With the rapid development of low-altitude economy, the low-altitude intelligent network (LAIN) serves as a critical infrastructure for supporting diversified aerial activities. However, current LAIN lacks a physical-network synchronization mechanism and fails to handle heterogeneity at the architecture level, which leads to difficulties in real-time adaptive adjustments and efficient unified coordination. To address these issues, this paper proposes the networked embodied intelligence (NEI) paradigm, with a network-level sensing-decision-action-feedback (SDAF) closed-loop mechanism to synchronize physical and network states. Building on this paradigm, we functionally reconfigure LAIN into four collaborative subnetworks: sensing, computing, communication and navigation. As a further step, we propose the NEI-LAIN architecture, where these subnetworks collaborate via the SDAF loop to achieve global collaboration and continuous evolution. Simulation results demonstrate that the proposed NEI-LAIN can significantly enhance the performance of communication robustness, resource utilization and task responsiveness in highly dynamic scenarios. Finally, we discuss its implementation challenges and future research directions.

With the rapid development of low-altitude intelligent networks (LAINs), the growing demand for data services poses significant challenges for the existing networks. At the same time, the airspace becomes increasingly complex due to the escalating count of low-altitude users. Although unmanned aerial vehicles (UAVs) carrying mobile base stations to provide communication services can effectively alleviate pressure on existing network infrastructure, they unfortunately face the dual challenge of sustaining reliable data transmission and guaranteeing UAV flight safety. Therefore, in this paper, we propose a collision-free UAVs communication model specifically designed for the hybrid low-altitude environment, incorporating both static and dynamic, as well as known and unknown obstacles. To efficiently support safe flight operations of UAVs, an artificial potential field (APF)-based collision probability map is constructed, enabling the UAVs to dynamically evaluate and avoid obstacles while maintaining high communication performance constrained by limited energy resources. To maximize energy efficiency in low-altitude environments with hybrid obstacles, an adaptive association multi-agent deep deterministic policy gradient (AA-MADDPG) algorithm is proposed to enable collaborative trajectory planning among multiple UAVs. Simulation results confirm that the proposed strategy enhances energy efficiency by 58.06% and reduces collision probability by 86.18%, achieving significant improvements in both communication performance and flight safety.

NOMA-aided cognitive satellite aerial terrestrial integrated networks (CSATINs) are considered revolutionary and key technologies for 6G Internet of Things (6G-IoT), offering enhanced connectivity, high spectral efficiency, and broad coverage. In this article, we first establish trustworthy CSATINs with multiple aerial relays, aiming to achieve reliable communication in the presence of an eavesdropper. Then, to enhance the system’s covert performance, we propose an unmanned aerial vehicle scheduling scheme. Moreover, based on the established covert system model, we derive the closed-form expressions of detection error probability (DEP), covert outage probability (COP), and effective covert rate (ECR). Particularly, an optimization is proposed to enhance the covert performance of the considered system. Finally, Monte Carlo simulations are given to validate the correctness of the theoretical analysis, demonstrating that the reliability and covertness of the proposed system can be simultaneously enhanced by appropriately adjusting the power allocation coefficients, jamming power, and the transmission power of the satellite and UAVs.

Due to the scalability and portability, low-altitude intelligent networks (LAINs) are essential in various fields such as surveillance and disaster rescue. However, in LAINs, unmanned aerial vehicles (UAVs) are characterized by the distributed topology and high mobility, thus vulnerable to security threats, which may degrade routing performances for data transmissions. Hence, how to ensure the routing stability and security of LAINs is challenging. In this paper, we focus on the routing with multiple UAV clusters in LAINs. To minimize the damage caused by potential threats, we present the zero-trust architecture with the software-defined perimeter and blockchain techniques to manage the identify and mobility of UAVs. Besides, we formulate the routing problem to optimize the end-to-end (E2E) delay and transmission success ratio (TSR) simultaneously, which is an integer nonlinear programming problem and intractable to solve. Therefore, we reformulate the problem into a decentralized partially observable Markov decision process. We design the multi-agent double deep Q-network-based routing algorithms to solve the problem, empowered by the soft-hierarchical experience replay buffer and prioritized experience replay mechanisms. Finally, extensive simulations are conducted and the numerical results demonstrate that the proposed framework reduces the average E2E delay by 59% and improves the TSR by 29% on average compared to benchmarks, while simultaneously enabling faster and more robust identification of low-trust UAVs.

Precise positioning and identification of unauthorized unmanned aerial vehicles (UAVs) are of crucial importance for spectrum security and privacy protection in future intelligent networks. Although various single-modality approaches have been investigated, their performance degrades under the sensor-specific noise, resulting in suboptimal performance and robustness. To address these security challenges, we propose a multi-layer radio frequency (RF)-vision fusion framework that synergistically exploits temporal-spectral features of UAV RF signals and spatial-visual information to achieve precise and robust UAV positioning and identification. Moreover, a corresponding unified RF-Vision fusion Network (RFViNet) is designed to exploit the RF-vision cross-modal complementary and semantic synergy. Specifically, by leveraging the novel RFinformed proposal generation, RF-enhanced feature modulation, and RF-guided semantic query modules, the RFViNet effectively exploits the complementary strengths of RF and visual modalities. Furthermore, a practical RF–vision platform is developed to evaluate the performance of our method under various challenging conditions. Experimental results on the real-world dataset demonstrate that the proposed method achieves a competitive 85.8% average precision AP50, highlighting its potential for enhancing the spectrum security in future intelligent wireless networks.

Due to the broadcasting characteristics of satellite-terrestrial integrated networks (STINs), security vulnerabilities have emerged as a critical concern requiring urgent mitigation strategies. Unlike traditional security methods, federated learning (FL) enables a large number of participants to collaborate without disclosing actual privacy data. Its potential as a framework that combines collaborative model training and covert payload transmission in STINs represents a significant research gap. This paper proposes FedSAT, a novel FL-based covert communication scheme for STINs, in which each participant in the FL process can utilize the shared learning protocol as a covert medium for transmitting arbitrary information in privacy-preserving framework. Our framework leverages the dual capabilities of FL for collaborative model training and covert payload embedding, utilizing Geostationary Earth Orbit (GEO) satellites and distributed terrestrial nodes to embed sensitive data within FL parameter updates. The system maintains model convergence accuracy while implementing strategic encryption to achieve robust sharing and transmission of payloads within the FL framework. Comprehensive simulation tests demonstrate the framework significant efficacy, achieving a 98.7% communication coverage for covert payload transmission under monitoring by low Earth orbit (LEO) surveillance satellites, with only a 0.8% decrease in model accuracy. This breakthrough achievement paves the way for a transformative paradigm in covert cross-domain communication for next-generation networks.

Intelligent spectrum management is crucial for improving spectrum efficiency and achieving secure utilization of spectrum resources. However, existing intelligent spectrum management methods, typically based on small-scale models, suffer from notable limitations in recognition accuracy, convergence speed, and generalization, particularly in the complex and dynamic spectrum environments. To address these challenges, this paper proposes a novel spectrum foundation model, termed SpectrumFM, establishing a new paradigm for spectrum management. SpectrumFM features an innovative encoder architecture that synergistically exploits the convolutional neural networks and the multi-head self-attention mechanisms to enhance feature extraction and enable robust representation learning. The model is pre-trained via two novel self-supervised learning tasks, namely masked reconstruction and next-slot signal prediction, which leverage large-scale in-phase and quadrature (IQ) data to achieve comprehensive and transferable spectrum representations. Furthermore, a parameter-efficient fine-tuning strategy is proposed to enable SpectrumFM to adapt to various downstream spectrum management tasks, including automatic modulation classification (AMC), wireless technology classification (WTC), spectrum sensing (SS), and anomaly detection (AD). Extensive experiments demonstrate that SpectrumFM achieves superior performance in terms of accuracy, robustness, adaptability, few-shot learning efficiency, and convergence speed, consistently outperforming conventional methods across multiple benchmarks. Specifically, SpectrumFM improves AMC accuracy by up to 12.1% and WTC accuracy by 9.3%, achieves an area under the curve (AUC) of 0.97 in SS at -4 dB signal-to-noise ratio (SNR), and enhances AD performance by over 10%.

Effective recognition of jamming in a communication system is essential to maintain the integrity of the electromagnetic spectrum space. In this paper, a novel feature-enhanced open-set jamming pattern recognition method (FOSR) is proposed. First, an in-phase and quadrature (I/Q) data feature enhancement module is designed based on a complex-valued autoencoder to capture the interaction features between the I and Q channels. Then, a jamming feature extraction module is designed to extract jamming characteristics for known patterns by integrating the raw I/Q data with their interaction features. Subsequently, an adaptive threshold open-set classification module is proposed to recognize both known and unknown patterns. Finally, to address the domain shift problem, we extend FOSR with a domain adaptation (DA) module based on distribution alignment and classifier calibration, referred to as FOSR-DA. Simulation results show that the proposed method achieves superior recognition accuracy and exhibits strong robustness when dealing with the domain shift problem.

Radiation source (RS) localization is crucial in electromagnetic environmental monitoring. Existing methods require prior knowledge of the environment and have overlooked the impact of multipath effects. Their positioning accuracy is penalized in practical applications. This paper presents an environment cognition-based variational Bayesian positioning method, which can achieve precise multi-source localization in uncooperative multipath environments using only the measurements of received signal strength (RSS). We begin by leveraging the signal propagation properties to design a model-data integrated unsupervised learning network, which partitions the positioning area according to the transmission states of different multipath signals. To estimate the number of RSs and mitigate the multipath effect, we identify the data samples of multipath RSS and divide them into groups, each corresponding to an RS. Then, a new variational Bayesian positioning algorithm is developed to operate without prior channel information and locate multiple RSs accurately across varying signal propagation models. Simulations show that our positioning method can effectively improve the accuracy of multi-RS localization by 10% in uncooperative multipath environments, compared to the state-of-the-art RSS-based localization techniques.

Semantic communication has shown exceptional performance in various tasks, such as image classification, owing to the advancements in deep learning technologies. However, due to the openness of wireless channels and the vulnerability of neural networks, semantic communication faces significant challenges from semantic impairment in the physical channel. In this paper, semantic impairment refers to the minor perturbations that cause discrepancies between the received features and the expected ones, which can lead to errors in image classification. We design four constraints from the perspectives of semantic level, concealment level and efficiency level to simulate potential malicious semantic impairment. These constraints are employed to generate adversarial perturbations specifically targeting semantic communication systems, ensuring that the perturbations can more effectively disrupt the normal function of the systems. Moreover, we innovatively propose knowledge graph enhanced anti-impairment cognitive semantic communication, which combines knowledge graph and adversarial training to boost robustness against semantic impairment. Specifically, we leverage the shared knowledge graph to transmit triplet information from the transmitter to the receiver in the form of indices and introduce the triplet information as additional information into the decoder to facilitate the decoding process. Simulation results show that our proposed knowledge graph enhanced cognitive semantic communication system achieves higher classification accuracy and robustness in environments with low signal-to-noise ratio and semantic impairment, compared to existing Better Portable Graphics (BPG) and Joint Source-Channel Coding(JSCC) schemes.

With the development of unmanned aerial vehicles (UAVs) and the diversification of low-altitude applications, the cooperation among UAVs with different capabilities and objectives offers an exciting prospect for achieving efficient and ubiquitous communication coverage. However, coordinating the cooperation and competition among heterogeneous UAVs is an intractable challenge. In this paper, we propose a novel centralized-distributed heterogeneous-UAVs intelligent communication network system, which addresses the cooperation-competition issue among heterogeneous UAVs through reasonable task allocation. Specifically, a hub UAV makes ground users (GUs) scheduling decisions based on global information and provides backhaul link support through trajectory optimization. Meanwhile, high-mobility distributed UAVs cooperate to ensure fair, efficient communication for assigned GUs. Although centralized user scheduling offers greater flexibility and better performance, it also faces the serious problems which includes time-varying local observation spaces, hybrid action spaces, heterogeneous state spaces, and reward discrepancies. To solve these problems, we propose a convolutional neural network-assisted heterogeneous-UAVs proximal policy optimization algorithm, which aims to jointly optimize UAV trajectories and user scheduling, maximizing the system’s total fair energy efficiency. The simulation results demonstrate that the proposed CNN-HUPPO algorithm outperforms the four multi-agent deep reinforcement learning (MADRL) benchmark algorithms and two baseline algorithms in terms of fairness and accumulative fair energy efficiency.

Cellular-connected unmanned aerial vehicles (UAVs) play essential roles across various smart-city applications in low-altitude domains, such as logistics delivery, environmental monitoring, etc. To ensure their reliable deployment, it significantly depends on efficient and intelligent UAV coverage-aware navigation, where deep reinforcement learning (DRL) has emerged as a promising method. However, current DRL-based methods typically simplify UAV flight dynamics by action discretization, which neglects realistic continuous flight dynamic and limits their practical implementation. Moreover, they suffer from the sample inefficiency, since learning the navigation policy requires extensive and costly real-time interactions with the environment. To overcome these two challenges, we propose a novel offline-online radio map-enhanced soft actor-critic (OORM-SAC) framework for the energy-efficient UAV coverage-aware navigation under continuous dynamics constraints. Specifically, our proposed OORM-SAC leverages the classic SAC algorithm to handle large continuous action spaces. It aims to learn continuous steering control to navigate toward the destination while minimizing energy consumption and communication outage. Moreover, to enhance learning efficiency, OORM-SAC adopts a hybrid offline-online learning approach, where the energy-efficient flight pattern is first pre-trained offline and the policy is then refined through online environmental interactions. Furthermore, it incorporates the radio map construction during the online phase to generate diverse virtual training samples, which further accelerates the policy learning. Experimental results demonstrate the effectiveness of OORM-SAC in navigation tasks under continuous dynamic constraints. The OORM-SAC method exhibits superior learning efficiency and generates intelligent trajectories that effectively balance energy consumption and communication requirements.

Camera calibration enables the automatic estimation of intrinsic and extrinsic camera parameters, uncovering correspondences between 2D images and 3D real-world coordinates. For highway surveillance cameras, existing methods often rely on cumbersome procedures to extract limited priors (e.g., vanishing points or reference points) and provide incomplete estimations (e.g., roll angle). Therefore, we leverage the multilayered lane lines on highways, which offer rich priors such as segment lengths, intervals, and lane widths, to develop a novel camera calibration and vehicle speed estimation method. For camera calibration, our approach performs road instance segmentation and extractsmultilayered lane-line keypoints (MLK)while mitigating environmental interference and dynamic vehicle occlusions. An MLK-based calibration model is constructed and anangle-polling Levenberg-Marquardt algorithmis designed to estimate key parameters, including focal length, three rotation angles, and lane-line distance. For vehicle speed estimation, multi-object tracking (MOT) algorithms are integrated with the calibration model to infer the average speeds of all identified vehicles. We collected real highway video footage from four different camera setups in Chinese highways. Experimental results demonstrate that our method outperforms existing methods across all setups. The impact of key parameters is evaluated to determine the optimal configuration. Lastly, its effectiveness in vehicle speed estimation is assessed based on advanced MOT algorithms.

Unmanned aerial vehicle (UAV) communication is of crucial importance for heterogeneous practical wireless communications. However, it is susceptible to the severe spectrum scarcity with the rapidly expanding market of wireless broadband, multimedia users, and high data-rate applications. Exploring the underutilized unlicensed spectrum through spectrum sharing is promising to tackle this issue, but the openness of the unlicensed spectrum makes UAVs susceptible to security threats from potential jammers. Therefore, a licensed and unlicensed UAV spectrum sharing network against uncertain jamming attack is studied. Moreover, to overcome the high complexity of the pure model-based optimization resource allocation schemes, the low learning efficiency and strong data dependency of data-driven deep reinforcement learning (DRL) methods, a novel optimization-driven DRL framework is proposed for the resource allocation. In particular, a model-based optimization module is exploited to derive the worst-case lower bound and a better informed target value of the formulated complex non-convex optimization problem. Furthermore, the model-based informed target value is integrated into the DRL to guide the agents for better strategies. Simulation results demonstrate that our proposed scheme can significantly improve the convergence speed and achieve a better reward performance than the pure DRL based scheme. It is also shown that the exploitation of the unlicensed spectrum can achieve approximately twice the sum transmission rate compared to using only the licensed spectrum.

The expansion of the low-altitude economy has underscored the significance of Low-Altitude Network Coverage (LANC) prediction for designing aerial corridors. While accurate LANC forecasting hinges on the antenna beam patterns of Base Stations (BSs), these patterns are typically proprietary and not readily accessible. Operational parameters of BSs, which inherently contain beam information, offer an opportunity for data-driven low-altitude coverage prediction. However, collecting extensive low-altitude road test data is cost-prohibitive, often yielding only sparse samples per BS. This scarcity results in two primary challenges: imbalanced feature sampling due to limited variability in high-dimensional operational parameters against the backdrop of substantial changes in low-dimensional sampling locations, and diminished generalizability stemming from insufficient data samples. To overcome these obstacles, we introduce a dual strategy comprising expert knowledge-based feature compression and disentangled representation learning. The former reduces feature space complexity by leveraging communications expertise, while the latter enhances model generalizability through the integration of propagation models and distinct subnetworks that capture and aggregate the semantic representations of latent features. Experimental evaluation con firms the efficacy of our framework, yielding a 7% reduction in error compared to the best baseline algorithm. Real-network validations further attest to its reliability, achieving practical prediction accuracy with MAE errors at the 5 dB level.

Active object tracking (AOT) in complex and dynamic environments remains a significant challenge for autonomous unmanned aerial vehicle (UAV) tracking systems, especially in anomalous situation such as prolonged occlusion and intense interference. In this paper, we propose a novel embodied learning framework, called the learning to ask for help (LA4H) framework, which integrates cross-modal anomaly cognition and adaptive expert assistance mechanisms to enhance the robustness and generalization of UAV active target tracking. The LA4H framework enables the agent to autonomously recognize and classify anomalous states through a cross-modal anomaly cognition module, and to adaptively request expert intervention when necessary via an assistance decision network. A teacher-student policy learning paradigm is further employed to distill the temporal-semantic knowledge, improving tracking efficiency and real-time performance. Extensive experiments in both simulated and real-world scenarios demonstrate that the LA4H significantly outperforms the state-of-the-art baselines in terms of tracking success rate, path efficiency, and generalization to unseen scenarios, while substantially reducing reliance on expert intervention. The results demonstrate the effectiveness of integrating expert knowledge and anomaly cognition for robust embodied AI in practical UAV applications.

Unmanned aerial vehicles (UAVs) can serve as aerial base stations (BSs) to extend the ubiquitous connectivity for ground users (GUs) in the sixth-generation (6G) era. However, it is challenging to cooperatively deploy multiple UAV swarms in large-scale remote areas. Hence, in this paper, we propose a hierarchical UAV swarms structure for 6G aerial access networks, where the head UAVs serve as aerial BSs, and tail UAVs (T-UAVs) are responsible for relay. In detail, we jointly optimize the dynamic deployment and trajectory of UAV swarms, which is formulated as a multi-objective optimization problem (MOP) to concurrently minimize the energy consumption of UAV swarms and GUs, as well as the delay of GUs. However, the proposed MOP is a mixed integer nonlinear programming and NP-hard to solve. Therefore, we develop a K-means and Voronoi diagram based area division method, and construct Fermat points to establish connections between GUs and T-UAVs. Then, an improved non-dominated sorting whale optimization algorithm is proposed to seek Pareto optimal solutions for the transformed MOP. Finally, extensive simulations are conducted to verify the performance of proposed algorithms by comparing with baseline mechanisms, resulting in a 50% complexity reduction.

A substantial body of work has focused on two-dimensional (2-D) self-localization of linear arrays using wireless sensor networks (WSN). However, tackling the higher-dimensional three-dimensional (3-D) case remains an open research question. This paper explores the use of one-dimensional (1-D) angle-of-arrival (AOA) measurements, also referred to as space angles (SA), to achieve 3-D self-localization of a linear array in the presence of anchor position errors. Unlike traditional 3-D source localization using SAs, 3-D self-localization requires simultaneous estimation of the array’s position and orientation (direction vector). First, we acquire a coarse solution to the weighted least-squares (WLS) problem via semidefinite relaxation (SDR), and then we enhance it through perturbation analysis. We then address the maximum likelihood (ML) estimation problem using block majorization-minimization (block-MM), which guarantees convergence to the Karush-Kuhn-Tucker (KKT) point. In addition, we propose an improved and tighter quadratic upper bound for a Rayleigh-quotient-like function introduced in our previous work. Simulations confirm that the proposed algorithm reaches the Cramér-Rao lower bound (CRLB) performance in low-noise regimes, with the block-MM-based ML method exhibiting minimal bias.

With the rapid popularization of Internet of Things (IoT) devices, the freshness of data has become a key factor affecting decision quality and system efficiency. The application of unmanned aerial vehicle (UAV) technology provides a new solution for IoT data collection. This article mainly studies how multiple UAVs can improve the freshness of IoT data collection through joint optimization of trajectory planning and channel selection in a three-dimensional (3D) interference environment. We conducted markov decision process (MDP) modeling on the combinatorial optimization problem of the model and proposed an intelligent joint trajectory planning and channel selection for data collection (ITPCS-DC) algorithm based on multi-agent deep reinforcement learning (MADRL). This algorithm can not only avoid the agent falling into local optimum caused by 3D interference, but also effectively reduce the age of information (AoI) of IoT data collection. Simulation results show that the proposed ITPCS-DC algorithm can achieve higher rewards, lower average AoI, reduced channel switching costs, and shorter trajectory lengths compared to other benchmark algorithms. Moreover, it has better adaptability to more complex collaborative environments.

Spectrum mapping (SM) visualizes spectrum information across a geographical area, constructing radio environment maps (REMs), which serve as a foundation for spectrum monitoring, management, and security. Most existing SM schemes rely on spatially distributed sensors or vehicle-mounted equipment, and assume prior environmental knowledge, limiting their applicability in dynamic or unknown 3D environments. In this paper, we propose a Bayesian learning-based three-dimensional (3D) SM framework that enables accurate REM construction through adaptive UAV sampling in complex and unknown environments. First, a mutual-information-driven UAV path planner is designed by integrating an enhanced sampling-based optimization scheme, enabling efficient data collection according to the maximum mutual information criterion and recent sensing data. Second, a semi-deterministic channel dictionary, refined with sampled field data, is established to model the correlation between observed spectrum values and environmental features. Based on this dictionary, a Bayesian learning-based recovery algorithm reconstructs the spectrum distribution at unsampled positions, producing the corresponding 3D REM. Experimental results on open simulated and measured datasets demonstrate that the proposed framework reduces the mean absolute error by over 60% compared with CS-based methods and by 35% with data-driven interpolation. It also improves sampling efficiency by up to 70% for a given recovery accuracy, highlighting the effectiveness in unknown 3D environments.

Resource allocation is paramount to improve spectral efficiency in spectrum-sharing networks. However, numerous existing resource allocation schemes, especially those based on deep reinforcement learning techniques, overlook the impact of time-variant channel quality caused by high dynamics of wireless environment and heterogeneous action space due to discrete actions and continuous parameters, which may significantly degrade the desired system performance. To tackle these issues, in this paper, two intelligent resource allocation schemes that can jointly optimize channel allocation and transmit power in a dynamic spectrum-sharing network are proposed. In particular, an intelligent framework, enhanced by channel prediction, is first proposed to capitalize fully on the latent evolutionary characteristics of time-varying channels, facilitating efficient resource allocation design. Subsequently, a hybrid action representation-based intelligent framework is proposed to learn the latent dependence between channel allocation and transmit power for each secondary user. Simulation results demonstrate that our proposed schemes achieve superior performance compared with several benchmark schemes, highlighting that the sum rate can be improved by exploiting latent channel characteristics and latent hybrid actions dependence.

