With the application of massive wireless devices, the receiver often receives mixed signals with time-frequency overlapping. Automatic modulation classification (AMC) of such mixed signals is a critical prerequisite to effectively separating target signals. AMC algorithms typically assume that the receiver processes the single desired transmission signal. However, receiving different modulation components overlapping leads to difficulties in using the single received signal AMC algorithm during characterization. In this paper, a single-channel time-frequency overlapping signal AMC network framework based on multi-domain adaptive feature fusion (Mdaff) is designed, which utilizes the multi-dimensional adaptive feature selection (Mdafs) module to allocate the attention to extract the multi-domain features, including time-frequency, autocorrelation, and statistical domains. Then, it feeds them into the multi-scale feature fusion (Msff) recognition network based on the residual module. Multi-domain preprocessing is used to analyze the signal information comprehensively; Mdafs is used to extract important feature components from different dimensions adaptively; and the Msff module enhances the network's expressive capability. In addition, a difficulty-weighted label smoothing cross entropy (Dwlsce) function is designed to learn samples with a large degree of overlapping more adequately. We have built a software radio platform for signal acquisition, and the experimental results show that the Mdaff-based scheme has excellent AMC capability for single-channel time-frequency overlapping mixed signals.

In complex maritime environments, heavy-tailed non-Gaussian sea clutter presents a significant challenge for radar target detection, especially at low signal-to-clutter ratios (SCR) where target echoes are easily masked. To overcome this, we propose a multiscale CFAR detector operating on the Hermitian Positive-Definite (HPD) matrix manifold, introducing a multiscale Gaussian-weighted fusion mechanism in the Log-Euclidean domain to enhance target responses and suppress clutter while preserving HPD geometry. Covariance matrices are mapped to Log-Euclidean space, enabling multiscale weighted fusion across selected scales for improved target-background separation. Monte Carlo simulations on both synthetic and real sea-clutter data across various SCRs verify the effectiveness of the method. Experimental results show that, at a false alarm probability of$\bf {10^{-3}}$and an SCR of 5dB in real sea clutter, the proposed detector achieves a 28.2% increase in detection probability over the Log-Euclidean mean, outperforming conventional CFAR and LE-CFAR methods.

The characteristics of UAV-assisted edge computing-low cost, high mobility, and fast response speed-render it more suitable for the marine environment. Deploying edge servers in UAVs is a feasible approach to enhance the performance of the marine communication network; however, resource and energy constraints exist when applying UAVs to the marine network. This paper is based on the UAV-assisted edge computing architecture with NOMA. We establish multi-dimensional variable coupling constraints for task completion timeframe, task offloading decision, power, computational resources, and UAV trajectory. We design a weighted minimization model for system energy consumption. We propose a vertically layered alternating iteration optimization scheme. To escape local optimal solutions effectively, a simulated annealing algorithm is employed for the integer planning problem in the outer layer. The inner layer problem is decomposed into subproblems: user device transmit power, computational resource allocation, and corresponding UAV trajectory planning, given a task offloading decision scheme. However, these decomposed subproblems remain non-convex. To address this, the constraint structure is converted, and the problem is approximated and solved as a convex optimization problem using successive convex approximations. The system utility optimization is approximated using a two-layer algorithm and iterative optimization of subproblems. Simulation experiments show that the proposed joint optimization scheme not only reduces the total energy consumption of the system but also outperforms the scheme under OMA in optimizing task offloading costs.

Underwater acoustic sensor networks (UASN) serve as an effective method for marine information monitoring, significantly dependent on the quality of service (QoS) in data transmission of underwater sensors. For this purpose, relay nodes are required for cooperative communication. Autonomous underwater vehicles (AUV s), used as mobile relays, offer lower costs and greater flexibility compared to fixed relay nodes. However, the application of AUV s faces challenges including limited communication resources, constrained service time, and energy limitations. Existing research has addressed several of these challenges, but a holistic approach encompassing all these facets remains unexplored. Moreover, most of the constraints and optimization problems involved in these challenges are non-convex, posing significant difficulties in solution. Therefore, this paper proposes an improved particle swarm optimization algorithm with multi-objective constraints, aimed at maximizing QoS by balancing the travel and service states of AUV s, addressing the optimal placement of relay AUV s. Simulation results show that the proposed algorithm achieves higher system throughput and faster convergence speed compared to existing relay deployment algorithms, advancing the efficacy of UASN in complex marine environments.

