In the era of 6G and dynamic spectrum access, the exponential growth of connected devices and diverse service demands intensifies spectrum scarcity and interference. Reliable spectrum prediction is thus essential to enable proactive access, alleviate congestion, and enhance spectral efficiency. Existing approaches suffer from a trade-off between accuracy and efficiency: model-driven methods often fail to capture inter-dimensional correlations, whereas data-driven methods achieve higher accuracy at the cost of excessive computational complexity. To address these challenges, we propose a lightweight spectrum prediction framework that integrates patch-based local feature extraction, sparse graph attention for efficient global dependency modeling, positional reconstruction for time–frequency alignment, and a closed-form continuous-time prediction network for accurate temporal forecasting. Simulation results demonstrate that the proposed method reduces the root mean square error by 2.7%~65% while lowering computational resource consumption by 19%~84% compared with state-of-the-art baselines. These results underline the potential of the proposed approach to support scalable spectrum management in 6G wireless networks, thereby facilitating ultra-reliable low-latency communication, massive IoT connectivity, and intelligent spectrum sharing.

The integration of sixth-generation (6G) networks with the Industrial Internet of Things (IIoT) promises unprecedented connectivity and intelligence for industrial applications. However, the massive scale of device deployment and dynamic spectrum requirements in 6G-IIoT systems pose significant challenges for reliable and trustworthy resource allocation. This paper proposes a multi-objective optimization approach that leverages cognitive radio technology and energy harvesting capabilities to ensure trustworthy resource allocation while maximizing data transmission and minimizing energy consumption. The framework incorporates imperfect spectrum sensing and interference constraints to guarantee reliable coexistence between primary and secondary networks, aligning with the reliability requirements of 6G-IIoT applications. This paper proposes a constraint repair strategy-based multi-objective artificial hummingbird algorithm (CPS-MOAHA) that effectively handles the complex constraints and provides Pareto optimal solutions. Simulation results demonstrate the superiority of the proposed algorithm in achieving better trade-offs between data transmission and energy efficiency compared to existing approaches.

With the rapid development of wireless communication technology, security issues in wireless networks have become increasingly serious, leading to the emergence of Radio Frequency Fingerprint (RFF) as an important device authentication technology. RFF identifies and verifies device identities by analyzing the wireless signals emitted by devices. However, the inherent complexity and non-Euclidean characteristics of signal features pose significant challenges for traditional machine learning and deep learning approaches in RFF. Graph Neural Networks (GNNs) uniquely address these limitations by explicitly modeling signal relationships through graph-structured representations, enabling effective capture of high-order interactions and dynamic adaptation to signal variations through message passing mechanisms. To this end, this paper proposes an efficient Attention-Enhanced Graph Convolutional Network (EAGCN) for RFF identification. The network employs an Adaptive Visibility Graph (AVG) Generator and Efficient Channel Attention (ECA) mechanisms to enhance the capture of key features, and combines these with DenseGCN graph convolution layers to better capture spatial correlations. Additionally, we introduce Graph Double Implicit Regularization (GDIR) into the network to further improve its generalization ability in few-shot transfer tasks. Experimental results on a multi-transmitter multi-receiver WiFi dataset show that GDIR-EAGCN significantly outperforms existing methods, particularly excelling in transfer learning tasks. Furthermore, an ablation study was conducted to validate the contribution of each component to the overall performance.

Radio Frequency Fingerprint Identification (RFFI) has emerged as a promising technique for enhancing wireless security by uniquely identifying individual devices through their inherent RF characteristics. However, the performance of conventional RFFI methods deteriorates significantly when training and testing involve different modulation schemes, primarily due to the resulting domain shift between modulation types. To address this challenge, this paper proposes Domain-Invariant Adaptive Mixup Enhancement (DIAME), a novel framework that integrates domain-invariant feature extraction with a similarity-aware adaptive mixup strategy to improve generalization across modulation domains. Specifically, DIAME dynamically adjusts the mixup intensity based on inter-feature similarity and incorporates domain alignment and feature matching with pretrained models to promote modulation-invariant representation learning. Extensive experiments on a synthetic RF dataset comprising four modulation types and five devices demonstrate that DIAME achieves an average cross-modulation identification accuracy of 86.18%, significantly outperforming state-of-the-art methods. These results confirm the effectiveness of DIAME in mitigating domain shift and highlight its suitability for robust RFFI in heterogeneous wireless communication environments.

Urban unmanned aerial vehicle (UAV) navigation operates under tight bandwidth, compute, and latency budgets. Interference and building blockage cause rapid link fluctuations, making interference-aware path planning on grid signal-to-interference-plus-noise ratio (SINR) maps essential for reliable communication. In this paper, we formulate the problem as a joint update–navigation decision: map uncertainty triggers on-demand partial refreshes that are co-optimized with motion under a bandwidth budget. We introduce UT-Grid, an uncertainty-triggered grid-update framework, that refreshes conditionally triggered upon necessity to reduce overall map-update traffic, and MoE-D3QN, a Dueling Double DQN with sparse Mixture-of-Experts (Top-1 routing) that activates a single expert per step, cutting per-decision active parameters and FLOPs while matching or surpassing comparable dense D3QN planners. In an urban simulation with multi-source interference, the framework outperforms static-map, periodic-refresh, and dense D3QN baselines, increasing reaching probability and path efficiency while markedly reducing communication overhead.

In the transition from pilot to mass production, certain fault classes lack available samples, creating a zero-shot condition that challenges the training of fault diagnosis models. Zero-shot learning (ZSL) maps features to shared attribute vectors formed by engineering knowledge information, offering a potential solution. In manufacturing processes, disturbances propagate across operations, causing multiple attributes to co-occur. However, the internal co-occurrence relationships among attributes are often overlooked, which may lead to discrepancies in attribute prediction. To address this issue, we propose a zero shot fault diagnosis method for manufacturing processes that leverages attribute co-occurrence relationships to identify unseen faults. To capture this relationship, mutual information is first employed to quantify attribute co-occurrence and construct an adjacency matrix of attribute relations. In parallel, distributional features are extracted using multi-delay ordinal patterns, and a distance-based loss function is designed to align these features with the attributes. The adjacency matrix and distributional features are then input into a graph convolutional network, with attribute relationships embedded into the distributional features to maintain consistency. Finally, distributional features support zero-shot fault diagnosis via mapping and similarity measures. Experimental validation on the Tennessee Eastman Process (TEP) and fuel rods manufacturing process demonstrates the effectiveness of the proposed method.

