Abstract:With regard to signal detection problems in sea clutter background， traditional methods can not achieve optimal performance due to that sea clutter is an example of nonstationary signal and its statistical characteristics vary over time. The existing nonstationary signal processing methods mainly include two categories： methods based on statistical models and methods based on time series analysis. From a statistical point of view， the most commonly used method is modeling sea clutter by compound Gaussian（CG） distribution. From the perspective of time series analysis， there are many models to describe nonstationary signals including time-varying autoregressive （TVAR） model， generalized autoregressive conditional heteroskedasticity （GARCH） model and stochastic volatility （SV） model. We make comparisons of these methods mentioned above and evaluate if they could be applied to detection in sea clutter background. All of the methods can accurately describe part of the characteristics of a nonstationary sea clutter signal to some extent. However， there exist difficulties if we try to design easy-to-implement detectors. Further research about modeling the characteristics of nonstationary signals is needed for signal detection in sea clutter background.

Abstract:The maximum a posteriori （MAP） algorithm is the most commonly used parameter estimation method. However， the MAP algorithm focuses on the position of the maximum peak of the posterior distribution and does not fully utilize the complete information of the posterior distribution. This article proposes a minimum divergence （MD） radar ranging estimation method based on relative entropy. Firstly， the posterior distribution of the parameters is derived. Secondly， a distribution similar to them is constructed. Therefore， the value is estimated by finding the minimum value of their divergence. Simulation results indicate that in radar ranging scenarios， the MD algorithm achieves approximately 1 dB gain in performance compared to the MAP algorithm， demonstrating its superior estimation performance.

Abstract:Most existing electromagnetic vector sensor multiple-input multiple-output（EMVS-MIMO） radars restrict the distribution of transceiver array elements. The resolution of radar direction measurement is limited due to half-wavelength constraints. To address this limitation， this paper proposes an algorithm based on the parallel factor （PARAFAC） decomposition for two dimension （2D） angle estimation of the target. The algorithm is applicable to arbitrary transmitter array geometries and sparse receiver array geometries. First， a third-order PARAFAC tensor model is constructed for the matched-filtered signal of the receiving array. Second， the PARAFAC decomposition is utilized to estimate the transmit direction， receive direction， and composite factor matrix. Finally， a closed-form solution for high-resolution， ambiguity-free 2D angle estimation of the target is obtained by combining the rotationally invariant method， the vector outer product method and the least squares method. The proposed algorithm is characterized by high accuracy and low computational complexity. Computer simulations verify the tensor decomposition-based algorithm can be applied to an arbitrary dual-base EMVS-MIMO radar model， and can accurately estimate the 2D angular parameters of multiple targets. This validation demonstrates the effectiveness and superiority of the proposed algorithm.

Abstract:Although multi-station radar cooperation can effectively improve the anti-jamming ability by using multi-view detection and information fusion processing， it is difficult to meet the detection conditions in the actual scene， or it suffers from the risk of network destruction in practice. Therefore， it is still necessary to improve the anti-jamming ability of single station radar. Aiming at problems of single-station radar， such as single detection angle， limited echo information and insufficient anti-jamming ability， a distributed detection condition is constructed by adding a reconfigurable intelligence surface （RIS） in the echo receiving process of single-station radar to receive the multi-directional scattering signal of the target， thus opening up a new way for the single-station radar to resist deceptive jamming. Simulation results show that adding RIS can effectively construct virtual channel and improve the anti-jamming ability of single station radar.

Abstract:To cope with the challenges brought by increasingly intelligent multifunctional radars to the opposing side， this paper proposes an jamming decision-making method based on the proximal policy optimization （PPO） algorithm and the Mask-Transformer in Transformer （Mask-TIT） network. Firstly， starting from a realistic scenario， the adversarial scene between the jammer and the radar is modeled as a partially observable Markov decision process （POMDP）. A new state transition function and reward function are designed based on the working principles of the radar， and the observation space is designed according to the hierarchy of the multifunctional radar model. Secondly， a Mask-TIT network structure is designed using the Transformer’s representation capacity for sequence data and the characteristics of radar jamming patterns， which is used to build a more powerful Actor-Critic network architecture. Finally， the PPO algorithm is used for optimization learning. Experimental results show that compared with existing methods， the proposed algorithm reduces the average amount of interactive data required for convergence by 25.6%， and the variance after convergence is significantly reduced.

