Spaceborne Synthetic Aperture Radar (SAR) working mode recognition is crucial for intention perception against SAR, threat level evaluation, and subsequently guiding the electronic jamming system to protect our key regions. However, as spaceborne SAR develops towards flexibility and intelligence, the agility of its waveforms and beams, as well as the overlap of parameters in different working modes, have posed significant challenges for the rapid and high-accuracy recognition of spaceborne SAR working modes. To improve the ability of spaceborne SAR working mode recognition in complex electromagnetic environments, this article proposes a spaceborne SAR working mode recognition method based on the Multi-scale Transformer (MFormer) network assisted by SAR semantic information. First, this method introduces SAR semantic information into the model input to mitigate the influence of outliers on recognition performance. Second, a multi-scale network is designed to sequentially input tokens of different scales into different layers of the Transformer encoder, fusing multi-scale information and enhancing the network’s ability to extract sequence features. Our experiments demonstrate the effectiveness, robustness, and generalization of this method in spaceborne SAR working mode recognition. In the non-ideal case of missing pulses and spurious pulses, our method outperforms other methods in terms of accuracy, macro Precision, macro Recall, and macro F1-score. Our method maintains over 80% recognition accuracy under conditions with 20% spurious and missing pulses.

The primary objective of jamming strategy optimization is to ensure that a jammer timely finds an effective jamming strategy against the multifunction radar (MFR), thereby ensuring the safety of targets. Deep reinforcement learning (DRL) has been widely applied in solving the problem of jamming strategy optimization. However, the process still faces challenges such as low learning efficiency and a heavy memory burden. Therefore, we propose a fast jamming strategy optimization method with imperfect experience. Firstly, we model the radar countermeasure process as a Markov decision process (MDP), and formulate the jamming reward function by combining the jamming effectiveness and the jammer’s operational intent. Secondly, we design a novel hybrid jamming strategy choice module, which uses imperfect experience to improve the optimization efficiency of jamming strategy. Furthermore, to improve sample efficiency and reduce forgetting caused by small replay buffer, we respectively employ a mixed replay buffer strategy and a knowledge consolidation technique. Finally, extensive experiments demonstrate that under the guidance of imperfect experience, our proposed method achieves faster convergence speed and higher strategy accuracy compared with existing DRL-based methods.

Compact low-poly building models with concise structures and texture fidelity are essential infrastructure for digital twin cities. Traditional point cloud-based reconstruction methods often rely on surface normals, and the presence of missing data and noise poses significant challenges for accurate reconstruction. In this paper, we propose GS2Poly, a textured polygonal mesh reconstruction method for buildings based on the 3D Gaussian Splatting (3DGS) framework. Firstly, 3DGS of the building scene is reconstructed under planar structure constraints. A density-weighted Gaussian sampling method is utilized to sample high-quality surface point clouds and extract planar primitives from 3DGS reconstruction results. Next, GS2Poly applies an adaptive spatial partitioning strategy to generate a set of candidate convex polyhedra. Finally, guided by the Gaussian opacity field, a Markov random field is constructed to extract the polygonal mesh surface, followed by high-fidelity texture mapping using an optimal rendering strategy. Experimental results across diverse building scenarios demonstrate that GS2Poly exhibits higher geometric fidelity than spatial partitioning-based or 3DGS-based mesh simplification methods. Additionally, the proposed texture mapping strategy effectively avoids typical texture artifacts such as occlusion, seams and distortions.

With the emergence of novel and complex jamming types, jamming recognition as the primary step in radar anti-jamming is facing tremendous challenges. However, traditional methods experience significant difficulties in identifying increasingly complicated jamming types due to excessive manual dependence and inferior generalization performance. To alleviate the above challenges, we propose a novel recognition framework called Residual Attention Network (RA-Net). Specifically, we integrate channel and spatial attention to learn refined feature representations, which benefits the final recognition accuracy. To further optimize our proposed method, we introduce a polynomial loss to learn a robust feature space. Experimental results on simulated datasets with 19 types of jamming have demonstrated improvement of our proposed RA-Net over traditional methods.

The existence of Comb Spectrum Modulation Jamming (CSMJ) degrades the imaging quality severely, which hinders the performance of Synthetic Aperture Radar (SAR). The frequency domain-notched filtering is applicable in dealing with CSMJ but would introduce severe signal loss. In this paper, we propose a novel method for CSMJ suppression based on a dual-path residual network with the attention mechanism (DPRA-Net). We use the attention mechanism to build inter-dependencies among local and global features in the frequency domain for improving the suppression performance of DPAR-Net. Consequently, the CSMJ suppression problem is transformed into an end-to-end mapping problem, which minimizes signal loss. The validity of our algorithm has been verified on the measured data collected by Sentinel-1.

