TY - GEN
T1 - Deep Learning Method for Generalized Modulation Classification under Varying Noise Condition
AU - Wang, Yu
AU - Gui, Guan
AU - Zhao, Nan
AU - Huang, Hao
AU - Liu, Miao
AU - Sun, Jinlong
AU - Gacanin, Haris
AU - Sari, Hikmet
AU - Fumiyuki, Adachi
N1 - Funding Information:
This work was funded by the Project Funded by the Jiangsu Specially Appointed Professor Grant under Grant RK002STP16001, the Innovation and Entrepreneurship of Jiangsu High-Level Talent Grant under Grant CZ0010617002, Summit of the Six Top Talents Program of Jiangsu under Grant XYDXX-010, 1311 Talent Plan of Nanjing University of Posts and Telecommunications
Funding Information:
ACKNOWLEDGEMENT This work was funded by the Project Funded by the Jiangsu Specially Appointed Professor Grant under Grant RK002STP16001, the Innovation and Entrepreneurship of Jiangsu High-Level Talent Grant under Grant CZ0010617002, Summit of the Six Top Talents Program of Jiangsu under Grant
Publisher Copyright:
© 2020 IEEE.
PY - 2020/2
Y1 - 2020/2
N2 - Modulation signal classification (MSC) is an indispensable technique to make the possible applications of non-cooperative communications. Currently, convolutional neural network (CNN) based MSC techniques can achieve an outstanding performance at a fixed noise regime. However, they are hard to generalize to all of noise scenarios. Because these conventional methods are trained on specific signal samples with fixed SNR and they only perform well under corresponding noise condition. Unlike the conventional methods, in this paper, we propose a robust CNN based generalized MSC (GMSC) method with powerful generality capability. This capability stems from the mixed dataset, containing in-phase and quadrature (IQ) samples under various SNR regimes. Experimental results show that the proposed method is robust under varying noise conditions, while merely losing a slight performance with comparing with conventional methods.
AB - Modulation signal classification (MSC) is an indispensable technique to make the possible applications of non-cooperative communications. Currently, convolutional neural network (CNN) based MSC techniques can achieve an outstanding performance at a fixed noise regime. However, they are hard to generalize to all of noise scenarios. Because these conventional methods are trained on specific signal samples with fixed SNR and they only perform well under corresponding noise condition. Unlike the conventional methods, in this paper, we propose a robust CNN based generalized MSC (GMSC) method with powerful generality capability. This capability stems from the mixed dataset, containing in-phase and quadrature (IQ) samples under various SNR regimes. Experimental results show that the proposed method is robust under varying noise conditions, while merely losing a slight performance with comparing with conventional methods.
KW - Convolutional neural network (CNN)
KW - Generalized ability
KW - Modulation signal classification (MSC)
KW - Non-cooperative communication
UR - http://www.scopus.com/inward/record.url?scp=85083423527&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85083423527&partnerID=8YFLogxK
U2 - 10.1109/ICNC47757.2020.9049786
DO - 10.1109/ICNC47757.2020.9049786
M3 - Conference contribution
AN - SCOPUS:85083423527
T3 - 2020 International Conference on Computing, Networking and Communications, ICNC 2020
SP - 938
EP - 943
BT - 2020 International Conference on Computing, Networking and Communications, ICNC 2020
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2020 International Conference on Computing, Networking and Communications, ICNC 2020
Y2 - 17 February 2020 through 20 February 2020
ER -