The enhancement of spectrum efficiency and the realization of secure spectrum utilization are critically dependent on spectrum cognition. However, existing spectrum cognition methods often exhibit limited generalization and suboptimal accuracy when deployed across diverse spectrum environments and tasks. To overcome these challenges, we propose a spectrum foundation model, termed SpectrumFM, which provides a new paradigm for spectrum cognition. An innovative spectrum encoder that exploits the convolutional neural networks and the multi-head self attention mechanisms is proposed to effectively capture both fine-grained local signal structures and high-level global dependencies in the spectrum data. To enhance its adaptability, two novel self-supervised learning tasks, namely masked reconstruction and next-slot signal prediction, are developed for pre-training SpectrumFM, enabling the model to learn rich and transferable representations. Furthermore, low-rank adaptation (LoRA) parameter-efficient fine-tuning is exploited to enable SpectrumFM to seamlessly adapt to various downstream spectrum cognition tasks, including spectrum sensing (SS), anomaly detection (AD), and wireless technology classification (WTC). Extensive experiments demonstrate the superiority of SpectrumFM over state-of-the-art methods. Specifically, it improves detection probability in the SS task by 30% at -4 dB signal-to-noise ratio (SNR), boosts the area under the curve (AUC) in the AD task by over 10%, and enhances WTC accuracy by 9.6%.1

Spectrum map construction is a key technology for enhancing dynamic spectrum management and spectrum efficiency in the sixth-generation wireless communication networks. However, traditional spectrum map construction methods face a dual bottleneck in model generalizability and data dependence. Specifically, the model-driven methods struggle to adapt to dynamic and complex electromagnetic environments, whereas data-driven methods depend on the quality of training data, including sampling density and spatial correlation complexity. To address these challenges, a vision transformer-based large model for spectrum map construction is proposed, namely GenSpectraLM. Inspired by bidirectional encoder representations from transformers masked semantic inference and masked autoencoders local-global construction mechanism, GenSpectraLM employs self-supervised masked pretraining to implicitly learn electromagnetic propagation patterns from diverse datasets. Then, fine-tune is performed to achieve cross-scenario generalization. Simulation results demonstrate that GenSpectraLM achieves accurate spectrum map construction with the root mean squared error of 1.3286 at a sampling rate of 25%. It consistently outperforms benchmark methods by approximately 40%, effectively addressing data efficiency challenges in complex environments.

Spectrum sensing is of crucial importance for improving spectrum efficiency and realizing immersive communication. Deep learning (DL) has been introduced for spectrum sensing, with test statistics generated directly from signal samples in an automatic manner. However, most of the existing data-driven spectrum sensing methods are based on supervised learning and they usually require a massive amount of labeled training data to achieve high detection performance. It is difficult to obtain sufficient labeled training data in practice. To address this issue, a pseudo labeling multi-scale network (PLMSNet) for semi-supervised spectrum sensing is proposed to make the best use of a majority of unlabeled samples and achieves well detection performance with only a few of labeled training samples. Moreover, the proposed scheme is implemented in a real-world software defined radio (SDR) communication system. Both simulation and real-world experiments demonstrate that our proposed method achieves superior detection performance compared with the benchmark methods.

Unmanned aerial vehicle (UAV) communication is of crucial importance in realizing heterogeneous practical wireless application scenarios. However, the densely populated users and diverse services with high data rate demands has triggered an increasing scarcity of UAV spectrum utilization. To tackle this problem, it is promising to incorporate the underutilized unlicensed spectrum with the licensed spectrum to boost network capacity. However, the openness of unlicensed spectrum makes UAVs susceptible to security threats from potential jammers. Therefore, a spectrum sharing UAV network coexisting with licensed cellular network and unlicensed Wi-Fi network is considered with the anti-jamming technique in this paper. The sum rate maximization of the secondary network is studied by jointly optimizing the transmit power, subchannel allocation, and UAV trajectory. We first decompose the challenging non-convex problem into two subproblems, 1) the joint power and subchannel allocation and 2) UAV trajectory design subproblems. A low-complexity iterative algorithm is proposed in a alternating optimization manner over these two subproblems to solve the formulated problem. Specifically, the Lagrange dual decomposition is exploited to jointly optimize the transmit power and subchannel allocation iteratively. Then, an efficient iterative algorithm capitalizing on successive convex approximation is designed to get a suboptimal solution for UAV trajectory. Simulation results demonstrate that our proposed algorithm can significantly improve the sum transmission rate compared with the benchmark schemes.

The rapid proliferation of UAV technology in civilian and military sectors has brought significant benefits but also raised concerns about unauthorized unmanned aerial vehicle (UAV), which pose potential risks to public safety. Current anti-UAV systems, which rely on radar, acoustic, antenna or visual sensors, encounter specific challenges, such as limited positioning ranges, susceptibility to noise, background interference and adverse environmental conditions. To address these limitations, we propose an RF-visual fusion-based memory augmentation network (RVUAV-Net) that integrates RF and visual images, enhancing the UAV positioning accuracy and robustness by utilizing the motion patterns derived from the historical UAV trajectory. Our proposed method capitalizes on the spatial-temporal characteristics of the historical data, enabling precise UAV positioning during partial occlusion and effective responses to high-speed movements. Moreover, our proposed RVUAV-Net minimizes false alarms in the complex environments by distinguishing UAVs from similar flying objects. Experimental results demonstrate superior positioning performance of our proposed method, highlighting its potential for anti-UAV in real-world scenarios where accuracy and continuity are critical.

With the development of low earth orbit (LEO) satellites and unmanned aerial vehicles (UAVs), the space-air-ground integrated network (SAGIN) becomes a major trend in the next-generation networks. However, due to the instability of heterogeneous communication and time-varying characteristics of SAGIN, it is challenging to meet the remote Internet of Things (IoT) demands for data collection and offloading. In this paper, we investigate a two-phase hierarchical data uplink model in SAGIN. Specifically, UAVs optimize trajectories to enable efficient data collection from IoT devices, and then they transmit the data to LEO satellites with computing capabilities for further processing. The problem is formulated to minimize the total energy consumption for IoT devices, UAVs, and LEO satellites. Since the problem is in the form of mixed-integer nonlinear programming and intractable to solve directly, we decompose it into two phases. In the IoT-UAV phase, we design the algorithm to jointly optimize the IoT pairing, power allocation, and UAVs trajectories. Considering the high dynamic characteristics of LEO satellites, a real-time LEO satellite selection mechanism joint with the Satellite Tool Kit is proposed in the UAV-LEO phase. Finally, simulation results show the effectiveness of the proposed algorithms, with about 10% less energy consumption compared with the benchmark algorithm.

The remote identification (Remote ID) broadcast capability allows unmanned aerial vehicles (UAVs) to exchange messages, which is a pivotal technology for inter-UAV communications. Although this capability enhances the operational visibility, low delay in Remote ID-based communications is critical for ensuring the efficiency and timeliness of multi-UAV operations in dynamic environments. To address this challenge, we first establish delay models for Remote ID communications by considering packet reception and collisions across both BLE 4 and Wi-Fi protocols. Building upon these models, we formulate an optimization problem to minimize the long-term communication delay through adaptive protocol selection. Since the delay performance varies with the UAV density, we propose an adaptive BLE/Wi-Fi switching algorithm based on the multi-agent deep Q-network approach. Experimental results demonstrate that in dynamic-density scenarios, our strategy achieves 32.1% and 37.7% lower latency compared to static BLE 4 and Wi-Fi modes respectively.

As an important issue in the sixth generation communication technologies, the space-air-ground integrated network (SAG IN), mainly composed of satellites, unmanned aerial vehicles (UAVs), and ground stations, can provide global information services. However, it is challenging to provide robust services due to the dynamic characteristics of UAV s and satellites, as well as the resource incompatibility among different nodes. By introducing the network function virtualization technique to SAGIN, tasks can be converted into service function chains (SFCs) composed of multiple virtual network functions in series, and the resource allocation of SAGIN is deemed as the SFC deployment and scheduling. However, the node failure or link disconnections may occur in SAG IN, resulting in failures of SFC implementation. Hence, how to guarantee the robust service recovery of SFCs is challenging. In this paper, we propose the SFC deployment and recovery model to cope with the resource failure. The problem is formulated to minimize the total time consumption to complete the SFC deployment and recovery. Since the problem is an integer linear programming and intractable to solve, we propose an algorithm based on two-sided matching game to implement robust recovery of affected SFCs. Finally, simulation results verify the effectiveness and advantages of the proposed algorithm over other benchmark algorithms.

Trust region optimization-based received signal strength indicator (RSSI) interference source localization methods have been widely used in low-altitude research. However, these methods often converge to local optima in complex environments, degrading the positioning performance. This paper presents a novel unmanned aerial vehicle (UAV)-aided progressive interference source localization method based on improved trust region optimization. By combining the Levenberg-Marquardt (LM) algorithm with particle swarm optimization (PSO), our proposed method can effectively enhance the success rate of localization. We also propose a confidence quantification approach based on the UAV-to-ground channel model. This approach considers the surrounding environmental information of the sampling points and dynamically adjusts the weight of the sampling data during the data fusion. As a result, the overall positioning accuracy can be significantly improved. Experimental results demonstrate the proposed method can achieve high-precision interference source localization in noisy and interference-prone environments.

The unmanned aerial vehicle assisted multi-access edge computing (UAV-MEC) technology has been widely applied in the sixth-generation era. However, due to the limitations of energy and computing resources in disaster areas, how to efficiently offload the tasks of damaged user equipments (UEs) to UAVs is a key issue. In this work, we consider a multiple UAVMECs assisted task offloading scenario, which is deployed inside the three-dimensional corridors and provide computation services for UEs. In detail, a ground UAV controller acts as the central decision-making unit for deploying the UAV-MECs and allocates the computational resources. Then, we model the relationship between the UAV controller and UEs based on the Stackelberg game. The problem is formulated to maximize the utility of both the UAV controller and UEs. To tackle the problem, we design a K-means based UAV localization and availability response mechanism to pre-deploy the UAV-MECs. Then, a chess-like particle swarm optimization probability based strategy selection learning optimization algorithm is proposed to deal with the resource allocation. Finally, extensive simulation results verify that the proposed scheme can significantly improve the utility of the UAV controller and UEs in various scenarios compared with baseline schemes.

The unmanned aerial vehicle (UAV) network has gained significant attentions in recent years due to its various applications. However, the traffic security becomes the key threatening public safety issue in an emergency rescue system due to the increasing vulnerability of UAVs to cyber attacks in environments with high heterogeneities. Hence, in this paper, we propose a novel anomaly traffic detection architecture for UAV networks based on the software-defined networking (SDN) framework and blockchain technology. Specifically, SDN separates the control and data plane to enhance the network manageability and security. Meanwhile, the blockchain provides decentralized identity authentication and data security records. Beisdes, a complete security architecture requires an effective mechanism to detect the time-series based abnormal traffic. Thus, an integrated algorithm combining convolutional neural networks (CNNs) and Transformer (CNN+Transformer) for anomaly traffic detection is developed, which is called CTranATD. Finally, the simulation results show that the proposed CTranATD algorithm is effective and outperforms the individual CNN, Transformer, and LSTM algorithms for detecting anomaly traffic.

Specific emitter identification (SEI), known as radio frequency fingerprint (RFF) identification, is one of the key techniques to provide effective protection for the low-altitude security. However, most existing SEI methods cannot achieve satisfactory identification performance in low signal-to-noise ratio (SNR) environments. By fusing background information of the environment, this paper presents a new deep learning-based SEI method that can accurately identify emitters in the environments with severe noises. We first construct a dual convolutional neural network (DCNN) and a U-shaped Convolutional Network (UNet) to extract the RFFs and background information features, respectively. Then, a background-fingerprint attention fusion network (BFAFN) is designed to fuse the background information with RFF features. Using this network, we can obtain detailed emitters information through the fused signals, improving the identification accuracy. Experimental results show that our proposed SEI method outperforms other methods in performance on both open-source and collected unmanned aerial vehicles (UAVs) datasets, with an improvement in identification accuracy of 2% to 5%.

The deployment of unmanned aerial vehicles (UAVs) to assist in measurement collection for radio map construction has significant potential. In this work, we investigate the UAV-assisted radio map updating system, where the UAV has to collect informative measurements to improve radio map accuracy and reach the destination within the constraint of limited onboard energy. We apply Ordinary Kriging to construct the radio map and use Kriging variance as a metric to evaluate the accuracy of the map. We then formulate a finite-horizon Markov Decision Process (MDP) that optimizes the UAVs trajectory, aiming to maximize the total reduction in Kriging variance under the system's constraints. The MDP is challenging due to its sparse reward and large, continuous state space. To address this, we propose an AT-DQN algorithm that utilizes reward shaping and combines Agent Transformer (AT) with Dueling DQN for effective trajectory learning. Finally, through numerical experiments, we verify the efficiency of the proposed algorithm in both radio map updating and trajectory optimization.

In the next-generation emergency communication networks, unmanned aerial vehicles (UAVs), serving as aerial base stations, have attracted increasing attention recently due to their high mobility and low cost. Therefore, this paper conceives a heterogeneous UAVs assisted intelligent communication network system, in which tethered UAVs (T-UAV) make ground users (GUs) scheduling decisions to avoid resource competition, while other UAVs cooperate to provide communication services. However, the limited onboard resources of UAVs and cooperativecompetitive problems among heterogeneous UAVs becomes key challenges in UAV-assisted intelligent emergency communication networks. In order to tackle these issues, we propose a heterogeneous multi-agent approximate policy optimization (HMAPPO) algorithm to maximize the total fair energy efficiency by jointly optimizing UAV trajectories and user scheduling. Simulation results demonstrate that HMAPPO outperforms other baseline algorithms in terms of energy efficiency of the system and fairness of GUs. Furthermore, benefit to the partial parameter sharing mechanism, the proposed HMAPPO significantly accelerates the training process compared to other benchmark algorithms.

Constructing three-dimensional (3D) radio environment maps (REMs) has emerged as a promising solution to visualize the spectrum information over the geographical map. In this paper, we propose a novel online path planning method for unmanned aerial vehicle (UAV)-based 3D spectrum mapping in unknown environments. The UAV can effectively collect spectrum data along dynamically planned paths while adhering to budget constraints. We formulate the path planning problem by a surrogate objective that maximizes the information gain along the sampling path. Specifically, a Gaussian process (GP) is adopted to estimate the spatial distribution of received signal strength (RSS) based on observations. A goal location decision algorithm based on the negative integrated posterior variance (NIPV) criterion is developed, which identifies high-value locations by maximizing the reduction in uncertainty. Besides, an uncertainty-aware local path planner is introduced to optimize sampling paths during flight. Simulation results demonstrate that it achieves at least a 66.49% improvement in REM construction accuracy and 42.74% reduction in mapping uncertainty compared to traditional methods.

Identifying key nodes in a network is crucial for practical applications, especially when it comes to accurately detecting cut vertices, which play a vital role in maintaining network stability. As network complexity increases, relying on a single method to identify key nodes often fails to provide a comprehensive assessment of node importance in real-world scenarios. To address this, this paper proposes a novel framework for cut vertex identification that evaluates node importance from three perspectives: weighted fusion centrality metrics, the spanning tree algorithm, and topology graph properties. Additionally, existing methods based on centrality metrics often struggle with low accuracy in identifying cut vertices. To overcome this limitation, we have devised a method, termed the MIS-CV algorithm, that enables the accurate identification of network cut vertices by solely evaluating the intersection of node neighborhoods within the maximum independent set. We validated our proposed algorithm through simulation analysis on the Barabasi-Albert scale-free network. The results demonstrate that the MIS-CV key nodes identification algorithm surpasses traditional search tree algorithms in terms of both accuracy and operational efficiency. This proves that the MIS-CV algorithm has higher recognition accuracy without increasing computational complexity.

The unmanned aerial vehicles (UAVs) are efficient tools for diverse tasks such as electronic reconnaissance, agricultural operations and disaster relief. In the complex three-dimensional (3D) environments, the path planning with obstacle avoidance for UAVs is a significant issue for security assurance. In this paper, we construct a comprehensive 3D scenario with obstacles and no-fly zones for dynamic UAV trajectory. Moreover, a novel artificial potential field algorithm coupled with simulated annealing (APF-SA) is proposed to tackle the robust path planning problem. APF-SA modifies the attractive and repulsive potential functions and leverages simulated annealing to escape local minimum and converge to globally optimal solutions. Simulation results demonstrate that the effectiveness of APFSA, enabling efficient autonomous path planning for UAVs with obstacle avoidance.

Due to the increasing demand for the accuracy of spectrum maps, fusing spectrum maps has gained attention as an effective method to improve the exactitude of spectrum map construction. However, most of the existing spectrum map fusion methods overlook the over-fitting problem and the correlation of spectral data in the fusion process, so the performance can hardly meet expectations. In this paper, a spectrum map fusion method based on differential ridge regression is proposed, which can construct accurate spectrum maps in the electromagnetic environment with strong-correlation data with high accuracy. First, we construct a spectrum map fusion model by exploiting the propagation characteristics of the spectrum signal. According to the path loss model, the differential ridge regression regularization term is designed to handle the correlation of spectral data and suppress anomalies from spectrum receivers. Finally, we construct a convex optimization problem for spectrum map fusion and obtain the lower bound of the problem by developing Lagrange duality. This method can ensure the convergence of the spectrum map fusion problem and accelerate the convergence speed under low complexity. Simulation results show that the proposed fusion method can effectively improve the accuracy of spectrum map construction compared with the state-of-the-art.

Autonomous aerial vehicles (AAVs) play significant roles in multiple fields, which brings great challenges for the airspace safety. In order to achieve efficient surveillance and break the limitation of application scenarios caused by single communication, we propose the collaborative surveillance model for hierarchical AAVs based on the cooperation of automatic dependent surveillance-broadcast (ADS-B) and 5G. Specifically, AAVs are hierarchical deployed, with the low-altitude central AAV equipped with the 5G module, and the high-altitude central AAV with ADS-B, which helps automatically broadcast the flight information to surrounding aircraft and ground stations. First, we build the framework, derive the analytic expression, and analyze the channel performance of both air-to-ground (A2G) and air-to-air (A2A). Then, since the redundancy or information loss during transmission aggravates the monitoring performance, the mobile edge computing (MEC) based on-board processing algorithm is proposed. Finally, the performances of the proposed model and algorithm are verified through both simulations and experiments. In detail, the redundant data filtered out by the proposed algorithm accounts for 53.48%, and the supplementary data accounts for 16.42% of the optimized data. This work designs a AAV monitoring framework and proposes an algorithm to enhance the observability of trajectory surveillance, which helps improve the airspace safety and enhance the air traffic flow management.

deep learning (DL) has been widely applied to enhance automatic modulation classification (AMC). However, the elaborate AMC neural networks are susceptible to various adversarial attacks, which are challenging to handle due to the generalization capability and computational cost. In this article, an explainable DL based defense scheme, called Shapley additive explanation enhanced adversarial fine-tuning (SHAP-AFT), is developed in the perspective of disclosing the attacking impact on the AMC network. By introducing the concept of cognitive negative information, the motivation of using SHAP for defense is theoretically analyzed first. The proposed scheme includes three stages, i.e., the attack detection, the information importance evaluation, and the AFT. The first stage indicates the existence of the attack. The second stage evaluates contributions of the received data and removes those data positions with negative Shapley values corresponding to the dominating negative information caused by the attack. Then the AMC network is fine-tuned based on adversarial adaptation samples using the refined data pattern. Simulation results show the effectiveness of the Shapley value as the key indicator as well as the superior defense performance of the proposed SHAP-enhanced adversarial fine-tuning (SHAP-AFT) scheme in face of different attack types and intensities.

The safe and high-efficiency operation of low-altitude vehicles (LAVs) is the key to supporting the rapid development of the low-altitude economy. However, the conventional space-air-ground integrated network (C-SAGIN) mainly focuses on ground users, which is difficult to provide high-quality services for LAVs. In this article, we first propose a novel architecture of low-altitude centric space-air-ground integrated network (LAC-SAGIN), where low-altitude airspace and LAVs become the communication centers. A detailed comparison is further illustrated between these two architectures in terms of their composition and performance metrics. Although LAC-SAGIN can effectively support the low-latency and continuous communication of LAVs, it still faces several key implementation challenges including insufficient low-altitude infrastructures, high mobility of LAVs and its diversified task requirements, and low transmission efficiency and energy efficiency in airspace communication. To address these challenges, the corresponding three countermeasures are proposed, which reveal the future research direction of LAC-SAGIN.

Radio environment maps (REMs) have been used to visualize the information of invisible electromagnetic spectrum. Although in the past there have been many research activities dealing with the reconstruction of static REMs, they did not consider the time variation of the dynamic spectrum operational environment. In this article, we present a novel time-variant REM reconstruction methodology based on sparsely distributed sensors which jointly considers sensor layout optimization, propagation model improvement, and missing spectrum data recovery. First, a low complexity and computationally efficient method is proposed to improve the sampling efficiency. The proposed method jointly employs the gradient descent method and an upgraded greedy matching algorithm to optimize the sensor positions even when large-scale scenarios are considered. Then, by using the sampled spectrum data obtained from these sensors, the accuracy of commonly employed propagation models is improved and subsequently used to construct a channel dictionary for such time-varying environments. By exploring the heterogeneity of dynamic spectrum operational environments, an improved optimal reconstruction method is designed to recover the spectrum data using their spatial-temporal correlation. By considering a typical university campus environment as a case study, simulation and measurement data are obtained to reconstruct the time-variant REM. Through the simulation data, the reconstruction performance results are compared with those obtained from other state-of-the-art methods showing that the proposed methodology outperforms the others with respect to the sampling scheme and missing rate. Additionally, field measurement results have demonstrated that the proposed approach can effectively reconstruct time-variant REMs under dynamic scenarios.

Federated learning (FL), as an innovative paradigm of distributed learning, provides reliable support for the growing edge intelligence (EI). The limitations of traditional FL’s reliance on ground base stations (BSs) make the development of aerial server unmanned aerial vehicles (UAVs) inevitable, thereby developing the air-ground integrated FL (AGIFL). However, current efforts predominately focus on static offline training based on existing datasets and some efforts consider online training in dynamic sample environments, where new samples need to be fully pre-trained to determine sample quality. To this end, we study how to realize high-performance of FL in dynamic environment without training all samples. Specifically, we formulate a joint optimization problem for sample selection, UAV deployment, and resource distribution aiming to minimize the trade-off between the user energy consumption and FL performance. To address the optimization problem without explicit expression, we employ meta-learning to derive an upper bound on the gradient norm of the loss function to evaluate learning performance, and describe how time-varying small-batch ratios affect this bound. Then, we propose an optimization algorithm that ensures convergence, capitalizing on the block coordinate descent techniques. To demonstrate the efficacy of our algorithm, we conduct both extensive simulations and proof-of-concept field experiments. The findings indicate an average improvement of approximately 39% in reducing the objective value when compared to the benchmarks.

With the rapid development of wireless communication services, spectrum map-based localization has become an important technology in the sixth-generation (6G) wireless communication networks due to their low cost and ease of implementation. However, signal source localization based on spectrum map construction is heavily dependent on the construction accuracy of the spectrum map. This challenge is further exacerbated in urban environments due to high-density connections and complex terrain. To address the aforementioned challenges, a data-and-semantic dual-driven method is proposed, which incorporates semantic knowledge of both binary city maps and binary sampling location maps. This approach first extracts spatial dimension information that reflects signal propagation, improving the accuracy of the constructed spectrum map and signal source localization in the complex urban environments. Then, to reduce the reliance of signal source localization on the accuracy of spectrum map construction, a data-and-semantic dual-driven intelligent inference framework for simultaneously spectrum map construction and signal source localization (DSD-SCL) is proposed. Moreover, a joint training framework is employed to collaboratively optimize both spectrum map construction and signal source localization. Simulation results demonstrate that DSD-SCL exhibits superior performance in terms of stability and convergence speed. Meanwhile, it significantly enhances the construction accuracy of spectrum maps and the localization accuracy of signal sources, particularly in low sampling density and multisignal source scenarios.

