LoRa Radio Frequency Fingerprinting with Residual of Variational Mode Decomposition and Hybrid Machine Learning/Deep Learning Optimization

Radio Frequency fingerprinting (RFF) refers to the technique for identifying and classifying wireless devices on the basis of their physical characteristics, which appear in the digital signal transmitted in space. Small differences in the radio frequency front-end of the wireless devices are generated across the same wireless device model during the implementation and manufacturing process. These differences creates small variations in the transmitted signal even if the wireless device is still compliant to the wireless standard. By using data analysis and machine learning algorithms, it is possible to classify different electronic devices on the basis of these variations. This technique has been well proven in literature but research is continuing to improve the classification performance, robustness to noise and computing efficiency. In recent times, Deep Learning (DL) has been applied to RFF with considerable success. In particular, the combination of time-frequency representations and convolutional neural networks (CNN) has been particularly effective, but this comes at a great computational cost because of the size of the time-frequency representation and the computing time of the CNN. This problem is particularly challenging for wireless standard where the data to be analysed is extensive (e.g., long preambles) as in the case of the LoRa wireless standard. This paper proposes a novel approach where two pre-processing steps are adopted to 1) improve the classification performance and 2) to decrease the computing time. The steps are based on the application of Variational Mode Decomposition (VMD) where (in opposition to the known literature) the residual of the VMD application is used instead of the extracted modes. The concept is to remove the modes, which are commmon among the LoRa devices and keep with the residuals the unique intrinsic features, which are related to the fingerprints. Then, the spectrogram is applied to the residual component. Even after this step, the computing complexity of applying CNN to the spectrogram is high. Then, this paper proposes a novel step where only segments of the spectrogram are used as input to the CNN. The segments are selected using a machine learning approach applied to the features extracted from the spectrogram using the Linear Bit Patterns (LBP). The approach is applied to a recently LoRa radio frequency fingerprinting public data set, where it is shown to significantly outperform the baseline approach based on the full use of the spectrogram of the original signal both in terms of classification performance and computing complexity.

BALDINI Gianmarco;  BONAVITACOLA Fausto; 

2024-06-25

MDPI

JRC137832

2079-9292 (online),   

https://www.mdpi.com/2079-9292/13/10/1925,    https://publications.jrc.ec.europa.eu/repository/handle/JRC137832,   

10.3390/electronics13101925 (online),