RF transmitter identification is facing a big challenge since the increasing use of wireless devices in recent years. Traditional methods for identification are implemented by choosing specific rapid fingerprints manually, which fails to distinguish threats from unknown or rogue transmitters in a few shots under the complex electromagnetic environment. In order to solve this problem, a combined Siamese networks learning method for RF transmitter identification (CSNTI) is proposed in this work by considering both the data augmentation and the classical fingerprints of RF signals. The proposed method is composed of a series of classifiers trained by Siamese networks. Each classifier is utilized to distinguish one transmitter from others. Based on the special structure of Siamese networks, the number of training samples for each classifier increases greatly, which is efficient for data augmentation and takes full use of the limited RF transmitter signals. Then, the softmax procedure is followed to normalize the output of all classifiers. A criterion for unknown transmitters’ identification is proposed. Numerical experiments for basic classification and new devices identification with eight known transmitters and three unknown transmitters are validated. Results of compared methods suggest that the highest accuracy across a broad range of conditions is achieved by the proposed method.
22 April 2024 in IEEE Transactions on Instrumentation and Measurement
In wireless communication security and spectrum management, specific emitter identification (SEI) is a potential technology to identify individual emitters. Recently, a novel SEI algorithm based on complex-valued neural network (CVNN) has emerged, which exhibits powerful processing capabilities in complex domains. However, it also brings high computational complexity, which makes it difficult to meet the power efficiency requirements of the system. To address the above challenge, a Zynq-based SEI platform with conditional-reconfigurable CVNN is proposed in this article, including processing system (PS) and programming logic (PL). The platform can adaptively reconfigure CVNN based on sample difficulty to perform conditional computation between lightweight student network and high-performance teacher network, which achieves high power efficiency while maintaining high accuracy. Inside the PL, a conditional configuration engine and a configurable CVNN engine are specifically designed for CVNN acceleration and controlled by the PS. The experiment results on the public ORACLE RF dataset show that our platform can achieve a high power efficiency of 88.32 giga operations per second per watt (GOPS/W) and a high accuracy of 99.18%.
Sparsity is one of the key concepts that allows the signal recovery at a significantly lower subsample rate than required by the Nyquist-Shannon sampling theorem. By using a multistate transform, such as wavelets and shearlets system, the sparse representation of signals can be obtained. To further exploit the sparsity of the reconstructed signal, a generalized gradient regularizer is introduced to the proposed model. Motivated by the idea of iterative support detection (ISD), an optimization algorithm framework for image deblurring is given. The algorithm aims to solve a reweighted ℓ0-minimization problem in split Bregman framework, and the weights used for the next iteration are decided by an ISD process. The advantage of this process is that it forms an iterative-feedback mechanism, which improves the effectiveness for solution searching. A series of experiments are presented to demonstrate the availability of the proposed framework. Experimental results show that this method yields significant improvement in peak signal-to-noise ratio when compared to other counterparts. However, the numerical experiments also show that more computing time is required due to the utilization of the redundant multiscale system.
In this paper, we will construct a new multilevel system in the Fourier domain using the harmonic wavelet. The main advantages of harmonic wavelet are that its frequency spectrum is confined exactly to an octave band, and its simple definition just as Haar wavelet. The constructed multilevel system has the circular shape, which forms a partition of the frequency domain by shifting and scaling the basic wavelet functions. To possess the circular shape, a new type of sampling grid, the circular-polar grid (CPG), is defined and also the corresponding modified Fourier transform. The CPG consists of equal space along rays, where different rays are equally angled. The main difference between the classic polar grid and CPG is the even sampling on polar coordinates. Another obvious difference is that the modified Fourier transform has a circular shape in the frequency domain while the polar transform has a square shape. The proposed sampling grid and the new defined Fourier transform constitute a completely Fourier transform system, more importantly, the harmonic wavelet based multilevel system defined on the proposed sampling grid is more suitable for the distribution of general images in the Fourier domain.
This work focuses on the problem of rain removal from a single image. The directional multilevel system, Shearlets, is used to describe the intrinsic directional and structure sparse priors of rain streaks and the background layer. In this paper, a Shearlets-based convex rain removal model is proposed, which involves three sparse regularizers: including the sparse regularizer of rain streaks and two sparse regularizers of the Shearlets transform of background layer in the rain drops’ direction and the Shearlets transform of rain streaks in the perpendicular direction. The split Bregman algorithm is utilized to solve the proposed convex optimization model, which ensures the global optimal solution. Comparison tests with three state-of-the-art methods are implemented on synthetic and real rainy images, which suggests that the proposed method is efficient both in rain removal and details preservation of the background layer.