Specific emitter identification (SEI) is a security authentication technology by utilizing radio frequency fingerprinting (RFF) features. However, current mainstream RFF feature extraction methods based on neural networks (NNs) generally suffer from poor interpretability and difficulties in architecture optimization. To address these issues, we propose a novel convolution-enhanced swin vision transformer (CoSwinVIT) that combines filter characteristics of NN architectures to achieve a uniform spectrum response. Specifically, we treat the NN used in SEI tasks as filters and investigate their filter characteristics by applying Fourier transforms to hidden vectors. Through spectral analysis, we found that different NN architectures exhibit significantly different responses to the signal spectrum. This affects the model’s sensitivity to specific frequency bands of the signal, thereby influencing its accuracy (Acc). Subsequently, by integrating the filtering properties of swin vision transformer (SwinVIT) and convolutional neural network (CNN), we achieve a uniform spectral response design. Finally, to evaluate the performance of the CoSwinVIT architecture, we design both a supervised learning algorithm and a contrastive learning-based self-supervised algorithm. Experimental results on a real-world automatic dependent surveillance-broadcast (ADS-B) and wireless fidelity (WiFi) dataset indicate that CoSwinVIT provides a more uniform spectrum response. Under supervised learning, the proposed CoSwinVIT obtains the accuracies of 98.6% and 99.8% on the ADS-B and WiFi datasets, respectively. Under self-supervised learning with 5% and 10% labeled data, the accuracies of 73.6% and 86.3% are achieved on the ADS-B dataset, and the accuracies of 81.6% and 91.5% are achieved on the WiFi dataset. These results surpass the state-of-the-art (SOTA) methods used in the SEI tasks.

Deep learning has demonstrated promising results over traditional hand-crafted methods for automatic modulation classification (AMC), which plays a critical role as an intermediate step between signal detection and modulation. However, acquiring large-scale labeled data remains challenging, as both data quality and annotation costs are critical factors in achieving accurate and efficient training. In this paper, we propose a novel self-supervised contrastive learning (SSCL) with gradient-adversarial-based data augmentation (GADA) approach for AMC. Additionally, a meticulous encoder based on Transformer-LSTM architectures is employed to pre-train a feature extractor using unlabeled base classes. Subsequently, knowledge transfer is employed to fine-tune the feature extractor, and ensemble learning is introduced to efficiently leverage multiple classifiers for joint decision-making. Experiments demonstrate that we achieve up to 91.87% accuracy on the challenging large-scale RadioML2018.10a dataset, demonstrating performance competitive with state-of-the-art supervised implementations.

The broadcast nature of device authentication systems in the Internet of Things (IoT) and maritime transportation makes real-time signals susceptible to forgery attacks, leading to critical risks, such as information leakage and navigation failures. specific emitter identification (SEI) plays a crucial role in protecting communication systems from spoofing and tampering. However, traditional SEI networks struggle with limited generalizability, high-computational costs, and susceptibility to extraction and inversion attacks. To overcome these challenges, this article introduces sliding window linear attention and the convolution mechanism (SWLC)-Conformer, a novel hybrid SEI architecture that seamlessly integrates SWLC. The proposed architecture dynamically captures both local signal characteristics and global temporal dependencies through a hybrid design incorporating window-based attention blocks and depth-wise convolution layers. Furthermore, to strengthen system security against model inversion threats, we incorporate a perturbation mechanism that employs reverse sigmoid activation in the final feature representation. Experimental results demonstrate that SWLC-Conformer achieves high recognition accuracy, reaching 91.10% on the AIS100 dataset and 97.89% on the WiSig dataset, while maintaining FLOPs at 22.17M and 11.11M, respectively. In terms of security, SWLC-Conformer reduces the accuracy of stolen models by over 40% when the stolen dataset ratio is 0.9. This result highlights the effectiveness of the introduced defense mechanism in degrading the usability of stolen models through controlled feature obfuscation.