This study tackles computational bottlenecks, training instability, and insufficient cross-modal semantic alignment in high-resolution multimodal image processing. We propose TriVLLo, an innovative multi-scale vision-language modeling framework. Our main contributions are: First, we introduce factorized 2D positional encoding and a dynamically configurable modular architecture. This approach decouples height and width position information. It improves spatial localization reliability for images with extreme aspect ratios. It also reduces computational parameters and alleviates training instability. Second, we design a unified multi-scale feature extraction and modality interaction mechanism. This uses adaptive image processing and multi-perspective feature pyramids. It enhances robustness to inputs of any resolution. It also achieves fine-grained alignment of vision-language features through a shared embedding space. Third, we build a high-quality dataset with 11K samples for fine-grained reasoning. This dataset supports improvements in visual ranking, semantic alignment, and narrative reasoning. Experiments show that TriVLLo achieves 87.4% of GPT-4V's performance on the MM-Vet benchmark. It demonstrates a 93.0 percentage-point improvement over Emu2 in spatial cognition tasks. It attains 89.2% accuracy on knowledge generation tasks. These results significantly outperform state-of-the-art methods.

Automatic modulation recognition is essential for large-scale wireless communications, but traditional methods often ignore unknown signals in open-set conditions, leading to their incorrect classification as known types and thereby compromising system reliability and communication security. To handle this challenge, a novel automatic modulation open set recognition (AMOSR) model based on deep metric learning with embedding enhancement is proposed in this article. First, for each known example, deep neural model is employed to separately extract the original in-phase and quadrature (IQ) signal and its instantaneous features, which are then fused to obtain embedding. Second, random erasing is employed to the original IQ signal and instantaneous features separately to obtain an augmented example, which has similar structure but different semantics with known example, and the embedding of this example is obtained by using first step. Then, the embedding space, in which tuplet loss and margin loss are combined with the embeddings of known and augmented examples, is trained to improve the overall performance of the model. Finally, after training, AMOSR is implemented using the class centers of known classes. Experiments on three automatic modulation datasets show that our model has better average performance than several mainstream methods in the field of computer vision.

This paper investigates a secure aerial reconfigurable intelligent surface (A-RIS) communication system, where user mobility, imperfect channel state information (CSI), and RIS phase errors induced by unmanned aerial vehicle (UAV) jitter significantly degrade performance. To address these challenges, we formulate a joint optimization problem for UAV trajectory, base station (BS) we propose abeamforming, and A-RIS beamforming to maximize the minimum secrecy energy efficiency (SEE), subject to constraints on user secrecy rates and UAV energy efficiency. To solve this highly non-convex problem, we propose a novel reinforcement learning framework termed IA-CSORL based on the twin-twin-delayed deep deterministic policy gradient (TTD3) architecture, which incorporates two novel modules. Specifically, we develop the phase-aware relativistic adaptive descent (PRAD) algorithm is proposed, which embeds the learning process into a conformal Hamiltonian system. By integrating gradient-based phase error correction and adaptive momentum adjustment, PRAD effectively counteracts phase noise and stabilizes training. Furthermore, we design an environment-state interactive attention (ESIA) mechanism to dynamically fuse UAV positioning and environmental features, enhancing state representation and deployment accuracy. Numerical results demonstrate that IA-CSORL significantly outperforms existing RL baselines in terms of both robustness and convergence performance. Moreover, IA-CSORL achieves superior beamforming accuracy under phase errors and CSI imperfections and provides a better trade-off between sum secrecy rate (SSR) and SEE, with performance gains becoming more significant as the number of RIS elements increases.

Low Earth Orbit (LEO) satellite communications have emerged as a promising paradigm for achieving ubiquitous coverage, driving the evolution of space-ground integrated networks (SGINs). The cell-free (CF) architecture has attracted significant attention in SGINs as the terrestrial segment for its potential to enhance capacity and connectivity. However, deploying CF necessitates numerous access points (APs), resulting in a prohibitive cost. To this end, we propose reconfigurable intelligent surface (RIS)- and simultaneous transmitting and reflecting (STAR)-RIS-assisted CF systems for SGINs, where part of the APs is replaced with cost-efficient RISs and STAR-RISs. Non-orthogonal multiple access (NOMA) is incorporated to improve connectivity under limited spectrum. We formulate transmit power minimization problems for both RIS- and STAR-RIS-assisted CF-NOMA in SGINs, jointly optimizing the active beamforming vectors of the satellite and APs, as well as the discrete passive beamforming (DPB) vectors of RISs/STAR-RISs. For the RIS-assisted scenario, a semi-definite programming (SDP)-based method is proposed to optimize the active beamforming vectors, while an enhanced integer linear programming (ILP) method is proposed to obtain the optimal DPB of RISs. To reduce complexity, we develop a low-complexity penalty-based SDP (PB-SDP) algorithm that achieves near-optimal DPB solutions. For the STAR-RIS-assisted scheme, both independent and coupled DPB for transmission and reflection are optimized alone with the active beamforming vectors. Numerical results demonstrate that: 1) The proposed systems outperform cell-based systems and heuristic optimization algorithms in terms of transmit power consumption; 2) The proposed PB-SDP algorithm achieves near-optimal performance with reduced complexity; 3) It is shown that DBP with 3 quantization bits achieves performance comparable to continuous passive beamforming (CPB) in both RIS- and STAR-RIS-assisted systems; 4) Also, it is shown that beyond a certain number of APs, further increasing the APs yields only limited transmit power consumption gains under a fixed total number of antennas.

In cognitive heterogeneous networks, multiple secondary transmitters (STs) co-exist with primary users (PUs) on the same frequency band channel through spectrum sensing. Due to inaccurate sensing of whether the channel is occupied, STs can cause interference to PUs, thereby affecting the transmission performance of PUs. This paper proposes a constrained deep reinforcement learning-based joint adaptive modulation coding and power selection (CDRL-JAMCPS) algorithm. The proposed CDRL-JAMCPS learns the interference patterns of STs to PUs through interaction with the environment and selects the modulation coding scheme and transmit power for future frames of PUs based on the learned patterns, aiming to maximize the transmission rate while reducing energy consumption. Furthermore, addressing the issue where existing optimization algorithms solely consider network transmission rates while neglecting data transmission quality, this paper proposes a reward function in Lagrangian form based on frame error rate (FER) constraints. By optimizing this reward function in its dual domain, the problem of poor data transmission quality is resolved. The simulation results demonstrate that the proposed algorithm achieves better transmission performance compared to other reinforcement learning algorithms in environments where signal interference is difficult to perceive. Meanwhile, compared to algorithms that do not consider transmission quality, our algorithm exhibits significant advantages in meeting FER requirements and improving data transmission quality.

Integrating vision and touch is key to understanding the physical world, but it faces two main challenges: effective multimodal fusion and high-fidelity tactile representation. This paper proposes a multimodal semantic communication framework based on foundation models through visual-tactile fusion. First, a multimodal enhancement fusion network extracts deep features from video to improve tactile recognition and semantic understanding. Second, a CLIP-driven framework, grounded in a tactile knowledge base, enhances the accuracy of tactile information transmission. An end-to-end model with joint source-channel coding further improves transmission efficiency. Finally, we introduce a tactile generative reconstruction method using ImageBind, which ensures high similarity in both visual features and pressure distribution. Experimental results confirm the effectiveness of our approach in semantic tactile reconstruction. Overall, the proposed method enables efficient, low-bit-rate communication with high semantic fidelity, offering a promising solution for visual-tactile fusion in real-world applications.

