The popularization of unmanned aerial vehicles (UAVs) has raised critical concerns about public security and personal privacy, necessitating drone recognition technology. Radio frequency-based monitoring methods are widely used because of their advantage of non-line-of-sight. However, most existing radio frequency-based recognition methods have closed-set assumption vulnerabilities. Although several open-set methods have been proposed, they still face robustness deficiencies when video transmission signal attenuation conditions are severe or when interference signals are present. To address this challenge, we propose a lightweight open-set drone recognition (LOSDR) method. First, IQ data are transformed into time-frequency spectra via a short-time Fourier transform. Second, regional block details and global frequency-hopping patterns are jointly extracted via a flight control signal block extractor and pattern extractors. Then, a semantic alignment module, which integrates text embeddings derived from the contrastive language-image pretraining model, and a class decorrelation module with orthogonal constraints are designed to increase the degree of interclass separation and reduce the ambiguity of classification. Additionally, an adaptive dynamic entropy threshold mechanism is used to balance known/unknown decisions under varying noise and interference levels. We construct datasets for three different electromagnetic environments. Extensive experiments conducted on these datasets demonstrate that LOSDR outperforms the state-of-the-art methods in terms of generalizability and accuracy.

Automatic modulation recognition (AMR) plays a crucial role in non-cooperative communication environment for identifying modulation types of received radio signals. Recently, the achievements of deep learning (DL) have sparked significant interest in applying DL to the field of AMR. However, existing DL-based AMR methods only use image modal or sequence modal as input, which cannot leverage sufficient information of the signal in complicated electromagnetic environment characterized by scarce labeled sample and multipath fading. To overcome this limitation, we explore different modal representations of the signal to fully exploit their complementary information and propose a hybrid modal contrast and fusion method for automatic modulation recognition (HMCF-AMR). It consists of two stages: 1) modal-level feature contrast for self-supervised pre-training and 2) modal-level feature fusion for supervised fine-tuning. In modal-level feature contrast, sequence encoder and image encoder are designed to extract multi-scale features of the modulated signal from the image modal and sequence modal. Meanwhile, a multi-task collaborative pre-training method combining generative and contrastive learning is achieved to enhance and align different modal representations. In modal-level feature fusion, an attentional feature fusion mechanism integrates the features learned from different modal to further improve modulation recognition performance and online learning is implemented by fine-tuning to handle different scenarios. Simulation results show that our proposed HMCF-AMR outperforms other baseline models in both adequate-sample and few-shot scenarios and demonstrates greater robustness in complicated multipath fading channels.

Wideband spectrum sensing based on sub-Nyquist sampling is an attractive approach to advance dynamic spectrum sharing (DSS), which can improve frequency resource utilization while overcoming sampling bottlenecks. Under the Compressive Sensing (CS) framework, finding occupied subbands can be equivalent to computing the support set for the Multiple Measurement Vectors (MMV) problem. To guarantee the performance of joint support recovery in noisy environments, different kinds of prior information are required, one of which is sparsity, a time-varying parameter. To address the dependence of recovery performance on signal sparsity, this paper proposed a two-step scheme for blind wideband spectrum sensing using a Modulated Wideband Converter (MWC) sub-Nyquist sampling front-end. The scheme first adopts the model order selection (MOS) method to estimate sparsity from the compressed covariance matrix, and then uses the estimates to dynamically adjust joint support recovery. The complete theoretical derivation innovatively applies MOS to sub-Nyquist sampling and presents a design method for MOS penalty constant. Extensive simulation results show that the proposed scheme can not only achieve blind sensing under the spectrum occupancy up to 40%, reduce the overall computational complexity of iterative SOMP, but also significantly improve the false alarm performance, meeting the requirements of the IEEE 802.22 standard.