In complex electromagnetic environments, wideband interference (WBI) may severely affect the imaging quality of synthetic aperture radar (SAR). Because it occupies a large bandwidth, which overlaps with target echoes, the WBI is difficult to mitigate. The existing WBI suppression methods based on filtering or transform-domain analysis usually suffer from a model mismatch. To tackle this problem, a method combining instantaneous frequency (IF) estimation and regularized time-frequency filtering (RTFF) is proposed for WBI suppression and individual components extraction. First, the WBI-corrupted SAR echo is characterized in the time-frequency domain by short-time Fourier transform (STFT) with adaptive window width, determined by the proposed window width optimization method. Then, the IFs of the WBI components are estimated by ridge path detection and regrouping. Finally, the WBI is extracted by RTFF. Experimental results of measured SAR data corrupted by simulated and real WBIs have demonstrated the effectiveness and practicability of the proposed method.

In this paper, a deceptive jamming template generative adversarial network (DJTGAN) is proposed, which can intelligently generate high-fidelity deceptive jamming template matched with the practical SAR scenario. The DJTGAN consists of a deceptive jamming template generative network and a discriminative network. The generative network combines low-frequency content and high-frequency details of the target, and the discriminative network adopts PatchGAN architecture to capture local texture statistics to improve the fidelity of the deceptive jamming template. The MSTAR dataset is utilized to verify the effectiveness of the proposed DJTGAN. Moreover, the strip SAR deceptive jamming experiment based on the deceptive jamming templates generated by DJTGAN is done to further validate the effectiveness of the DJTGAN.

Recently, a fog computing network that widely deploys fog nodes (FNs) at the edge of the network has been able to provide better communication performance and powerful computation support to the resource-limited Internet-of-Things (IoT) devices. In this article, we analyze the energy-efficient (EE) resource allocation problem in fog computing networks with the candidate FNs mechanism to ensure the network loading balance under the transmission performance constraints. In the scenario, the associated computation capability allocated to IoT devices from FNs is related to the historical energy consumption and the current energy consumption. The FN that reports nonzero computation capability is considered as the candidate FN and included in the candidate set. Moreover, a candidate FN-based EE resource allocation (CF-EE) algorithm is proposed to maximize network EE, which is converted into the Lyapunov optimization for each time slot. The optimal resource allocation can be obtained by minimizing the upper bound of the Lyapunov drift function and the penalty term to guarantee the loading balance and network stability. Finally, the optimization problem is decomposed into two suboptimization problems: 1) transmission resource allocation optimization and 2) power allocation optimization, and solved separately. The simulation results demonstrate that the proposed CF-EE algorithm can achieve a considerable performance improvement compared with algorithms in the literature.

In this paper, we proposed a ship detection method based on deep convolutional neural networks for PolSAR images. The proposed ship detector firstly segments PolSAR images into sub-samples using a sliding window of fixed size to effectively extract translational-invariant spatial features. Further, the modified faster region based convolutional neural network (Faster-RCNN) method is utilized to realize ship detection for ships with different sizes and fusion the detection result. Finally, the proposed method was validated using real measured NASAlJPL AIRSAR datasets by comparing the performance with the modified constant false alarm rate (CFAR) detector. The comparison results demonstrate the validity and generality of the proposed detection algorithm.

This paper presents an automatic ship detection algorithm for polarimetric synthetic aperture radar (PolSAR) data. Based on the non-Gaussian K-Wishart distribution model for complex backscattering coefficients, the PolSAR image is clustered automatically by a modified expectation maximization algorithm. A goodness-of-fit test is incorporated to improve the model fitness of the cluster iteratively. Then, the SPAN of ship cluster center is used to detect ships. Finally, the experimental results of a real measured UAVSAR dataset show that the proposed algorithm could improve the ability of weak target detection while reduces the rate of false alarm and miss detections.

Cellular processes are typically carried out by protein complexes and functional modules. Identifying them plays an important role for our attempt to reveal principles of cellular organizations and functions. In this article, we review computational algorithms for identifying protein complexes and/or functional modules from protein-protein interaction (PPI) networks. We first describe issues and pitfalls when interpreting PPI networks. Then based on types of data used and main ideas involved, we briefly describe protein complex and/or functional module identification algorithms in four categories: (i) those based on topological structures of unweighted PPI networks; (ii) those based on characters of weighted PPI networks; (iii) those based on multiple data integrations; and (iv) those based on dynamic PPI networks. The PPI networks are modelled increasingly precise when integrating more types of data, and the study of protein complexes would benefit by shifting from static to dynamic PPI networks.