Specific emitter identification (SEI) is crucial in the Internet of Everything (IoE). Over the past decade, deep learning (DL) and broad learning (BL)-enabled SEI technologies have emerged. Recently, many researchers have begun exploring semi-supervised learning techniques to address the semi-supervised SEI (SS-SEI) problem with limited labeled RF signals. However, existing SS-SEI solutions often prioritize identification performance, leading to high computational overheads and lacking iterability. To overcome these challenges, this paper proposes a novel SS-SEI solution based on a learnable broad learning network (LBL). Initially, a pretrained DL-based SEI model is downloaded to the edge device. Meanwhile, an updatable BL-based SEI method is deployed locally on the edge device to identify unlabelled signals. When the LBL solution is operational, edge devices capture real-time unlabelled RF signals. The pretrained DL-based SEI method and the locally BL-based SEI method jointly identify these RF signals. The identification results and the new real-time RF signals are then used to update the weights of the BL-based SEI method at the edge devices. The LBL SS-SEI solution is validated using an open-source, large-scale, real-world automatic dependent surveillance-broadcast (ADS-B) dataset. Experimental results demonstrate that the proposed LBL solution offers significant advantages regarding SS-SEI performance.

In this study, we present an innovative architecture for blind modulation-type identification in single-antenna channels, specifically engineered for scenarios lacking transmitter cooperation and featuring time-varying spectrum occupancy. The proposed method integrates a lightweight Transformer-based deep learning architecture with a higher-order statistics-driven noise reduction module, designed to enhance feature discrimination in environments with poor signal clarity. Comprehensive testing demonstrates that the proposed approach significantly improves classification accuracy from 52% to 75% at 0 dB. The model achieves this with a highly compact footprint of only 0.228 M parameters and minimal computational overhead (0.0095 GFLOPs), highlighting its excellent balance of robustness and efficiency. The model consistently performs well across a broad range of signal-to-noise ratio, validating its generalization capability in challenging environments. By addressing the critical challenges of automatic modulation classification in non-cooperative and spectrum-constrained contexts, this work offers a scalable and efficient solution that supports intelligent spectrum awareness and facilitates robust cognitive communication in next-generation wireless networks.

To address the conflict between the limited availability of spectrum resources and the swiftly growing number of frequency equipment in the Internet of Vehicles, this article starts from the solution of dynamic access of radio equipment and studies the problem of power spectrum density prediction of different channels, which is called spectrum prediction. We first propose the graph structure learning problem of electromagnetic spectrum data under the graph contrastive learning (GCL) framework from the causal perspective, and establishes a graph structure representation model between channel signal activity rules. Then, we establish the statistical distribution models of different channels at fine resolution based on the Gaussian mixture model. Then, the statistical model is embedded as prior knowledge using a graph convolutional network (GCN), and the channel association features are mapped to the association knowledge embedding using a graph structure encoder. This article proposes a novel spectrum prediction architecture based on GCL and multiscale feature fusion GCN (CL-MFGCN) to mine the time-frequency implicit knowledge of spectrum data, and the above knowledge embedding is integrated. This article visualizes the channel association relationship in the form of a graph structure. The experimental results indicate that the CL-MFGCN, reduces the average MAE by 14.6% (from 1.436 to 1.226) and the average MAPE by 12.9% (from 0.017 to 0.0148) compared to the second-best Pyraformer model, while maintaining a lower model complexity.

Unmanned Aerial Vehicle (UAV) recognition using Deep Learning (DL) is critical for ensuring the safety of low-altitude airspace. However, the limited availability of labeled UAV signal data poses significant challenges to achieving high recognition accuracy and robustness. To address this, we propose a novel method, Self-Supervised learning with Self-Adaptive Pseudo-Labeling (SS-SAPL), designed to enhance UAV recognition performance. The method operates in two stages: a self-supervised pre-training stage and a semi-supervised fine-tuning stage. In the pre-training stage, contrastive learning with weak and strong data augmentations is employed to extract generic feature representations from all UAV signal samples. In the fine-tuning stage, Pseudo-Labeling (PL) is combined with a Self-Adaptive Threshold (SAT) and Self-Adaptive Fairness (SAF) mechanism to improve the accuracy of PSeudo-Labels (PSLs) and leverage both labeled and unlabeled data for refining feature representations. Simulation results demonstrate the effectiveness of our method. For UAV signals at 2.4 GHz with only 30 labeled samples, our approach achieves a recognition accuracy of 82.38%, outperforming state-of-the-art methods by at least 6.63%. In mixed-frequency scenarios (2.4 GHz and 5.8 GHz) with only 10 labeled samples, our method exceeds 92.13% accuracy, surpassing competitors by at least 4.63%. These results highlight the robustness and practical value of the proposed method in challenging environments.

Specific emitter identification (SEI) enhances wireless communication security by identifying specific devices or signals to monitor anomalies effectively. However, data scarcity and heterogeneity challenge traditional centralized methods and few-shot learning (FSL), which depend on centralized data. We propose a personalized decentralized federated FSL method (FedDePF) for SEI. FedDePF organizes edge devices into clusters, enabling local aggregation within clusters and global collaboration between cluster centers. This reduces server communication overhead and addresses data heterogeneity in distributed environments. Experiments show FedDePF significantly improves SEI performance in data-scarce scenarios, outperforming traditional decentralized methods, providing a secure and efficient solution.

Radio Frequency Fingerprinting Identification (RFFI) leverages signal processing to extract unique characteristics from wireless signals for device identification. In recent years, deep learning (DL) has significantly advanced signal identification, catalyzing progress in RFFI research. This paper proposes an enhanced RFFI method to manage variable-length signal inputs, typically problematic for neural networks such as convolutional neural networks (CNNs) and multilayer perceptrons (MLPs), by treating these signals as images to solve data formatting problems. The robust representation of the variable-length signal ultimately achieves over 90% accuracy, meeting the expected results. Furthermore, conventional DL-based RFFI methods require a comprehensive analysis of the entire RF signal, consuming significant computational resources and vulnerable to environmental variations. We address these issues by proposing an incremental learning (IL)-based RFFI method that allows dynamic model updates and improves recognition and generalization performance. Our method’s efficacy, tested on the power amplifiers (PA) dataset, enables real-time data stream processing.

