期刊
IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS
卷 39, 期 8, 页码 2604-2616出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/JSAC.2021.3087250
关键词
Deep learning; Spectrogram; Signal representation; Time-frequency analysis; Hardware; Authentication; Wireless communication; Internet of Things; LoRa; device authentication; radio frequency fingerprint; deep learning; carrier frequency offset
资金
- U.K. Royal Society [RGS/R1/191241]
- National Key Research and Development Program of China [2020YFE0200600]
The paper presents a deep learning-based RFFI scheme for LoRa systems, investigating signal representations and CFO compensation to improve system stability and accuracy. Experimental results suggest that the spectrogram-CNN model is optimal for classifying LoRa devices.
Radio frequency fingerprint identification (RFFI) is an emerging device authentication technique that relies on the intrinsic hardware characteristics of wireless devices. This paper designs a deep learning-based RFFI scheme for Long Range (LoRa) systems. Firstly, the instantaneous carrier frequency offset (CFO) is found to drift, which could result in misclassification and significantly compromise the stability of the deep learning-based RFFI system. CFO compensation is demonstrated to be effective mitigation. Secondly, three signal representations for deep learning-based RFFI are investigated in time, frequency, and time-frequency domains, namely in-phase and quadrature (IQ) samples, fast Fourier transform (FFT) results and spectrograms, respectively. For these signal representations, three deep learning models are implemented, i.e., multilayer perceptron (MLP), long short-term memory (LSTM) network and convolutional neural network (CNN), in order to explore an optimal framework. Finally, a hybrid classifier that can adjust the prediction of deep learning models with the estimated CFO is designed to further increase the classification accuracy. The CFO will not change dramatically over several continuous days, hence it can be used to correct predictions when the estimated CFO is much different from the reference one. Experimental evaluation is performed in real wireless environments involving 25 LoRa devices and a Universal Software Radio Peripheral (USRP) N210 platform. The spectrogram-CNN model is found to be optimal for classifying LoRa devices which can reach an accuracy of 96.40% with the least complexity and training time.
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