期刊
IEEE ACCESS
卷 9, 期 -, 页码 166423-166435出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/ACCESS.2021.3135568
关键词
Sensors; Convolutional neural networks; Deep learning; Feature extraction; Training; Covariance matrices; OFDM; Cognitive radio; spectrum sensing; deep neural network; semi-supervised learning; limited data
资金
- State Key Program of National Natural Science of China [U19B2016]
- Key Lab of Data Storage and Transmission Technology of Zhejiang Province, Hangzhou Dianzi University
The study introduces a spectrum sensing method based on semi-supervised deep neural network, which expands the labeled dataset by utilizing a large amount of unlabeled samples. Experimental results demonstrate good performance in both multi-path fading channel and additive white Gaussian noise channel.
Spectrum sensing methods based on deep learning require massive amounts of labeled samples. To address the scarcity of labeled samples in a real radio environment, this paper presents a spectrum sensing method based on semi-supervised deep neural network (SSDNN). Firstly, a deep neural network is established to extract the features of signals by using small amounts of labeled samples; Then, plenty of unlabeled samples are used for self-training process, and the ones with high confidence are marked with pseudo-label to expand the labeled dataset. Finally, the extended dataset is used to retrain the network. Plentiful experiments are carried out on a dataset of 124,800 samples. The results demonstrate that the proposed algorithm has good detection performance over multi-path fading channel and additive white Gaussian noise channel due to the utilization of a great deal of unlabeled dataset. When the labeled samples account for only 5% of the traditional fully supervised deep learning model and the SNR is higher than -13 dB, the detection probability of SSDNN is higher than 90%.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据