Specific Emitter Identification (SEI) is a non-encrypted authentication technology that adds a layer of security to wireless communications in intelligent transportation systems. However, most existing SEI methods are constrained to identify fixed classes and cannot learn incrementally. In practical applications, the constant emergence of new classes or tasks necessitates the capacity to continuously learn new classes from streaming data. In this paper, combining momentum-based prototype correction and hierarchical regularization, a simple and effective non-example class-incremental method for SEI is proposed, named MoPC-HR. The momentum-based prototype correction dynamically adjusts old class prototypes (i.e., old class centers), strengthening the separation between old and new classes and enabling smoother integration of new classes. Hierarchical regularization is applied at multiple levels to control feature differences between old and new classes, preventing the model from favoring new classes and reducing catastrophic forgetting. Experiments on real-world AIS-100 and ADS-B datasets show that MoPC-HR outperforms state-of-the-art methods. Specifically, in the incremental phase 20, MoPC-HR achieves an average accuracy of 97.04%, average forgetting of 2.95%, and average intransigence of 2.85% on the AIS-100 dataset; and an average accuracy of 95.99%, average forgetting of 3.66%, and average intransigence of 3.60% on the ADS-B dataset. The code is available at https://github.com/xmuLdz/MoPC-HR.git

In this paper, the Star‐Transformer model is improved to obtain more accurate direction of arrivals (DOA) estimation of underwater sonar uniform linear array (ULA) under low signal‐to‐noise ratio (SNR) conditions. The ideal real covariance matrix is divided into three channels: real part channel, imaginary part channel, and phase channel to obtain more input features. In training, the real covariance matrix is used under different SNRs. In testing, the covariance matrix of samples in the real environment is used as input. The on‐grid form is used to estimate the DOA of multiple signal sources, which is modelled as a multilabel classification problem. The results show that the model can be effective and can still have a good DOA estimation performance under the conditions of trained and untrained SNRs, different snapshots, signal power mismatch, different separation angles, signal correlation, and so on. It shows that the model has excellent robustness.

In this letter, we consider the problem of joint delay-Doppler shift estimation of multiple moving targets in a passive radar system using orthogonal frequency-division multiplexing communication signals. An atomic norm-based algorithm is proposed for better estimation performance and higher robustness against the demodulation error. We utilize a new atomic set with the unknown demodulation error from the direct-path signal included, aiming to reduce the impact of high symbol error rate (SER), in contrast to previous works that introduce$\ell _{1}$-norm to exploit the sparsity of the afore-mentioned error. By converting to a semidefinite program, the problem is solved under the convex optimization framework. Simulation results show that the proposed method performs better under high SER conditions.

Specific emitter identification (SEI) is a non-cryptographic authentication technique to provide an extra security layer for wireless devices, which has promising applications. However, the traditional methods of SEI are only available in limited equipments. In actual application scenarios, new devices (as new classes) are constantly appearing. In this paper, an effective class incremental learning (CIL) method is proposed for SEI, named class-incremental with self-training and prototype augmentation (CISP). It is a teacher-student network. Firstly, the teacher network trained by the old-class data is utilized to instruct the student network to adapt the new classes while retaining the old-class knowledge through the knowledge distillation (KD) techniques. Secondly, in order to mitigate the problem of favoring the new classes, weight aligning (WA) method is introduced to balance the weights of the new-class and old-class classification layers in the student network. Lastly, the old-class samples are recalled from the unlabeled dataset by the student network and input into the teacher network. Then the feature prototypes of the old classes are constructed and augmented. This would further ease the imbalance between the old and new classes and alleviate the problem of noisy pseudo-labels. Experiment results on the real AIS-100 dataset and ADS-B-100 dataset with the number of the initial classes being 20 and 20 classes per incremental step demonstrate that the proposed method can achieve an average accuracy of 95.29% and 95.84%, respectively. It effectively mitigates the catastrophic forgetting of the model and is superior to the state-of-the-art incremental learning approaches of not saving the old-class samples.

Two-dimensional Direction of arrival (2D DOA) is a challenging problem in sparse circular arrays (SCAs), especially in the field of underdetermined estimation. In this paper, based on sparse signal recovery (SSR) theory, an underdetermined 2D DOA estimation method is proposed for SCAs. The Khatri-Rao (KR) subspace method is introduced to construct a signal model for underdetermined DOA estimation. Then, different from the previous method of converting 2D discrete grids into 1D vectors, a new 2D SSR model based on a 2D over-complete basis is constructed. Finally, an improved algorithm based on the compressed sampling matching pursuit algorithm (CoSaMP) is used to realize SSR and implement underdetermined 2D DOA estimation. Numerical simulation results indicate that the proposed method has excellent DOA estimation accuracy with extremely low complexity.

