期刊
IEEE COMMUNICATIONS LETTERS
卷 25, 期 3, 页码 864-868出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/LCOMM.2020.3037273
关键词
Deep learning; Time-frequency analysis; Fourier transforms; Simulation; Robustness; Sensors; Signal to noise ratio; Spectrum sensing; deep learning; short-time Fourier transform
资金
- Jiangsu Provincial Natural Science Foundation of China [BK20191328]
In this letter, a STFT-CNN method for spectrum sensing is proposed, which utilizes time-frequency domain information to achieve state of the art detection performance. The method is suitable for various primary users' signals and maintains a high detection probability even at low signal-to-noise ratio.
Spectrum sensing is one of the crucial technologies used to solve the shortage of spectrum resources. In this letter, based on the short-time Fourier transform (STFT) and convolutional neural network (CNN), we firstly develop a STFT-CNN method for spectrum sensing. The proposed method exploits the time-frequency domain information of the signal samples and achieves the state of the art detection performance. In particular, the method is suitable for various primary users' signals and does not need any priori information. Besides, we also analyze the signal-to-noise ratio robustness and the generalization ability of the proposed algorithm. Finally, simulation results demonstrate that the proposed method outperforms other popular spectrum sensing methods. Notably, the proposed method can achieve a detection probability of 90.2% with a false alarm probability of 10% at SNR = -15dB.
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