In wireless communications, unauthorized broadcasting within licensed spectrum bands disrupts legitimate signals and interferes with adjacent frequencies, risking critical systems. Existing methods for detecting unauthorized broadcasting often underutilize known signal data, reducing their effectiveness in dynamic, open-set scenarios. To address this, we propose a novel framework combining a temporal convolutional autoencoder (TCAE) with boundary-guided support vector data description (BGSVDD) for accurate detection of unauthorized signals in the radio frequency spectrum. The TCAE captures temporal signal features effectively with an adaptive temporal convolutional network (ATCN), while the BGSVDD uses a small set of known unauthorized samples to create robust decision boundaries with our proposed adaptive misclassification penalty (AMP) loss. Moreover, a global-local support vector (GLSV) strategy enables efficient online model updates, maintaining detection performance in evolving wireless environments with minimal resource overhead. Experiments with real-world broadcast signals show our method outperforms state-of-the-art techniques, especially under challenging interference conditions. Tests on public datasets further confirm its strong generalization across diverse spectrum protection applications.

Automatic modulation classification (AMC) plays a vital role in advancing future wireless communication networks. Although deep learning (DL)-based AMC frameworks have demonstrated remarkable classification capabilities, they typically require large-scale training datasets and assume consistent class distributions between training and testing data-prerequisites that prove challenging in few-shot and open-set scenarios. To address these limitations, we propose a novel few-shot open-set automatic modulation classification (FSOS-AMC) framework that integrates a multi-sequence multi-scale attention network (MS-MSANet), meta-prototype training, and a modular open-set classifier. The MS-MSANet extracts features from multi-sequence input signals, while meta-prototype training optimizes both the feature extractor and the modular open-set classifier, which can effectively categorize testing data into known modulation types or identify potential unknown modulations. Extensive simulation results demonstrate that our FSOS-AMC framework achieves superior performance in few-shot open-set scenarios compared to state-of-the-art methods. Specifically, the framework exhibits higher classification accuracy for both known and unknown modulations, as validated by improved accuracy and area under the receiver operating characteristic curve (AUROC) metrics. Moreover, the proposed framework demonstrates remarkable robustness under challenging low signal-to-noise ratio (SNR) conditions, significantly outperforming existing approaches.

Cellular-connected autonomous aerial vehicles (AAVs) act as aerial users to accomplish navigation missions while maintaining a cellular connection, which are of great importance for developing low-altitude Internet of Things (IoT) systems. However, the full aerial cellular coverage is an extreme challenge. To tackle this issue, existing coverage-aware navigation studies focus on designing AAV flight trajectories to avoid weak coverage areas while completing the mission, where considerable efforts of deep-reinforcement-learning-(DRL)-based methods have been conducted. However, they lack adaptability to various targets, which limits their practical applicability in real-world scenarios. In this article, we propose a novel DRL-based multitarget coverage-aware navigation (MTCN) framework, where the AAV learns a navigation policy to minimize the weighted sum of navigation time and the expected communication outage duration. MTCN allows the AAV to efficiently navigate to arbitrary targets without the need of the separate policy training for each target. Furthermore, to improve the sample efficiency of the MTCN, we introduce the radio map-enhanced MTCN (RM-MTCN) framework, which leverages a virtual radio map to generate supplementary navigation training data. RM-MTCN can significantly reduce the need for extensive real-world interactions. Extensive experimental results demonstrate that both MTCN and RM-MTCN achieve generalized navigation behaviors across different targets while avoiding weak communication coverage areas. It is also shown that RM-MTCN exhibits faster learning speed and better performance compared to MTCN, which indicates the effectiveness of leveraging the virtual radio map during the policy training.

The rapid development of the autonomous aerial vehicle (AAV) technology has significantly facilitated its application in the burgeoning Internet of Things (IoT) ecosystem. AAV visual navigation has emerged as a particularly vibrant and crucial research area, holding the potential to greatly enhance automated IoT services. deep reinforcement learning (DRL), recognized as an effective method for visual navigation, encounters two significant challenges in the complex outdoor environments, i.e., the partial observability and the local optima trapping. In this article, to address these two challenges, we propose a novel semantic map-based cognitive escape reinforcement learning (SM-CERL) navigation method, which consists of two innovatively designed modules, namely the semantic mapping module (SMM) and the cognitive escape module (CEM). By deeply exploring the similarity structure of raw images and mapping them to the advanced semantic representations, the SMM constructs a semantic map with rich implications, which provides the AAV with the memory to enhance its understanding of the environment. Meanwhile, the CEM can proactively identify local optima and leverage the rule knowledge to establish efficient escape strategies. The holistic fusion of semantic mapping and cognitive escape mechanisms efficiently enhances the environmental comprehension and prevents AAVs from being trapped in local optima. Extensive experimental results demonstrate that our SM-CERL outperforms the existing classical and state-of-the-art methods in terms of the navigation accuracy and efficiency.

This paper explores the waveform design problem for multiple-input multiple-output radar, focusing on minimizing the mean square error between the idealized beampattern and its actual implementation. The optimization respects two practical non-convex constraints: constant modulus and similarity. To address this non-convex optimization challenge, we propose a solution based on the Riemannian Product Manifold Conjugate Gradient (RPM-CG) framework. The RPM-CG framework transforms the multi-constrained non-convex problem in Euclidean space into a straightforward unconstrained one on the product manifold. Specifically, we leverage the conjugate gradient method to perform a descent search on the developed product manifold. Simulations demonstrate that RPM-CG outperforms other candidate beampattern design methods, enhancing the matching performance of the beampattern, reducing computational complexity, and maintaining waveform ambiguity properties.

Spectrum sharing unmanned aerial vehicle (UAV) network is a promising technology for future communication systems to mitigate the spectrum scarcity problem. However, the future sixth-generation large-scale wireless communication networks are expected not only to provide a high data rate for massive numbers of users but also to meet their stringent service requirements. Particularly in dynamic spectrum sharing UAV networks, the coupling of multi-dimensional resources and diverse user demands make the efficient and real-time resource allocation exceptionally challenging. A partially observable deep multi-agent active inference (PODMAI) framework is proposed to tackle these issues. The variational free energy is minimized to update the policy exploiting the belief based learning method. A decentralized training and execution multi-agent strategy is designed to navigate the challenges posed by partially observable information. To further satisfy the dynamic user demand and supplement partial observations, a joint spatial-temporal-attention prediction network is designed to construct the demand prediction enhanced PODMAI framework for resource allocation. Exploiting the established framework, an intelligent spectrum allocation and trajectory optimization scheme is elaborated for a spectrum sharing UAV network with multi-modal dynamic transmission rate demands. Simulation results demonstrate that our proposed scheme outperforms benchmark schemes in terms of the network sum transmission rate. Additionally, our proposed scheme exhibits faster convergence compared to the conventional reinforcement learning. Overall, our proposed framework can enrich intelligent resource allocation frameworks and pave the way for realizing real-time resource allocation.

Due to the high flexibility and versatility, uncrewed aerial vehicles (UAVs) are leveraged in various fields including surveillance and disaster rescue. However, in UAV networks, routing is vulnerable to malicious damage due to distributed topologies and high dynamics. Hence, ensuring the routing security of UAV networks is challenging. In this paper, we characterize the routing process in a time-varying UAV network with malicious nodes. Specifically, we formulate the routing problem to minimize the total delay, which is an integer linear programming and intractable to solve. Then, to tackle the network security issue, a blockchain-based trust management mechanism (BTMM) is designed to dynamically evaluate trust values and identify low-trust UAVs. To improve traditional practical Byzantine fault tolerance algorithms in the blockchain, we propose a consensus UAV update mechanism. Besides, considering the local observability, the routing problem is reformulated into a decentralized partially observable Markov decision process. Further, a multi-agent double deep Q-network based routing algorithm is designed to minimize the total delay. Finally, simulations are conducted with attacked UAVs and numerical results show that the delay of the proposed mechanism decreases by 13.39%, 12.74%, and 16.6% than multi-agent proximal policy optimal algorithms, multi-agent deep Q-network algorithms, and methods without BTMM, respectively.

It is challenging to ensure both high accuracy and low complexity when localizing radiation sources. To address this challenge, we propose two novel methods leveraging time difference of arrival (TDOA) measurements. Specifically, we introduce a TDOA estimation method and a direct position determination (DPD) method based on parallel factor (PARAFAC) analysis in the cross-correlation domain. Initially, multiple sensors synchronously capture the source signal, and the cross-correlation function between signals received from a reference sensor and other sensors is calculated. Then, the primary cross-spectrum data undergoes an expansion and integration process to establish the PARAFAC model. Through cross-spectrum expansion, virtual nodes are formed, which further improves the estimation performance. The TDOA estimates for each sensor are obtained by normalizing and extracting the phase from this matrix. Additionally, we introduce a novel DPD method tailored for multipath propagation scenarios. Simulations and real-world measurements demonstrate the superiority and effectiveness of our proposed methods compared with cutting-edge methods.

Unmanned aerial vehicles (UAVs) are widely used for object detection. However, the existing UAV-based object detection systems are subject to severe challenges, namely, their limited computation, energy and communication resources, which limits the achievable detection performance. To overcome these challenges, a UAV cognitive semantic communication system is proposed by exploiting a knowledge graph. Moreover, we design a multi-scale codec for semantic compression to reduce data transmission volume while guaranteeing detection performance. Considering the complexity and dynamicity of UAV communication scenarios, a signal-to-noise ratio (SNR) adaptive module with robust channel adaptation capability is introduced. Furthermore, an object detection scheme is proposed by exploiting the knowledge graph to overcome channel noise interference and compression distortion. Simulation results conducted on the practical aerial image dataset demonstrate that our proposed semantic communication system outperforms benchmark systems in terms of detection accuracy, communication robustness, and computation efficiency, especially in dealing with low bandwidth compression ratios and low SNR regimes.

The ever-increasing requests of users in emergency communication scenarios lead to high data traffic and transmission delay, posing challenges for resource-limited space-air-ground integrated networks (SAGINs). To address this issue, this paper proposes a joint caching optimization and user selection (JCOUS) problem that leverages unmanned aerial vehicle (UAV) caching to maximize the residual energy of the satellite, considering the limited resources of UAVs. To address the complex time-coupling optimization problem with discrete variables, we propose a primal decomposition method to decouple the problem, and design an energy-efficient user selection algorithm with dynamic caching. Furthermore, to reduce computational complexity and cost, we consider a statistical scenario and maximize the statistical residual energy in the JCOUS problem. Simulation results verify that the proposed scheme can achieve a higher residual energy and fast optimization, thus realizing energy saving and quick decision making especially in large-scale computation-intensive SAGINs.

Although integrated sensing and communication (ISAC) has an advantage of mutual gain of its dual functions, it is susceptible to be eavesdropped by mobile targets due to the broadcast nature of wireless channels. In this paper, we propose a secure predictive beamforming scheme against a mobile eavesdropping target for ISAC, where the intelligent reflecting surface (IRS) is utilized to assist the sensing and secure transmission. To tackle the mobility of eavesdropping target, we first develop a secure predictive beamforming protocol and formulate a sum secrecy rate maximization problem. However, due to the non-convex objective function and the outdated channel state information (CSI), it is difficult to solve the problem directly. Thus, we develop a deep learning based predictive beamforming scheme, which incorporates the parallel convolutional neural network, the long short-term memory modules and the attention mechanism to learn the features from the historical CSI. It can directly design the beamformings for the next time slot with low computational complexity and bypass the need of CSI prediction. Simulation results show that the proposed scheme can significantly enhance the security of ISAC with low overhead.

Cryptocurrencies, underpinned by blockchain technology, face persistent threats such as money laundering and extortion due to their decentralized and anonymous nature. Detecting fraudulent transactions is crucial for ensuring the security of block-chain systems. However, the existing detection methods face the following challenges: lack of labeled data, severe class imbalance in labeled data, complex network structure, numerous parameters, and long training time. To address these challenges, we propose a novel semisupervised learning framework that combines the graph augmented with pseudolabels generation (GAPLG) model and postprocessing technique. Our framework employs graph learning networks to elucidate relationships between transactions and users. By utilizing pseudolabels for unlabeled transaction data and embedding them onto diverse graph nodes, we achieve precise labels, enhancing prediction accuracy. Additionally, we employ specific post-processing technique, such as correction and smoothing (C&S) technology, to rectify residuals and refine labels, ensuring our framework rivals the best parameter and baseline models. Our method boasts high scalability and flexibility, aiding in optimizing various evaluation indicators. Experimental verification through multiple real transaction datasets under varying data segmentations, demonstrated its effectiveness when compared with other representative frameworks. The analysis validates the effectiveness and benefits of our method.

While a majority of single-modal ship detectors solely rely on RGB images, a novel multi-modal real-time transformer-based ship detection and classification method, called the MM-ShipNet, is proposed in this paper that integrates the data acquired from three modalities—i.e., RGB camera, radar, and automatic identification system (AIS). First, a bounding box is generated based on the position information from radar and ship’s actual size information from AIS. This physical information are fused and projected onto the camera-acquired RGB image frame. Each bounding box is then possibly weighted depending on the ship size presented on the image. The generated weighted ship masks (WSMs) will be exploited for facilitating ship classification task. In the second stage of MM-ShipNet, multi-modal detection transformer (MM-DETR) introduces an multi-modal cross-scale encoder (MCE) for improving ship detection and classification performance. Our MCE exploits a dual-flow structure to fuse the features extracted from the WSMs and the RGB images under different scales. Since our method is the first work entailing three aforementioned modalities, no such dataset with all modalities can be found in the open source. Thus, we construct a multi-modal ship dataset, termed MMShips, as another contribution. Our MMShips dataset comprises 9,513 camera-acquired real-life maritime RGB images and their aligned ship masks generated from radar and AIS. Experimental results clearly demonstrate that our MM-ShipNet significantly outperforms multiple state-of-the-art single-modal and multi-modal ship detectors.

The fifth-generation new radio (NR) cellular communication is featured with numerous advancements over Long Term Evolution (LTE) and earlier technologies. It enables more flexible physical-layer resource scheduling across multiple dimensions, and two representative techniques are beamspace transmissions and time-frequency numerology selection. Nevertheless, the lightweight physical-layer secure transmission in NR remains under investigation, especially taking NR beamspace and mobility into consideration. In this work, we propose a physical-layer wireless key generation (KG) efficient beamspace adaptation scheme for NR, where the KG capacity is theoretically characterized by critical NR components including beam direction and beamwidth. In addition, we consider the impacts of user mobility on KG performance. Since NR beamspace plays a key role in deciding the channel probing window in the spatial dimension, the NR beamspace directly affects channel probing results and hence the KG efficiency. To this end, NR beam parameters are obtained to improve the KG performance. Especially, we propose to optimize the NR beamwidth for maximizing the secrecy-delay efficiency, because a tradeoff exists in adapting the beamwidth where smaller beamwidth can improve the channel estimation accuracy but increase the beam sweeping delay. Theoretical analysis and simulation results show that the beam direction adaptation provides spatial degrees of freedom for NR to enhance KG, by enabling beam selection pointing at target areas with richer multipath scatterings. Experimental results demonstrate that the narrow beam is beneficial to enhancing the channel estimation accuracy and the resultant key agreements.

Precise unmanned aerial vehicle (UAV) detection over long distances is of crucial importance for guaranteeing the airspace security. Although deep learning-based vision detectors have been developed, they still rely on a large amount of hand-crafted fixed feature priors. The existing static dense-based detectors suffer from the severe mismatch and imbalance between the small size and the high mobility of UAVs. To solve the problem, a novel multimodal fusion-based dynamic sparse UAV detection framework is proposed. The framework reformulates the feature priors in a completely dynamic sparse paradigm by using the radar data. Based on the framework, a vision-radar fusion-based dynamic sparse network (Vira-DSNet) is proposed for more balanced and robust UAV detection. The Vira-DSNet exploits our designed dynamic sparse candidate generator and radar-guided semantic feature transform to generate a small set of customized high-quality object candidates and semantic features based on the radar data. Moreover, based on Hungarian bisection matching, our Vira-DSNet eliminates the post-processing and is completely end-to-end differentiable. Furthermore, the Vira-DSNet is deployed in our developed actual vision-radar fusionbased UAV detection system to evaluate the performance in the practical applications. Experimental results demonstrate that our Vira-DSNet achieves an average precision AP50of 88.2%. It is also shown that the average recall AR1of Vira-DSNet is higher than the state-of-the-art scheme by 10.1%, while maintaining the real-time performance.

Unmanned aerial vehicles (UAVs) are increasingly being integrated into next-generation networks to enhance communication coverage and network capacity. However, the dynamic and mobile nature of UAVs poses significant security challenges, including jamming, eavesdropping, and cyber-attacks. To address these security challenges, this paper proposes a federated learning-based lightweight network with zero trust for enhancing the security of UAV networks. A novel lightweight spectrogram network is proposed for UAV authentication and rejection, which can effectively authenticate and reject UAVs based on spectrograms. Experiments highlight LSNet’s superior performance in identifying both known and unknown UAV classes, demonstrating significant improvements over existing benchmarks in terms of accuracy, model compactness, and storage requirements. Notably, LSNet achieves an accuracy of over 80% for known UAV types and an Area Under the Receiver Operating Characteristic (AUROC) of 0.7 for unknown types when trained with all five clients. Further analyses explore the impact of varying the number of clients and the presence of unknown UAVs, reinforcing the practical applicability and effectiveness of our proposed framework in real-world FL scenarios.

Array self-position determination methods based on multiple emitter data can avoid significant deviations of vehicle satellite navigation in harsh environments. However, existing array self-position determination methods show decrease in performance under multipath environments. To deal with this problem, we propose an array self-position determination method based on orthogonal grid matching with the spatial differencing method. Specifically, the direction of arrival (DOA) of direct path and multipath signals are respectively estimated by array spatial differencing method. The matching accuracy is enhanced by utilizing the prior information of direct path signal. After calculating correlation coefficients of different sources, estimated angles with high correlation are then classified into the same set. Then, the noise subspace of each angle set is reconstructed and the position is estimated by grid matching with the orthogonal property between the noise subspaces and the characteristic steering vectors. The matching results of redundant angle sets are removed as non-matching items, thus averting positioning deviations. The simulation results demonstrate that the computational complexity of the proposed method is comparable to that of the signal subspace fitting (SSF). Moreover, in terms of positioning precision, the proposed method outperforms multiple signal classification with enhanced spatial smoothing (ESSMUSIC), initial signal fitting (ISF), and SSF.

With an extensive increment of computation demands, the aerial multi-access edge computing (MEC), mainly based on unmanned aerial vehicles (UAVs) and high altitude platforms (HAPs), plays significant roles in future network scenarios. In detail, UAVs can be flexibly deployed, while HAPs are characterized with large capacity and stability. Hence, in this paper, we provide a hierarchical model composed of an HAP and multi-UAVs, to provide aerial MEC services. Moreover, considering the errors of channel state information from unpredictable environmental conditions, we formulate the problem to minimize the total energy cost with the chance constraint, which is a mixed-integer nonlinear problem with uncertain parameters and intractable to solve. To tackle this issue, we optimize the UAV deployment via the weighted K-means algorithm. Then, the chance constraint is reformulated via the distributionally robust optimization (DRO). Furthermore, based on the conditional value-at-risk mechanism, we transform the DRO problem into a mixed-integer second order cone programming, which is further decomposed into two subproblems via the primal decomposition. Moreover, to alleviate the complexity of the binary subproblem, we design a binary whale optimization algorithm. Finally, we conduct extensive simulations to verify the effectiveness and robustness of the proposed schemes by comparing with baseline mechanisms.

In low-altitude networks, unmanned aerial vehicles (UAVs) can offer services such as logistics, intelligence surveillance, and environmental monitoring, aided by base stations (BSs) with substantial computational resources. However, BSs must defend against malicious UAVs that may overload resources or launch denial-of-service attacks. In this paper, we formulate a blockchain-enabled access control model, which uses the UAV identities (IDs) and trajectories, positive and negative interactions with the BS to evaluate the reputations of UAVs. In the blockchain, the elected miner generates blocks containing UAV IDs, coordinates, interactions, and reputation values. To defend against malicious UAVs, this paper formulates a trusted computational resource allocation optimization problem, solved by safe reinforcement learning (RL) with a three-level hierarchical structure. Specifically, this method uses the designed structure to optimize the BS access control, resource allocations, and block size. In particular, we design an E-network to evaluate the long-term risk resulting from the chosen policy, which is used to refine the policy distribution for safe exploration. A modified reward function accounts for immediate risks, preventing short-term dangerous explorations that could lead to illegal access or computational failures. We prove the Lyapunov asymptotic stability of the proposed system and derive the reward upper bound. Simulation results show that our scheme can converge to the upper bound, outperform the benchmark, and validate the effectiveness via ablation experiments.

Uncrewed aerial vehicles (UAVs) positioning is of crucial importance in diverse applications. However, it is extremely challenging to realize the precise UAVs positioning over long distances due to the small size and dramatic scale variations associated with the high mobility in the wide area. To tackle this issue, a multimodal scale normalization framework is proposed for the scale-robust precise pixel-level UAV positioning. The framework exploits our proposed distance-aware image slicing and distance-aware scale normalization module. Moreover, a modal fusion-based scale normalization network is proposed that can accept arbitrary low-resolution UAV patches and produce the consistent high-resolution images at a uniform UAV instance scale with a single learnable model. The proposed framework is generic and can be directly used in the existing pixel-level positioning pipelines to improve the positioning performance and scale robustness. To verify the proposed framework in the real application, a practical vision-radar UAV positioning system is developed. Experimental results on the real-world dataset demonstrate the generality and effectiveness of our framework. Moreover, the ablation experiments also confirm the contribution of each module in the framework.

Owing to the ability of reconfiguring wireless channels, intelligent reflecting surface (IRS) can help non-orthogonal multiple access (NOMA) to release its tremendous potential. However, the inter-user interference becomes the bottleneck of IRS-NOMA networks. To tackle this challenge, we propose two constructive interference precoding (CIP) based countermeasures in this paper for interference exploitation in IRS-NOMA networks. Specifically, the first scheme makes the residual interference from higher-order users (HUs) be constructive to lower-order users (LUs), so that the interference-free decoding can be achieved. While the second scheme directly utilizes the interference from LUs for the signal reception of HUs to avoid successive interference cancellation (SIC). The transmit power is minimized by jointly optimizing the BS active beamforming and the IRS passive beamforming for the two schemes, subject to the signal-to-interference-plus-noise ratio (SINR) requirement of each user, SIC decoding constraints, constructive condition and IRS unit-modulus constraint. Due to the coupled variables and non-convex constraints, we first decompose each problem into two subproblems, and then apply successive convex approximation (SCA) to convert them into convex ones. Finally, an alternating optimization (AO) based algorithm is proposed to solve the two convex subproblems for each scheme iteratively. Simulation results are presented to show the superiority and applicability of the proposed schemes compared to benchmarks.

Automatic modulation classification (AMC) is a promising technology to realize intelligent wireless communications in the sixth-generation (6G) wireless communication networks. Recently, many data-and-knowledge dual-driven schemes have achieved high accuracy in AMC. However, most of these schemes focus on generating additional prior knowledge of unknown signals, which needs more computation cost in the inference phase. To solve these problems, we propose for the first time a modulation knowledge graph (MKG), and a novel knowledge graph (KG) driven AMC (KGAMC) framework by training the networks under the guidance of MKG domain knowledge. To achieve the best performance by exploiting KGAMC, a KG-driven multi-time-scale network (KG-MTSNet) is proposed to extract the MKG knowledge and the scale and frequency features of the sampled signals. Moreover, to utilize the knowledge, a designed feature aggregation loss is implemented to improve the signal feature presentation obtained by the data-driven model. Simulation results demonstrate that KGAMC significantly boosts the performances of data-driven models, and the KG-MTSNet achieves a superior classification performance compared to other benchmarks. Furthermore, the effectiveness of KGAMC is demonstrated in terms of the interpretability of the feature extraction and the sample shortage situation.

