Figure - available from: Electronics Letters
This content is subject to copyright. Terms and conditions apply.
Source publication
Automatic modulation classification (AMC) is an important and challenging task that aims to discriminate modulation formats of received signals, such as military communications, cognitive radio and spectrum management. With the development of deep learning techniques, research in AMC has gained promising results because of its powerful representati...
Similar publications
Direct sequence spread spectrum (DSSS) communications are highly significant in military and civilian wireless communications because of its ability to resist narrowband interference, multipath interference and high security. However, under low signal-to-noise ratio (SNR), the detection of DSSS signals becomes very difficult under non-cooperative c...
Citations
... In [9], the modulated signals are converted into cyclic spectra and constellation diagrams, and classified by neural networks. In [10], a new network architecture that combines a frequency selection module and a convolutional neural network (CNN) is proposed to handle raw signal data with carriers. In [11], constellation diagrams of signals are used for the classification and achieve significant performance. ...
Automatic modulation classification (AMC) plays an important role in various applications such as cognitive radio and dynamic spectrum access. Many research works have been exploring deep learning (DL) based AMC, but they primarily focus on single-carrier signals. With the advent of various multicarrier waveforms, the authors propose to revisit DL-based AMC to consider the diversity and complexity of these novel transmission waveforms in this letter. Specifically, the authors develop a novel representation of multicarrier signals and use suitable networks for classification. In addition, to cope with non-target signals, support vector data description (SVDD) is applied with the activations of the networks’ hidden layer. Experimental results demonstrate the effectiveness of the proposed scheme.
... For instance, the authors in reference [5] used continuous wavelet transform (CWT) and a feed-forward neural network, which showed good performance on four signal categories. In FSMCNN [6], a convolutional neural network (CNN) was introduced for the classification of six signal categories, where a weighted frequency selection layer was used to process the raw signal data with carriers and increase the in-band SNR. Despite their powerful feature representation abilities, CNNs require a large number of labelled samples at a finegrained modulation level for all categories to perform the training, which limits their applicability under the condition of scarce samples. ...
... In the work [25], the effect of ResNet was analysed on the baseline performance of radio signal classification based on deep learning. Similarly, to reduce the interference of noise and achieve a faster convergence, a frequency selection module was presented for forward feature extracting, followed by a CNN to classify the modulation patterns [6]. Besides, the authors in [26] constructed a CNN to identify the features extracted by the Wigner-Ville distribution (WVD). ...
... Compared with meta-learning models, the proposed method achieved a better feature extraction to adapt to MFR finegrained modes classification rather than relying on the previous experiences with other datasets, such as ImageNet [41]. Step length [4,6,8] Baker Carrier frequency fc 0~500 MHz ...
Multi‐function radars (MFRs) are sophisticated sensors with fine‐grained modes, which modify their modulation types and parameters range generating various signals to fulfil different tasks, such as surveillance and tracking. In electromagnetic reconnaissance, recognition of MFR fine‐grained modes can provide a basis for analysing strategies and reaction. With the limit of real applications, it is hard to obtain a large number of labelled samples for existing methods to learn the difference between categories. Therefore, it is essential to develop new methods to extract general knowledge of MFRs and identify modes with only a few samples. This paper proposes a few‐shot learning (FSL) framework based on efficient neural architecture search (ENAS) with high robustness and portability, which designs a suitable network structure automated and quickly adapts to new environments. The experimental results show that the proposed method can still achieve excellent fine‐grained modulation recognition performance (92.6%) under the condition of ‐6 dB signal‐to‐noise ratio (SNR), even when each class only provides one fixed‐duration signal sample. The robustness is also verified under different conditions.
... To deal with crashed signals due to additive noise, a novel CNN-based framework [103] was introduced with three modules: SNR prediction, classification, and signal processing, in which the input signals estimated with low SNR were first reconstructed by U-Net [104] for signal re-construction and enhancement and then provided to a CNN for classification. To handle the unknown intermediate frequency and noncooperative modulation, Liu et al. [105] introduced a novel frequency selection layer to first detect the frequency band of signals and then filter out the out-of-band noise. In [106], the problem of unfixed-length signals feeding to the fixed-size input layer of CNNs was solved by three fusion mechanisms, including feature-based fusion, confidence-based fusion, and voting-based fusion, which were integrated into the adapted multi-stream architectures of VGG and ResNet [79]. ...
Automatic modulation classification (AMC), which aims to blindly identify the modulation type of an incoming signal at the receiver in wireless communication systems, is a fundamental signal processing technique in the physical layer to improve the spectrum utilization efficiency. Motivated by deep learning (DL) high-impact success in many informatics domains, including radio signal processing for communications, numerous recent AMC methods exploiting deep networks have been proposed to overcome the existing drawbacks of traditional approaches. DL is capable of learning the underlying characteristics of radio signals effectively for modulation pattern recognition, which in turn improves the modulation classification performance under the presence of channel impairments. In this work, we first provide the fundamental concepts of various architectures, such as neural networks, recurrent neural networks, long short-term memory, and convolutional neural networks as the necessary background. We then convey a comprehensive study of DL for AMC in wireless communications, where technical analysis is deliberated in the perspective of state-of-the-art deep architectures. Remarkably, several sophisticated structures and advanced designs of convolutional neural networks are investigated for different data types of sequential radio signals, spectrum images, and constellation images to deal with various channel impairments. Finally, we discuss some primary research challenges and potential future directions in the area of DL for modulation classification.
