Extraction and Fusion of Dual-Modal RFF Features in OFDM

Traditional single-modal radio frequency fingerprinting (RFF) approaches often suffer from limitations such as sensitivity to environmental changes and limited discriminative power. Therefore, this paper takes Universal Software Radio Peripheral (USRP) devices as an example to build an Orthogonal Frequency Division Multiplexing (OFDM) system based on a specific frame format and proposes a USRP equipment identification method that integrates differential Quadrature Phase Shift Keying (QPSK) constellation trajectory diagrams with logarithmic differences of adjacent synchronization symbols to enhance the accuracy of Internet of Things (IoT) device identification. The experimental results demonstrate that the dual-feature fusion method proposed in this paper outperforms other single-feature methods, including Fast Fourier Transform (FFT) signals, I/Q signals, the Difference of the logarithm of the spectrum (Dolos), and Differential Constellation Trace Figure (DCTF), making it an effective radio frequency fingerprinting technique.