In this paper, we propose a deep learning (DL)-based task-driven spectrum prediction framework, named DeepSPred. The DeepSPred comprises a feature encoder and a task predictor, where the encoder extracts spectrum usage pattern features, and the predictor configures different networks according to the task requirements to predict future spectrum. Based on the DeepSPred, we first propose a novel 3D spectrum prediction method combining a flow processing strategy with 3D vision Transformer (ViT, i.e., Swin) and a pyramid to serve possible applications such as spectrum monitoring task, named 3D-SwinSTB. 3D-SwinSTB unique3D Patch Merging ViT-to-3D ViT Patch Expandingand pyramid designs help the model accurately learn the potential correlation of the evolution of the spectrogram over time. Then, we propose a novel spectrum occupancy rate (SOR) method by redesigning a predictor consisting exclusively of 3D convolutional and linear layers to serve possible applications such as dynamic spectrum access (DSA) task, named 3D-SwinLinear. Unlike the 3D-SwinSTB output spectrogram, 3D-SwinLinear projects the spectrogram directly as the SOR. Finally, we employ transfer learning (TL) to ensure the applicability of our two methods to diverse spectrum services. The results show that our 3D-SwinSTB outperforms recent benchmarks by more than 5%, while our 3D-SwinLinear achieves a 90% accuracy, with a performance improvement exceeding 10%.

Non-orthogonal multiple access (NOMA) can help integrated sensing and communication (ISAC) to accommodate more users and well manage interference. In this paper, we first propose a NOMA-ISAC scheme, in which a multiantenna base station (BS) transmits ISAC signal to detect a radar user (RU), and provide wireless service to the RU and the communication user (CU) simultaneously. The inter-user interference can be mitigated by the successive interference cancellation (SIC). We further investigate the trade-off between minimizing the beampattern matching error and maximizing the CU’s achievable signal-to-noise ratio (SNR), and propose a penalty-based semi-definite relaxation (SDR) method to solve this non-convex problem. Then, to mitigate the instantaneous NOMA-ISAC beampattern shaking and enhance its stability, we utilize constructive interference precoding (CIP) to assist the NOMA-ISAC beampattern design. Introducing CIP can convert the interference from RU into the beneficial signal to CU and the complex SIC can be avoided. Then, the corresponding trade-off can be transformed into a convex problem by the Taylor-series approximation, and an iterative algorithm is proposed to solve it. Moreover, the Manopt toolbox assisted initialization is utilized to accelerate its convergence speed. Simulation results verify that the proposed CIP-NOMA-ISAC scheme can effectively enhance the stability of instantaneous NOMA-ISAC beampattern over limited time slots, and provide higher SNR for CU.

Learning-task oriented semantic communication is pivotal in optimizing transmission efficiency by extracting and conveying essential semantics tailored to the specific tasks, such as image reconstruction and classification. Nevertheless, the challenge of eavesdropping poses a formidable threat to semantic privacy due to open nature of wireless communications. In this paper, intelligent reflective surface (IRS)-enhanced secure semantic communication (IRS-SSC) is proposed to guarantee the physical layer security from a task-oriented semantic perspective. Specifically, a multi-layer codebook is exploited to discretize continuous semantic features and describe semantics with different numbers of bits, thereby meeting the need for hierarchical semantic representation and further enhancing the transmission efficiency. Novel semantic security metrics, i.e., secure semantic rate (S-SR) and secure semantic spectrum efficiency (S-SSE), are defined to map the task-oriented security requirements at the application layer into the physical layer. To achieve artificial intelligence (AI)-native secure communication, we propose a noise disturbance enhanced hybrid deep reinforcement learning (NdeHDRL)-based resource allocation scheme. This scheme dynamically maximizes the S-SSE by jointly optimizing the bits for semantic representations, reflective coefficients of the IRS, and the subchannel assignment. Moreover, we propose a novel semantic context awared state space (SCA-SS) to fusion the high-dimensional semantic space and the observable system state space, which enables the agent to perceive semantic context and solves the dimensional catastrophe problem. Simulation results demonstrate the efficiency of our proposed schemes in both enhancing the security performance and the S-SSE compared to several benchmark schemes.

With the rapid increment of multiple users for data offloading and computation, it is challenging to guarantee the quality of service (QoS) in remote areas. To deal with the challenge, it is promising to combine aerial access networks (AANs) with multi-access edge computing (MEC) equipments to provide computation services with high QoS. However, as for uncertain data sizes of tasks, it is intractable to optimize the offloading decisions and the aerial resources. Hence, in this paper, we consider the AAN to provide MEC services for uncertain tasks. Specifically, we construct the uncertainty sets based on historical data to characterize the possible probability distribution of the uncertain tasks. Then, based on the constructed uncertainty sets, we formulate a distributionally robust optimization problem to minimize the system delay. Next, we relax the problem and reformulate it into a linear programming problem. Accordingly, we design a MEC-based distributionally robust latency optimization algorithm. Finally, simulation results reveal that the proposed algorithm achieves a superior balance between reducing system latency and minimizing energy consumption, as compared to other benchmark mechanisms in the existing literature.

Spectrum maps reflect the utilization and distribution of spectrum resources in the electromagnetic environment, serving as an effective approach to support spectrum management. However, the construction of spectrum maps in urban environments is challenging because of high-density connection and complex terrain. Moreover, the existing spectrum map construction methods are typically applied to a fixed frequency, which cannot cover the entire frequency band. To address the aforementioned challenges, a UNet-based data-and-semantic dual-driven method is proposed by introducing the semantic knowledge of binary city maps and binary sampling location maps to enhance the accuracy of spectrum map construction in complex urban environments with dense communications. Moreover, a joint frequency-space reasoning model is exploited to capture the correlation of spectrum data in terms of space and frequency, enabling the realization of complete spectrum map construction without sampling all frequencies of spectrum data. The simulation results demonstrate that the proposed method can infer the spectrum utilization status of missing frequencies and improve the completeness of the spectrum map construction. Furthermore, the accuracy of spectrum map construction achieved by the proposed data-and-semantic dual-driven method outperforms the benchmark schemes, especially in scenarios with low sampling density.

The radio map, which describes spatial signal strength and network coverage information, is crucial in modern wireless systems for network planning and resource management. Fine-grained radio maps rely on measurements collected by sparsely deployed spectrum sensors in the area of interest. However, due to physical limitations and security considerations, these measurements may exhibit non-uniform distribution and be entirely absent in certain inaccessible areas, making it challenging for accurate radio map reconstruction. Thus, in this work, considering the issues of non-uniform sampling and inaccessible areas, we propose a deep completion partial convolution network for radio map reconstruction. This approach captures the spatial characteristics by separating the missing measurements from sampled ones and does not require prior knowledge of emitters. We evaluate our method using a simulated dataset for campus environments and demonstrate its effectiveness over several baselines for reconstructing radio maps.

In this paper, we explore the joint design of a transmit waveform and receive filter to enhance the detection performance of multiple-input multiple-output (MIMO) radar. Target echoes are assumed to be embedded in signal-dependent interference and colored Gaussian noise. As design metrics, we exploit two information-theoretic criteria, including mutual information (MI) and relative entropy. The joint design problems of MIMO radar associated with different information- theoretic criteria are established as a unified optimization framework within a constant-envelope (CE) constraint. We propose an efficient method based on the Riemannian optimization framework, which transforms the constraint optimization problems into unconstrained problems by leveraging the geometry of the feasible region. Several numerical examples are included to demonstrate the effectiveness of the proposed method.

Automatic modulation classification (AMC) is a promising technology to realize intelligent wireless communications in the sixth generation (6G) wireless communication networks. Recently, many data-and-knowledge dual-driven AMC schemes have achieved high accuracy. However, most of these schemes focus on generating additional prior knowledge or features of blind signals, which consumes longer computation time and ignores the interpretability of the model learning process. To solve these problems, we propose a novel knowledge graph (KG) driven AMC (KGAMC) scheme by training the networks under the guidance of domain knowledge. A modulation knowledge graph (MKG) with the knowledge of modulation technical characteristics and application scenarios is constructed and a relation-graph convolution network (RGCN) is designed to extract knowledge of the MKG. This knowledge is utilized to facilitate the signal features separation of the data-oriented model by implementing a specialized feature aggregation method. Simulation results demonstrate that KGAMC achieves supe-rior classification performance compared to other benchmark schemes, especially in the low signal-to-noise ratio (SNR) range. Furthermore, the signal features of the high-order modulation are more discriminative, thus reducing the confusion between similar signals.

Unmanned aerial vehicles (UAVs) are widely used for object detection. However, the existing UAV-based object detection systems are subject to the serious challenge, namely, the finite computation, energy and communication resources, which limits the achievable detection performance. In order to overcome this challenge, a UAV cognitive semantic communication system is proposed by exploiting knowledge graph. Moreover, a multi-scale compression network is designed for semantic compression to reduce data transmission volume while guaranteeing the detection performance. Furthermore, an object detection scheme is proposed by using the knowledge graph to overcome channel noise interference and compression distortion. Simulation results conducted on the practical aerial image dataset demonstrate that compared to the benchmark systems, our proposed system has superior detection accuracy, communication robustness and computation efficiency even under high compression rates and low signal-to-noise ratio (SNR) conditions.

Semantic communication is a promising approach to address the challenge of limited spectrum resources in the sixth-generation (6G) communication networks. However, prior works on semantic communication focus primarily on semantic coding, and they do not investigate how to efficiently construct a semantic knowledge base. In this paper, a codebook-based unified hierarchical semantic knowledge base (UH-SKB) framework is studied for multi-task semantic communications. To maximize semantic representation spaces and effectively explore the semantic relevance among multiple tasks, the semantic knowledge base is constructed jointly in both the horizontal and vertical directions. A deep K-subspace cluster method is proposed to facilitate semantic relevance extraction and semantic subspace construction for high-dimensional semantic information. Simulation results demonstrate that the proposed UH-SKB can support multi-task semantic communications efficiently, achieving up to 13.4%, 14% and 6.3% performance improvement respectively for reconstruction, segmentation and classification tasks compared to standalone semantic knowledge bases at the novel dataset when SNR is 0 dB. Moreover, the proposed UH-SKB exhibits 95.3% knowledge search efficiency improvement on the reconstruction task compared to standalone semantic knowledge bases.

Resource allocation is paramount to improve spectral efficiency in spectrum-sharing networks. However, numerous existing resource allocation schemes, especially those based on deep reinforcement learning, overlook the impact of time-variant channel quality caused by high dynamics of wireless environment, resulting in limited performance. To tackle this issue, an intelligent resource allocation scheme, enhanced by channel prediction, is proposed to jointly optimize channel allocation and transmission power. A multiple-channel prediction network utilizing the gated recurrent unit is designed to learn the evolutionary characteristics of time-varying channels. Meanwhile, an intelligent framework is proposed to capitalize fully on channel quality variations for resource allocation. Simulation results demonstrate that our proposed scheme achieves superior performance compared with other benchmark schemes, highlighting that the sum transmission rate can be improved by exploiting channel characteristics.

Unmanned Aerial Vehicles (UAVs)-assisted networks play a pivotal role in both terrestrial base stations (BSs) and non-terrestrial networks (NTNs) due to their extensive coverage and collaborative decision-making capabilities. However, the presence of diverse node types, rapidly evolving requirements, and dynamic channel conditions poses substantial challenges for ground users (GUs) access, particularly in an unknown environment within BS-UAV-NTN integrated networks. To tackle these challenges, this paper introduces a novel approach-a deep Q-learning network (DQN)-based algorithm for UAVs deployment and an adaptive and load balancing (ALB) scheme for GUs access. This paper formulates the GUs access problem in BS-UAV-NTN networks as a maximization problem, transforming it into a Markov Decision Process (MDP) problem for UAVs deployment in unknown environment. The proposed solution includes a DQN-based UAVs deployment algorithm and an access scheme that prioritizes BSs and UAVs. Simulation results convincingly show that this access scheme outperforms traditional Q-learning and random schemes in terms of rewards and the number of accessed GUs.

A novel image decomposition-guided network (IDGN) for image interpolation is proposed in this paper by incorporating the fundamentals of subband image decomposition into the design of our deep-learning network. In our work, a filter bank consisting of a Gaussian filter and a differenceof-Gaussian filter is designed for decomposing the low-resolution input image into multiple subbands of the same resolution without downsampling. These subbands are inherited with different low-frequency and high-frequency information and are ready to be interpolated individually in our developed network. For training our IDGN, the decomposed low-resolution subbands need to be paired up with their corresponding ground-truth high-resolution subbands. Since our human visual system is sensitive to high-frequency signals, a perception-regulated (PR) loss function is proposed to guide our IDGN by putting more emphasis on the high-frequency subbands during the training process. Extensive experimental results have shown that our IDGN can achieve superior performance when compared with a number of state-of-the-art image interpolation methods.

Deep Neural Networks (DNNs) are now widely used in Low Earth Orbit (LEO) satellites, such as in remote sensing and environmental monitoring. DNN tasks are generally resource-intensive, while the resources of LEO satellites including computation and storage resources are usually limited, which implies directly running high-precision and complex DNNs on them is extremely challenging. A promising way is leveraging the layered structure of DNNs and executing DNN tasks collaboratively between satellites and ground, i.e., satellite-terrestrial collaborative inference. However, most existing works about satellite- terrestrial collaborative inference mainly focus on the optimization of DNN offloading strategy in terms of latency and energy minimization, without considering how to minimize the highly precious satellite communication resources in the collaboration. In this paper, we study how to jointly optimize the offloading decision and satellites' communication bandwidth, to achieve the minimization of weighted sum of latency, energy consumption, and communication bandwidth consumption. The aforementioned problem is a Mixed Integer Nonlinear Programming (MINLP) problem and hard to resolve. We design an alternating optimization algorithm combining branch-and-bound and gradient descent methods (AO-SA) to obtain an efficient solution. Extensive simulations validate the efficiency of the proposed algorithm: compared to existing satellite-terrestrial offloading algorithms, it improves the performance in terms of latency and energy consumption by up to 31 %, while saving the bandwidth resource of satellites by 28 % on average.

Unmanned aerial vehicles (UAVs) are widely applied in multiple fields, which emphasizes the challenge of obtaining UAV flight information to ensure the airspace safety. UAVs equipped with automatic dependent surveillance-broadcast (ADSB) devices are capable of sending flight information to nearby aircrafts and ground stations (GSs). However, the saturation of limited frequency bands of ADS-B leads to interferences among UAVs and impairs the monitoring performance of GS to civil planes. To address this issue, the integration of the 5th generation mobile communication technology (5G) with ADS-B is proposed for UAV operations in this paper. Specifically, a hierarchical structure is proposed, in which the high-altitude central UAV is equipped with ADS-B and the low-altitude central UAV utilizes 5G modules to transmit flight information. Meanwhile, based on the mobile edge computing technique, the flight information of sub-UAVs is offloaded to the central UAV for further processing, and then transmitted to GS. We present the deterministic model and stochastic geometry based model to build the air-to-ground channel and air-to-air channel, respectively. The effectiveness of the proposed monitoring system is verified via simulations and experiments. This research contributes to improving the airspace safety and advancing the air traffic flow management.

Recent advancements in unmanned aerial vehicle (UAV) technology have propelled the popularity of edge intelligence (EI) applications with deep learning in UAV swarm. Nevertheless, the high computational demands of deep neural networks (DNNs) conflict with the limited computing power and battery capacity of UAV. Furthermore, many UAV applications require real-time performance such as object detection and recognition. In this paper, we study how to achieve fast DNN inference in UAV swarm by the collaboration of multiple UAVs, and formulate the problem of minimizing the completion time of a series of arriving DNN inference tasks, under memory and energy constraints. To solve the aforementioned challenging problem with combinatorial explosion, we propose an efficient solution exploiting deep reinforcement learning (DRL) with action space simplification to find the allocation strategy of each DNN inference task within a resource-constrained UAV swarm. Simulation results validate the effectiveness of the proposed solution compared to five benchmark algorithms.

With the increasing use of autonomous unmanned aerial vehicles (UAVs), it is critical to ensure that they are continuously tracked and controlled, especially when UAVs op-erate beyond the communication range of ground stations (GSs). Conventional surveillance methods for UAVs, such as satellite communications, ground mobile networks and radars are subject to high costs and latency. The automatic dependent surveillance-broadcast (ADS-B) emerges as a promising method to monitor UAVs, due to the advantages of real-time capabilities, easy deployment and affordable cost. Therefore, we employ the ADS-B for UAV trajectory tracking in this work. However, the inherent noise in the transmitted data poses an obstacle for precisely tracking UAVs. Hence, we propose the algorithm of recurrent neural network-enhanced interacting multiple model-Kalman filter (RNN-enhanced IMM-KF) for UAV trajectory filtering. Specifically, the algorithm utilizes the RNN to capture the maneuvering behavior of UAVs and the noise level in the ADS-B data. Moreover, accurate UAV tracking is achieved by adaptively adjusting the process noise matrix and observation noise matrix of IMM-KF with the assistance of the RNN. The proposed algorithm can facilitate GSs to make timely decisions during trajectory deviations of UAVs and improve the airspace safety. Finally, via comprehensive simulations, the total root mean square error of the proposed algorithm decreases by 28.56%, compared to the traditional IMM-KF.

In hierarchical cognitive radio networks, the edge or cloud servers utilize the data collected by the edge devices for modulation classification, which, however, is faced with problems of the computation load, transmission overhead, and data privacy. In this article, an edge learning (EL)-based framework jointly mobilizing the edge device and the edge server for intelligent co-inference is proposed to realize the collaborative automatic modulation classification (C-AMC) between them. A spectrum semantic compression neural network is designed for the edge device to compress the collected raw data into a compact semantic embedding that is then sent to the edge server via the wireless channel. On the edge server side, a modulation classification neural network combining the bidirectional long-short term memory and attention structures is elaborated to determine the modulation type from the noisy semantic embedding. The C-AMC framework decently balances the computation resources of both the sides while avoiding the high transmission overhead and data privacy leakage. Both the offline and online training procedures of the C-AMC framework are elaborated. The compression strategy of the C-AMC framework is also developed to further facilitate the deployment, especially for the resource-constrained edge device. Simulation results show the superiority of the EL-based C-AMC framework in terms of the classification accuracy, computational complexity, and the data compression rate as well as reveal useful insights paving the practical implementation.

In the space–air–ground integrated emergency communication network, unmanned aerial vehicles (UAVs) have become ideal candidates for expanding traditional base stations through the air–ground Line of Sight (LoS) link, providing more comprehensive and efficient support for emergency communication. To ensure timely information transmission among all the ground users (GUs) involved in rescue, utilizing fair communication can reduce communication conflicts caused by resource competition and ensure that the GUs can obtain the necessary communication resources to improve rescue efficiency. Therefore, this article investigates the joint optimization of trajectory planning and communication design of multiple UAV base stations (UAV-BSs), as well as the access control of GUs in intelligent collaborative air–ground communication systems. The optimization problem is modeled as a hybrid cooperative competition model, where GUs compete for limited UAV-BS resources to maximize their own long-term throughput, while UAV-BSs collaborate to provide maximum fair throughput for GUs in need. This model belongs to heterogeneous agent collaboration, where the goals of GUs and UAV-BSs are inconsistent, and the UAV-BS has inconsistent goals at different stages with or without GU requests. Therefore, a trajectory planning and communication design algorithm for intelligent collaborative air–ground communication (TPCD-ICAGC) algorithm is designed. By introducing a multihead attention mechanism to quickly determine the target correlation with other agents in a complex state space, so as to improve the adaptability of agents to the model and make more effective decisions. The simulation results show that TPCD-ICAGC outperforms other benchmark algorithms in terms of the fair communication services of UAV-BSs and the accumulative throughput of GUs.

Federated learning (FL) as an emerging distributed machine learning (ML) paradigm enables participants to train their on-device data locally and share model parameters with others by the parameter server. Differing from the centralized ML, FL splits the high requirements of training data and computing power from the server to clients, which is well adapted to unmanned aerial vehicle (UAV) swarms with scattered nodes, heterogeneous data, and limited computing power. However, pre-trained models are unsatisfactory in unfamiliar scenes and most existing approaches fail to concentrate on the communication-sensitivity and real-time requirements in UAV-enabled FL scenarios. To address this problem, this paper proposes participant and sample selection for efficient online federated learning in UAV swarms (FedOL). Through the combination of online learning and FL, UAVs can supplement real-time samples and quickly improve the model accuracy in unfamiliar scenes. Meanwhile, to reduce the training latency with expected model accuracy, FedOL allows the server UAV to select participants with high training utility, while the client UAVs select more important samples. We implement FedOL and deploy it on UAV embedded devices. Experimental results show that compared with existing FL approaches, FedOL speeds up by about 2.61× and reaches the final accuracy about 1.02× higher.

Anti-unmanned aerial vehicle (UAV) systems are crucial for preventing unauthorized individuals from exploiting UAVs for illegal activities, including surveillance and attacks. Precise real-time positioning of small UAVs is the premise of the effective operation of anti-UAV systems. However, its performance is confined due to the small size of the target and its high susceptibility to disturbance caused by birds or other aircraft. To tackle this problem, a radio-frequency (RF)-visual directional fusion framework is proposed for precise UAV positioning. In the framework, radio signals are aligned with images by jointly calibrating the array antenna and camera. The spatial spectrum is extracted by an array antenna to concentrate on target areas within the image modal. Moreover, in order to improve the precision of joint calibration, a segmentation-based denoising method is proposed to remove the spectrum noise. Furthermore, a practical anti-UAV positioning platform is established, and two synchronized data sets, which include visual images and UAV RF signals, are collected on the platform. Experimental results demonstrate that our proposed framework improves positioning accuracy and robustness compared to the benchmark methods.

Existing multi-scale feature extraction methods extract image features using various convolution window sizes conducted on the spatial dimension of the feature maps. However, such an approach inevitably encounters redundant convolution operations. To address this concern, we propose to extract multiscale features on the channel dimension rather than on the spatial dimension. To demonstrate, a channel-wise multi-scale network (CMSN) is proposed for conducting single image super-resolution (SISR). In our CMSN, a sequence of channel-wise multi-scale blocks (CMSBs) is designed to extract multi-scale features at increasing levels by performing convolutions with different channel numbers (i.e., scales). To fuse the image features generated from different levels in our CMSN, a hybrid attention-aware feature fusion block (HAFFB) is proposed. Extensive experimental results have clearly shown the superiority of our CMSN to that of several state-of-the-art SISR methods on delivering superior high-resolution images, both objectively and subjectively. This reveals the potential of channel-wise, versus spatial-wise, on the effectiveness of multi-scale feature extraction.

Direct position determination (DPD) (a.k.a. direct localization) offers enhanced precision over traditional two-step approaches. This technique, however, involves considerable communication overhead for transmitting raw data. Low-bit direct localization methods have recently been introduced to address this issue. In this letter, we present a gridless, one-bit maximum likelihood (ML) approach for the direct localization of an orthogonal frequency division multiplexing (OFDM) signal source. A recent majorization-minimization (MM) algorithm introduced a surrogate function for the log-likelihood function, which lacks a closed-form optimal solution and requires exhaustive searches at each iteration. Our method improves upon this algorithm by developing a refined surrogate function that yields a closed-form optimal solution, thereby eliminating the need for exhaustive searches. Accordingly, the proposed MM approach can eliminate grid quantization errors (GQE) by eliminating the search process. Simulation results validate the proposed method's efficacy in mitigating GQE and its efficiency in scenarios with densely populated search grids.

