Cross-Domain Segmenter Self-Learning Classifier for Multi-UAV Blind FH Uplink Signal Recognition

he emergence of unauthorized unmanned aerial vehicles (UAVs) has raised widespread safety threats, making the blind signal recognition of unauthorized multiple UAVs (multi-UAV) critically important.he emergence of unauthorized unmanned aerial vehicles (UAVs) has raised widespread safety threats, making the blind signal recognition of unauthorized multiple UAVs (multi-UAV) critically important.T Meanwhile, the frequency hopping (FH) control signals with the start-end identical preamble (SIP) structure, have three major characteristics: non-stationarity, short dwell time, and scarcity of known labels. These characteristics pose significant challenges to the recognition of unauthorized SIP signals in spectrograms. In this paper, we propose a cross-domain segmenter self-learning classifier (CS-SC) scheme for SIP signals, which can segment each class of UAV in-phase/quadrature (I/Q) signals in multi-UAV environments, and detects the features of unauthorized and unknown SIP signal via self-learning. First, the CS scheme performs time-frequency analysis on received SIP signals, locates signals via an adaptive statistical feature detector on spectrograms, then combines with time-frequency segmentation to obtain I/Q representations of each class of signals. Second, we design a cyclic self-search algorithm in the SC scheme, and the SC scheme can learn discriminative features via the preamble structures, and reduces the interference from payload of unknown UAV signals. Then, these learned features are utilized in template matching for blind SIP signal recognition, which is more efficient than the related learning algorithms. Simulation results validate that, our CS-SC scheme achieves 40% higher clustering accuracy compared with the existing clustering algorithms, and improves the recognition accuracy about 40% than related deep learning algorithms in a wide signal-to-noise ratio (SNR) region.