TY - JOUR
T1 - Data-Limited Modulation Classification with a CVAE-Enhanced Learning Model
AU - Ji, Xuefei
AU - Wang, Jue
AU - Li, Ye
AU - Sun, Qiang
AU - Jin, Shi
AU - Quek, Tony Q.S.
N1 - Funding Information:
Manuscript received May 28, 2020; accepted June 22, 2020. Date of publication June 25, 2020; date of current version October 9, 2020. The work was supported in part by the National Natural Science Foundation of China under Grants 61771264, 61801248, and 61971467, the Natural Science Foundation of Jiangsu Province under Grant BK20180943, and the Nantong University-Nantong Joint Research Center for Intelligent Information Technology under Grant KFKT2017A04. The work of Jue Wang and Ye Li was supported by the project “The Verification Platform of Multi-tier Coverage Communication Network for Oceans (LZC0020). The work of Shi Jin was supported in part by the National Science Foundation (NSFC) for Distinguished Young Scholars of China with Grant 61625106. The associate editor coordinating the review of this letter and approving it for publication was M. Chafii. (Corresponding author: Jue Wang.) Xuefei Ji and Qiang Sun are with the School of Information Science and Technology, Nantong University, Nantong 226019, China (e-mail: jijif1994@hotmail.com; sunqiang@ntu.edu.cn).
Publisher Copyright:
© 1997-2012 IEEE.
PY - 2020/10
Y1 - 2020/10
N2 - The modulation classification problem can be effectively handled by modern machine learning techniques, however, the available data for training is usually limited due to costly measurements in practice. Concerning the problem of insufficient training data, we propose a conditional variational auto-encoder (CVAE)-enhanced learning model for modulation classification. Different from the conventional data augmentation approaches where the data is independently generated, we introduce a feedback unit from the classifier to the CVAE generative network, to ensure that the generated data helps improving the classification accuracy. A two-stage generating-training algorithm is proposed. Via both simulation and practical implementation on a universal software radio peripheral (USRP) platform, it is shown that the proposed method effectively improves the classification accuracy in realistic propagation environment.
AB - The modulation classification problem can be effectively handled by modern machine learning techniques, however, the available data for training is usually limited due to costly measurements in practice. Concerning the problem of insufficient training data, we propose a conditional variational auto-encoder (CVAE)-enhanced learning model for modulation classification. Different from the conventional data augmentation approaches where the data is independently generated, we introduce a feedback unit from the classifier to the CVAE generative network, to ensure that the generated data helps improving the classification accuracy. A two-stage generating-training algorithm is proposed. Via both simulation and practical implementation on a universal software radio peripheral (USRP) platform, it is shown that the proposed method effectively improves the classification accuracy in realistic propagation environment.
UR - http://www.scopus.com/inward/record.url?scp=85092715094&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85092715094&partnerID=8YFLogxK
U2 - 10.1109/LCOMM.2020.3004877
DO - 10.1109/LCOMM.2020.3004877
M3 - Article
AN - SCOPUS:85092715094
VL - 24
SP - 2191
EP - 2195
JO - IEEE Communications Letters
JF - IEEE Communications Letters
SN - 1089-7798
IS - 10
M1 - 9125974
ER -