In this paper, we propose an adaptive semantic resource allocation paradigm with semantic-bit quantization (SBQ) compatible with existing wireless communications, where the inaccurate environment perception introduced by the additional mapping relationship between semantic metrics and transmission metrics is solved. Specifically, SBQ is a hybrid uniform-non-uniform quantization method, which aims to facilitate the coding between semantics and bits. In order to investigate the performance of semantic communication networks, the quality of service for semantic communication (SC-QoS), including the semantic quantization efficiency (SQE) and transmission latency, is proposed for the first time. A problem of maximizing the overall effective SC-QoS is formulated by jointly optimizing the transmit beamforming of the base station, the bits for semantic representation, the subchannel assignment, and the bandwidth resource allocation. To address the non-convex formulated problem, an intelligent resource allocation scheme is proposed based on a hybrid deep reinforcement learning (DRL) algorithm, where the intelligent agent can perceive both semantic tasks and dynamic wireless environments. Simulation results demonstrate that our design can effectively combat semantic noise and achieve superior performance in wireless communications compared to several benchmark schemes. Furthermore, compared to mapping-guided paradigm based resource allocation schemes, our proposed adaptive scheme can achieve up to 13% performance improvement in terms of SC-QoS.

Wireless signal recognition (WSR) is crucial in modern and future wireless communication networks since it aims to identify properties of the received signal. Although many deep learning-based WSR models have been developed, they still rely on a large amount of labeled training data. Thus, they cannot tackle the few-sample problem in the practically and dynamically changing wireless communication environment. To overcome this challenge, a novel SSwsrNet framework is proposed by using the deep residual shrinkage network (DRSN) and semi-supervised learning. The DRSN can learn discriminative features from noisy signals. Moreover, a modular semi-supervised learning method that combines labeled and unlabeled data using MixMatch is exploited to further improve the classification performance under few-sample conditions. Extensive simulation results on automatic modulation classification (AMC) and wireless technology classification (WTC) demonstrate that our proposed WSR scheme can achieve better performance than the benchmark schemes in terms of classification accuracy. This novel method enables more robust and adaptive signal recognition for next-generation wireless networks.

Semantic communication (SemCom) is envisioned as a promising technique to break through the Shannon limit. However, semantic inference and semantic error correction have not been well studied. Moreover, error correction methods of existing SemCom frameworks are inexplicable and inflexible, which limits the achievable performance. In this paper, to tackle this issue, a knowledge graph (KG) is exploited to develop SemCom systems. Two cognitive semantic communication frameworks are proposed for the single-user and multiple-user communication scenarios. Moreover, a simple, general, and interpretable semantic alignment algorithm for semantic information detection is proposed. Furthermore, an effective semantic correction algorithm is proposed by mining the inference rule from the KG. Additionally, the pre-trained model is fine-tuned to recover semantic information. For the multi-user cognitive SemCom system, a message recovery algorithm is proposed to distinguish the messages of different users by matching the knowledge level and the context at the destination. Extensive simulation results conducted on a public dataset demonstrate that our proposed single-user and multi-user cognitive SemCom systems are superior to benchmark communication systems in terms of the data compression rate and communication reliability. Finally, we present realistic single-user and multi-user cognitive SemCom systems results by building a software-defined radio prototype system.

Fake news detection is of crucial importance and has received great attention. However, the existing fake news detection methods rarely consider the news release time, which limits the achievable detection performance, especially for detecting the instant fake news clusters that have sudden and aggregated characteristics. To tackle this issue, a temporal enhanced multimodal graph neural networks (TEMGNNs) method is proposed. The multimodal graph with semantic complementary enhancement is developed by feature aggregation of textual information, image information, and external knowledge. Moreover, the associations among different modalities are obtained by using the graph attention networks and the weights of each modality are adaptively learned. Furthermore, the aggregation of news with adjacent time and the same topic to form a temporal news cluster and learning temporal features for fake new detection by using our proposed graph neural networks. Extensive experiments results obtained on two public datasets demonstrate that our proposed method has the best performance compared with the benchmark methods. It is also shown that the exploitation of the temporal information and multimodal information benefits for fake news detection.

Set-valued data are widely used to represent information in the real word, such as individual daily behaviors, items in shopping carts and web browsing history. By collecting set-valued data and identifying heavy hitters, service providers (i.e., the collector) can learn usage preferences of costumers (i.e., users), and improve the quality of their services by the learned information. However, the collection of raw data would bring privacy risks to users. Recently, local differential privacy (LDP) has emerged as a rigorous privacy framework for user private data collection. At the same time, many LDP schemes have been designed to achieve heavy hitters, but most of them are limited by the large data domain due to the huge computation cost. In this paper, we propose an LDP framework: PemSet, to efficiently identify heavy hitters from set-valued data with a large domain. In PemSet, users mainly focus on the prefix of each item (i.e., the first few bits of the binary expression of each item), and only perturb and report prefixes to reduce computation cost. Sometimes the prefixes of different items are the same, so the reported set-valued data could be a multiset, i.e., a set including multiple same items. As such, we design four LDP protocols MOLH, MOLH-S, MPCKV, MWheel to estimate frequencies of items in the multiset setting, and compare their performance under PemSet framework by experiments. Experimental results demonstrate that MOLH can perform the best in a high privacy region, i.e.,$\epsilon < 1$, while MWheel can obtain the highest utility when privacy budget is large, i.e.,$\epsilon \geqslant 1$.

The global positioning system (GPS), which provides ubiquitous location-awareness with a constellation of satellites, has become an instrumental function of multiple mass-market applications. Satellite signals, however, may not be capable of penetrating obstacles in harsh environments (e.g., urban canyons, tree canopies, and flyovers). Hence, GPS may not provide adequate localization accuracy for applications like autonomous vehicles. Resorting to data fusion of heterogeneous signals emanating from multiple anchors, we advocate a self-localization method that provides accurate estimates of the vehicle position. To be more specific, several heterogenous emitters whose positions are known are used as anchors to determine the vehicle’s position based on the weighted direct position determination (DPD) method that eliminates nonhomogeneity among different emitters. However, the weighted DPD method requires an exhaustive search of the parameter search space and is thus time-consuming. To reduce the computational burden, we propose a weighted cascade compensation estimator (WCCE) that is tailored for real-time tracking and self-localization. The proposed WCCE outperforms traditional DPD methods in terms of computational complexity while achieving nearly comparable localization accuracy. The effectiveness of the proposed method is corroborated by extensive simulated examples.

Recommendation systems are of crucial importance due to their wide applications. Knowledge graph (KG) enabled recommendation schemes have attracted great attention due to their superior performance and interpretability. However, the rich social information is not exploited for those systems, which limits the recommendation performance . In this paper, a novel explainable recommendation scheme is proposed by exploiting our designed social enhanced knowledge graph attention network (SKGAN). The hidden relations among users and items are learned and used for recommendation with the collaborative KG (CKG) and the user social graph (USG). Moreover, the high-order semantic information in both CKG and USG are obtained by using the graph convolution networks (GCNs) and the node level attention algorithm. Furthermore, a graph level user-specific attention algorithm is proposed to capture the user personalized preference between CKG and USG. Extensive experiment results demonstrate that normalized discounted cumulative gain (NDCG), precision, recall and hits ratio (HR) achieved with our proposed recommendation system are the best among those obtained with the state-of-the-art benchmark recommendation systems.

Federated learning (FL) that improves data privacy reduces the computational overhead for Internet of Vehicles (IoV) systems but has difficulty in defending against selfish attacks due to the restricted quality of service requirements and the high mobility of vehicles. In this paper, we design a risk-aware hierarchical reinforcement learning-based FL framework for IoV to resist selfish attacks. By designing a two-level hierarchical policy selection module that consists of two deep neural networks, this framework divides the training policy into two sub-policies, i.e., the selection of FL participants and the corresponding local training data size, which are chosen based on the previous training performance and vehicle participation performance. This framework designs a risk-aware safety guide to avoid dangerous states such as local task failure resulting from risky training policies. Specifically, the guide uses a warning signal to evaluate the short-term risk of each state-action pair, applies an R-network to estimate the long-term risks for modifying the chosen training policy, and designs a punishment function for the modified training policy to revise the immediate reward to further enhance the safe exploration. We analyze the convergence performance and computational complexity of our scheme. Experimental results on MNIST, CIFAR-10, and Stanford Cars datasets verify the effectiveness of our scheme, including the global model accuracy, training latency, detection success rate, and convergence speed compared with the benchmarks FedAvg, MFL, DQNPS, and SHRL.

Unmanned aerial vehicles (UAVs) play an essential role in emergency cases and adverse environments for applications like disaster detection and mine exploration. To process the massive volume of sensing data generated by various sensory payloads in these applications, existing works either compress deep learning (DL) models to conduct onboard computing, or offload raw data back to the resourceful ground station with the help of relay UAVs due to base station damage. However, the former sacrifices the inference accuracy of DL models (up to 10% accuracy loss), while the latter achieves high accuracy at the cost of significant latency, due to limited wireless communication resources in the multi-hop transmission. To address the problem, exploiting the resources of the UAV swarm including both task UAVs and relay UAVs, we build up anall-skyautonomous computing (ASAP) system to autonomously conduct collaborative computing in the swarm, to achieve both high accuracy and low latency of sensing data processing. In detail, we first propose a novel UAV swarm-native collaborative computing architecture, considering the general hierarchy and clustering structure of UAV swarms, as well as the characteristic of DL model execution. We then design an elastic efficient task scheduler to allocate computing tasks for UAVs, and update the scheduling scheme online when some UAVs are unavailable, with the aid of a lightweight and accurate DL inference performance predictor. Finally, we design an adaptive inter-UAV data compressor, to adapt to the limited and dynamic communication resources between UAVs. Experiment results on 24 airborne computers and five real-world UAVs show that, the proposed system can perform collaborative computing in a timely manner and effectively deal with situations when some UAVs become unavailable.

Automatic modulation classification (AMC) is of crucial importance in the sixth generation wireless communication networks. Deep learning (DL)-based AMC schemes have attracted extensive attention due to their superior accuracy compared with the conventional methods. However, a pure data-driven DL method relies on a large amount of labeled training samples and the classification accuracy is poor, especially in the low signal-to-noise ratio (SNR). In order to tackle this problem, two data-and-knowledge dual-driven AMC schemes are designed. A novel data and semantic knowledge driven AMC scheme is proposed by exploiting the semantic attribute information of different modulations. Moreover, a prior knowledge driven multi-task learning visual model is established to improve the classification performance in low SNR. Furthermore, another novel data and multi-domain knowledge joint driven AMC scheme is proposed by using the semantic attribute knowledge and the prior knowledge based multi-task learning visual model. Extensive simulation results demonstrate that our proposed data-and-knowledge dual-driven AMC schemes achieve the best performance compared with the benchmark schemes in terms of classification accuracy. Moreover, it is shown that the expert knowledge spawns for AMC accuracy improvement and a decrease in the required number of training samples.

Unmanned aerial vehicle (UAV) communication is of crucial importance in realizing heterogeneous practical wireless application scenarios. However, it is susceptible to the severe spectrum scarcity and interference issues since it operates in the unlicensed frequency band. To tackle those issues, a dynamic spectrum sharing UAV network adopting an anti-jamming technique is considered. Two intelligent spectrum allocation and trajectory optimization schemes are designed, capitalizing on the proposed external interaction and internal inference based frameworks. For the first scheme, a novel external interaction based hybrid online-offline multi-agent actor-critic and deep deterministic policy gradient (MA2C-DDPG) framework is proposed taking into account the hybrid characteristics of discrete spectrum allocation and continuous UAV trajectory. As for the second scheme, another novel framework, the deep active inference (DAI) based on internal inference is proposed, which minimizes the internal variational free energy. Moreover, a belief learning based method is exploited to enhance the agents’ perception and improve the action selection in the dynamic spectrum sharing environment. Extensive simulation results demonstrate the high efficiency of our proposed schemes. It is shown that our proposed schemes significantly improve the secondary network sum transmission rate compared to various benchmark schemes. Moreover, the proposed MA2C-DDPG and DAI frameworks demonstrate the advantages in improving the training stability and convergence speed.

Existing path planning schemes designed for wireless sensor networks generally account for abstract payload sensors, rendering them inapplicable to concrete sensor-array-based localization systems due to differences in measurement models. In this paper, we establish a general framework for path planning of a practical sensor array and factor in an oft-neglected degree of freedom regarding optimality, i.e., the array’s orientation/attitude. The optimization problem is formulated based on the A-optimality criterion under constraints arising from the maximum distance between consecutive waypoints, maximal heading change, and forbidden regions. To facilitate semidefinite relaxation (SDR), we recast the optimization function into a fractional nonhomogeneous quadratic structure and transform the constraints into a bilinear form. By applying SDR and replacing the bilinear terms with a matrix variable, the problem is relaxed into a single-ratio fractional program. By leveraging the Charnes-Cooper variable transformation, we transform the single-ratio fractional program into a mixed semidefinite/second-order cone program (SD/SOCP) that can be solved in polynomial time. Finally, we apply the results to angle-of-arrival (AOA) and direct localization. Simulation results demonstrate that the proposed path planning scheme attains near-optimal performance.

Secure communications are of paramount importance in spectrum sharing networks due to the allocation and sharing characteristics of spectrum resources. To further explore the potential of intelligent reflective surfaces (IRSs) in enhancing spectrum sharing and secure transmission performance, a multiple intelligent reflection surface (multi-IRS)-assisted sensing-enhanced wideband spectrum sharing network is investigated by considering physical layer security techniques. An intelligent resource allocation scheme based on double deep Q networks (D3QN) algorithm and soft Actor-Critic (SAC) algorithm is proposed to maximize the secure transmission rate of the secondary network by jointly optimizing IRS pairings, subchannel assignment, transmit beamforming of the secondary base station, reflection coefficients of IRSs and the sensing time. To tackle the sparse reward problem caused by a significant amount of reflection elements of multiple IRSs, the method of hierarchical reinforcement learning is exploited. An alternative optimization (AO)-based conventional mathematical scheme is introduced to verify the computational complexity advantage of our proposed intelligent scheme. Simulation results demonstrate the efficiency of our proposed intelligent scheme as well as the superiority of multi-IRS design in enhancing secrecy rate and spectrum utilization. It is shown that inappropriate deployment of IRSs can reduce the security performance with the presence of multiple eavesdroppers (Eves), and the arrangement of IRSs deserves further consideration.

Spectrum sensing and communication security are of crucial importance in cognitive radio networks (CRNs). In this paper, we utilize intelligent reflecting surfaces (IRS) to simultaneously enhance spectrum sensing accuracy and the secrecy performance of secondary users (SUs) through physical layer security (PLS) techniques. Additionally, we employ IRS as a novel approach to achieve the target probability of detection. We formulate a joint sensing and transmission security optimization problem to maximize the sum secrecy rate of SUs under both perfect and imperfect channel state information (CSI). To transform the probability of detection into a tractable expression, we adopt a safe approximation for theQ-function. We use a computationally-efficient block coordinate descent (BCD)-based algorithm to optimize the beamforming design and IRS phase shifts alternately. Specifically, we employ theS-procedure to handle the semi-infinite constraints under the imperfect CSI case. Simulation results demonstrate that by leveraging IRS for spectrum sensing, we can significantly reduce the sensing time while achieving the required probability of detection and the probability of false alarm. Furthermore, our proposed scheme improves both sensing accuracy and secrecy rate in both cases compared to the benchmark schemes.

The radio environment map (REM) visually displays the spectrum information over the geographical map and plays a significant role in monitoring, management, and security of spectrum resources. In this paper, we present an efficient 3D REM construction scheme based on the sparse Bayesian learning (SBL), which aims to recover the accurate REM with limited and optimized sampling data. In order to reduce the number of sampling sensors, an efficient sparse sampling method for unknown scenarios is proposed. For the given construction accuracy and the priority of each location, the quantity and sampling locations can be jointly optimized. With the sparse sampled data, by mining the sparsity of the spectrum situation and channel propagation characteristics, a SBL-based spectrum data hierarchical recovery algorithm is developed to estimate the missing data of unsampled locations. Finally, the simulated three-dimensional (3D) REM data in the campus scenario are used to verify the proposed methods as well as to compare with the state-of-the-art. We also analyze the recovery performance and the impact of different parameters on the constructed REMs. Numerical results demonstrate that the proposed scheme can ensure the construction accuracy and improve the computational efficiency under the low sampling rate.

Spectrum sharing is promising as a solution to address the spectrum crunch by enabling the coexistence of different networks in the same frequency band. However, interference from concurrent transmissions remains an obstacle to further enhance spectral efficiency. Therefore, to overcome the bottleneck caused by multi-user interference, both rate-splitting multiple access (RSMA)-enabled underlay and overlay spectrum-sharing strategies are proposed in this paper. To facilitate a robust resource allocation design, the common and the private beamforming vectors as well as the common rate allocation are jointly optimized under the norm-bounded channel state information (CSI) error model to maximize the worst-case weighted sum rate (WSR) of the secondary networks. To address the formulated challenging non-convex quadratically-constrained resource allocation optimization problems, a computationally efficient successive convex approximation (SCA)-based algorithm capitalizing on semidefinite relaxation (SDR) is proposed. Simulation results demonstrate that the proposed algorithms outperform non-orthogonal multiple access (NOMA)-based benchmark schemes in worst-case WSR and robustness. Moreover, the results indicate that the proposed novel RSMA-enabled overlay spectrum-sharing strategy can offer a higher flexibility in resource allocation compared to their underlay counterparts. Furthermore, the tradeoff between interference management and spectral performance enhancement for the proposed RSMA-enabled overlay spectrum-sharing strategy is unveiled.

The unmanned aerial vehicle (UAV) network is popular these years due to its various applications. In the UAV network, routing is significantly affected by the distributed network topology, leading to the issue that UAVs are vulnerable to deliberate damage. Hence, this paper focuses on the routing plan and recovery for UAV networks with attacks. In detail, a deliberate attack model based on the importance of nodes is designed to represent enemy attacks. Then, a node importance ranking mechanism is presented, considering the degree of nodes and link importance. However, it is intractable to handle the routing problem by traditional methods for UAV networks, since link connections change with the UAV availability. Hence, an intelligent algorithm based on reinforcement learning is proposed to recover the routing path when UAVs are attacked. Simulations are conducted and numerical results verify the proposed mechanism performs better than other referred methods.

Resource allocation is of crucial importance in wireless communications. However, it is extremely challenging to design efficient resource allocation schemes for future wireless communication networks since the formulated resource allocation problems are generally non-convex and consist of various coupled variables. Moreover, the dynamic changes of practical wireless communication environment and user service requirements thirst for efficient real-time resource allocation. To tackle these issues, a novel partially observable deep multi-agent active inference (PODMAI) framework is proposed for realizing intelligent resource allocation. A belief based learning method is exploited for updating the policy by minimizing the variational free energy. A decentralized training with a decentralized execution multi-agent strategy is designed to overcome the limitations of the partially observable state information. Exploited the proposed framework, an intelligent spectrum allocation and trajectory optimization scheme is developed for a spectrum sharing unmanned aerial vehicle (UAV) network with dynamic transmission rate requirements as an example. Simulation results demonstrate that our proposed framework can significantly improve the sum transmission rate of the secondary network compared to various benchmark schemes. Moreover, the convergence speed of the proposed PODMAI is significantly improved compared with the conventional reinforcement learning framework. Overall, our proposed framework can enrich the intelligent resource allocation frameworks and pave the way for realizing real-time resource allocation.

Spectrum sensing and the communication security are of crucial importance in cognitive radio networks (CRNs). In this paper, intelligent reflecting surface (IRS) is exploited in CRNs to simultaneously enhance the spectrum sensing accuracy and the secure performance achieved by using physical layer security (PLS) techniques. The sum secrecy rate of the secondary users (SUs) is maximized by jointly optimizing the sensing time, the beamforming design and the IRS phase shifts. A safe approximation is adopted to transform the probability of detection into a tractable expression. A computationally efficient block coordinate descent (BCD)-based algorithm with the techniques of successive convex approximation (SCA) and semidefinite relaxation (SDR) is exploited to optimize the beamforming and the phase shifts alternately. Simulation results demonstrate that our proposed algorithm can significantly improve both the sensing performance and the secrecy rate compared with the benchmark schemes.

With the continuous increment of maritime applications, the development of marine networks for data offloading becomes necessary. However, the limited maritime network resources are very difficult to satisfy real-time demands. Besides, how to effectively handle multiple compute-intensive tasks becomes another intractable issue. Hence, in this paper, we focus on the decision of maritime task offloading by the cooperation of unmanned aerial vehicles (UAVs) and vessels. Specifically, we first propose a cooperative offloading framework, including the demands from marine Internet of Things (MIoTs) devices and resource providers from UAVs and vessels. Due to the limited energy and computation ability of UAVs, it is necessary to help better apply the vessels to computation offloading. Then, we formulate the studied problem into a Markov decision process, aiming to minimize the total execution time and energy cost. Then, we leverage Lyapunov optimization to convert the long-term constraints of the total execution time and energy cost into their short-term constraints, further yielding a set of per-time-slot optimization problems. Furthermore, we propose a Q-learning based approach to solve the short-term problem efficiently. Finally, simulation results are conducted to verify the correctness and effectiveness of the proposed algorithm.

Leveraging the unique characteristics of blockchain, secure and efficient dynamic spectrum sharing (DSS) can be achieved, which has been regarded as a promising solution to meet the spectrum requirement in future wireless communication systems. However, proper incentive mechanism with guaranteed fairness is essential for blockchain-enabled DSS. In this paper, we investigate fairness-oriented spectrum auction, where multiple access points can share resources on the blockchain platform with smart contract. Specifically, we propose a fairness factor to adjust users’ satisfaction considering both the historical spectrum allocation results and current spectrum auction results. Then, an improved virtual auction mechanism is proposed to balance the long-term satisfaction of participants. Simulation results show that the multi-round fairness-based auction algorithm (FBAA) can enhance the fairness of spectrum allocation and increase the number of radio users served.

Abstract Spectrum resources are becoming harder to come by for wireless communications. The spectrum environment map (SEM), which depicts the electromagnetic environment's current state and future trend, is a valuable technique for managing and allocating spectrum resources. Most SEM construction approaches only take static SEMs into account and cannot forecast time‐domain changes and trends of SEMs in dynamic scenes. In this paper, a brand‐new temporal SEM prediction method for the high dynamic spectrum environment is proposed. This method is based on knowledge of radiation source and the optical flow driven by propagation channel models. First, a novel radiation source localization strategy is designed to obtain the radiation source movement information. Then, the optical flow field of the available SEMs is combined with the information regarding radiation source movement. In order to forecast future SEMs, a propagation model driven reconstruction technique is developed. Simulation findings demonstrate how well the suggested strategy is tailored to capture the spatiotemporal correlation of SEMs. This technique performs better than the state‐of‐the‐art in terms of single‐ and multiple‐step SEM predictions.

Complex status updates have attracted widespread attention in real-time monitoring services (e.g., real-time fire gas monitoring and wildfire spread prediction). In complex status updates, the status information needs to be obtained by processing the perceived original data. However, as lightweight terminals, temporarily deployed Internet of Things (IoT) devices have no computing modules. Unmanned aerial vehicle (UAV) can act as a edge server to help IoT devices complete computing tasks by mobile-edge computing (MEC). To this end, this article considers a complex status update in UAV-assisted IoT, where an UAV moves in hovering-flight-hovering mode to ensure that it can serve IoT devices in different areas. When the UAV hovers, it obtains the status information based on the original data transmitted by the IoT device and sends it to the control center. During the complex status update, the short packet communication and time-varying channel are considered. To realize the tradeoff optimization of the average Age of Information (AoI) and average power consumption of both IoT device and UAV within a long time, we formulate a location and dynamic status update strategy optimization problem for UAV hovering-flight-hovering mode. In order to solve the problem with Markov properties, we derive the state probability equations and further establish the linear programming problem with fixed UAV location. Then, we propose a probability-based algorithm to obtain UAV location and dynamic status update strategy. To adapt to more urgent scenarios, we propose an AoI threshold-based strategy to reduce the complexity of the problem. State probability equations are derived under the strategy and a linear programming problem with a fixed AoI threshold is established. Next, we propose a low-complexity algorithm to obtain the optimal AoI threshold. Simulation results show that the proposed algorithms can optimize the three performance metrics in a balanced way and we need to select the appropriate transmit power of the IoT device and the computing capacity of the UAV to achieve better performance.