The automatic identification system (AIS) is the automatic tracking system for automatic traffic control and collision avoidance services, which plays an important role in maritime traffic safety. However, it faces a possible security threat when the maritime mobile service identity (MMSI) that specifies the vessels’ identity in AIS is illegally counterfeited. To guarantee the communication security of AIS for preventing fraudulent devices, we design a novel lightweight Transformer-based network GLFormer for specific emitter identification (SEI) to provide an extra security layer for AIS terminal emitters. Concretely, the gated local attention unit (GLAU) and the gated sliding local attention unit (GSLAU) modules that combine a simplified gated attention unit (GAU) and a sliding local self-attention (SLA) are developed in GLFormer to extract the radio frequency fingerprint (RFF) features automatically from the raw in-phase signals. Especially, the simplified GAU focuses on more critical RFF features and filters out the irrelevant information from the raw signal to improve performance, which is also a single-head self-attention module with fewer parameters for lightweight. Meanwhile, the SLA limits self-attention operation to a window, introducing the inductive bias of local information to enhance performance further and reducing the quadratic computational complexity to linearity for efficiency. Experimental results demonstrate that the GLFormer achieves 96.31% and 89.38% identification accuracy in the constructed AIS transient and AIS steady-state datasets with 50 vessels, respectively. The 99.90% identification accuracy is achieved in the universal software radio peripheral (USRP) dataset with ten devices. It is not only better than the existing methods but requires much fewer parameters and lower computational complexity; besides, it is also suitable for working with long signal sequences.

Illegally forged signals in automatic identification system (AIS) pose a threat to maritime traffic safety management. In this paper, a multi-level sparse representation based identification (MSRI) algorithm is proposed for specific emitter identification (SEI) in the AIS. The MSRI innovatively combines neural networks with sparse representation based classification (SRC). Channel attention mechanism is introduced to a multi-scale convolutional neural network (CNN) for extracting hidden features in the signal. These extracted features are divided into shallow and deep features according to the depth of the network layer they are extracted from. The original AIS signals and the two-level features are spliced together to form a multi-level dictionary. Subsequently, a sparse representation based identification is performed on the decorrelated multi-level dictionary using the principal components analysis (PCA) method. The proposed MSRI is evaluated on a dataset composed of real-world AIS signals, and compared with the state-of-the-art identification algorithms. The evaluation is based on several factors including computational complexity, number of training samples, and number of emitters. Numerical results indicate that the proposed algorithm can identify emitters with higher accuracy and requires lower training time compared to other methods. Given more than 15 training samples at each emitter, the MSRI can identify nine emitters with an accuracy higher than 90%.

It has been demonstrated that the cubic convolution spline interpolation (CCSI) scheme is one of the best algorithms for image resampling or compression. In this paper, a new simple direct computation of CCSI is proposed, where the sampled data are directly calculated by the use of the original data. Moreover, the proposed algorithm provides a regular and simple structure based on linear correlation and thus is naturally suitable for VLSI implementation. Computer simulations on several standard images indicate that the proposed simple direct computation of CCSI scheme can achieve almost the same objective and subjective performance with lower complexity.

The joint base matrix BJof the joint source-channel coding (JSCC) system based on double protograph low-density parity-check (DP-LDPC) codes consists of four components, namely, the source code Bs, the channel code Bc, the type1 connection edge BL1and the type-2 connection edge BL2, each having a non-negligible influence on the system performance. Different from the traditional component-specific design approach, we propose a joint design and optimization algorithm based on the idea of multi-objective differential evolution (MODE). Specifically, we consider the optimization of the DP-LDPC JSCC system through joint design of three components Bs, Bc, BL1and all four components Bs, Bc, BL1, BL2, respectively. The proposed algorithm has low search complexity due to the reduction in size and element value of base matrices. The joint protograph extrinsic information transfer (JPEXIT) analyses and the simulation results demonstrate that the resulting JSCC system is free from a high error floor, requires fewer number of iterations for reaching the same bit error rate (BER) and achieves significant coding gains as compared to the state-of-the-art. Our DP-LDPC JSCC system is also shown to outperform its separation-based counterpart by a wide margin.

A novel near lossless image compression method is proposed in this paper. In the proposed method, a redundant representation of the image is firstly obtained by pixel level shifting and then partitioned into image blocks with the same size. Next, the image blocks are classified into smooth image blocks and non-smooth image blocks. For the smooth image blocks, improved block coding which includes mean residual error is utilized for pixel rectangles with the same pixel value in each to remove the redundancy. Lastly, the whole image is scanned by efficient image scanning that only one pixel is scanned for each pixel rectangle and then compressed by Huffman coding. Simulation results indicate that the proposed method has good performance compared with traditional lossless/near lossless image compression methods.