Abstract:In modern wars， using unmanned aerial vehicle （UAV） clusters to jam the enemy network radar for track deception is an effective way of anti-enemy radar detection. However， given the complexity and uncertainty of the battlefield environment， there are station location errors due to the limited positioning accuracy of the networked radar， and jitter errors due to the influence of air flow and control system. These can cause the generated false track points to deviate from the preset positions and the expected deception effect cannot be achieved. To solve the above problems， this paper analyzes the radar station location errors and UAV jitter errors when the radar station position， UAV position and deception distance are known and the networked radar space resolution cell （SRC） is certain. The UAV cluster successfully deceives the maximum error range allowed by the jamming network radar. For a typical networked radar system， the influence rules of two kinds of errors on the track deception effect are summarized. Some suggestions are put forward to improve the track deception effect. Numerical simulation results show that the analysis and derivation results can effectively evaluate whether the networked radar can be successfully tricked under the condition of radar position error and UAV jitter error seperately.

Abstract:Radio frequency （RF） tunable filtering and RF interference cancellation have always been the focus of RF interference suppression research. The combination of these two key technologies is considered to be a RF protection scheme to improve anti-known cooperative interference ability for receivers. This paper systematically sorts out the merits and drawbacks of the available RF protection circuits and summarizes the advanced technologies of RF tunable filtering and RF interference cancellation after investigation. Aiming at application requirements of anti-unknown non-cooperative interference， based on the main path of RF spectrum sensing and the auxiliary path of RF interference cancellation， the architecture of wideband adaptive RF protection （WARP） for spectrum sensing receivers is preliminarily proposed， and the difficult problems are discussed lastly.

Abstract:In response to the problem of holes in traditional coprime planar array （CPA） structures when using difference coarray （DCA） for two-dimensional direction of arrival （DOA） estimation， this paper proposes a hole-free coprime planar array （HFCPA） structure. The array is obtained by extending hole-free coprime linear arrays along the x and y axes， and its DCA is a hole-free rectangular array. Furthermore， this paper presents the optimal HFCPA structure to maximize the available continuous degrees of freedom. Simulation results demonstrate the superiority of the proposed array structure over existing coprime planar array structures in terms of the number of continuous degrees of freedom， virtualization efficiency， and two-dimensional DOA estimation performance.

Abstract:Modulation recognition technology has been widely used in cognitive radio and electronic reconnaissance countermeasures. In recent years， thanks to the powerful feature extraction ability of deep neural networks， the research of automatic modulation recognition based on deep learning has made great progress. In practical modulation recognition scenarios， modulation signals usually transmit bit sequences without semantic information， and each modulation symbol appears in waveforms with uniform probability， so its feature information is uniformly distributed in signal. However， existing automatic modulation recognition methods based on deep learning usually use structures of convolutional neural network （CNN） or recurrent neural network （RNN）. They are difficult to be adapted to the data distribution in the scenarios above and thus fail to make full use of the global characteristics of long sequential data. Therefore， the accuracy of modulation recognition can be further improved by exploiting the sequential information. In this paper， an automatic modulation recognition method based on improved Transformer， AMR-former， is proposed. Firstly， the input signal is preprocessed to strengthen the temporal characteristics. Then， the AMR-Encoder structure for feature extraction is designed and implemented by combining the multi-head attention mechanism and long short-term memory （LSTM） network， which effectively improves the ability of global temporal feature extraction and provides richer representations for the subsequent recognition and classification. Experiments on the RadioML 2016.10a dataset show that the average recognition accuracy of the AMR-former method reaches 91.90% with the signal-to-noise ratio （SNR） from 0 dB to18 dB， which is 6.38%，2.15%，1.99% and 1.75% higher than the typical networks of GRU， PET-CGDNN， LSTM and MCLDNN， respectively.

Abstract:Ordered successive interference cancellation （OSIC） is a commonly utilized signal detection algorithm in multiple input multiple output （MIMO） systems. However， the algorithm’s performance in terms of throughput and latency is constrained by the computational complexity of the channel matrix inverse operation. Therefore， matrix inverse decomposition pre-processing with low computational complexity and high speed is the key to hardware implementation of the algorithm. In this paper， we adopt a hardware-accelerated matrix pre-processing scheme for sorted orthogonal triangle （QR） decomposition of the channel matrix， in which the sorting process introducing a fast estimation method for complex-valued 1-norm to eliminate complex modulus computation. The QR decomposition process uses a deeply pipelined coordinate rotation digital computer （CORDIC） iterative method to eliminate the element vectorization and nulling rotation angle computation in the Givens rotation process， thus a pipeline circuit structure with a reusable Givens rotation structure for QR decomposition is designed， obviating the necessity for multipliers in the matrix decomposition process. Simulation results demonstrate that the OSIC enhancement algorithm proposed achieves the bit error rate（BER） performance comparable to that of the signal-to-noise ratio-based OSIC detection algorithm. The CORDIC iterative Givens rotation structure proposed in this paper can achieve highly time-sharing multiplex. It significantly improves the system parallelism and reduces the resource consumption， and the system design clock attains up to 250 MHz， and the matrix decomposition throughput reaches 1.88 M Matrices/s， meeting the processing throughput and latency requirements of 4 or more antennas MIMO systems at the receiver.