With the explosive increment of computation requirements, the multiaccess edge computing (MEC) paradigm appears as an effective mechanism. Besides, as for the Internet of Things (IoT) in disasters or remote areas requiring MEC services, unmanned aerial vehicles (UAVs) and high altitude platforms (HAPs) are available to provide aerial computing services for these IoT devices. In this article, we develop the hierarchical aerial computing framework composed of HAPs and UAVs, to provide MEC services for various IoT applications. In particular, the problem is formulated to maximize the total IoT data computed by the aerial MEC platforms, restricted by the delay requirement of IoT and multiple resource constraints of UAVs and HAPs, which is an integer programming problem and intractable to solve. Due to the prohibitive complexity of the exhaustive search, we handle the problem by presenting the matching game theory-based algorithm to deal with the offloading decisions from IoT devices to UAVs, as well as a heuristic algorithm for the offloading decisions between UAVs and HAPs. The external effect affected by the interplay of different IoT devices in the matching is tackled by the externality elimination mechanism. Besides, an adjustment algorithm is also proposed to make the best of aerial resources. The complexity of proposed algorithms is analyzed and extensive simulation results verify the efficiency of the proposed algorithms, and the system performances are also analyzed by the numerical results.

In this article, source localization exploiting time difference of arrival (TDOA) information is discussed, and a parallel factor (PARAFAC) analysis-based method for multi-TDOA estimation and direct position determination (DPD) is proposed. First, signals from the radiation source are received by multiple antennas through synchronous sensing. Then, the data from multiple antennas is fused by extracting the time-delay matrix to construct a PARAFAC model. Thereafter, the time-delay matrix is obtained by fast iterative decomposition using the trilinear alternating least square (TALS) algorithm. In the case of no multipath or weak multipath, where the typical scenario is the antennas being deployed on the airborne platform, the multi-TDOA estimation can be obtained simultaneously according to the time-delay matrix to improve the processing speed. In the case of multipath, such as the antennas being located on the ground, the DPD cost function directly related to the source position can be established based on the time-delay matrix, and the source position estimation can be achieved through grid search. Compared with the other DPD methods, the proposed DPD method has better positioning performance and lower complexity. The effectiveness and superiority of the proposed methods are verified by both simulations and actual scenario tests.

Unmanned aerial vehicles (UAVs) have been widely used to perform search and tracking tasks in military and civil fields. To perform these tasks autonomously, a swarm of multiple UAVs need to be endowed with intelligence through machine learning (ML). However, the traditional centralized ML cannot be directly applied in UAV networks, since it is challenging to transmit raw data with limited bandwidth and energy budget. As a distributed manner, federated learning (FL) is more suitable for UAV networks than traditional ML schemes in order to boost edge intelligence for UAVs. Considering the limited energy supply of UAVs, we study how to minimize UAVs’ overall training energy consumption by jointly optimizing the local convergence threshold, local iterations, computation resource allocation, and bandwidth allocation, subject to the FL global accuracy guarantee and maximum training latency constraint. The formulated nonconvex mixed-integer programming problem is solved by a joint training and resource allocation optimization algorithm. In addition, we also study how to solve the problem considering fairness among different UAVs by changing the objective to minimizing the maximum energy consumption of UAVs, and extend the aforementioned approach to this problem. Our simulation results show that while satisfying both the training accuracy and latency constraints, the proposed algorithm can reduce more UAVs’ overall training energy consumption and the maximum energy consumption in the UAV swarm than four baseline schemes.

Wireless network security can be improved by radio frequency fingerprinting due to its stability and uniqueness. Although many radio frequency fingerprint identification (RFFI) methods based on deep learning have been proposed, they have low identification accuracy, especially at low signal-to-noise ratio. In order to overcome this drawback, a data-and-knowledge dual-driven RFFI scheme is proposed by utilizing a knowledge-driven multiscale attention convolutional network (AttMsCN). The protocol knowledge is exploited to provide more advanced semantics. Moreover, the AttMsCN is utilized to capture higher level features. Simulation results demonstrate that our designed scheme has the best performance than the representative schemes in the matter of convergence speed and identification accuracy.

Spectrum maps are of crucial importance for realizing efficient spectrum management in the sixth-generation (6G) wireless communication networks. However, existing spectrum map construction schemes mainly depend on spatial interpolation or just simply exploit the frequency correlation and cannot accurately construct the spectrum map when measurement data at the target frequency are not available. To overcome this challenge, we propose two accurate spectrum map construction schemes using different intelligent frequency-spatial reasoning methods. The frequency correlation among different spectrum maps at different frequencies is fully exploited to construct highly accurate spectrum maps of the frequencies without spectrum data by combining the joint frequency-spatial spectrum representation method with deep learning data-driven techniques. Specifically, a joint three-dimensional spectrum representation model is established and both a novel autoencoder network and a novel conditional generative adversarial network suitable for processing the three-dimensional spectrum data are proposed to realize the intelligent frequency-spatial reasoning. Simulation results demonstrate that our proposed schemes are superior to the benchmark schemes in terms of the spectrum map construction accuracy. Moreover, simulation results demonstrate that our proposed neural networks have a fast convergence speed, which achieves a better tradeoff between the computation efficiency and the construction accuracy.

A heterogeneous unmanned aerial vehicle (UAV) network where UAVs carrying different resources form coalition and cooperatively carry out tasks is of crucial importance for fulfilling diverse tasks. However, the existing coalition formation (CF) game model only optimizes the composition of UAVs in a single coalition, which results in disjoined coalitions. In order to tackle this issue, a sequential overlapping coalition formation (OCF) game is proposed by considering the overlapping and complementary relations of resource properties and the task execution order. Moreover, different from the traditional Pareto and Selfish orders, a bilateral mutual benefit transfer (BMBT) order is proposed to optimize the cooperative task resource allocation through partial cooperation among overlapping coalition members. Furthermore, using the preference relation between UAVs carrying resources and tasks requiring the same type of resource, a preference gravity-guided Tabu Search (PGG-TS) algorithm is developed to obtain a stable coalitional structure. Numerical results verify that the utility of the proposed OCF game scheme based on the PGG-TS algorithm increases by 18% against that of the non-overlapping CF game scheme, and the utility of the proposed BMBT order increases by 25%, compared with other orders.

Spectrum data compression with a high-rate compression and accurate reconstruction is of crucial importance for reducing the ultra-large data transmission from the edge sensors to the cloud for establishing high-quality spectrum maps. However, the current methods ignore the imbalanced edge-cloud computation resources and cannot tackle the outlier signals, resulting in significant challenges for achieving effective compression. Therefore, we develop an efficient heterogeneous edge-cloud learning framework. In the framework, paralleled methods compress normal data and outlier data distinctively based on their different structure information. Meanwhile, those methods are asymmetric for achieving low-cost compression at the edge and accurate reconstruction on the cloud. Based on the framework, we propose an outlier-processable attention-based asymmetric compression algorithm. A novel attention-based asymmetric convolutional neural network performs the normal data compression while a non-linear outlier compression algorithm realizes the outlier data compression. Compared with the state-of-the-art schemes in real-world settings, our proposed framework’s convergence speed increases by 120% . Meanwhile, our framework’s reconstruction accuracy increases by 68.42% under the interfered environments while maintaining superior compression speed and comprehensive performance. We also confirm our framework’s generalization ability to transfer among different tasks by deploying it under various spectrum environments.

Cognitive radio (CR) is one of the most disruptive techniques for enabling the next generation wireless communication networks due to its potential in improving the spectral efficiency. In this paper, intelligent reflecting surface (IRS) is exploited to enhance both the accuracy of spectrum sensing and the secondary transmission in a CR network (CRN) employing the opportunistic spectrum access. A novel detection threshold based on the probability of false alarm is derived for improving the spectrum sensing performance. The average achievable rate of the secondary network is maximized under both the two-stage and one-stage IRS phase shifts case. To tackle the challenging non-convex optimization problem under the two-stage case, a computationally efficient block coordinate descent (BCD)-based algorithm is proposed coputilizing the techniques of successive convex approximation (SCA) and semidefinite relaxation (SDR). Moreover, a BCD method and a tractable approximation of the probability of detection are exploited to tackle the problem under one-stage IRS phase shifts case. Simulation results demonstrate that our proposed designs are superior to the benchmark schemes in terms of the achievable rate and the sensing performance, and IRS can greatly improve the spectral efficiency of the CRN.

Orthogonal frequency division multiplexing (OFDM) systems have been widely applied in practice since OFDM has diverse outstanding advantages. However, their performance improvement is confronted with bottlenecks. In this paper, in order to tackle this issue, intelligent resource allocation driven by reinforcement learning is studied in intelligent reflecting surface (IRS) enhanced OFDM systems. The system sum rate is maximized by jointly optimizing the subcarrier allocation, the transmit beamforming of the base station and the phase shift of the IRS. An intelligent resource allocation scheme based on combining deep Q networks (DQN) and deep deterministic policy-gradient (DDPG) is proposed to tackle the formulated challenging non-convex problems. In order to further improve the spectrum efficiency, spectrum sharing is considered in the IRS-enhanced OFDM system. The secondary users sum rate maximization framework is formulated by jointly optimizing the channel allocation, the transmit beamforming of the secondary base station (SBS) and the phase shift of the IRS. Dueling double deep Q networks (D3QN) and twin delayed deep deterministic policy gradient (TD3) are exploited to tackle the hybrid action space issue under interference. Simulation results demonstrate that our proposed schemes can significantly improve the transmission rate compared to the benchmark schemes.

Cognitive radio (CR) is one of the most disruptive techniques for enabling the next generation wireless communication networks due to its potential in improving the spectral efficiency. In this paper, an intelligent reflecting surface (IRS) is exploited to assist both spectrum sensing and secondary transmission in the CR network (CRN) employing opportunistic spectrum access. A novel IRS-enhanced spectrum sensing scheme and a redesigned detection threshold are proposed to improve the sensing performance. We formulate the throughput maximization problem by jointly optimizing the sensing time, the beamforming, and the IRS phase shifts. A computationally efficient block coordinate descent (BCD)-based algorithm is proposed to tackle the non-convex problem. Simulation results show that our proposed scheme is superior to other benchmark schemes in terms of both the throughput and the sensing performance.

With their high mobility, unmanned aerial vehicles (UAVs) become appealing data collectors in hard-to-reach wide-area distributed sensor networks. Different from existing works focusing on the perspective of UAVs for service order optimization and UAV utility maximization, we consider the utilities of both sensors and UAVs, and innovatively model the competition among sensors (buyers) for the service of UAVs (sellers) as an auction game. A “unity makes strength” strategy is exploited. That is, to strengthen the bidding competitiveness, a group-buying coalition auction method that encourages sensors to form coalitions to bid for UAV service is proposed. Besides, we propose a parallel variable neighborhood ascent search algorithm, we can quickly determine the approximately optimal group-buying coalition structure. Numerical results show that the proposed method outperforms the joint trajectory design-task scheduling (TDTS) UAV-to-community method and the single coalition formation game (CFG) method.

Spectrum map is of crucial importance for realizing efficient spectrum management in the sixth-generation (6G) wireless communication networks. However, the existing spectrum map construction schemes mainly depend on spatial interpolation and cannot construct the spectrum map when the measurement data of the target frequency are not obtained. In order to overcome this challenge, an accurate spectrum map construction scheme is proposed by using an intelligent frequency-spatial reasoning approach. The frequency correlation among different spectrum maps at different frequencies is fully exploited to construct the highly accurate spectrum maps of the frequencies without spectrum data. A novel autoencoder adapting to the three-dimensional (3D) spectrum data is proposed. Simulation results demonstrate that our proposed scheme is superior to the benchmark schemes in terms of the construction accuracy. Moreover, it is shown that our proposed autoencoder network has a fast convergence speed.

Recently, unmanned aerial vehicles (UAVs) are gathering increasing attentions from both the academia and industry. The ever-growing number of UAV brings challenges for air traffic control (ATC), and thus trajectory prediction plays a vital role in ATC, especially for avoiding collisions among UAVs. However, the dynamic flight of UAV aggravates the complexity of trajectory prediction. Different with civil aviation aircrafts, the most intractable difficulty for UAV trajectory prediction depends on acquiring effective location information. Fortunately, the automatic dependent surveillance-broadcast (ADS-B) is an effective technique to help obtain positioning information. It is widely used in the civil aviation aircraft, due to its high data update frequency and low cost of corresponding ground stations construction. Hence, in this work, we consider leveraging ADS-B to help UAV trajectory prediction. However, with the ADS-B information for a UAV, it still lacks efficient mechanism to predict the UAV trajectory. It is noted that the recurrent neural network (RNN) is available for the UAV trajectory prediction, in which the long short-term memory (LSTM) is specialized in dealing with the time-series data. As above, in this work, we design a system of UAV trajectory prediction with the ADS-B information, and propose the recurrent LSTM (RLSTM) based algorithm to achieve the accurate prediction. Finally, extensive simulations are conducted by Python to evaluate the proposed algorithms, and the results show that the average trajectory prediction error is satisfied, which is in line with expectations.

In this paper, we study the resource allocation problem for an intelligent reflecting surface (IRS)-assisted OFDM system. The system sum rate maximization framework is formulated by jointly optimizing subcarrier allocation, base station transmit beamforming and IRS phase shift. Considering the continuous and discrete hybrid action space characteristics of the optimization variables, we propose an efficient resource allocation algorithm combining multiple deep Q networks (MDQN) and deep deterministic policy-gradient (DDPG) to deal with this issue. In our algorithm, MDQN are employed to solve the problem of large discrete action space, while DDPG is introduced to tackle the continuous action allocation. Compared with the traditional approaches, our proposed MDQN-DDPG based algorithm has the advantage of continuous behavior improvement through learning from the environment. Simulation results demonstrate superior performance of our design in terms of system sum rate compared with the benchmark schemes.

Automatic modulation classification is of crucial importance in wireless communication networks. Deep learning based automatic modulation classification schemes have attracted extensive attention due to the superior accuracy. However, the data-driven method relies on a large amount of training samples and the classification accuracy is poor in the low signal-to-noise radio (SNR). In order to tackle these problems, a novel data-and-knowledge dual-driven automatic modulation classification scheme based on radio frequency machine learning is proposed by exploiting the attribute features of different modulations. The visual model is utilized to extract visual features. The attribute learning model is used to learn the attribute semantic representations. The transformation model is proposed to convert the attribute representation into the visual space. Extensive simulation results demonstrate that our proposed automatic modulation classification scheme can achieve better performance than the benchmark schemes in terms of the classification accuracy, especially in the low SNR. Moreover, the confusion among high-order modulations is reduced by using our proposed scheme compared with other traditional schemes.

Non-orthogonal multiple access (NOMA) is a promising candidate for the sixth generation wireless communication networks due to its high spectrum efficiency (SE), energy efficiency (EE), and better connectivity. It can be applied in cognitive radio networks (CRNs) to further improve SE and user connectivity. However, the interference caused by spectrum sharing and the utilization of non-orthogonal resources can downgrade the achievable performance. In order to tackle this issue, intelligent reflecting surface (IRS) is exploited in a downlink multiple-input-single-output (MISO) CRN with NO-MA. To realize a desirable tradeoff between SE and EE, a multi-objective optimization (MOO) framework is formulated. An iterative block coordinate descent (BCD)-based algorithm is exploited to optimize the beamforming design and IRS reflection coefficients iteratively. Simulation results demonstrate that the proposed scheme can achieve a better balance between SE and EE than baseline schemes.

Semantic communication is envisioned as a promising technique to break through the Shannon limit. However, the existing semantic communication frameworks do not involve inference and error correction, which limits the achievable performance. In this paper, in order to tackle this issue, a cognitive semantic communication framework is proposed by exploiting knowledge graph. Moreover, a simple, general and interpretable solution for semantic information detection is developed by exploiting triples as semantic symbols. It also allows the receiver to correct errors occurring at the symbolic level. Furthermore, the pre-trained model is fine-tuned to recover semantic information, which overcomes the drawback that a fixed bit length coding is used to encode sentences of different lengths. Simulation results on the public WebNLG corpus show that our proposed system is superior to other benchmark systems in terms of the data compression rate and the reliability of communication.

This demonstration shows a working prototype of IDEA, Intelligent Divine Eye on Air through multi-UAV collaborative inference, to improve the throughput and accuracy of onboard object detection. Different from most existing UAV airborne object detection systems relying single UAV to run the convolutional neural networks (CNN)-based inference independently, IDEA leverages the abundant resources of multiple UAVs in a swarm, and collaboratively executes the inference task. Specifically, IDEA divides the CNN model into multiple submodels (each consisting of several successive layers), and distributes each submodel to a UAV, where the execution sequence of the submodels is coordinated to output the final prediction. The prominent advantage of IDEA lies in that, it can not only run highly accurate complex CNN models, but also perform the object detection tasks in a pipeline manner, which thus boosts high detection accuracy and frame rate. IDEA prototype with three self-constructed real-world UAVs shows ~2.6× frame rate improvement over that with one single UAV, while achieving higher detection accuracy.

Abstract Although unmanned aerial vehicle (UAV) relay can provide auxiliary communication due to its flexible mobility, it is vulnerable to jamming attacks. This paper considers the UAV relay anti‐jamming communication issue under the threat of a malicious jammer with beam‐forming jamming capability. To prevent the relay link from deteriorating, UAV trajectory adjustment and transmission mode switching between half‐duplex and full‐duplex are two available schemes, while they will incur the additional flying costs and continuous mode switching, respectively. To balance the trade‐off between trajectory optimization and mode selection, this paper investigates the joint trajectory optimization and mode selection anti‐jamming approach. First, an anti‐jamming utility considering the cost‐efficient and end‐to‐end capacity gains is designed. Second, to model the bounded rationality of both the UAV relay and the jammer due to the adversarial context, a biased Stackelberg game to analyse the competitive system interactions is proposed. Moreover, the existence of Stackelberg equilibrium (SE) in the problem is proved. Finally, a joint mode selection and trajectory optimization (JMSTO) algorithm based on the multi‐armed bandit is proposed to obtain the SE. It is further demonstrated that the JMSTO algorithm has a logarithmic regret. The results show that our proposed JMSTO algorithm is superior to non‐joint optimization methods.

Spectrum prediction is of crucial importance for realizing the cognitive Internet of Things to tackle the spectrum scarcity problem. Deep-learning-based spectrum prediction methods have attracted extensive attention due to their superior accuracy. However, the training speed of deep networks is low and the architecture of traditional networks is uninterpretable. In order to tackle these problems, a radio frequency machine-learning-driven spectrum prediction scheme is proposed by exploiting a novel model-enabled autoregressive (AR) network. A cell with only two parameters is exploited in each layer of the AR, which accelerates the network training. Moreover, the domain knowledge of the AR structure enables our proposed scheme to be explainable. Simulation results show that our proposed scheme has the best prediction accuracy than the long short-term memory (LSTM)-based scheme and the AR scheme. It is also shown that its convergence speed is higher than that of the LSTM-based scheme.

An unmanned aerial vehicle (UAV) array is composed of multiple UAVs carrying array elements, which can sense signals synchronously through a global positioning system (GPS) trigger. However, gain-phase errors caused by synchronization errors and the inconsistent complex gains of receiving array channels result in array manifold perturbation, which makes the performance of traditional localization methods degrade or even fail. In this article, two efficient algorithms for source direction finding and direct localization using a UAV array are, respectively, presented. First, the array manifold changes with the movement of UAVs, which contributes to multiposition fusion, thus avoiding the infinite solutions of underdetermined equations. Then, the quadratic optimization problem can be constructed by using the orthogonal relation between noise subspaces and contaminated steering vectors obtained from multiple observations. Thereafter, we can construct the cost function and obtain the spectral function, from which the source directions and positions can be all estimated by grid search. Meanwhile, the gain-phase error values can be solved successively. Moreover, in order to avoid the influence of heteroscedasticity of different observation positions in direct localization, we carry out a blind weighting operation. Simulation results demonstrate the effectiveness and superiority of the proposed algorithms.

Recently, the development of unmanned aerial vehicle (UAV) mobile-edge computing (MEC) networks has brought unprecedented gains and opportunities. In this article, the joint computation offloading, UAV role, and location selection problem in hierarchical multicoalition UAV MEC network is investigated. To capture the hierarchical feature and discrete optimization, the discrete Stackelberg game with multiple leaders and followers is formulated. We prove that both the leader-level and member-level subgames are ordinal potential games (OPGs) with Nash equilibrium (NE). Thus, the Stackelberg equilibrium (SE) is guaranteed. To achieve the SE, the log-linear-based hierarchical learning algorithm (LHLA) is proposed and analyzed. The simulation results show that the LHLA can converge fast and achieve better performance compared with the existing schemes.

Wireless technique classification (WTC) is of crucial importance in Internet of Things for realizing efficient spectrum sharing and interference management. However, the existing deep-learning-based methods have low classification accuracy, especially at low signal-to-noise ratio levels. In this article, a multiscale convolutional neural network framework is proposed for WTC. A multiscale module is exploited to capture the higher abstraction features. Simulation results demonstrate that our proposed scheme can achieve a better classification performance and a higher convergence speed compared to the state-of-the-art schemes.

Cognitive radio networks (CRNs) are expected to be promising techniques for improving the spectrum efficiency of wireless network utility in the squeezed sub-6-GHz frequency bands. Nevertheless, frequency allocation and transmission scheduling for secondary users (SUs) in CRNs suffer from no prior knowledge of other SUs’ network behaviors or the distribution of the amount of data generated at each SU. As a countermeasure, this article develops a protocol for the joint channel selection and transmission scheduling such that SUs with heterogeneous data transmission demands could be served with limited spectrum resources. Then, we formulate the dynamic optimization of the protocol as mutually embedded Markov decision processes (MDPs). To address the intractable MDPs,$Q$-learning-based channel selection and transmission scheduling based on reinforcement learning with basis function approximation are, respectively, proposed. It is shown that compared with various baselines, the proposed channel selection algorithm enables each SU to select the best frequency-domain channel that does not interfere with other SUs. In particular, the proposed transmission scheduling algorithm outperforms algorithms based on off-the-shelf approaches, such as$Q$-learning and Lyapunov optimization, in terms of both energy efficiency and long-term accumulative amount of bits at each SU.

In this paper, we study the self-healing problem of unmanned aerial vehicle (UAV) swarm network (USNET) that is required to quickly rebuild the communication connectivity under unpredictable external destructions (UEDs). Firstly, to cope with theone-off UEDs, we propose a graph convolutional neural network (GCN) that can find the recovery topology of the USNET in an on-line manner. Secondly, to cope withgeneral UEDs, we develop a GCN based trajectory planning algorithm that can make UAVs rebuild the communication connectivity during the self-healing process. We also design a meta learning scheme to facilitate the on-line executions of the GCN. Numerical results show that the proposed algorithms can rebuild the communication connectivity of the USNET more quickly than the existing algorithms under both one-off UEDs and general UEDs. The simulation results also show that the meta learning scheme can not only enhance the performance of the GCN but also reduce the time complexity of the on-line executions.

Millimeter-wave (mmWave) fifth-generation (5G) and beyond 5G localization enables the provisioning of extremely accurate positioning information, a feature that has attracted substantial research efforts. In this paper, we contribute to this effort by exploring optimal array geometric structures of direct position determination (DPD) systems, inspired by sensor placement problems that predominantly focus on two-step localization and have not yet been extended to DPD. Specifically, we research an optimal array placement and orientation strategy for two-dimensional (2-D) DPD systems that use sensors equipped with uniform linear arrays (ULA) to localize an agent. The A-optimality criterion in Bayesian optimal (experimental) design theory is invoked to formulate this problem. We use an optimization subproblem that optimizes array orientations when array locations are arbitrary but fixed to tackle this high-dimensional optimization problem. Then the optimization problem is converted into a typical optimal angular separation problem in two-step localization. Experimental results show that judiciously designed array geometric structures can lead to significant performance improvements.