Sparse signal reconstruction algorithms in compressive sensing mainly focus on greedy algorithms, which are short-sighted. In this letter, an optimization-oriented algorithm using global optimization method is proposed to reconstruct the sparse signal. First, a pre-selection is made to estimate the most likely support of the sparse signal. Second, a backtracking strategy is introduced to avoid the over-fitting problem. Last, an optimization-oriented search strategy is designed to refine the pre-selected support toward the best estimate of the signal support. Numerical results demonstrate that the proposed algorithm performs better for sparse signal reconstruction with moderate computational complexity compared with the existing algorithms.

Joint-sparse signal reconstruction is a key issue in distributed compressed sensing based on the mixed support set model. In this letter, a novel joint-sparse signal reconstruction algorithm is proposed based on the common support set refinement. The common support set is first roughly estimated by greedy pursuit algorithms. The roughly estimated common support set is then refined by pruning the incorrect elements. With the refined common support set, greedy pursuit is utilized to reconstruct the joint-sparse signals. The complexity analysis and simulation results indicate that the proposed algorithm achieves better estimates of the support sets and finally reduces the reconstruction error for the joint-sparse signals with a moderate complexity compared with the state-of-the-art algorithms.

In this paper, a dual-mode differential chaos shift keying with index modulation (DM-DCSK-IM) is proposed. In the proposed system, the bit stream is partitioned into two subblocks, where the first subblock is the mapped bits used to select the active time slot, which presents the time slot's constellation mode, and the second subblock is the modulated bits, which are further divided into two groups and modulated by a pair of distinguishable modem-mode constellations, respectively. Unlike the recently proposed pulse-position-modulation differential chaos shift keying (PPM-DCSK), since both the active and inactive time slots are applied to convey the information bits, the data rate of the proposed system can be promoted significantly. In order to detect the active time slots and recover the mapped bits as well as modulated bits correctly, we propose an effective detection algorithm for the proposed system. Furthermore, the theoretical bit error rate (BER) expressions are derived over additive white Gaussian noise (AWGN) and multipath Rayleigh fading channels, and the simulation results validate the accuracy of our derivations. Finally, the BER performance of the proposed system is compared with the other non-coherent chaotic communication systems, and the results indicate that the proposed system can offer competitive and satisfactory BER performance.

In this paper, an M -ary orthogonal multilevel differential chaos shift keying system with code index modulation (CIM-OM-MDCSK) is proposed. In the proposed system, the multiple information bearing signals are modulated by the selected Walsh codes with specific indices and the M -ary information signals which are composed of modulated bits, chaotic signals, and their Hilbert transform. Since the reference signal along with the information bearing signals are overlapping in time domain and orthogonal in code domain by using Walsh code sequences, the spectral efficiency of the CIM-OM-MDCSK system is improved largely. By combining the M -ary modulation, orthogonal multilevel modulation, and code index modulation, the proposed CIM-OM-MDCSK system can achieve high data rate and superior bit error rate (BER) performance compared to its rivals. Moreover, we derive the BER expressions of the proposed system over additive white Gaussian noise and multipath Rayleigh fading channels. Finally, we make a performance comparison between the proposed system and other state-of-the-art non-coherent chaotic communication systems. The results confirm the competitive benefits of the proposed system.

Cubic-spline interpolation (CSI) scheme is known to resample the discrete image data based on the least-square method with the cubic convolution interpolation (CCI) function. It is superior in performance to other interpolation functions for digital image processing. In this paper, an improved approach to the CSI scheme is proposed for the decimation and interpolation of image data. The proposed CSI scheme combines the least-square method with six-point CCI function to improve performance. Moreover, a novel low-complexity implementation algorithm is proposed to simplify the decimation and achieve improvement of the computational efficiency. Computer simulations indicate that the proposed CSI scheme can achieve better performance without increasing the computational complexity compared with the four-point CSI scheme.

In this paper, we propose a method for fusion of low-resolution multispectral (LRM) image and high-resolution panchromatic (HRP) image to obtain high-resolution multispectral (HRM) image based on distributed compressed sensing (DCS). In the proposed method, HRP image is firstly used to obtain approximation and detail dictionary. Then, joint-sparsity-model-1 (JSM-1) is applied directly to both LRM bands and HRM bands. Each band in LRM image is decomposed into common component and innovation component which can be sparsely represented over the approximation dictionary. Based on Orthogonal Matching Pursuit (OMP) algorithm, the sparse coefficients are calculated from JSM-1 of the LRM image. Lastly, each band in HRM image is modeled as the fusion of the corresponding LRM band and detail band over the detail dictionary. Two datasets are used in the experiments to validate the proposed method and the results show that the proposed method has better performance than the traditional methods.