Abstract:Data compression technology can reduce the offloading energy consumption of users in mobile edge computing （MEC） by compressing computing tasks. Aiming at the problem that the communication link between the mobile users and the base station is blocked， which has an impact on communication quality， this paper proposes a task offloading scheme based on data compression to meet the requirements of emergency communication and energy-saving offloading in MEC assisted by the unmanned aerial vehicle （UAV） equipped with relay devices and edge servers. Considering constraints such as task compression ratios， system resource and the onboard energy of UAV， we formulate a problem to minimize the sum energy consumption of users. The non-convex optimization problem is modeled as a Markov decision process and the soft actor-critic algorithm based deep reinforcement learning is used to tackle the problem. The simulation results reveal that the proposed scheme achieves better convergence performance and the total energy consumption of users can be reduced by 24.7%—42.2%， compared with the benchmark algorithms.

Abstract:Improving the autonomous landing capability of unmanned aerial vehicles （UAVs） holds significant importance in enhancing their operational efficiency and survival ability in the field. This paper presents a novel approach utilizing onboard video for automatic detection of UAV landing zones， aiming to enhance the UAV’s autonomous obstacle avoidance and landing capabilities in the absence of prior scene knowledge. We integrate a deep learning network incorporating multi-view geometric constraint methods into the simultaneous localization and mapping （SLAM） algorithm， aiming to construct a three-dimensional map of the scene while actively identifying potential obstacles. Subsequently， we propose a landing area detection algorithm that takes into account factors such as landing area and flatness. By conducting spatial analysis on voxel grid maps， we can identify the landing area of UAVs. This algorithm utilizes spatial analysis on a voxel grid map to identify the suitable landing area for the UAV. Experimental evaluation is conducted in various scenarios， demonstrating the accuracy of the proposed approach.

Abstract:Due to the large differences of target size in remote sensing images and the difficulty in effectively capturing the effective features of targets at different scales， it is difficult to effectively identify targets at different scales. And， when dealing with high-resolution images， traditional Transformers may face the problem of insufficient computational resources. In addition， the combination of a single loss calculation method and the Hungarian algorithm can increase the fluctuation of cost loss and affect the convergence speed and accuracy of the algorithm. Therefore， a multi-scale remote sensing target detection algorithm， named as MSDAB-DETR， is proposed. Firstly， the algorithm creates a new multi-scale attention fusion module to leverage the differences between different resolution feature information to achieve multi-scale prediction of remote sensing images. Secondly， an efficient attention mechanism is adopted to improve the self-attention mechanism in the Transformer model， reducing the memory footprint of the original model. Finally， the SIoU loss function is used as the bounding box regression loss， combined with the Hungarian algorithm， to weaken the fluctuation of binary graph matching， accelerate the convergence speed， and further improve the regression ability of bounding boxes. Experimental results show that the detection accuracy of this method on the NWPU VHR-10 and DIOR datasets is as high as 95.3% and 71.5%，respectively. Among them， on the NWPU VHR-10 dataset， the average detection accuracy for small， medium， and large-scale targets is improved by 10.5%， 1.8%， and 2.7%，respectively compared to the DAB-DETR model. At the same time， the memory footprint is reduced by about 9%.

Abstract:In view of high computational complexity of the probability data association （PDA） algorithm in cluttered environments， a data association method based on the PDA algorithm is designed. When the number of measurement points in the wavegate exceeds a certain threshold， the PDA algorithm is employed to update the target state. When the number of measurement points falls below or equals the threshold， a nearest-neighbor approach is used to filter the target measurement points.Subsequently， the Kalman filter （KF） algorithm is utilized to achieve fast filtering updates in cluttered environments.Additionally， the paper proposes an adaptive interval smoothing method that dynamically corrects the smoothing interval to achieve reverse smoothing of the overall state estimation.This approach aims to improve the algorithm’s accuracy. Experimental results of various clutter environments demonstrate that the proposed method effectively enhances the estimation accuracy of the system state while ensuring tracking efficiency. Moreover， the results validate the robustness and effectiveness of the method compared to the PDA algorithm and the KF-PDA algorithm.

Abstract:Data association is an important step in multiple object tracking（MOT）， which generally requires identity matching between objects and detections based on feature similarity. Some objects or detections may remain isolated after match is completed， which is the missing phenomenon that may lead to track interruption or identity confusion. Therefore， in order to improve the accuracy and stability of MOT and suppress the missing phenomenon in data association， this paper proposes an anti-missing mechanism based on high-performance single object tracker（SOT） and rematching. The mechanism uses Transformer and diffusion model to design a SOT that meets the requirements of MOT to track missing objects and rematch missing detections by remembering the object information. The effect of SOT and rematching methods in anti-missing mechanism is verified by ablation experiments， and the effect of this mechanism on the tracking performance of MOT algorithm is tested on standard datasets. The results show that the performance of all algorithms is improved comprehensively with the addition of this mechanism， which can effectively suppress the missing phenomenon in MOT.