This paper is the first to investigate both communication and control in traffic channel (TCH) and control channel (CCH) respectively when considering leader-follower formation keeping in UAV communication networks. In this paper, we analyze the relationship between the mutual interference and information exchange cost, and then formulate the joint channel and link selection problem as a two-way consensus game between CCH and TCH. To characterize the two-way choice of link selection, we creatively propose the generalized two-way consensus equilibrium (GTCE) to capture the stable state. Then, we prove that the formulated game has at least one pure-strategy GTCE which can maximize the UAV communication network utility. A distributed better reply based joint channel and link selection (BRJCLS) algorithm as well as two-dimensional minimum spanning tree (MST) based initialization (TMSTI) algorithm is proposed to achieve the GTCE. Simulation results are presented to show the convergence and effectiveness of the formulated two-way consensus game and proposed algorithms.

Spectrum mapping has emerged as an important problem in wireless communications, which generates a spectrum map for the spectrum resource analysis and management. Given the constrained transceiver volume and the limited energy consumption, how to effectively reconstruct the spectrum situation by the limited sampling data is a pressing challenge for spectrum mapping. In this paper, by exploiting the sparse nature of spectrum situation, we firstly attempt to solve the three-dimensional (3D) compressed spectrum mapping problem in the way of compressed sensing. Then, we develop a quadrature and right-triangular (QR) pivoting based measurement matrix optimization algorithm. By iteratively selecting new dominant sampling locations, it promotes the recovery accuracy compared to random measurement. After that, we propose a 3D spatial subspace based orthogonal matching pursuit (OMP) algorithm to recover spectrum situation for 3D compressed spectrum mapping. Finally, simulations are presented to show the comparisons in terms of localization, source signal strength recovery, recovery success rate and situation recovery. Results show our proposed 3D spectrum mapping scheme not only effectively reduces the sampling number, but also achieves a high level of spectrum mapping accuracy.

Non-orthogonal multiple access (NOMA) is a promising candidate for the sixth generation wireless communication networks due to its high spectrum efficiency (SE), energy efficiency (EE), and better connectivity. It can be applied in cognitive radio networks (CRNs) to further improve SE and user connectivity. However, the interference caused by spectrum sharing and the utilization of non-orthogonal resources can downgrade the achievable performance. In order to tackle this issue, intelligent reflecting surface (IRS) is exploited in a downlink multiple-input-single-output (MISO) CRN with NOMA. To realize a desirable tradeoff between SE and EE, a multi-objective optimization (MOO) framework is formulated under both the perfect and imperfect channel state information (CSI). An iterative block coordinate descent (BCD)-based algorithm is exploited to optimize the beamforming design and IRS reflection coefficients iteratively under the perfect CSI case. A safe approximation and the$ \mathcal {S}$-procedure are used to address the non-convex infinite inequality constraints of the problem under the imperfect CSI case. Simulation results demonstrate that the proposed scheme can achieve a better balance between SE and EE than baseline schemes. Moreover, it is shown that both SE and EE of the proposed algorithm under the imperfect CSI can be significantly improved by exploiting IRS.

The integration of mobile-edge computing (MEC) and energy harvesting (EH) can potentially improve the network performances and prolong the battery life of the device. In this article, we study the resource management problem in the device-to-device (D2D)-aided wireless powered MEC networks where one device can forward or execute computation data for other devices with its resources. Our problem seeks to optimize the computation offloading strategy, transmission power, energy transmit power, as well as CPU speed to maximize the long-term utility energy efficiency (UEE). UEE is defined as the achieved computation data per unit energy. Since the formulated problem is in fractional form and hard to solve, we employ the Dinkelbach algorithm to transform the problem into a parametric subtractive form. Furthermore, considering that the formulated problem is time varying and stochastic due to the dynamic task arrival rate and battery level, we transform the long-term problem into deterministic drift-plus-penalty subproblems for each time slot by introducing virtual queues and adopting the Lyapunov optimization theory. The proposed scheme can balance the optimal UEE and stable data queue by introducing the control parameter$V$. Theoretically, we reveal the tradeoff between the UEE and stable queue length for wireless powered MEC systems as$[O(1/V), O(V)]$. Finally, the simulations illustrate the efficiency of the proposed scheme compared with the existed work in terms of the UEE, stable queue length, and battery level.

Area coverage is one of the most common and important tasks for flying ad hoc networks (FANETs). The increasingly large scale of FANETs brings challenges in communication and coverage. Clustering is an effective technique for networking and management for large-scale ad hoc networks. Meanwhile, some applications, i.e., face recognition, need to perform intensive computation after unmanned aerial vehicles (UAVs) perform area coverage. Due to long response delay in transferring data to the cloud, it becomes a trend to use mobile-edge computing (MEC) for processing data in FANETs, which selects the node of rich computing resources, i.e., cluster head (CH), as MEC server, thus the delay performance of the edge node to the server is particularly critical. However, there is a conflict between area coverage efficiency and delay performance. Area coverage expects UAVs to spread as widely as possible, which may lead to a longer delay. In this article, we consider maximizing coverage efficiency under delay constraints. We define the coverage efficiency and propose an iterative coverage-efficient clustering algorithm (CECA) by applying penalty and block coordinate descent methods. Specifically, the CHs, positions and transmit powers are alternately optimized in each iteration. In addition, CECA can adjust delay constraints according to task requirements. Extensive simulation results show that our proposed approach is superior to other approaches in terms of coverage efficiency and delay.

Unmanned aerial vehicle (UAV)-enabled mobile edge computing has been recognized as a promising technology to flexibly and efficiently handle computation-intensive and latency-sensitive tasks in the era of fifth generation (5G) and beyond. In this paper, we study the problem of Service Provisioning for UAV-enabled mobile edge computiNg (SPUN). Specifically, under task latency requirements and various resource constraints, we jointly optimize the service placement, UAV movement trajectory, task scheduling, and computation resource allocation, to minimize the overall energy consumption of all terrestrial user equipments (UEs). Due to the non-convexity of the SPUN problem as well as complex coupling among mixed integer variables, it is a non-convex mixed integer nonlinear programming (MINLP) problem. To solve this challenging problem, we propose two alternating optimization-based suboptimal solutions with different time complexities. In the first solution with relatively high complexity in the worst case, the joint service placement and task scheduling subproblem, and UAV trajectory subproblem are iteratively solved by the Branch and Bound (BnB) method and successive convex approximation (SCA), respectively, while the optimal solution to the computation resource allocation subproblem is efficiently obtained in the closed form. To avoid the high complexity caused by BnB, in the second solution, we propose a novel approximation algorithm based on relaxation and randomized rounding techniques for the joint service placement and task scheduling subproblem, while the other two subproblems are solved in the same way as that of the first solution. Extensive simulations demonstrate that the proposed solutions achieve significantly lower energy consumption of UEs compared to three benchmarks.

Channel emulator is an important tool to evaluate communication system performance at the physical link, and network levels. In this paper, a new discrete 3D non-stationary geometry-based stochastic model (GBSM) for UAV to vehicle (U2V) channels is proposed, which considers 3D scattering space, 3D trajectory, and 3D antenna array. And a tailed channel emulator is developed on a field programmable gate array (FPGA) platform. All channel parameters, i.e., the power, delay, and phase are calculated by FPGA hardware for the first time instead of software or pre-storage method. Meanwhile, a Greedy CORDIC-based exponential calculation method for generating massive complex sinusoids is designed and implemented. The latency is reduced by 50% than traditional CORDIC method. By further utilizing the compact architecture with time division scheme, the hardware resource is significantly reduced from 16.51% to 7.55% for 16-bit data width. Meanwhile, the fixed-point output statistical properties are also derived for quantitatively validation. Finally, the U2V channel under the campus scenario is reproduced by the proposed emulator. The generated results demonstrate that the statistical properties are consistent well with the theoretical and ray tracing ones, which verifies the correctness of both proposed channel model and emulator.

In adversarial scenarios, it is crucial to timely monitor what tactical messages that opponent transmitters are sending to intended receiver(s), and disrupt the transmissions immediately if in need. The issue becomes more challenging in face of an intelligent transmitter. To address the above-stated issue, a full-duplex (FD) technique is utilized to enable simultaneous jamming and eavesdropping (SJE) at a friendly jammer node. In particular, the “Two Birds with One Stone” strategy is utilized at the jammer node to realize effective rate degradation and information eavesdropping. A confrontation game between an intelligence-empowered FD jammer and its opponent is investigated. Specifically, to capture their adversarial relationship in an environment with incomplete information, a power-domain Bayesian-Stackelberg game is proposed. The existence of a Stackelberg equilibrium (SE) power solution is proved. The semi-closed-form solutions of SE are derived, which are proved to be asymptotically optimal (have a gap of less than 1% with the exact utility), and improves the jammer node 10% utility compared with the Nash equilibrium. Additionally, the SJE strategy outperforms the half-duplex (HD) and other benchmark schemes.

The increasing of illegal radiations, which are either artificial or unintentional, has seriously influenced the reliable communication and operation of industrial facilities. In this article, we discuss the simultaneous localization of multiple emitters based on big data monitored by a moving unmanned aerial vehicle. Conventional direct position determination (DPD) method suffers from the non-homogeneity of the observation error and is sensitive to the environment, so we develop the weight DPD methods. First, we consider to strengthen the spectrums obtained at slots with higher signal-to-noise ratio, which is blindly calculated. Thereafter, an improved weight is designed to further enhance the localization accuracy, and it can obtain the asymptotically optimal performance under the general Gaussian noise model, which is proved theoretically. Numerical simulations demonstrate that the proposed weight DPD methods outperform the conventional two-step methods and subspace data fusion DPD method in terms of localization accuracy and resolution.

Coalition structure is an efficient networking architecture for task implementation in unmanned aerial vehicle (UAV) networks. However, both the formation of coalition and the spectrum resource for intra-coalition communication affect the reconnaissance performance. In this paper, we investigate a cooperative reconnaissance and spectrum access (CRSA) scheme for task-driven heterogeneous coalition-based UAV networks by jointly optimizing task layer and resource layer. Specifically, coalition formation game (CFG) is formulated to jointly optimize task selection and bandwidth allocation. In addition to the traditional Pareto order and selfish order, coalition expected altruistic order maximizing coalitions' utility is proposed. The CFG under the proposed order is proved to be an exact potential game (EPG). Then the existence of stable coalition partition is guaranteed with the help of Nash equilibrium (NE). We propose a joint bandwidth allocation and coalition formation (JBACF) algorithm to achieve stable coalition partition wherein an efficient gradient projection (GP) based method is applied to solve bandwidth allocation. The effectiveness of the proposed scheme and algorithms are demonstrated through in-depth numerical simulations. The results show that our proposed CRSA scheme is superior to non-joint optimization scheme. Also, the proposed order is superior to traditional Pareto order and selfish order.

In this article, we study the unmanned aerial vehicle (UAV)-enabled opportunistic data collection in wireless sensor networks (WSNs). The UAV performing remote missions is expected to collect data from the WSN during the return flights. Due to the specified task and safety restrictions, flight trajectory and time of the UAV are strictly constrained, resulting in the limited coverage ability in the data collection process. Moreover, the unknown distribution of active sensors makes it difficult for ground sensors and the UAV to complete the offline optimization of flight mode and transmission. To tackle these problems, we develop an air-ground collaborative online planning method. On the one hand, ground sensors actively form terrestrial transmission clusters to improve the data upload efficiency. After analyzing the Line-of-Sight (LoS) reliability and transmission correlation, we construct a coalition formation game model for the clustering of ground sensors. We discuss the equilibrium property of the game model, which can be achieved by the proposed distributed coalition formation algorithm. On the other hand, to avoid conflicts during the data collection, a data upload protocol is designed. We further discuss various flight speed planning schemes based on different detection capabilities of the UAV. The simulation results show that the performance of ground coalition-based air-ground collaborative online optimization is much better than that of the unilateral data collection by the UAV. Moreover, UAV flight online planning can further improve data uploading efficiency.

Unmanned aerial vehicles (UAVs) are envisioned to be widely deployed as an integral component in the next generation cellular networks, where spectrum sharing between the aerial and terrestrial communication systems will play an important role. However, there exist significant security and privacy challenges due to the untrusted broadcast features and wireless transmission of the UAV networks. This article endeavors to resolve the security issues through proposing a novel privacy-preserving secure spectrum trading and sharing scheme based on blockchain technology. Specifically, from the operator's perspective, a pricing-based incentive mechanism is first introduced, in which a primary mobile network operator (MNO) leases its owned spectrum to a secondary UAV network in exchange for some revenue from the UAV operators. To address the potential security issues, a spectrum blockchain framework is then proposed to illustrate detailed operations of how the blockchain helps to improve the spectrum trading environment. Under this framework, a Stackelberg game is formulated to jointly maximize the profits of the MNO and the UAV operators considering uniform and nonuniform pricing schemes. Security assessment and numerical results confirm the security and efficiency of our schemes for spectrum sharing in UAV-assisted cellular networks.

Due to the flexibility and affordability, multi-target positioning based on cooperation of Unmanned Aerial Vehicles (UAVs) becomes attractive in recent years. Trilateration is popular and easy to implement, but still faces challenges in multi-UAV scenario. First, multiple distance measurements from a single UAV on same targets will lead to large accumulated errors. Second, the time interval between successive distance measurements on the same target cannot be long due to the mobility of the target. Finally, UAVs have limited onboard energy which constrains the flight duration and the mission will fail when some UAVs reach the limitation. In this paper, to complete multi-target positioning mission, we aim at minimizing the maximum energy consumption among all UAVs, which can be decomposed into two subproblems after dividing all UAVs into groups of three. Then we propose a two-stage heuristic algorithm, in which we first use adjusted Genetic Algorithm (GA) to plan the trajectories of all groups with bounded maximum energy consumption and then we pursue to minimize the maximum energy consumption among UAVs in a group. Compared to two other algorithms, extensive simulations show that the proposed algorithm can reduce up to 24.9% and 11.8% in terms of maximum and average energy consumption, respectively.

In this paper, we investigate the problem of distributed ferrying transmission in UAV-assisted device-to-device (D2D) communication networks. When drones are performing tasks with given trajectories, terrestrial communication devices can select them for loading data opportunistically, and then drones will offload the data to corresponding receivers in the appropriate later time. For the dynamic multi-device network, there are composite optimization problems including competition of drone selection, time allocation of data loading and offloading, as well as limited channel access. Due to the distributed feature, devices share resources through independent perception and decision making. Therefore, a dynamic hierarchical game is designed for the problem of joint UAV allocation and channel access. Specifically, a predictable dynamic matching market is constructed to address the problem of UAV selection and time allocation, while the problem of channel access is studied by the congestion game. Based on the game model, a distributed hierarchical algorithm is proposed and the property of convergence is discussed. Simulation results confirm that the effective selection of data ferrying approach can improve the transmission performance significantly, while unreasonable optimization approaches may lead to the decline of the transmission performance.

The problem of Byzantine attack in collaborative spectrum sensing (CSS) is considered in this paper. To defend against Byzantine attack, a robust defense framework is proposed to efficiently identify the Byzantine attackers. Specifically, we first propose a robust defense framework, where a reference is built based on the extended sensing, and the transmit results and sensors are continuously evaluated via the reference and identified at intervals. In the framework, except of data falsification, multiple practical factors are considered, including the variation characteristic of sensors' attributes, reporting channel imperfection, and inference errors based on the transmit results. Further, we derive the closed-form expressions of the reference and the identification performance and make optimization of the identification threshold in two cases: with and without the prior knowledge of attack behaviors, where the probability of correctly detecting Byzantine attackers is maximized under the constraint of the probability of falsely identifying honest sensors as attackers. In particular, when the prior knowledge is unavailable, maximized likelihood estimation is made based on the reference to achieve the optimization. Furthermore, we present in-depth simulations to demonstrate the high robustness of the proposed defence framework to multiple practical factors under a homogeneous scenario and a heterogeneous scenario.

This paper deals with symbol detection in ambient backscatter communication systems with multi-antenna reader. Unlike most of the existing works which assume deterministic ambient radio frequency (RF) signals, we consider another important scenario with complex Gaussian RF signals. Focusing on the on-off keying modulation, the optimal detector minimizing the bit error rate (BER) is devised based on the maximum a posteriori principle, and an exact closed-form expression for the BER is derived. In addition, a simple energy detector is proposed to serve as a performance benchmark. Simulation results show that, implementing multiple antennas at the reader is an effective means to enhance the BER performance. Also, the proposed optimal detector always outperforms the energy detector. Furthermore, unlike the energy detector, whose BER settles in the high signal to noise ratio regime, no error floor exists for the proposed optimal detector.

Nowadays, Flying Ad hoc NETworks (FANETs) which consists of multiple Unmanned Aerial Vehicles (UAVs) are widely used in various military and civilian applications which need different Quality of Service (QoS) guarantees, for example, low delay for safety packet and high throughput for service packet. Meanwhile, to provide high bandwidth and spatial reuse, directional antennas are equipped on the UAVs more and more. However, due to the high mobility of UAVs, how to support different QoS with directional antenna is challenging for Media Access Control (MAC) protocol of FANETs. Recently, multi-channel MAC protocol has been proved to be effective to support different QoS. In this paper, we propose a FANETs multi-channel MAC protocol called FM-MAC, which combines the advantages of multi-channel and directional antenna to provide different QoS guarantees. Firstly, a reservation scheme based on mobile prediction is proposed to address the link interruption issue brought by high mobility of UAVs. Secondly, we propose a preemption mechanism to provide priority for service packets. Simulation results show that compared with other two representative protocols, FM-MAC not only improves the throughput of service packets, but also achieves lower delay and higher reliability for safety packets.

Unmanned aerial vehicle (UAV)-satellite communication has drawn dramatic attention for its potential to build the integrated space-air-ground network and the seamless wide-area coverage. A key challenge to UAV-satellite communication is its unstable beam pointing due to the UAV navigation, which is a typical SatCom on-the-move scenario. In this paper, we propose a blind beam tracking approach for Ka-band UAV-satellite communication system, where UAV is equipped with a hybrid large-scale antenna array. The effects of UAV navigation are firstly released through the mechanical adjustment, which could approximately point the beam towards the target satellite through beam stabilization and dynamic isolation. Specially, the attitude information for mechanical adjustment can be realtimely derived from data fusion of low-cost sensors. Then, the precision of beam pointing is blindly refined through electrically adjusting the weight of the massive antennas, where an array structure based simultaneous perturbation algorithm is designed. Simulation results are provided to demonstrate the superiority of the proposed method over the existing ones.

In this paper, a new WINNER+-based 3-D non-stationary geometry-based stochastic model (GBSM) for multiple-input multiple-output channels is proposed, as well as extended evolving algorithms of time-variant channel parameters. Meanwhile, important statistical properties of the channel model, i.e., time-variant autocorrelation function, time-variant cross-correlation function, and time-variant Doppler power spectrum density are derived and analyzed. Moreover, we propose an efficient hardware implementation method, namely, sum-of-frequency-modulation (SoFM) method, to generate non-stationary channel coefficients. By utilizing compact hardware architecture with SoFM modules, the proposed 3-D non-stationary GBSM is realized on a field-programmable gate array hardware platform. Simulations and hardware measurement results demonstrate that our proposed channel simulator and emulator can get more accurate and realistic Doppler frequency than those of the existing models. In addition, hardware measurements of statistical properties are also well consistent with the corresponding theoretical ones, which verify the correctness of both the hardware emulation scheme and theoretical derivations.

Spectrum misuse behaviors, brought either by illegitimate access or by rogue power emission, endanger the legitimate communication and deteriorate the spectrum usage environment. In this paper, our aim is to detect whether the spectrum band is occupied, and if it is occupied, recognize whether the misuse behavior exists. One vital challenge is that the legitimate spectrum exploitation and misuse behaviors probabilistically coexist and the illegitimate user may act in an intermittent and fast-changing manner, which brings about much uncertainty for spectrum sensing. To tackle it, we first formulate the spectrum sensing problems under illegitimate access and rogue power emission as a uniform ternary hypothesis test. Then, we develop a novel test criterion, named the generalized multi-hypothesis Neyman-Pearson (GMNP) criterion. Following the criterion, we derive two test rules based on the generalized likelihood ratio test and the Rao test, respectively, whose asymptotic performances are analyzed and an upper bound is also given. Furthermore, a cooperative spectrum sensing scheme is designed based on the global GMNP criterion to further improve the detection performances. In addition, extensive simulations are provided to verify the proposed schemes' performance under various parameter configurations.

In this paper, we present a secrecy outage performance analysis of wireless powered communication networks with multiple eavesdroppers, where an energy-limited information source with multiple antennas harvests the radio frequency (RF) energy from a dedicated power beacon (PB) before transmission. To exploit the benefits of multiple antennas at source, two popular multi-antenna transmission schemes, i.e., maximal ratio transmission and transmit antenna selection, are investigated for two intercepting ways at Eves, i.e., non-colluding and colluding scenarios, respectively. Specifically, adopting the time-switching protocol at PB, we derive exact and asymptotic closed-form expressions of the secrecy outage probability for both two transmission schemes taking into account the outdated channel state information (CSI). From our analysis, several important concluding remarks are obtained as follows: a) Full secrecy diversity order can be achieved by both two transmission schemes with no feedback delay, however, it reduces to zero in the presence of feedback delay; b) MRT scheme always outperforms TAS scheme with no feedback delay. However, TAS scheme achieves a similar performance as MRT scheme or even better in moderate and even serious feedback delay conditions.

The problem of distributed and dynamic sensing user selection in cognitive systems is studied in this paper, where channel sensing consumes resources and users behavior is distributed. Since users can obtain the channel state from the fusion center, if there are other users sensing the channel, users may enjoy the results sensed by others rather than sense the channel themselves. Such selfish behavior decreases both network utility and individual rewards. Inspired by the social expectation that no one should always enjoy the fruits of others' labor and that one should provide compensation after obtaining a benefit, we propose a distributed sensing compensation algorithm in this paper. The main concept of this algorithm is that after a channel is accessed successfully, users must sense the channel as a compensation for enjoying others' sensing results. The system state probabilities are obtained using Markov chain analysis. We show that there are always an optimal or near optimal number of users sensing the channel and hence, the near-optimal performance is achieved on average using the proposed algorithm. Additionally, the algorithm achieves good fairness performance with respect to the sensing cost. It is further shown that the proposed algorithm is not only suitable for static scenarios but also adaptable for dynamic scenarios with a changing active user set.

This letter studies a single-user power splitting-based multiple-input multiple-output system for simultaneous wireless information and power transfer. We aim to maximize the harvested power by joint design of transmit signal covariance matrix and receive power splitting factor under both a system rate constraint and a total power constraint. The harvested power maximization problem is difficult to solve due mainly to the nonconcave objective and the nonlinear coupling of design variables in the constraints. To tackle these challenges, we first derive a good approximation of the problem by ignoring some negligible noise terms and then further simplify it to a more tractable form by well exploiting the problem structure. Based on the Frank-Wolfe algorithm, we propose a simple yet efficient iterative algorithm to address the resulting problem. Numerical results validate the efficiency of the proposed algorithm.

This paper investigates the problem of dynamic spectrum access for canonical wireless networks, in which the channel states are time-varying. In the most existing work, the commonly used optimization objective is to maximize the expectation of a certain metric (e.g., throughput or achievable rate). However, it is realized that expectation alone is not enough since some applications are sensitive to fluctuations. Effective capacity is a promising metric for time-varying service process since it characterizes the packet delay violating probability (regarded as an important statistical quality-of-service index), by taking into account not only the expectation but also other high-order statistic. Therefore, we formulate the interactions among the users in the time-varying environment as a non-cooperative game, in which the utility function is defined as the achieved effective capacity. We prove that it is an ordinal potential game which has at least one pure strategy Nash equilibrium. Based on an approximated utility function, we propose a multi-agent learning algorithm which is proved to achieve stable solutions with dynamic and incomplete information constraints. The convergence of the proposed learning algorithm is verified by simulation results. Also, it is shown that the proposed multi-agent learning algorithm achieves satisfactory performance.