For a joint source–channel coding system based on double protograph low‐density parity‐check codes, the exchange of extrinsic information through edge connection between the source code and channel code is essential for good performance. In this study, the relationship between the performance and edge connection in the tanner graph is analysed and it has never been seen in the literature to the authors' knowledge. Both the joint protograph extrinsic information transfer and simulation results indicate that the edge connection should be optimised in practical applications since it plays an important role in the bit error rate performance and an optimisation scheme for the edge connection is put forward to enhance performance.

In this paper, by applying M-ary constellation modulation to code shifted differential chaos shift keying (CS-DCSK), a new M-ary DCSK which is called CS-MDCSK, is proposed. In the proposed scheme, the reference chaos signal is the same with the CS-DCSK, and the two orthogonal components of information bearing signal are obtained by two Walsh codes. Furthermore, the proposed CS-MDCSK is extended to general scheme (GCS-MDCSK), which transmits more than one M-ary constellation information bearing signals with one reference. Since high order constellations are used, the proposed scheme enhances the spectrum efficiency compared to CS-DCSK and GCS-DCSK. By computer simulations, the bit error rate (BER) performance of two proposed systems are compared to that of CS-DCSK and GCS-DCSK, respectively. Simulation results show that the proposed systems outperform the CS-DCSK and GCS-DCSK when 4-ary constellation is applied.

The cubic‐spline interpolation (CSI) scheme is known to be designed to resample the discrete image data based on the least‐square method in conjunction with the cubic convolution interpolation (CCI) function. In this CSI scheme, the improved quality of resampling can be achieved as the interpolation kernel size increases. However, the improvement of the performance gets less and less. This means that the performance of the CSI scheme has not been significantly improved and converges toward a constant value when the interpolation kernel size exceeds a certain value. A proof of this result is given in this study and has never been seen in the literature to the authors' knowledge. Moreover, this study analyses the relationship between the performance and computational complexity of the CSI schemes with different interpolation kernel sizes and compares them from a structural point of view. Simulation results indicate that it is in agreement with the theoretic derivations. Since the arithmetic operations required are increasing linearly with the increment of the interpolation kernel size, selecting an interpolation kernel size gives the best trade‐off between the performance and computational complexity in practical applications. However, the optimum choice of the interpolation kernel size depends crucially on effective demand.

Recently, the perfect Gaussian integer sequences have been widely used in modern wireless communication systems, such as code division multiple access and orthogonal frequency-division multiplexing systems. This letter presents two different methods to generate the long perfect Gaussian integer sequences with ideal periodic auto-correlation functions. The key idea of the proposed methods is to use a short perfect Gaussian integer sequence together with the polynomial or trace computation over an extension field to construct a family of the long perfect Gaussian integer sequences. The period of the resulting long sequences is not a multiple of that of the short sequence, which has not been investigated so far. Compared with the already existing methods, the proposed methods have three significant advantages that a single short perfect Gaussian integer sequence is employed, the long sequences consist of two distinct Gaussian integers, and their energy efficiency is monotone increasing.

In this paper, we propose an efficient data-driven particle probability hypothesis density (PHD) filter for real-time multitarget tracking of nonlinear/non-Gaussian system in dense clutter environment. In specific, the input measurements are first classified into two sets, namely survival measurements and spontaneous birth measurements, after eliminating clutters by using existing historic state data of targets. Since most clutters do not participate in the complex weight computation of particle PHD filter, better real-time performance can be achieved. The tracking performance is also improved because the survival measurements are used for survival targets and the spontaneous birth measurements are used for spontaneous birth targets, resulting in less interference from each other and from clutters. Extensive simulations validate the improvement of both the real-time performance and tracking performance of the proposed data-driven particle PHD filter in comparison with the traditional particle PHD filter.

The cubic-spline interpolation (CSI) scheme can be utilized to obtain a better quality reconstructed image. It is based on the least-squares method with cubic convolution interpolation (CCI) function. Within the parametric CSI scheme, it is difficult to determine the optimal parameter for various target images. In this paper, a novel method involving the concept of opportunity costs is proposed to identify the most suitable parameter for the CCI function needed in the CSI scheme. It is shown that such an optimal four-point CCI function in conjunction with the least-squares method can achieve a better performance with the same arithmetic operations in comparison with the existing CSI algorithm. In addition, experimental results show that the optimal six-point CSI scheme together with cross-zonal filter is superior in performance to the optimal four-point CSI scheme without increasing the computational complexity.