Spectrum sensing is one of the technologies that is used to solve the current problem of low utilization of spectrum resources. However, when the signal-to-noise ratio is low, current spectrum sensing methods cannot well-handle a situation in which the prior information of the licensed user signal is lacking. In this paper, a blind spectrum sensing method based on deep learning is proposed that uses three kinds of neural networks together, namely convolutional neural networks, long short-term memory, and fully connected neural networks. Experiments show that the proposed method has better performance than an energy detector, especially when the signal-to-noise ratio is low. At the same time, this paper also analyzes the effect of different long short-term memory layers on detection performance, and explores why the deep-learning-based detector can achieve better performance.

Automatic modulation classification (AMC) is pivotal in both cooperative and non-cooperative communication systems. Despite achieving significant success in this field, deep learning (DL) is challenging to adapt to varying modulation parameters and channel conditions for its reliance on training data. Deep transfer learning (DTL) emerges as a potent tool to address the distribution divergence of the training and testing data, demonstrated by its successful applications in computer vision (CV). Since research on DTL within signal processing remains infantile, this paper offers a comprehensive review of current state-of-the-art (SOTA) research on DTL in modulation classification. The background and theoretical models of DTL are firstly illustrated. Specially, a detailed analysis of how transmission and reception impact data probability density function (PDF) is demonstrated for the first time. Through analyzing current literature, we identify three key classification criteria for DTL-based AMC: 1) what to transfer, 2) relationship between source and target domains or tasks, and 3) availability of labels. In addressing what to transfer, we provide a detailed conclusion and comparison of subclasses, including model-parameter-transfer, feature-representation-transfer, and instance-transfer methods. Lastly, this review discusses recent research trends and outlines future directions for DTL in AMC.

With the advance in wireless network technique, its security becomes of paramount importance. Radio Frequency Fingerprint (RFF) is the underlying characteristic of hardware chains in transmitters, which can be used as a unique ID for specific emitter identification (SEI) and a non-cryptographic access authentication technology in the physical layer to enhance wireless network security. To date, few studies have extracted the inevitable non-linearity in the transmitter as RFF features. Hence, this letter provides a novel nonlinear dynamics approach based on Multi-dimension Approximate Entropy (MApEn) for SEI. Specifically, this method utilizes the steady-state portion of the preamble structure of Standard IEEE802.11b/g to obtain the nonlinear properties of wireless network cards. The experimental results demonstrate that the proposed identification method outperforms the existing steady-state methods in terms of identification accuracy.

The widespread and massive application of multi-function radars (MFRs) pushes MFR modeling to become a recognized need in electronic intelligence (ELINT). Since pioneer research has made trials in the model-centric ELINT from various viewpoints, a universal hierarchical modeling framework is needed at the emergence. To fill the absence and capture future trends, we illustrate the mathematical logic in modeling MFR and propose an MFR modeling framework (named MFRModeling ) by studying and summarizing current literature. To be specific, the MFRModeling contains pulse interception, pulse representation, hierarchical model design, pulse dictation, and evaluation. For the pulse dictation step, we design a novel two-stage processor, comprising of the pulse-to-symbol and symbol-to-symbol transformer. Based on the proposed MFRModeling , current literature’s phases are extracted, grouped, and compared. Finally, recent research trends and the overarching future outlook for MFR modeling in next-generation ELINT are discussed.

With the popularization of the Internet of Things (IoT), its security has become increasingly prominent. Radio-frequency fingerprinting (RFF) is a promising approach to identify a specific emitter by extracting the intrinsic physical layer characteristics from transmitted signals, adopted as a lightweight noncryptographic access authentication technique. The realization of RFF relies on unintentional modulation of the pulse (UMOP). In this article, we discover the locality and inhomogeneity of RFF, that is, UMOP is concentrating in the radio-frequency fingerprint distribution subregion (RFDR), instead of evenly distributed over the entire feature. This property is demonstrated in the cepstral domain based on the transmitter distortion models. This is the first time that the inhomogeneity of UMOP and the cepstral domain analysis are employed in RFF. First, to automatically search the RFDRs, a method based on the dispersion characteristic index (DCI) and emitter-specific information index (ESI) is proposed, where DCI provides constraints on the scattering characteristics of RFF feature clusters and ESI evaluates the local differences of RFF features. Second, combining the RFDR selection method with the cepstrum analysis, a new feature CepH is obtained. Systematic experiments are conducted on the simulated data sets containing multiple modulation patterns and received data sets from multiple sources, which show that the RFDR is not affected by the modulation pattern and noise, and has high practicability. It also demonstrates that the proposed algorithm outperforms the state-of-art algorithms, especially in the case of a low signal-to-noise ratio (SNR). It can achieve a recognition accuracy of more than 90% under 0 dB.

This letter addresses the issue of underfitting or failure of deep learning models caused by insufficient training samples. Unlike previous supervised methods, a new few-shot learning semi-supervised automatic modulation recognition method based on multimodal information and domain adversarial network is proposed herein. The fusion input of multimodal information realizes the joint utilization of modulated signal modal features in the time and frequency domains. Domain adversarial training mines the potential knowledge information of a large number of unlabeled target domain data and introduces the convolutional block attention module (CBAM) to enhance the ability of the network to represent the key features of data. Numerical results validate the high-average classification accuracy of the proposed scheme compared to that of state-of-the-art schemes using fewer samples, particularly in high-order modulation classification. Alternative network structures are compared to confirm the applicability of multimodal information, domain adversarial training, and CBAM.