Specific emitter identification (SEI) is a technique that identifies individual emitters based on the inherent characteristics reflected in the radio frequency signals due to the individual differences of the emitters. Deep learning (DL) has become the primary research method for identifying and authenticating wireless devices in SEI. However, in the real world, electromagnetic signals continuously change with the channel environment and time, causing models trained on datasets collected from known specific domains to exhibit significant performance degradation when applied to unknown channel environments. This limitation makes general DL methods unsuitable, and domain generalization (DG) becomes a key method to address this issue. To overcome the limitations of SEI identification performance across different scenarios, we propose a robust SEI method by mixing augmentation, named SigMix. Specifically, we innovatively introduce the Mixup method into the SEI task, mixing data from different source domains and then performing pairwise linear interpolation before using it for training the neural network. The SigMix method helps the model learn more comprehensive features by generating new samples in the training data, thereby improving the model’s generalization ability. To validate the effectiveness of the SigMix method, while also considering the impact of different receivers on identification performance, we evaluate a dataset spanning both time and receivers. The experimental results indicate that the average identification accuracy of the proposed SigMix method in unknown domains reaches 84.40%, significantly outperforming existing DG methods, demonstrating the robustness and generalization of our proposed SigMix method in SEI tasks. Our code is available for download at://github.com/frownean/SigMix.

In complex electromagnetic environments, targets that need to be interfered with often possess high levels of concealment and anti-interference capabilities. Additionally, due to the dynamic characteristics of these targets, interference tasks must be conducted within strict time constraints to ensure interference effect. In this article, we adopt a reconnaissance-first approach for concealed targets. After detecting the accurate location of the target, we deploy autonomous aerial vehicles (AAVs) to interfere with the targets. First, we established a AAV swarm task scheduling optimization model after considering constraints, such as target threat range, priority of reconnaissance and interference tasks, interference task time, and AAV energy consumption. Meanwhile, we model the anti-interference capability of the target as a threat range. Second, we propose a nondominated sorting genetic algorithm based on distance in the solution space and a dynamic parent selection strategy (DPSNSGA-II) to solve AAV resource scheduling optimization problem. The diversity of the population is increased and the situation of falling into local optima is reduced by improving the parent individual selection strategy, mutation strategy, and elite solution retention mechanism. Finally, we construct two data sets of varying sizes to evaluate the quality of solution sets and the convergence performance of the proposed algorithm. The simulation results indicate that the proposed DPSNSGA-II algorithm has better result for population diversity and convergence compared to state-of-the-art algorithms.

In smart wireless communication environments, specific emitter identification (SEI) technology has become a crucial means to ensure the security and stability of the wireless communication system. With the rapid increase in the number of Internet of Things (IoT) devices, traditional closed-set identification methods are no longer adequate to handle dynamic and complex wireless environments, particularly for unknown and rogue device intrusions. Consequently, open set SEI (OS-SEI) methods have emerged, which not only identify known devices but also effectively detect previously unseen rogue devices, thereby providing enhanced security and reliability. Therefore, this paper proposes an OS-SEI method based on reciprocal points learning and deep reconstruction learning (RPDRL). Firstly, by introducing an attention-based convolutional autoencoder (ACAE) with skip-layer connections (SC), which is used for deep reconstruction learning, along with reciprocal points learning (RPL), the extracted features become more robust. Furthermore, we design a classification algorithm that combines an appropriate fingerprint metric and extreme value theory (EVT), effectively achieving the detection of rogue devices and the classification of known devices. An open-source automatic dependent surveillance-broadcast (ADS-B) dataset and an intercom dataset are used to evaluate the RPDRL-based OS-SEI method. Experimental results indicate that the proposed method achieves an accuracy of 94.88% on the ADS-B dataset and 96.00% on the intercom dataset. Ablation experiments demonstrate the effectiveness of the efficient channel attention (ECA) modules and SC in the proposed network structure, as well as the efficacy of each loss function.

Specific emitter identification (SEI) is a passive physical layer authentication technology that mines subtle hardware differences between emitters to identify devices. However, traditional deep learning-based SEI is trained for scenarios with massive signal samples and performs poorly in sample-limited scenarios. To solve this problem, we proposed a robust few-shot SEI (FS-SEI) method using dual-level data augmentation, consisting of phase shift position prediction and manifold cutMix (P3MC). We perform data augmentation in both the sample space and the feature space to accelerate the complex valued time series lightweight adaptive network (CV-TSLANet) to learn robust features and use machine learning to identify ADS-B emitters. Our experimental results show that the performance of our proposed FS-SEI method reaches 90% when the number of samples per category is 30. We have open-sourced the proposed FS-SEI method at https://github.com/IcedWatermelonJuice/P3MC.

Specific Emitter Identification (SEI) in wireless communications enhances security by distinguishing devices through their unique RF signal impairments. Deep learning (DL) techniques have become instrumental and have attracted considerable focus in this domain. Nevertheless, significant challenges arise from pronounced domain distribution disparities and the lack of labeled signal for target domain emitters, complicating cross-domain individual emitter identification. This paper proposes an innovative domain generalization framework for SEI, which exploits both intra-domain and inter-domain invariant features to enhance cross-domain robustness. These features significantly enhance the model’s generalization capabilities: intra-domain invariants are captured through the use of Fourier phase information and knowledge distillation, while inter-domain invariants are derived via Maximum Mean Discrepancy (MMD) feature alignment. The proposed methodology exhibits strong performance across three domain generalization scenarios, utilizing datasets SUI-1, SUI-3, and SUI-5. Each dataset comprises signals from seven distinct transmitters, recorded over varying fading channels. This approach achieves an approximate 5% improvement over state-of-the-art SEI domain adaptation methods, highlighting its superior generalization capability. The code and datasets for the paper can be found at: https://github.com/ZHR-HEU/Cross-Domain-Generalization-for-SEI.

With the rapid advancement of Internet of Things applications, the demand for integrated sensing, communication, computing, and caching (ISC3) functions has surged. However, existing systems optimize these functions independently, leading to suboptimal resource utilization and performance bottlenecks. In this paper, we propose a multi-layer aerial ISC3 architecture where a versatile unmanned aerial vehicle (UAV) provides edge computing and caching services to ground wireless devices (WDs) alongside its radar sensing capabilities. A high-altitude platform maintains the complete service library, delivering required services to the UAV when cache misses occur. Partial data compression is employed to reduce uplink communication overhead, where WDs partially compress their offloaded task data before transmitting to the UAV. The objective is to minimize total system energy consumption by jointly optimizing time scheduling ratios, task offloading ratios, compression selection ratios, service caching decisions, and UAV trajectory, subject to task latency, sensing quality, energy budgets, and cache capacity constraints. An efficient iterative algorithm utilizing specialized optimization techniques such as Lagrangian duality and successive convex approximation is developed to solve the resulting mixed-integer nonlinear programming problem. Extensive simulations demonstrate fast convergence under diverse network configurations, with the proposed scheme consistently outperforming all baselines by 22.5%-67.0% in total energy consumption.