The demand for heterogeneous unmanned aerial vehicles (UAVs) equipped with various types and complementary resources to perform complex tasks is increasing. Existing researches on game theory-based resource allocation primarily focus on continuous resources, by establishing models and transforming them into convex optimization problems. However, the discrete task resource allocation problem considered in this paper does not meet the assumptions of continuous optimization models, therefore, a reasonable allocation method is needed. To enhance the allocation efficiency for multi-UAVs operating under discrete resource constraints, we design a heuristic task allocation method based on game theory. Our method integrates multiple critical factors, including task priority and dynamic task benefits, into the resource matching process, offering a robust solution tailored to the diverse demands. Specifically, we first establish an optimization model encompassing UAVs, requirements and revenue, then we adopt a utility function to depict these relationships. Furthermore, considering the distributed cooperative characteristics of UAVs during task execution, we incorporate the correspondence between UAVs and tasks into the framework of a coalition formation game (CFG). Building on this foundation, we develop a heuristic allocation method based on task validity matching and an ineffective resource exit mechanism. We also introduce tabu lists to avoid ineffective searches, aiming to enhance resource utilization while ensuring task utility. Finally, we analyze the convergence of our proposed algorithm and conduct simulation validations across various scenarios. The results indicate that our algorithm can adapt to dynamic changes in task demands, exhibits good scalability, and is capable of enhancing task utility.

Abstract In the wake of the development and advancement of signal processing technology for communication radiation source individual, Signal fingerprint feature extraction and analysis technology for communication radiation source individual has broad application prospects in many fields. To effectively extract the individual characteristics of different modulated signals under low SNR environment, and recognize the subtle features for communication radiation source individuals has been a hot spot. Aiming at the problem of signal feature extraction and classifier design under low SNR environment, in the paper, a multifractal dimension and improved gray relation theory based classifier design algorithm is proposed. Firstly, the multifractal dimension feature extraction of nine modulated communication signals is realized. Then multifractal dimension features of these modulated signals under different SNR are compared. An improved gray relation algorithm is used to recognize the extracted subtle characteristics. Meanwhile, FSK signal is used to simulate radio subtle features by adding different distribution of noise. Subtle feature extraction by means of multifractal dimension algorithm and pattern recognition by means of improved gray relation algorithm are used to test the effectiveness of the proposed method for identification of modulated signals and radio subtle features. The simulation results show that the recognition success rate of nine different communication modulated signals can reach 93% even under the SNR of 2 dB, and the recognition success rate of the subtle features of distributed noise can reach 100%. The proposed method provides an effective theoretical basis for identifying of radio modulated signals and communication radiation source individual subtle features.

To improve the accuracy of modulated signal recognition in variable environments and reduce the impact of factors such as lack of prior knowledge on recognition results, researchers have gradually adopted deep learning techniques to replace traditional modulated signal processing techniques. To address the problem of low recognition accuracy of the modulated signal at low signal-to-noise ratios, we have designed a novel modulation recognition network of multi-scale analysis with deep threshold noise elimination to recognize the actually collected modulated signals under a symmetric cross-entropy function of label smoothing. The network consists of a denoising encoder with deep adaptive threshold learning and a decoder with multi-scale feature fusion. The two modules are skip-connected to work together to improve the robustness of the overall network. Experimental results show that this method has better recognition accuracy at low signal-to-noise ratios than previous methods. The network demonstrates a flexible self-learning capability for different noise thresholds and the effectiveness of the designed feature fusion module in multi-scale feature acquisition for various modulation types.

Unlike normal images, remote sensing images (RSI) often contain complex backgrounds and multi-scale targets with arbitrary directions. This makes existing detection methods ineffective. In contrast to the usual rotating frame RSI target detection methods, the Reppoints-based method can learn autonomously to capture target features of arbitrary pose based on the target’s characteristics. Therefore, a new Reppoints-based detector is proposed in this letter to improve the accuracy from multiple perspectives. In order to better expand the receptive fields and obtain finer features, the multi-scale task enhancement Network (MSTEN) preserves the multi-scale receptive fields and multi-scale information through the deformable convolution and the skip connection, while improving the feature extraction capability of the network for targets of arbitrary orientation. At the same time, the network adapts the features to the characteristics of different tasks in order to better suit the needs of the respective tasks. Finally, the dynamic reppoints learning (DRL) is proposed in order to select samples that perform well in both the regression and classification tasks. The experimental results on two challenging datasets, DOTA and HRSC2016, show the effectiveness of our proposed method.

