With the implementation of deep learning in signal recognition, the processing efficiency and accuracy of radar automatic modulation recognition (AMR) have been effectively improved. The success of deep learning usually depends on plentiful labeled training data, but in actual electromagnetic environments, due to expensive annotation cost and non-cooperative characteristic, there is often a scarcity of labeled samples and an abundance of unlabeled samples. Therefore, this paper designs a contrastive semi-supervised learning (SSL) method that employs unlabeled samples with predicted pseudo-label to assist model training. First, the convolutional attention network is pre-trained utilizing the contrastive learning method, and positive sample pairs are constructed by adding noise and rotation. Then the pre-trained backbone network and stochastically initialized classifier are fine-tuned with labeled samples. In order to avoid the influence of false negative sample pairs, the fine-tuned network is employed to predict unlabeled samples. The filtered samples with pseudo-label and real label samples constitute a new dataset through stratified sampling to balance the samples. Finally, the network is fine-tuned again using the mixed dataset. By comparing the proposed algorithm with existing supervised and semi-supervised methods on a simulation dataset, the algorithm can significantly improve the recognition performance under conditions of small sample size and low signal-to-noise ratio (SNR), verifying its superiority and robustness.

With the increasing adoption of deep learning in signal processing, the performance and efficiency of automatic modulation recognition (AMR) for radar intra-pulse signal have been significantly enhanced. However, existing methods typically focus on feature extraction at a single level, neglecting the potential of multi-level feature learning. Consequently, they are often inadequate in addressing the complexity and diversity of radar signals. This paper proposes a Multi-level and Multi-scale Feature learning approach for AMR (MMFAR) that combines masked autoencoder and contrastive learning to improve the accuracy and robustness of radar signal modulation recognition. During the pre-training phase, the model generates positive sample pairs by applying random masking twice. Subsequently, these samples are processed through a dual-path: one path is dedicated to signal reconstruction, while the other focuses on feature comparison. The reconstruction path uses mean squared error loss for optimization at the sampling point level, ensuring the quality of signal recovery, while the feature extraction path applies contrastive loss for learning discriminative features at the feature level. Finally, the model is fine-tuned through cross-entropy loss to further enhance classification performance at the sample level. Furthermore, the encoder employs convolutional networks to extract multi-scale features and integrates a multi-head attention mechanism to capture long-range dependencies in complex signals. Experimental results demonstrate that the proposed approach significantly outperforms existing methods in modulation recognition tasks under low signal-to-noise ratio (SNR) and complex environmental conditions.

In this paper, we investigate the issue of direction‐of‐arrival (DOA) estimation of multiple signals in coprime arrays. An algorithm based on multiple signal classification (MUSIC) and forward and backward spatial smoothing (FBSS) is used for DOA estimation of this signal caused by multipath and interference. The large distance between adjacent elements of each subarray in the coprime arrays will bring phase ambiguity issues. According to the feature of the coprime number, the ambiguity problem can be eliminated. The correct DOA estimation can be obtained by searching for the common peak of the spatial spectrum and finding the overlapping peaks in the MUSIC spectrum of the two subarrays. For the rank deficit problem caused by the coherent signal, the FBSS algorithm is used for signal preprocessing before the MUSIC algorithm. Theoretical analysis and simulation results show that the algorithm can effectively solve the rank deficiency and phase ambiguity problems caused by coherent signals and sparse arrays in the coprime arrays.