Unmanned aerial vehicle (UAV) swarm shows great potential as an effective tool for target tracking through completing complex tasks by collaboration of heterogeneous UAVs. However, UAV swarm scheduling faces challenges with poor quality communication and obstacles, especially in communication denial environment with multiple obstacles. To overcome these challenges, first, this paper proposes a scheduling slot model which divides the scheduling process into multiple time slots, allowing UAVs to communicate in communication slots while predicting instead of communication in communication denial slots. In communication denial slots, this model utilizes route fitting and two-stage Kalman filtering for UAV location prediction and optimizes UAV scheduling to align with predicted positions. In enabled slots, this model corrects position deviations to obtain precise UAV locations manually. Then, we propose an obstacle avoidance strategy to facilitate swarm scheduling for target searching under communication constraints. The obstacle avoidance strategy simplifies obstacles as regular hexagons and facilitates the determination of UAV avoidance routes by introducing intermediary points. Finally, to optimize UAV scheduling strategy, we propose a region co-evolution algorithm (RCEA), which emphasizes the collaboration among diverse individuals or populations. RCEA adopts area evaluation and Pareto strategy to enhance scheduling efficiency with following three steps. RCEA divides the overall scheduling region into multiple sub-regions, generates the foundational solution pool through the implementation of the area evaluation or Pareto strategy, and then proceeds to execute the region cooperation process base on the foundational solution pool. Simulation experiments are conducted to validate the performance of human-UAV interaction scheduling model with proposed scheduling methods and obstacle avoidance strategy. The simulation results demonstrate that RCEA outperforms other scheduling algorithms for UAV swarm in communication denial environment with multiple obstacles. Note to Practitioners—This paper addresses challenges inherent in real-world application scenarios, and the proposed algorithm has the potential to bring many benefits to practitioners. Firstly, the scheduling slot model can be applied not only to UAV swarm for target searching but can also be extended to other swarm devices for complex tasks with collaboration relying on communication support while facing poor quality communication or obstacles. Secondly, the proposed RCEA focuses on collaboration and region partitioning, the algorithm demonstrates remarkable scalability, effectively tackling challenges across diverse scales and complexities. Thirdly, the experimental scenarios can serve as a validation dataset for other peer researchers, and although the simulation experiment is based on a 2D movement model, this study still offers theoretical support applicable to a 3D movement model.

Automatic Modulation Open Set Recognition (AMOSR) has practical significance in detecting unknown classes. However, a challenge arises when unknown samples closely resemble known samples, posing a formidable task for accurate detection. A novel AMOSR framework based on multi-view discriminators’ joint judgment is proposed to handle this challenge. Firstly, utilizing signal domain knowledge, multi-dimensional features are extracted through varied signal time-frequency transforms and encoders, baesd on which multiple discriminators are created. Secondly, Constrained Clustering Prototype Loss and Geodesic Contrastive Loss are introduced to pretrain these discriminators, providing more space for unknown signals. Then, collaborative learning is employed to further fine-tune the aforementioned discriminators, enhancing information sharing between modalities. Furthermore, a set of indicators is constructed, and multi-criteria fusion is performed using the TOPSIS algorithm to evaluate the discrimination capabilities of different classifiers in both closed-set and open-set scenarios. Furthermore, a decision tree is constructed to segregate test signals into known and unknown classes, in which discriminators with higher confidence levels are given precedence. Finally, TOPSIS hierarchical ensemble pruning algorithm that considers diversity and open-set recognition capabilities is adopted to reduce model complexity while maintaining original performance. Extensive experiments conducted on modulation datasets demonstrate the superiority of this framework over state-of-the-art AMOSR results.

Accurate road network extraction from remote sensing images (RSIs) is essential for applications such as urban planning, map updates, and autonomous navigation. However, challenges such as complex backgrounds, varying spatial resolutions, and occlusions hinder traditional single-modality approaches, which often fail to capture comprehensive contextual information. To address these limitations, we propose DEFNet, a novel Dual-Layer Evidential Fusion Network for robust multimodal road extraction. DEFNet features two key modules: Cross-Attention Feature Interaction (CAFI) and Dual-Layer Evidential Fusion (DEF). The CAFI module facilitates adaptive multimodal interaction at both pixel and superpixel levels, enhancing feature fusion while mitigating noise. The DEF module, leveraging the Dirichlet framework and Dempster-Shafer Theory, performs uncertainty-aware fusion, improving prediction reliability and robustness. Extensive experiments on multiple benchmark datasets demonstrate that DEFNet consistently outperforms state-of-the-art methods in both accuracy and robustness, making it highly effective for multimodal road extraction in remote sensing applications. The codes can be downloaded from GitHub1.

With the rapid development of low-end maritime devices and shipborne sensors, traditional single-modal recognition can no longer meet the demand for high accuracy in maritime environment. As a result, multimodal learning, which integrates data from different sensors, has gradually become the main approach for maritime target recognition. However, due to variations in the environments and platforms where data is collected, the quantity of useful information provided by each modality differs, and certain modalities may even introduce noise. This discrepancy adversely affects the performance of multimodal fusion recognition. However, most existing multimodal maritime recognition methods overlook these differences, which constrains the performance of the recognition models. To address this concern, we propose a multi-modal contribution evaluation fusion network (MCEF-NET) to achieve efficiency-enhanced fusion for multimodal maritime target recognition. In this model, a Feature Filter Module (FFM) is introduced to effectively suppress irrelevant information, mitigate distribution discrepancies between modalities, and enhance the robustness of multimodal feature extraction. Furthermore, we design a Contribution-Rating Fusion (CRF) mechanism that dynamically allocates fusion weights according to the contribution of each modality’s features, thereby minimizing the influence of low-value modalities on the final fusion performance. The MCEF-NET was evaluated on the publicly available VAIS maritime infrared-visible multimodal dataset, exhibiting superior accuracy and computational efficiency compared to existing state-of-the-art methods.

Wireless Technology Recognition (WTR) distinguishes different wireless technologies by analyzing characteristic features extracted from radio signals. While deep learning (DL)-based methods are extensively used in WTR due to their ability to extract hidden data features and make accurate classification decisions, their application is often limited by excessive power consumption. In this paper, we propose a novel WTR method that addresses this challenge using a time-frequency feature fusion spiking neural networks (TFSNN) framework. Our approach combines information from both the time and frequency domains to enhance feature extraction. Experimental results demonstrate that our model performs exceptionally well at high signal-to-noise ratios on open-source datasets. Specifically, at a sampling rate of 15 Msps, our method achieves a recognition accuracy of 99.85%. Even when the sampling rate is reduced to 10 Msps, the average accuracy remains 1.61% higher than the best existing method. Additionally, our method reduces energy consumption by about half compared to most current methods. These results emphasize the effectiveness and necessity of time-frequency domain feature fusion (TFSF) in WTR.

