TY - JOUR
T1 - Automatic Modulation Classification Using Compressive Convolutional Neural Network
AU - Huang, Sai
AU - Chai, Lu
AU - Li, Zening
AU - Zhang, Di
AU - Yao, Yuanyuan
AU - Zhang, Yifan
AU - Feng, Zhiyong
N1 - Funding Information:
This work was supported in part by the National Key Research and Development Program of China under Grant 2018YFF0301202, in part by the National Natural Science Foundation of China under Grant 61801052, Grant 61525101, and Grant 61227801, in part by the Supplementary and Supportive Project for Teachers at Beijing Information Science and Technology University under Grant 5029011103, and in part by the Key Research and Cultivation Project at Beijing Information Science and Technology University under Grant 5211910926.
Publisher Copyright:
© 2013 IEEE.
PY - 2019
Y1 - 2019
N2 - The deep convolutional neural network has strong representative ability, which can learn latent information repeatedly from signal samples and improve the accuracy of automatic modulation classification (AMC). In this paper, a novel compressive convolutional neural network (CCNN) is proposed for AMC, where different constellation images, i.e., regular constellation images (RCs) and contrast enhanced grid constellation images (CGCs), are generated as network inputs from received signals. Moreover, a compressive loss constraint is proposed to train the CCNN, which aims at capturing high-dimensional features for modulation classification. Additionally, CCNN utilizes intra-class compactness and inter-class separability to enhance the classification and robustness performance for the different orders of modulations. The simulation results demonstrate that CCNN displays superior classification and robustness performance than existing AMC methods.
AB - The deep convolutional neural network has strong representative ability, which can learn latent information repeatedly from signal samples and improve the accuracy of automatic modulation classification (AMC). In this paper, a novel compressive convolutional neural network (CCNN) is proposed for AMC, where different constellation images, i.e., regular constellation images (RCs) and contrast enhanced grid constellation images (CGCs), are generated as network inputs from received signals. Moreover, a compressive loss constraint is proposed to train the CCNN, which aims at capturing high-dimensional features for modulation classification. Additionally, CCNN utilizes intra-class compactness and inter-class separability to enhance the classification and robustness performance for the different orders of modulations. The simulation results demonstrate that CCNN displays superior classification and robustness performance than existing AMC methods.
KW - Automatic modulation classification
KW - compressive loss constraint
KW - deep convolutional neural network
KW - multiple constellation images
UR - http://www.scopus.com/inward/record.url?scp=85068988165&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85068988165&partnerID=8YFLogxK
U2 - 10.1109/ACCESS.2019.2921988
DO - 10.1109/ACCESS.2019.2921988
M3 - Article
AN - SCOPUS:85068988165
SN - 2169-3536
VL - 7
SP - 79636
EP - 79643
JO - IEEE Access
JF - IEEE Access
M1 - 8734711
ER -