processing.IEEE,2015:1-5. [5]ZHANG X,GE T,CHEN Z.Automatic Modulation Recognition of Communication Signals Based on Instantaneous Statistical Characteristics and SVM Classifier[C]//IEEE Asia-Pacific Conference on Antennas and Propagation.2018:344-346. [6]SWAMI A,SADLER B M.Hierarchical digital modulation classification using cumulants[J].IEEE Trans Commun,2000,48(3):416-429. [7]WU X,ZHANG J,HOU C,et al.Signal Modulation Recognition based on Convolutional Autoencoder and Time-Frequency Ana-lysis[C]//2021 8th International Conference on Dependable Systems and Their Applications(DSA).2021:664-668. [8]PENG S L,JIANG H Y,WANG H X,et al.Modulation classifi-cation based on signal constellation diagrams and deep learning[J].IEEE Transactions on Neural Networks and Learning Systems,2018,30(3):718-727. [9]YU X,LI L,YIN J,et al.Modulation Pattern Recognition ofNon-cooperative Underwater Acoustic Communication Signals Based on LSTM Network[C]//2019 IEEE International Conference on Signal,Information and Data Processing(ICSIDP).IEEE,2019. [10]WANG Y.Kernel Cross-Modal Factor Analysis for Information Fusion With Application to Bimodal Emotion Recognition[J].IEEE Transactions on Multimedia,2012,14(3):597-607. [11]LIU W,ZHENG W L,LU B L.Emotion Recognition UsingMultimodal Deep Learning[C]//Neural Information Proces-sing:23rd International Conference(ICONIP 2016).2016:521-529. [12]SIMONYAN K,ZISSERMAN A.Two-stream convolutionalnetworks for action recognition in videos[C]//Advances in Neural Information Processing Systems.2014:568-576. |
|
||
首页