In modern communication systems, automatic modulation recognition (AMR) has broad application prospects but a large amount of training data is usually required. Due to the high cost of adding annotations to signals, it is of great significance to study AMR under the condition of few labeled samples. In this paper, an end-to-end semi-supervised radio signal recognition algorithm is proposed. In view of the poor anti-noise performance of the original IQ data, short-time Fourier transform (STFT) is introduced to mine the stable modulation characteristics. In order to overcome the noise problem caused by pseudo-labels, a mixed sample data augmentation (MSDA) method PFMix is proposed, and the consistency constraint of the model disturbance based on mean teacher (MT) framework and data disturbance based on PFMix is designed. Meanwhile, in order to provide pseudo-labels with high confidence, entropy regularization is constructed by taking the prediction variance of MT framework as correction factor. The experimental results using the open source RML2016.10A dataset show the superior performance of the proposed method. The average recognition accuracy with 1% labeled data is 88.82% at 0 dB, which is a significant improvement compared with state of the art in semi-supervised AMR.

Radar signal recognition is of great significance for threat analysis and intelligence support in radar electronic warfare. However it remains a challenging task due to (1) the variety of radar signal modulation types, (2)the increasingly saturated electromagnetic environment and the more serious influence of noise interference, and (3)the intrinsic real-time requirement of this application. In this paper, a novel automatic modulation recognition algorithm based on the joint architecture of convolution neural network (CNN) and the support vector machine (SVM) is proposed to comprehensively address these challenges. In particular, this algorithm first employs time-frequency analysis to better show the pulse representation in the time-frequency domain. Then a well-designed DCNN equipped with a hybrid attention (HA) mechanism and skip feature aggregation (SFA) is used to automatically learn the feature representations of distinctiveness from time frequency images. HA is designed to quickly capture the important information of local parts in sight and enhance the ability of the backbone network to mine high-level features. SFA is applied to selectively aggregate features among channels for self-monitoring, which improves the expression and generalization ability. Sixteen types of radar signals are used to verify the feasibility and effectiveness of this algorithm. The experimental evaluation shows that the proposed method not only achieve competitive accuracy with a better timeliness than state-of-the-art methods, but also achieves effective identification of most of the signal modulation types.

In this paper, a new wideband/narrowband fusion based motion estimation method is proposed for maneuvering target. In the fusion scheme, a fast motion parameters estimation method based on cross-correlation of adjacent echoes (CCAE) is adopted as the wideband estimation method. The narrowband estimation method is the maximum likelihood estimation with Newton’s method (MN method). The proposed method mainly includes three steps. Firstly, the velocity and acceleration of the target are estimated by CCAE. Secondly, the velocity and acceleration estimated by CCAE are adopted as the initial velocity and final acceleration of MN method, respectively. Finally, the high precision velocity and distance of the target are estimated by MN method. The proposed fusion method has two advantages. First, due to the large scope of the unambiguous velocity of CCAE, the velocity ambiguity problem of MN method is solved. Second, the three dimensional (3D) search in MN method is reduced to two dimensional (2D) search. Simulation results demonstrate that the proposed fusion method achieves similar estimation performances on distance and velocity with much lower computational cost, compared with the MN method.

Due to the mobility of underwater equipment, high-precision underwater positioning technology will face two technical challenges: dealing with mixed-field signals composed of near-field signals and far-field signals; adapting to variable component of mixed-field signals considering the mobility of equipment. Under this condition, an effective method based on MUSIC is addressed in this paper. After distinguishing far-field signal subspace from mixed-field signal subspace, estimations of DOAs and powers of far-field sources are carried out. Then the corresponding far-field and noise signal components can be eliminated from the signal subspace. After that, based on path-following algorithm, modified 2D-MUSIC is performed for DOA and range estimations of near-field sources. The performance of the proposed method is verified and compared with the other methods through computer simulations. Reasonable classification of source types and accurate localization estimation can be achieved by using the proposed method.

Voice activity detection remains a significant challenge in the presence of transients since transients are more dominant than speech, though it has achieved satisfactory performance in quasi-stationary noisy environments. This paper studies the differences between speech and transients in nonlinear dynamic characteristics and proposes a new method for accurately detecting speech and transients. Limited by algorithm complexity, previous research has proposed few detectors to model speech and transients based on contextual information and thus failing to detect transient frames accurately. To address this challenge, our study proposes to map features of audio signals to a time series complex network, a kind of graph data, analyzed by the Laplacian and adjacency matrix of graphs, then classified by the support vector machine (SVM) classifier. The proposed algorithm can analyze a more extended speech period, allowing the full utilization of contextual information of preceding and following frames. The experimental results show that the performance of this method has obvious superiority over other existing algorithms.

Automatic modulation recognition plays an important role in many military and civilian applications, including cognitive radio, spectrum sensing, signal surveillance, and interference identification. Due to the powerful ability of deep learning to extract hidden features and perform classification, it can extract highly separative features from massive signal samples. Considering the condition of limited training samples, we propose a semi-supervised learning framework based on Haar timefrequency (HTF) mask data augmentation and the positionalspatial attention (PSA) mechanism. Specifically, the HTF mask is designed to increase data diversity, and the PSA is designed to address the limited receptive field of the convolutional layer and enhance the feature extraction capability of the constructed network. Extensive experimental results obtained on the public RML2016.10a dataset show that the proposed semi-supervised framework utilizes 1 of the given labeled data and reaches a recognition accuracy of 92.09 under 6dB signals.