In this paper, we investigate the secrecy performance of dual-hop amplify-and-forward (AF) multi-antenna relaying systems over Rayleigh fading channels by taking into account the direct link between the source and destination. To improve the secrecy performance, two linear processing schemes at relay and maximal ratio combining (MRC) at destination are proposed, namely, Zero-forcing/MRC (ZF/MRC) and Maximal ratio transmission/MRC (MRT/MRC). For these schemes, we present new tight analytical expressions of the secrecy outage probability. In addition, we examine the performance in high signal-to-noise ratio (SNR) regimes, and present simple secrecy outage approximations for all schemes. The results reveal that: 1) The MRT/MRC scheme achieves a full diversity order of M+1, while the ZF/MRC scheme achieves a diversity order ofM, where M is the number of antennas at relay. 2) The ZF/MRC scheme outperforms the MRT/MRC scheme in the low SNR regime, while becomes inferior to the MRT/MRC scheme in the high SNR regime.

This paper presents a systematic approach to exploiting TV white space (TVWS) for device-to-device (D2D) communications with the aid of the existing cellular infrastructure. The goal is to build a location-specific TVWS database, which provides a lookup table service for any D2D link to determine its maximum permitted emission power (MPEP) in an unlicensed digital TV (DTV) band. To achieve this goal, the idea of mobile crowd sensing is first introduced to collect active spectrum measurements from massive personal mobile devices. Considering the incompleteness of crowd measurements, we formulate the problem of unknown measurements recovery as a matrix completion problem and apply a powerful fixed point continuation algorithm to reconstruct the unknown elements from the known elements. By joint exploitation of the big spectrum data in its vicinity, each cellular base station further implements a nonlinear support vector machine algorithm to perform irregular coverage boundary detection of a licensed DTV transmitter. With the knowledge of the detected coverage boundary, an opportunistic spatial reuse algorithm is developed for each D2D link to determine its MPEP. Simulation results show that the proposed approach can successfully enable D2D communications in TVWS while satisfying the interference constraint from the licensed DTV services. In addition, to our best knowledge, this is the first try to explore and exploit TVWS inside the DTV protection region resulted from the shadowing effect. Potential application scenarios include communications between internet of vehicles in the underground parking and D2D communications in hotspots such as subway, game stadiums, and airports.

Spectrum auction is one of the most effective solutions to allocate the spectrum resource following the market rules and has attracted much attention from both academia and industry. However, most of the existing studies assume that the spectrum buyers' demands are homogeneous and the interference relationship is fixed without any change with the variation of spectrum. Furthermore, the economical efficiency of auction outcome has not drawn enough attention. That motivates us to design an auction scheme to jointly consider the multi-demand of buyers, heterogeneous spectrum, and economical efficiency. In this paper, we propose a novel overlapping coalition formation-based double auction, called VERACITY, to address this problem. The auctioneer groups the conflict free buyers into the same coalition and allows a buyer to join multiple coalitions based on the heterogeneous demand. Dynamic overlapping coalition formation implemented by the auctioneer is to find the approximately optimal coalition structure corresponding to the economical efficiency outcome, i.e., maximizing the social welfare. Furthermore, we prove that VERACITY is individually rational, budget balanced, truthful, and economically efficient. Simulation results are presented to show the convergence and effectiveness of the proposed VERACITY.

Abstract In heterogeneous wireless networks, network selection algorithms provide the user with the optimum network access choice. The optimal network is evaluated according to network parameters. Considering that the network parameters are dynamic and unavailable for the user in realistic heterogeneous wireless network environments, most existing network selection algorithms cannot work effectively. Learning‐based algorithms can address the problem of uncertain network parameters, while they commonly need considerable network handoff, resulting in unbearable handoff cost. In order to tackle the uncertainty of network parameters, we formulate the network selection problem as a multi‐armed bandit problem. Moreover, two online learning‐based network selection algorithms with a special consideration on reducing network handoff cost are proposed. By updating in a block manner, both algorithms achieve optimal logarithmic‐order regret and limited network handoff cost. The simulation indicates that the two algorithms can significantly reduce the network handoff cost and improve the transmission performance compared with existing algorithms, simultaneously. Copyright © 2014 John Wiley & Sons, Ltd.

Radio resource management (RRM) is crucial for improving resource utilization in heterogeneous wireless networks. Existing work attempts to exploit the network diversity to gain throughput improvement for users, which, however, neglects the impact of user demand on RRM. Armed with the idea that the ultimate goal of communications is to serve users with personalized demand, we introduce another dimension of potential performance gain, user demand diversity gain. This gain derives from the elaborate matching between user demand and radio resource, which can not be directly attained in existing throughput-centric optimization due to users' blindness in maximizing throughput. Aiming at obtaining this gain, we propose the user demand-centric optimization, where users seek to maximize quality of experience (QoE), instead of throughput. This shift enables us to propose a novel game formulation, QoE game. We derive the condition on the existence of the QoE equilibrium, validate the user demand diversity gain and propose a distributed QoE equilibrium learning algorithm. Finally, a cloud assisted learning framework is proposed to accommodate the learning algorithm with significantly reduced cost. Simulation results validate the existence of user demand diversity gain and the effectiveness of the proposed learning algorithm in improving the system efficiency and QoE fairness.

This paper investigates the issue of cooperative spectrum sensing with a crowd of low-end personal spectrum sensors (such as smartphones, tablets, and in-vehicle sensors), where one critical challenge is the uncertainty of the quality of sensing data from crowd sensors that may be unreliable, untrustworthy, or even malicious. Moreover, due to either unexpected equipment failures or malicious behaviors, every crowd sensor could sporadically and randomly contribute abnormal data, which makes the existing defense schemes ineffective. To tackle these unique challenges, we propose a robust spectrum sensing scheme by developing a data cleansing framework, where the underutilization of licensed spectrum bands and the sparsity of nonzero abnormal data are jointly exploited to robustly cleanse out the potential nonzero abnormal data component from the original corrupted sensing data. Simulation results demonstrate that the proposed robust sensing scheme outperforms the state-of-art schemes under various abnormal data parameter configurations.

Starting from Neyman-Pearson criterion, this paper derives an optimal spectrum sensing scheme which exploits spatial diversity among multiple cognitive sensors and temporal diversity among consecutive time slots jointly. In the proposed scheme, the impact of the imperfect reporting channel on the design of the spectrum sensing scheme is effectively integrated. Simulation results show that compared with singular (either spatial or temporal) diversity-based sensing schemes, the proposed scheme brings not only improvement of sensing performance, but also significant reduction of sensing overhead.

Current research on Internet of Things (IoT) mainly focuses on how to enable general objects to see, hear, and smell the physical world for themselves, and make them connected to share the observations. In this paper, we argue that only connected is not enough, beyond that, general objects should have the capability to learn, think, and understand both physical and social worlds by themselves. This practical need impels us to develop a new paradigm, named cognitive Internet of Things (CIoT), to empower the current IoT with a “brain” for high-level intelligence. Specifically, we first present a comprehensive definition for CIoT, primarily inspired by the effectiveness of human cognition. Then, we propose an operational framework of CIoT, which mainly characterizes the interactions among five fundamental cognitive tasks: perception-action cycle, massive data analytics, semantic derivation and knowledge discovery, intelligent decision-making, and on-demand service provisioning. Furthermore, we provide a systematic tutorial on key enabling techniques involved in the cognitive tasks. In addition, we also discuss the design of proper performance metrics on evaluating the enabling techniques. Last but not the least, we present the research challenges and open issues ahead. Building on the present work and potentially fruitful future studies, CIoT has the capability to bridge the physical world (with objects, resources, etc.) and the social world (with human demand, social behavior, etc.), and enhance smart resource allocation, automatic network operation, and intelligent service provisioning.

This paper investigates the issue of cooperative spectrum sensing with a crowd of low-end personal spectrum sensors (such as smartphones, tablets, and in-vehicle sensors), where the sensing data from crowd sensors that may be unreliable, untrustworthy, or even malicious. Moreover, due to either unexpected equipment failures or malicious behaviors, every crowd sensor could sporadically and randomly contribute with abnormal data, which makes the existing cooperative sensing schemes ineffective. To tackle these challenges, we first propose a generalized modeling approach for sensing data with an arbitrary abnormal component. Under this model, we then analyze the impact of general abnormal data on the performance of the cooperative sensing, by deriving closed-form expressions of the probabilities of global false alarm and global detection. To improve sensing data quality and enhance cooperative sensing performance, we further formulate an optimization problem as stable principal component pursuit, and develop a data cleansing-based robust spectrum sensing algorithm to solve it, where the under-utilization of licensed spectrum bands and the sparsity of nonzero abnormal data are jointly exploited to robustly cleanse out the potential nonzero abnormal data component from the original corrupted sensing data. Extensive simulation results demonstrate that the proposed robust sensing scheme performs well under various abnormal data parameter configurations.

This paper presents a comprehensive performance analysis of multiuser multiple antenna amplify-and-forward relaying networks employing opportunistic scheduling with feedback delay and co-channel interference over Rayleigh fading channels. Specifically, we derive exact as well as approximate closed-form expressions for the outage probability and average symbol error rate (SER) of the system. In addition, simple asymptotic expressions at the high signal-to-noise ratio (SNR) regime are obtained, which facilitate the characterization of the achievable diversity order and coding gain of the system. Moreover, two novel ergodic capacity bounds valid for general systems with arbitrary number of antennas and users are proposed. Finally, the optimum power allocation scheme in terms of minimizing the average SER is studied, and simple analytical solutions are obtained. Simulation results are provided to corroborate the derived analytical expressions, and it is demonstrated that the ergodic capacity bounds remain sufficiently tight across the entire range of SNRs and the proposed power allocation scheme offers significant improvements on the SER performance. The findings of the paper suggest that the full diversity order can only be achieved when there is ideal feedback, i.e., no feedback delay, and the diversity order always reduces to one in the presence of feedback delay. Also, the impact of key parameters such as the number of antennas and users on the system performance is intimately dependent on the level of feedback delay.

In this paper, we propose transmit antenna selection with maximal ratio combining (TAS/MRC) in dual-hop decode-and-forward spectrum-sharing relaying networks with the primary user's interference and outdated channel state information (CSI). In this network, a single antenna that maximizes the received SNR is selected at the secondary transmitter, and the MRC is adopted at the secondary receiver. To efficiently evaluate the impact of key parameters on the system performance, we derive the exact analytical expression for the outage probability of the secondary network in a Rayleigh fading channel. Moreover, we present simple asymptotic expressions for the outage probability in a high SNR regime, which reveal practical insights on the achievable diversity order and coding gain. The findings suggest that whether the outdated CSI concerning the secondary transmission links has significant impact on the outage probability of the system depends on the interference power constraint at primary receivers. Specifically, under the proportional interference power constraint, the achievable diversity order is affected by imperfect CSI regarding the secondary transmission links, and the diversity-multiplexing tradeoff is independent of the primary network. However, under the fixed interference power constraint, the error floor is displayed, and the achievable diversity order reduces to zero regardless of the CSI concerning the secondary transmission links.

For cognitive wireless networks, one challenge is that the status and statistics of the channels' availability are difficult to predict. Numerous learning based online channel sensing and accessing strategies have been proposed to address such challenge. In this work, we propose a novel channel sensing and accessing strategy that carefully balances the channel statistics exploration and multichannel diversity exploitation. Unlike traditional MAB-based approaches, in our scheme, a secondary cognitive radio user will sequentially sense the status of multiple channels in a carefully designed order. We formulate the online sequential channel sensing and accessing problem as a sequencing multi-armed bandit problem, and propose a novel policy whose regret is in optimal logarithmic rate in time and polynomial in the number of channels. We conduct extensive simulations to compare the performance of our method with traditional MAB-based approach. Simulation results show that the proposed scheme improves the throughput by more than 30% and speeds up the learning process by more than 100%.

In this paper, we investigate the ergodic capacity and the average symbol error probability (SEP) of uplink cognitive cellular networks with opportunistic scheduling in Nakagami-m fading channels. Considering the same opportunistic scheduling scheme as [1], we derive closed-form expressions for the ergodic capacity and the average SEP of the system. Depending on closed-form expressions, we further investigate the impact of various key system parameters, i.e., channel fading severity, primary user's target outage probability and primary user's transmission rate, on cognitive user's performance. Theoretical results, verified by simulations, about the ergodic capacity and the average SEP are expressed in terms of the Meijer's G-function and the confluent hypergeometric function of the second kind, respectively. From the simulations, we get that the ergodic capacity and the average SEP are independent of the number of cognitive users and the transmit power of primary user.

This paper investigates the problem of distributed channel selection for interference mitigation in cognitive radio networks (CRNs) with block-fading channels, using a game-theoretic solution. Specifically, the channel gains are blockfixed in a slot and change randomly in the next slot. Existing algorithms, which are originally designed for static channels, can not converge in the presence of time-varying channels. We formulate this problem as a non-cooperative game with random payoffs, in which the utility of each player (CR user) is defined as the expected weighted experienced interference. This game is proved to be a potential game with the network utility, the expected weighted aggregate interference, serving as the potential function. Then, we propose a stochastic learning automata based distributed channel selection algorithm, with which the CR users learn the desirable channel selections from their action-payoff history. It is analytically shown that the proposed learning algorithm converges to pure strategy Nash equilibrium (NE), which maximizes the network utility globally or locally, without information exchange. Moreover, simulation results show that it achieves higher normalized transmission rate.

This article investigates the problem of distributed channel selection in opportunistic spectrum access (OSA) networks with partially overlapping channels (POC) using a game-theoretic learning algorithm. Compared with traditional non-overlapping channels (NOC), POC can increase the full-range spectrum utilization, mitigate interference and improve the network throughput. However, most existing POC approaches are centralized, which are not suitable for distributed OSA networks. We formulate the POC selection problem as an interference mitigation game. We prove that the game has at least one pure strategy NE point and the best pure strategy NE point minimizes the aggregate interference in the network. We characterize the achievable performance of the game by presenting an upper bound for aggregate interference of all NE points. In addition, we propose a simultaneous uncoupled learning algorithm with heterogeneous exploration rates to achieve the pure strategy NE points of the game. Simulation results show that the heterogeneous exploration rates lead to faster convergence speed and the throughput improvement gain of the proposed POC approach over traditional NOC approach is significant. Also, the proposed uncoupled learning algorithm achieves satisfactory performance when compared with existing coupled and uncoupled algorithms.

This paper investigates the issue of spatial-temporal opportunity detection for spectrum-heterogeneous cognitive radio networks, where at a given time secondary users (SUs) at different locations may experience different spectrum access opportunities. Most prior studies address either spatial or temporal sensing in isolation and explicitly or implicitly assume that all SUs share the same spectrum opportunity. However, this assumption is not realistic and the traditional non-cooperative sensing (NCS) and cooperative sensing (CS) schemes are not very effective in a more realistic setting considering the heterogeneous spectrum availability among SUs. We define new performance metrics to guide the spatial-temporal opportunity detection and propose a two-dimensional sensing (TDS) framework to improve the opportunity detection performance, which exploits correlations in time and space simultaneously by effectively fusing sensing results in a spatial-temporal sensing window. Furthermore, in terms of maximum interference constrained transmission power (MICTP), we classify the spatial opportunities for SUs into three groups: black, grey, and white, and propose a TDS-based distributed power control scheme to further improve the spectrum utilization by exploiting both grey and white spectrum opportunities. The effectiveness of the proposed scheme is demonstrated through in-depth numerical simulations under a variety of scenarios.

This article investigates the problem of distributed channel selection for opportunistic spectrum access systems, where multiple cognitive radio (CR) users are spatially located and mutual interference only emerges between neighboring users. In addition, there is no information exchange among CR users. We first propose a MAC-layer interference minimization game, in which the utility of a player is defined as a function of the number of neighbors competing for the same channel. We prove that the game is a potential game with the optimal Nash equilibrium (NE) point minimizing the aggregate MAC-layer interference. Although this result is promising, it is challenging to achieve a NE point without information exchange, not to mention the optimal one. The reason is that traditional algorithms belong to coupled algorithms which need information of other users during the convergence towards NE solutions. We propose two uncoupled learning algorithms, with which the CR users intelligently learn the desirable actions from their individual action-utility history. Specifically, the first algorithm asymptotically minimizes the aggregate MAC-layer interference and needs a common control channel to assist learning scheduling, and the second one does not need a control channel and averagely achieves suboptimal solutions.

In this paper, decentralized cooperative spectrum sensing in cognitive radio networks is studied based on the recent advances in unsupervised learning. To balance a tradeoff between the sensing reliability and the cooperation overhead (e.g., energy, delay, and signaling, etc.), a distributed clustering algorithm, without any central coordinator, is introduced for inducing the sensors with the best detection performance to join together and take charge of cooperative spectrum sensing. Numerical results show that the proposed scheme can obtain detection performance comparable to that of optimal soft combination scheme with reduced cooperation overhead. Moreover, the proposed scheme does not require any priori knowledge of spectrum sensors' received signal-to-noise-ratios (SNRs) or locations.

For cognitive wireless networks, one challenge is that the status of the channels' availability and quality is difficult to predict and quantify. Numerous learning based online channel sensing and accessing strategies have been proposed to address such challenge. In this work, we propose a novel channel sensing and accessing strategy that carefully balances the channel statistics exploration and multichannel diversity exploitation. Unlike traditional MAB-based approaches, in our scheme, a secondary cognitive radio user will sequentially sense the status of multiple channels in a carefully designed ordering. We formulate the online sequential channel sensing and accessing problem as a sequencing multi-armed bandit problem, and propose a novel policy whose regret is in optimal logarithmic rate in time and polynomial in the number of channels. We conducted extensive simulations to compare the performance of our method with traditional MAB-based approach. Our simulation results show that our scheme improves the throughput by more than 30% and speed up the learning process by more than 100%.

We investigate efficient channel learning and opportunity utilization problem in cognitive radio networks (CRN). We find that the sensing order of multiple channels and channel accessing policy play a critical role in designing effective and efficient scheme to maximize the throughput. Leveraging this important finding, we propose a near optimal online channel access policy. We prove that, our policy can converge to an optimal point in a guaranteed probability. Further, we design a computational efficient channel access policy, integrating optimal stopping theory and multi-armed bandit policy effectively. The computational complexity is reduced from O(K NK) to O(K), where N is the number of channels, and K is the maximum number of sensing/probing times in each procedure. Our simulation results validate our policy, showing at least 40% performance improvement over statistically optimal but fixed policy.

In multichannel system, user could keep transmitting over an instantaneous “on peak” channel by opportunistically accessing and switching among channels. Previous studies rely on constant transmission duration, which would fail to leverage more opportunities in time and frequency domain. In this paper, we consider opportunistic channel accessing/releasing scheme in multichannel system with Rayleigh fading channels. Our main goal is to derive a throughput-optimal strategy for determining when and which channel to access and when to release it. We formulate this real-time decision-making process as a two-dimensional optimal stopping problem. We prove that the two-dimensional optimal stopping rule can be reduced to a simple threshold-based policy. Leveraging the absorbing Markov chain theory, we obtain the optimal threshold as well as the maximum achievable throughput with computational efficiency. Numerical and simulation results show that our proposed channel utilization scheme achieves up to 140 percent throughput gain over opportunistic transmission with a single channel and up to 60 percent throughput gain over opportunistic channel access with constant transmission duration.

We investigate the problem of distributed channel selection using a game-theoretic stochastic learning solution in an opportunistic spectrum access (OSA) system where the channel availability statistics and the number of the secondary users are apriori unknown. We formulate the channel selection problem as a game which is proved to be an exact potential game. However, due to the lack of information about other users and the restriction that the spectrum is time-varying with unknown availability statistics, the task of achieving Nash equilibrium (NE) points of the game is challenging. Firstly, we propose a genie-aided algorithm to achieve the NE points under the assumption of perfect environment knowledge. Based on this, we investigate the achievable performance of the game in terms of system throughput and fairness. Then, we propose a stochastic learning automata (SLA) based channel selection algorithm, with which the secondary users learn from their individual action-reward history and adjust their behaviors towards a NE point. The proposed learning algorithm neither requires information exchange, nor needs prior information about the channel availability statistics and the number of secondary users. Simulation results show that the SLA based learning algorithm achieves high system throughput with good fairness.

A critical challenge in Cognitive Radio Networks (CRN) is to make decision in real-time on accessing and releasing available channels that maximize the spectrum utilization and the overall system throughput. In this work, we make investigations on optimal action point to explore and exploit the frequency-temporal diversity in addition to spectrum availability. By modeling the Rayleigh fading channel under primary user (PU) activity to be a finite state Markov channel (FSMC) with an absorbing state, we formulate this difficulty into a 2-Dimension optimal stopping problem. Further, we've proved that, the complexity of the 2D optimal stopping rule can be reduced to one threshold policy, where the optimal character still holds. After properly constructing multi-absorbing-states Markov chain for dynamic analysis, we get the throughput of our strategy accurately. Numerical and simulations results have verified that, our threshold based access/switch strategy gains much more throughput than conventional idle/busy based access/switch strategy at the cost of access delay in most cases.

The issue of distributed channel selection in opportunistic spectrum access is investigated in this paper. We consider a practical scenario where the channel availability statistics and the number of competing secondary users are unknown to the secondary users. Furthermore, there is no information exchange between secondary users. We formulate the problem of distributed channel selection as a static non-cooperative game. Since there is no prior information about the licensed channels and there is no information exchange between secondary users, existing approaches are unfeasible in our proposed game model. We then propose a learning automata based distributed channel selection algorithm, which does not explicitly learn the channel availability statistics and the number of competing secondary users but learns proper actions for secondary users, to solve the proposed channel selection game. The convergence towards Nash equilibrium with respect to the proposed algorithm also has been investigated.

In multichannel system, user could keep transmitting over an instantaneous "on peak" channel by opportunistically accessing and switching among channels, so as to exploit link layer time-frequency diversity. In this paper, we consider an opportunistic channel accessing/releasing scheme for maximizing system throughput in multichannel system under Rayleigh fading environment. The time-dependence of Rayleigh fading is accurately characterized by finite-state Markov channel (FSMC) model. The main goal of this paper is to devise throughput-optimal strategy for determining when to access (which) channel and when to release it. The chanllenge of the problem comes from the fact that user can never know the instantaneous quality of all channels. In fact, it has to make real time decisions purely depending on the quality of current channel and the statistics of candidate channels. We formulate this real time decision making process as a two dimension optimal stopping problem. We prove that the complexity of the two dimensional optimal stopping rule can be reduced to a simple threshold-based policy. The dynamic data transmission process under threshold-based opportunistic channel access/release strategy is then analyzed by properly constructing absorbing Markov chain. Leveraging the absorbing Markov chain theory, we attain the optimal threshold as well as maximum achievable throughput with computational efficiency. Numerical results show that our proposed channel utilization scheme achieves up to 120% throughput gain over opportunistic transmission with a single channel and up to 70% throughput gain over opportunistic channel access with constant transmission duration.

Opportunistic spectrum access is an important issue in cognitive radio systems. In this paper, we propose a distributed opportunistic spectrum access scheme based on sequential channel-sensing in decentralized CRN (cognitive radio network). Different from the traditional spectrum sensing scheme, the scheme proposed allows a secondary users to sense many channels one by one sequentially in a slot. Simulation results show that the proposed scheme can attain better performance of throughput. At the same time, we analyze three sequential channel-sensing orders of the proposed scheme. The simulation results show that the learning based channel-sensing order is better in the performance of throughput.