Search

Automatic modulation recognition is a major project in the field of radio cognition; however, the generalization ability of conventional models cannot satisfy practical applications. In order to improve the generalization performance of the deep learning model and increase its recognition efficiency, we propose a novel model: ElsNet (elastic convolutional neural network). This network designs a channel optimization module, by inputting the average pooling information of the feature map and the intrinsic parameters of the batch normalization layer, to dynamically optimize the connection relations between network neurons and enhance the generalization ability of the model. ElsNet achieves an accuracy of about 94% at signal-to-noise ratios of 0-20 dB. Subsequent experiments have also demonstrated that, the ElsNet has a satisfying performance in transferred data sets and a peak accuracy of 82% through transfer learning, which to a certain extent alleviates the problem that the current signal modulation recognition can only be applied to signals with the same modulation parameters as the training dataset and has poor performance in recognizing real signals with different modulation parameters. [ABSTRACT FROM AUTHOR]

Deep learning (DL) classifiers have significantly outperformed traditional likelihood-based or feature-based classifiers for signal modulation recognition in non-cooperative environments. However, despite these recent improvements, the conventional DL classifiers still have an unintended problem in handling the received signal in which the in-phase and quadrature components are separated. Even though the two components seem to be individually uncorrelated to each other, they are definitely the theoretical real and imaginary parts of a signal sample in the complex domain. Thus, it may be helpful for a classifier to regard and treat the modulated signal as a complex data array representing beneficial mutual information between the two real data arrays. In this paper, we propose two types of fully complex convolutional neural network (CNN) and residual neural network (ResNet) classifiers that deal with the complex data instead of the two separated data. First, we organize and define the core complex operations for implementing the complex DL classifiers. Next, the architectures of the proposed classifiers are realized by applying the structural optimizations and the regularization technique. Then, the various aspects of the classifiers’ performance are analyzed and explained for providing comprehensive and deep understandings: (a) the effectiveness of the complex signal handling, (b) the in-depth evaluation of classification accuracy, (c) the impact of the data size on performance, and (d) the computational complexity. The experimental results show that the proposed classifiers can provide the faster learning speed, the higher optimization, and the better generalization with sacrificing acceptable learning and classification costs. Especially, our approaches remarkably improve the performance on the mutually correlated modulation types (i.e., the phase-related modulations: PSK, APSK, and QAM) even in the less-scale datasets.

Automotive radars have faced to various jamming signals with different types and parameters. One counter measure is to identify the fine-grained modulation types of these jamming signals, which can provide supplementary information for intercepting. Most existing signal modulation recognition methods attempt to establish a machine-learning mechanism by training with a large number of annotated samples, which is hardly applicable in real-world electronic reconnaissance scenarios where only a few samples can be intercepted in advance. Few-Shot Learning aims to learn from base classes with many samples and infuse this knowledge to support classes with only a few samples, thus realizing model generalization. In this paper, inspired by the fact that the energy distribution of the signal of interest is always concentrated in time-frequency images, a novel few-shot learning framework based on foreground segmentation is proposed, which benefits from its powerful filtering to remove the noise and clutter from background. The experimental results show that the proposed method can achieve excellent performance for fine-grained signal modulation recognition even with only one support sample and is robust under different signal-to-noise-ratio conditions. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Signal Processing is the property of Journal of Signal Processing and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Signal modulation recognition is the core of cognitive radio and spectrum sensing. With the rapid development and application of deep learning technology in recent years, multi-modal deep learning has become the mainstream of multi-modal machine learning. However, its usage in communication systems has not been well explored. This paper proposes a signal contour stellar images domain recognition method based on deep learning (DL) to achieve the problem of low recognition accuracy under low signal-to-noise ratio. A signal I/Q waveform domain recognition method based on deep complex-valued neural network is proposed to extract the amplitude and phase features of signals to achieve high-precision and high-robustness recognition of multiple signals. A multi-modal deep learning method is proposed to fuse image features, amplitudes, and phase features extracted by complex-valued neural networks to further improve the recognition accuracy and robustness of signals. Finally, the simulation results show the superiority of the scheme and prove that the scheme utilizes the complementarity between signal multi-modalities, removes the redundancy between the modes, and realizes the deep intelligent extraction of signal features, which can lead to a better signal recognition effect. [ABSTRACT FROM AUTHOR]