Radio frequency fingerprint (RFF) identification is a promising solution for Internet of Things (IoT) device authentication. However, this technique encounters practical challenges such as noise interference, channel coupling, and open-set recognition (OSR). This paper proposes a unified RFF-OSR framework to jointly address these problems in complex environments. Firstly, the framework mitigates the noise interference by employing a low-pass filter-integrated autoencoder, where the low-pass filter is used to obtain a “quasi-clean” signal as the autoencoder reference, thereby reducing the demand for ideal signals. Then, the channel influence on RFF is modeled as three types: frequency offset, phase noise, and amplitude distortion. Based on this model, parameterized channel augmentation is performed to improve the generalization ability of RFF identification in unknown channel scenarios. In terms of OSR, instead of a coarse-grained uniform probability threshold for rogue device recognition, we conduct independent similarity judgments for all legitimate classes, each with an individual threshold. It effectively reduces information loss in the feature probability transformation and increases OSR performance. Under additive white Gaussian noise (AWGN) and multipath channel conditions, our method achieves OSR accuracies of 99.37% and 97.05% in ZigBee device identification, respectively, which demonstrates the effectiveness of our approach.

Radio Frequency Fingerprinting (RFF) has emerged as a vital technique for enhancing Physical Layer Authentication (PLA) in New Radio (NR) networks. Unlike cryptographic methods, RFF leverages device-specific signal impairments to uniquely identify transmitters. Deep Learning (DL) advances have improved PLA, though challenges persist due to communication channel dynamics and device state changes. In this study, we propose a novel framework that integrates 5G NR protocol-specific structures and channel knowledge via SRS-based CSI to generate relative RFF features. Through a tailored frame design and carefully engineered processing pipeline, we achieve cross-domain stability and improved robustness against time-varying conditions. By applying regularization techniques (e.g., mixup) during training, our method further mitigates model overfitting and domain bias. Simulation and real-world SDR experiments, using data from 9 ADALM-PLUTO devices, validate the approach’s effectiveness. The proposed system attains recognition accuracies of 99.878%, 93.376%, 86.325%, and 66.558% in intra-domain, cross-channel, cross-time, and cross-scenario tests, respectively, highlighting its potential to substantially enhance physical layer security in NR-based networks.

Specific emitter identification (SEI) is crucial in the Internet of Everything (IoE). Over the past decade, deep learning (DL) and broad learning (BL)-enabled SEI technologies have emerged. Both DL- and BL-based SEI methods rely on extensive radio frequency (RF) signal samples and corresponding labels, but labeling unknown signals is a considerable overhead and costly task. Consequently, many researchers have begun exploring semi-supervised learning techniques to address the semi-supervised SEI (SS-SEI) problem with limited labeled RF signals. However, existing SS-SEI solutions often prioritize identification performance, leading to high computational overheads and lacking iterability and scalability. To overcome these challenges, this paper proposes a novel SS-SEI solution, termed deep cloud and broad edge (DCBE). This approach integrates a DL-based SEI method at the cloud server with an updatable BL-based SEI method at the edge node. Initially, several DL-based SEI models are trained using labeled historical data at the cloud server. Meanwhile, an updatable BL-based SEI method is deployed locally on the edge node to identify unlabelled signals. When the DCBE solution is operational, edge nodes capture real-time unlabelled RF signals. The pre-trained DL-based SEI method and the locally BL-based SEI method jointly identify these RF signals. The identification results, along with the new real-time RF signals, are then used to update the weights of the BL-based SEI method at the edge nodes. The DCBE SS-SEI solution is validated using an open-source, large-scale, real-world automatic dependent surveillance-broadcast (ADS-B) dataset. Experimental results demonstrate that the proposed DCBE solution offers significant advantages in terms of SS-SEI performance, reduced computational overhead without GPU dependency, and system robustness in complex environments.

Radio map estimation (RME) is a crucial method for analyzing spectrum space utilization and network coverage, serving as an essential tool for the mobile communication. However, physical constraints, security, privacy, and other issues often render some areas inaccessible, resulting in extremely sparse and unevenly distributed measurement data. To address these challenges, we propose a multimodal feature fusion graph convolution network (MFFGCN). The model incorporates a dual-encoder architecture with an adaptive multi-feature fusion module to exploit environmental information and learn the shadowing effects of radio-signal propagation. We then convert the coarse estimation into regional feature patches and construct a graph over these patches. A graph neural network aggregates contextual information among them, thereby alleviating the impact of uneven spatial sampling. Extensive experiments on open datasets demonstrate that our method achieves state-of-the-art performance, effectively reducing the effects of uneven sampling.

Automatic modulation classification (AMC) is a key technology in cyber-physical systems (CPSs), which enables the monitoring and identification of communication signals exchanged between devices. One of the most recognized solutions for the AMC is deep learning (DL), which can automatically learn and extract feature representations in signals. However, data-driven DL models are susceptible to adversarial examples, which can cause significant instability in the CPS. To tackle this issue, in this article, we examine the distribution shift between original signals and adversarial examples from a domain distribution perspective and present a system model for addressing the defense problem. We propose the adversarial domain generalization defense (ADGD) framework. The ADGD framework adopts a dual-stream architecture with the AMC as its central task, and extracts and constrains the maximum mean discrepancy distance between the task-relevant features of original signals and adversarial examples to reduce the distribution shift and improve the adversarial robustness. Comprehensive experiments and ablations were conducted to demonstrate the superiority of the proposed ADGD framework on the RML2016.10a and miniRML2018.01a datasets. The results indicate that the ADGD framework shows promising results in improving the adversarial robustness of AMC systems, which is crucial for the stability of the CPS.

Given the exponential surge in wireless devices and data traffic, a key objective for forthcoming wireless communication systems lies in reducing energy consumption, thereby adhering to the emerging trend of green communication. Thus, devising an energy-efficient resource allocation scheme for Heterogeneous Networks (HetNets) is of utmost importance. In this paper, on the purpose of reducing energy consumption while ensuring users’ Quality of Service (QoS) requirements, we construct an energy-efficient optimization function for joint allocation of sub-channels, power and wireless backhaul bandwidth (JASPW) in NOMA-assisted HetNets with wireless backhaul considering imperfect channel state information (CSI), which poses non-convex and hybrid nonlinear challenge, providing an un-affordable computational complexity. Unlike the previous approach of decomposing the JASPW issue into several sub-convex problems, to tackle the problem efficiently, we first give the closed-form expressions through the derivation of the outage probability constraints, thus transforming the problem into a deterministic and convex one, subsequently, we propose a novel quantum-inspired equilibrium optimizer (QEO) algorithm to allocate the joint resource simultaneously, thereby obtaining the optimal resource allocation solution. Simulation results indicate that the proposed QEO yields an outstanding performance over other strategies in different communication scenarios.