Abstract:How to extract multi-scale features and model semantic dependencies between remote channels remains a challenge for expression recognition networks. This paper proposes a residual network based on pyramid split attention （PSA-ResNet）， which replaces the 3 × 3 convolution in the ResNet50 residual module with PSA to effectively extract multi-scale features and enhance the correlation of cross channel information. In order to reduce the differences between similar expressions and expand the distance between different types of expressions， a joint loss function optimization parameter of Softmax loss and Center loss is introduced during the training process. The proposed model is simulated on two publicly available datasets， Fer2013 and CK+， and achieves accuracies of 74.26% and 98.35%， respectively， further confirming that this method has better recognition results compared to cutting-edge algorithms.

Abstract:Aiming at the problems of overlapping targets in complex and changeable road scenes， it is difficult to segment image edges and extract small target features. A multi-level attention feature optimization method for real-time semantic segmentation of road scenes is proposed. Firstly， a lightweight residual attention module is designed， taking into account the difference in feature weights at different levels， and optimizing local features of the image through a compressed attention mechanism， thereby improving the edge effect between pixels. Then， the channel attention and depth aggregation pyramid pooling module are designed to further strengthen the extraction of semantic context information， thereby solving the problem of small target information loss. Finally， the attention fusion module is designed to fuse feature information at different scales from top to bottom. It can achieve effective interaction of global feature information and enhance the network’s expression of important features. Experimental tests are carried out on the Cityscapes and CamVid road scene datasets， and the segmentation accuracy is 74.4% and 67.7%， respectively， and the inference speed are 138 frames/s and 148 frames/s. Compared with the excellent methods in recent years， this method improves the loss of image edge information and optimizes the segmentation accuracy of small objects in the image.

Abstract:Job shop scheduling problem （JSSP） is a non-deterministic polynomial （NP）-hard classical combinatorial optimization problem. In JSSP， it is usually assumed that the scheduling environment information is known and remains unchanged during the scheduling process. However， the actual scheduling process is often affected by many uncertain factors （such as machine failures and process changes）. A proximal policy optimization with hybrid prioritized experience replay （HPER-PPO） scheduling algorithm is proposed for solving JSSPs with uncertainties. The JSSP is modeled as a Markov decision process where the state features， reward function， action space， and scheduling policy networks are designed. In order to improve the convergence of the proposed deep reinforcement learning model， a new hybrid prioritized experiential replay training method is proposed. The proposed scheduling method is evaluated on standard datasets and datasets generated based on standard datasets. The results show that in static scheduling experiments， the proposed scheduling model achieves more accurate results than existing deep reinforcement learning methods and priority dispatching rules. In dynamic scheduling experiments， the proposed scheduling model can achieve more accurate scheduling results in a reasonable time for JSSP with process order uncertainty.

Abstract:With the increasing emphasis on data security in public safety emergencies， federated learning has gained attention for its ability to perform computations without uploading data to a central server， thereby reducing the risk of privacy breaches. However， current federated learning approaches based on smart contracts face challenges such as inefficiency due to their computational demands. To address it， this paper proposes an asynchronous federated learning method for detecting public health emergencies， integrating smart contracts and federated storage. This approach allows federated nodes to join and leave the federated learning process at any time. By leveraging smart contracts and distributed storage， it enhances data security and training efficiency in the public health domain. Furthermore， adaptive differential privacy is employed to dynamically protect the gradients uploaded to distributed storage nodes， further reducing the risk of privacy leakage. Extensive experiments conducted on public datasets and public health security datasets demonstrate that the proposed method outperforms existing approaches in terms of accuracy and requires less time to achieve the same level of precision.

Abstract:Current emotion recognition methods for eletroencephalogram（EEG） signals seldom fuse spatial， temporal and frequency information， and most methods can only extract local EEG features， resulting in limitations in global information correlation. The article proposes an EEG emotion recognition method based on 3D-CNN-Transformer mechanism （3D-CTM） model with multi-domain information fusion. The method first designs a 3D feature structure based on the characteristics of EEG signals， simultaneously fusing the spatial， temporal， and frequency information of EEG signals. Then a convolutional neural network module is used to learn the deep features for multi-domain information fusion， and then the Transformer self-attention module is connected to extract the global correlations within the feature information. Finally， the global average pooling is used to integrate the feature information for classification. Experimental results show that the 3D-CTM model achieves an average accuracy of 96.36% in the SEED dataset for triple classification and 87.44% in the SEED-Ⅳ dataset for quadruple classification， which effectively improves the emotion recognition accuracy.