Search

This letter proposes a deep learning-based method for wireless communication signal modulation recognition. Modified generalized end-to-end (GE2E) loss is used to train the designed neural network, which can increase the similarity of the feature vectors of the same modulation type and reduce that of different types. The similarities between training samples and centroid vectors are calculated to set the adaptive thresholds for each known modulation type. The experimental results show that the proposed method can reject unknown signals while remaining the recognition quality of known signals, which has higher efficiency and lower complexity than other open set recognition (OSR) algorithms in modulation recognition. [ABSTRACT FROM AUTHOR]

Specific emitter identification (SEI) is a well-established approach to providing precise target information for civilian and military applications. For most deep learning (DL) based SEI schemes, neural operators directly learn mappings from the raw baseband waveform or its transformed representation. Different from existing schemes, we propose a novel complex Fourier neural operator (CFNO) in this letter, which introduces a time and frequency domain attention mechanism. With the CFNO block, features are fully learned from different domain perspectives. We evaluate the proposed method based on the joint distortion model of the transmitter and compare it with several state-of-the-art SEI algorithms. Simulation results demonstrate its excellent performance, making the CFNO block a good candidate for extracting fingerprints. [ABSTRACT FROM AUTHOR]