Specific Emitter Identification (SEI) is a critical component of the Industrial Internet of Things (IIoT), enabling effective identification and validation of unauthorized communication devices, thereby preventing malicious interference and signal spoofing. However, SEI methods based on deep learning involve significant computational overhead, and SEI methods based on feature engineering require specialized expertise for feature design, limiting their ability to capture complex patterns. In this paper, we propose a data-knowledge dual-driven adaptive feature fusion approach for specific emitter recognition. Specifically, we present an adaptive feature fusion strategy that integrates domain experts’ prior knowledge with the complex feature recognition capability of deep learning models to achieve efficient SEI classifiers. The approach is evaluated using Automatic Dependent Surveillance-Broadcast (ADS-B) data. The experimental results demonstrate that the proposed method achieves a higher level of identification accuracy and lower time complexity.

Automatic Modulation Open Set Recognition (AMOSR) is a crucial technological approach for cognitive radio communications, wireless spectrum management, and interference monitoring within wireless networks. Numerous studies have shown that AMR is highly susceptible to minimal perturbations carefully designed by malicious attackers, leading to misclassification of signals. However, the adversarial security issue of AMOSR has not yet been explored. This paper adopts the perspective of attackers and proposes an Open Set Adversarial Attack (OSAttack), aiming at investigating the adversarial vulnerabilities of various AMOSR methods. Initially, an adversarial threat model for AMOSR scenarios is established. Subsequently, by analyzing the decision criteria of both discriminative and generative open set recognition, OSFGSM and OSPGD are proposed to reduce the performance of AMOSR. Finally, the influence of OSAttack on AMOSR is evaluated utilizing a range of qualitative and quantitative indicators. The results indicate that despite the increased resistance of AMOSR models to conventional interference signals, they remain vulnerable to attacks by adversarial examples.

Lying posture recognition is of great significance for pressure ulcer prevention, obstructive sleep apnea syndrome, and sleep quality assessment. Correct lying posture is particularly important for certain special patients as it can shorten the course of the disease and accelerate recovery. This paper discusses the transfer effects of convolutional neural networks based on two different signal processing methods, AlexNet and InceptionTime, for the problem of lying posture recognition using piezoelectric signals collected by the SleepMatrix@ device. Three different transfer strategies are applied to both networks to transfer the knowledge learned from a 5cm mattress thickness to the task of classifying 20cm mattress thickness in a semi-supervised scenario. Ultimately, applying the Maximum Classifier Discrepancy do-main adaptation method on InceptionTime achieved an accuracy of 77.9%, which represents a significant improvement compared to the traditional fine-tuning method.

In recent years, with the rise of deep learning, it has become a hot research topic to combine time-frequency analysis technology with deep learning to recognize radar signals. For the application of deep learning in radar signal recognition, however, the discovery of adversarial examples poses a tremendous security risk. Based on experiments, it appears that the radar signal recognition model based on the time-frequency image have been shown to be less vulnerable to adversarial attack methods based on time domain. Therefore, we propose a cross-modal attack (CMA). Firstly, we establish a surrogate model architecture locally, including three parts: time-frequency analysis, data quantization, and classifier. Secondly, we train this architecture as a whole and generate adversarial examples utilizing the trained surrogate model architecture parameters and adversarial attack methods. Finally, we carry out the CMA on the radar signal recognition model based on the time-frequency image by adding adversarial perturbations to the original signal. According to experimental results, the CMA can reduce the model recognition accuracy by more than 30%, demonstrating good attack performance, when the perturbation strength is 0.1 and the signal-to-noise ratio is 0 dB.

Specific emitter identification(SEI) plays an integral role in network security. In recent years, deep neural networks (DNNs) have demonstrated significant success in various application scenarios. The robust feature extraction capabilities of DNNs have led to advancements in SEI. However, it has been shown that DNNs are susceptible to adversarial attacks. The proposal of well-performing adversarial attacks is conducive to improving the security of SEI with DNN-based models. This paper introduces an universal black-box adversarial attack algorithm, named UBBA, for SEI with DNN-based models. The experimental findings indicate that this universal black-box adversarial attack algorithm substantially reduces the identification accuracy of SEI models. Given a sufficient number of queries, the proposed algorithm achieves an attack effect similar to that of the universal adversarial perturbations (UAP), a universal white-box attack algorithm. Additionally, the results demonstrate that when the perturbation signal is not synchronized with the signal under attack, the proposed algorithm outperforms the fast gradient sign method (FGSM).

In this paper, we introduce an innovative Radio Frequency Fingerprinting (RFF)-based device authentication scheme for the Internet of Things (IoT), a network marked by extensive interconnections and interactions among various entities. Our approach, designed for an open and dynamic communication environment, not only identifies devices encountered during training but also effectively rejects those not previously seen. The scheme employs a hypersphere projection for feature embedding, strategically avoiding the need to optimize intra-device variations in the radial direction. It uses a K-Means-based binary classifier for initial device assessment based on cosine similarity scores, followed by a SoftMax classifier for precise identification of known devices. Our extensive numerical analysis confirms that this method delivers superior performance, setting a new benchmark in RFF authentication for IoT security.

In the context of emerging 6G technology challenges, this paper introduces the LSMFF-AMC approach, leveraging multimodal feature fusion (MFF) with Long-Short range attention (LSRA) to enhance automatic modulation classification(AMC). The method significantly boosts classification accuracy by employing convolutional neural networks (CNN) for diverse modal feature extraction and integrating LSRA for comprehensive feature combination. Our experiments demonstrate an increase in accuracy from 88% to nearly 97%, outperforming traditional single-modal approaches. Additionally, a convergence analysis of the training loss function reveals LSMFF-AMC's superior and faster convergence compared to standard AMC methods.

Deep learning-based recognition of Unmanned Aerial Vehicles (UAVs) has become a critical tool for enhancing UAV control through improved accuracy and efficiency. However, the practical deployment of these systems is often hampered by the costly acquisition and scarcity of annotated data, which challenges the generalizability of the models. To address this bottleneck, our study employs semi-supervised (SS) learning strategies to exploit the untapped potential of unlabeled data effectively. We introduce a novel semi-supervised approach for UAV recognition that utilizes a self-adaptive threshold mechanism. This technique features Self-adaptive Threshold (SAT) and Self-adaptive Fairness (SAF) mechanisms, designed to dynamically optimize threshold values and guarantee a balanced distribution of labels among various classes. Our method is rigorously evaluated against a comprehensive, open-source UAV dataset. The findings indicate that our semi-supervised model significantly outperforms existing supervised learning models, static threshold SS approaches, and generative models, especially in scenarios with a limited amount of labeled data. These results underscore the effectiveness of our approach in enhancing the practicality and applicability of UAV recognition systems.

