Specific emitter identification (SEI) aims to distinguish different emitter individuals based on the subtle differences in the signals. The technology can be widely applied to various wireless communication systems. Existing individual identification methods often ignore the radio frequency (RF) fingerprint information carried by the waveforms and thus can be interfered by unreliable RF features. To alleviate these issues, we devise the deep bidirectional long short-term memory (DBi-LSTM) and the one-dimensional residual convolution network with dilated convolution and squeeze-and-excitation block (Conv-OrdsNet). We exploit the combination of DBi-LSTM and Conv-OrdsNet (CoBONet) to extract temporal structure features directly from baseband in-phase and quadrature (I/Q) samples. The proposed network is able to capture the fine-grained details of signals and combine different information extracted by two networks. Moreover, we propose a data augmentation method to solve the interference of unreliable features by randomly changing the values of noise, power, frequency offset (FO), and phase offset (PO). It is worth noting that our method only needs a short slice of a steady-state signal without complex preprocessing, which reduces the cost of acquisition and calculation. Extensive experiments show that our method can effectively extract reliable RF fingerprinting features from I/Q samples and the classification results are better than most existing methods.

Learning from a limited number of samples in automatic modulation classification (AMC) has garnered considerable attention. However, existing few-shot AMC works solely focus on single-domain conditions where the training and testing data share the same data distribution, which overlook the potential domain differences. In practice, the complex and variable communication channels, along with different radio frequency (RF) devices, may result in significant data distribution differences, which can be defined as cross-domain conditions. The neglect of such cross-domain conditions may leads to a significant decline in the performance of existing few-shot AMC models. To consider a more general situation, this paper unifies single-domain and cross-domain few-shot AMC into one task, named SaC-FSL. We propose the Paired Samples Relationship Network (PSRNet) as a solution. PSRNet does not require additional network structure design for domain shifts. It distinguishes categories by learning the relationships between sample pairs rather than directly learning the features of samples. To achieve this, we randomly pair the samples to construct different relationships between different classes and domains, and learn these relationships through classification task. Extensive experiments conducted on multiple datasets have demonstrated the superiority of our PSRNet, which can achieve considerable improvements in both single-domain and cross-domain conditions.

In modulation classification domain, handcrafted feature based method can fit well from a few labeled samples, while deep learning based method require a large amount of samples to achieve the superior classification performance. In order to improve the modulation classification accuracy under the constraint of limited labeled samples, this paper proposes a few-shot modulation classification method based on feature dimension reduction and pseudo-label training (FDRPLT), which combines handcrafted feature based method with deep learning based method. First, an optimal low-dimensional feature subset is created by the combination of the handcrafted features and autoencoder-extracted features post-processed by a feature selection algorithm. Then, a fully connected network (FCN), trained on a small number of labeled signals, is designed for the automated annotating, where unlabeled samples can be annotated and used for the later convolution neural network (CNN) training. The simulation results show that the classification accuracy of eight kinds of modulation types can reach to 98.3% when the SNR is 20dB.

The recognition of modulation schemes for communication signals is an important part of communication surveillance and spectrum monitoring. An algorithm based on deep learning and spectrum texture is proposed to recognize modulation schemes. Based on imperceptible differences among various spectrums of modulation schemes, the algorithm uses Convolution Neural Network to capture the features of image texture and thus classify the features with a SOFTMAX classifier. The experiment shows the algorithm performs better than traditional algorithm based on feature parameters, while the features captured can better reveal the signal detail and reduces effort on feature parameter design.

Reinforcement learning (RL)’s powerful optimization capabilities have been extensively applied in the field of wireless communication jamming decision-making. However, the generalization of jamming policies has rarely been explored, and most existing studies rely on task-customized reward functions, which are often intractable to design. To address these issues, we propose a meta RL method for frequency-hopping spread spectrum (FHSS) jamming decision-making, aided by inexpert demonstrations. Firstly, the policy network is meta-trained with multiple diverse tasks to obtain initial network parameters with good generalization. Subsequently, we combine RL and behavioral cloning (BC) to extract useful information from demonstrations, along with learning rate adaptation to achieve efficient policy exploration without the task-customized jamming reward. Simulations confirm that our proposed method not only adapts to unseen jamming tasks with just a few fine-tuning steps under general binary rewards condition, but also achieves higher accumulated jamming rewards and results in lower normalized throughput for users, outperforming state-of-the-art methods.

Wideband signal detection and recognition (WSDR) is considered an effective technical means for monitoring and analyzing spectra. The mainstream technical route involves constructing time–frequency representations for wideband sampled signals and then achieving signal detection and recognition through deep learning-based object detection models. However, existing methods exhibit insufficient attention on the prior information contained in the time–frequency domain and the structural features of signals, leaving ample room for further exploration and optimization. In this paper, we propose a novel model called TFDP-SANet for the WSDR task, which is based on time–frequency distribution priors and structure-aware adaptivity. Initially, considering the horizontal directionality and banded structure characteristics of the signal in the time–frequency representation, we introduce both the Strip Pooling Module (SPM) and Coordinate Attention (CA) mechanism during the feature extraction and fusion stages. These components enable the model to aggregate long-distance dependencies along horizontal and vertical directions, mitigate noise interference outside local windows, and enhance focus on the spatial distributions and shape characteristics of signals. Furthermore, we adopt an adaptive elliptical Gaussian encoding strategy to generate heatmaps, which enhances the adaptability of the effective guidance region for center-point localization to the target shape. During inference, we design a Time–Frequency Clustering Optimizer (TFCO) that leverages prior information to adjust the class of predicted bounding boxes, further improving accuracy. We conduct a series of ablation experiments and comparative experiments on the WidebandSig53 (WBSig53) dataset, and the results demonstrate that our proposed method outperforms existing approaches on most metrics.