The method proposed in this letter for synthetic aperture radar (SAR) image classification has two main stages. In the first stage, a convolutional neural network (CNN) is trained for normal SAR image classification task. After training, the sample features can be obtained by extracting the output of middle layer in the forward propagation process of CNN. In the second stage, an end-to-end metric network is trained to measure the relations between sample features. The method proposed in this letter is tested with some of the larger targets in OpenSARShip data set which is collected from Sentinel-1 satellite, and it is also tested with the MSTAR data set which is created by the U.S. Air Force Laboratory. The experimental results show that our method can get a higher recognition accuracy than normal CNN structure.

Oriented object detection in remote sensing images (RSI) has received more and more attention due to its broader applicability in natural scenes relative to horizontal bounding boxes. The complex scenes and multi-scale targets in remote sensing images make it often difficult for existing studies to extract key features of the targets effectively. At the same time, due to the problem of feature inconsistency in different layers, the direct fusion of these features is likely to cause feature conflicts, resulting in degradation of detection accuracy. To solve these problems, the dual-path multi-head feature enhancement detector (DP-MHFE Det), which contains two novel architectures, is proposed in this letter. The dual-path rotation feature aggregation module (DP-RFAM) improves the feature extraction capability of the network for rotating objects through dual-path structure and deformable convolution (DCN). To use these features effectively, the multi-head multi-level feature fusion enhancement network (MMFFENet) is proposed to guide the feature layers to learn and retain the key features they need autonomously, and then enhance their features according to the characteristics of different subtasks. Experiments conducted on two remote sensing datasets, DOTA and HRSC2016, show that DP-MHFE Det is faster than almost all detection methods compared to the state-of-the-art methods while showing strong competitiveness in accuracy.

Due to prominent advantages in local coverage enhancement and indoor cellular capacity improvement, femtocell (FC) is considered as a vital component in long‐term evolution advanced (LTE‐A) heterogeneous networks (HetNets). A two‐tier LTE‐A HetNet with conventional macro base stations in the first tier and femto base stations in the second tier is considered. Under this architecture, a new downlink interference evaluation scheme is proposed, based on which a FC enhanced multi‐target resource allocation algorithm is developed to maximise user equipment (UE) throughput in a dense FC deployment scenario meanwhile providing every UE a minimum signal to interference plus noise rate (SINR) guarantee. The optimal resource allocation problem is formulated as a MAX‐K cut problem based on the graph theory approach. System‐level simulations reveal that intra‐cell interference is greatly reduced and the spectral efficiency is significantly improved by using the proposed resource allocation scheme. Femtocell throughput is elevated significantly without causing much degradation on the macrocell throughput.

Effective inter-cell interference mitigation has been extensively studied because of its outstanding cell-edge signal quality improvement capability. Conventional static inter-cell interference coordination strategies, including fractional frequency reuse and soft frequency reuse, have received much attention owing to their effectiveness in mitigating interference and low complexity in implementation. However, they are less effective when dealing with dense uneven traffic distributions and dynamic traffic demands and thus incur low spectrum utilization in some cells and spectrum shortage in others. This paper proposes a universal frequency reuse scheme in a two-layer Long Term Evolution-Advanced heterogeneous network to ensure good throughput for all user equipment (UE), especially UEs at cell edge. The proposed scheme allows each cell to use all the spectrum resources, limited by an orderly regulation of all sub-bands. This scheme minimizes the potential occurrence probability of inter-cell co-sub-band interference through an intra-cell sub-band resource management. Furthermore, a graph-theoretic based sub-band allocation algorithm is developed to optimize UE throughput performance, especially for the cell-edge low signal to interference noise ratio UEs. A comprehensive performance comparison among different frequency reuse schemes is conducted by considering performance metrics, including cell-edge throughput, average throughput, and signal to interference noise ratio cumulative distribution function. Simulation result shows that the universal frequency reuse scheme outperforms other two schemes significantly. Copyright © 2016 John Wiley & Sons, Ltd.