Radar emitter identification (REI) is a crucial function of electronic radar warfare support systems. The challenge emphasizes identifying and locating unique transmitters, avoiding potential threats, and preparing countermeasures. Due to the remarkable effectiveness of deep learning (DL) in uncovering latent features within data and performing classifications, deep neural networks (DNNs) have seen widespread application in REI. In many real-world scenarios, obtaining a large number of annotated radar transmitter samples for training identification models is essential yet challenging. Given the issues of insufficient labeled datasets and abundant unlabeled training datasets, we propose a novel REI method based on a semi-supervised learning (SSL) framework with virtual adversarial training (VAT). Specifically, two objective functions are designed to extract the semantic features of radar signals: computing cross-entropy loss for labeled samples and virtual adversarial training loss for all samples. Additionally, a pseudo-labeling approach is employed for unlabeled samples. The proposed VAT-based SS-REI (SS-VAT) method is evaluated on a radar dataset. Simulation results indicate that the proposed SS-VAT method outperforms the latest SS-REI method in recognition performance.

In the field of Industrial Internet of Things (IIoT) security, Specific Emitter Identification (SEI) plays a crucial role. Recent advancements have seen a rise in the adoption of machine learning (ML) and deep learning (DL) techniques in SEI methodologies, recognized for their impressive effectiveness. However, DL-based SEI methods often incur significant computational costs, making them less suitable for IIoT environments. Similarly, conventional ML-driven SEI approaches depend heavily on feature extraction and employ complex, often redundant classifiers. These methods typically lack in optimizing feature integration and computational efficiency. To overcome these limitations, we introduce an advanced DL-based SEI methodology that focuses on harnessing signal features more effectively. Our method centers around an Adaptive Feature Combination (AFC) strategy, enhanced by an attention mechanism, to develop a more efficient SEI classifier. The essence of our approach is the strategic exploration of adaptive feature combinations, aiming to fine-tune the SEI classifier for peak performance. Simulation results demonstrate that our AFC algorithm outperforms existing SEI methods in both identification accuracy and computational efficiency. This breakthrough offers a viable and promising solution for implementing SEI in IIoT scenarios, achieving heightened effectiveness without sacrificing computational resources.

Automatic modulation classification (AMC) plays an important role in the field of physical layer security, providing a new way to enhance the security of data transmission and anti-interference ability. Recently, deep learning (DL) has been widely applied in radar and communication signal classification, which requires sufficient labeled training samples to achieve high classification accuracy. However, in non-cooperative situations, it is difficult to obtain a large number of labeled signal samples. Therefore, we propose a novel few-shot AMC method using architecture search and knowledge transfer. This method first utilizes the state-of-the-art neural architecture search algorithm, A-DARTS, to automatically search for the optimal network structure (i.e., Auto-MCNet) based on the auxiliary sample set. Then, the Auto-MCNet model is pre-trained on the auxiliary dataset to explore prior knowledge about signal classification. Finally, we transfer this knowledge to a few-shot training dataset and fine-tune the Auto-MCNet model to enhance its generalization ability. The simulation results show that compared to advanced competitors, Auto-MCNet achieves higher classification accuracy with lower model complexity.

Radiofrequency signal identification (RSI) provides a critical security solution for device authentication in the Internet of Things (IoT), characterized by extensive interconnections and interactions among numerous entities. By analyzing received radiofrequency signals, device-specific features are extracted at the receiver and used for identification. In a dynamic and ever-changing communication environment, where some devices not visible during the training process may appear during testing, a robust RSI method must not only identify devices encountered during training but also reject those that were not. In this article, we propose an open-set RSI method based on hypersphere manifold embedding. This approach leverages hypersphere projection for radiofrequency signal feature extraction on a hypersphere manifold, thereby avoiding the need to optimize intradevice variation in the radial direction. Additionally, we introduce an open-set identification approach based on generalized Pareto distribution, which does not rely on any radiofrequency signals from unknown devices. Extensive experimental results demonstrate that the proposed method achieves state-of-the-art identification performance.

Deep learning (DL)-based automatic modulation classification (AMC) has made breakthroughs and is generally used for signal detection and recognition in wireless communication systems, unmanned aircraft vehicle (UAV) systems, and other fields. However, high storage and computational demands limit its use in resource-constrained UAV systems. This paper presents an AMC method featuring a streamlined design with lower computational needs, using the ultra-lite convolutional neural network (ULCNN). This innovative model combines data augmentation, complex-valued convolution, separable convolution, channel attention, and shuffling techniques for enhanced performance. The proposed ULCNN model balances efficiency and accuracy, with simulations showing it achieves 62.47% accuracy on the RML2016.10a dataset using only 9,751 parameters. Furthermore, we evaluated the actual speed of ULCNN on a Raspberry Pi, an edge platform with roughly equivalent computing power to a conventional UAV, achieving an inference speed of only 0.775 ms per sample. This high performance, coupled with a significantly smaller model size, underscores the potential of ULCNN for integration into resource-constrained UAV systems, thereby enabling rapid and efficient data processing.

The detection of abnormal electricity load data using big data analysis technology has garnered considerable attention from the academic community. However, traditional methods often require ample labeled data to train the model which increases the cost. This article tackles the issues of high model training costs and poor transferability associated with traditional supervised learning methods. We propose a contrastive learning network-based abnormal electricity load detection method (ED-CLN). First, our model enhances training samples through data augmentation and learns the similarities and differences between samples from temporal and contextual perspectives of the sample sequence. This approach enables the acquisition of common feature representations for model training tasks. Then, the weight data of the model trained using unlabeled data is migrated to the supervised training model. Finally, the trained source model is fine-tuned for abnormal electricity load data detection tasks to improve the overall learning effectiveness of the model. The results demonstrate that ED-CLN outperforms both supervised learning methods and various classic contrastive learning methods in anomaly detection, which can effectively identify the abnormal electricity load data.

3-D radio maps provide significantly richer information than their 2-D counterparts in spectrum cartography. However, reconstruction methods for 3-D radio maps remain underexplored. Classic methods, such as spatial interpolation and matrix completion, can be adapted for 3-D scenarios, but they are often computationally intensive and require a substantial number of sampling measurements. To address these challenges, we propose a novel and efficient 3-D radio map reconstruction paradigm inspired by cross tensor approximation (CTA). During the measurement phase, only piecewise straight-line paths are required, making this method well-suited for the flying trajectories of unmanned aerial vehicles (UAVs). In the reconstruction phase, we utilize the inherent tensor structure of 3-D radio maps by employing the fiber sampling tensor decomposition (FSTD) algorithm, which ensures high-quality and computationally efficient reconstruction from the measurements. To further reduce the number of measurements, we introduce a new algorithm called interpolation-integrated FSTD (II-FSTD). This algorithm builds on the original FSTD yet exploits the smoothness of radio maps to incorporate interpolation, thereby reducing the required measurement frequency. Extensive experimental results demonstrate that the proposed paradigm can reconstruct 3-D radio maps with high quality, using fewer measurements and less computational time compared to state-of-the-art techniques. Notably, in scenarios with lower measurement frequency, II-FSTD outperforms other methods, achieving superior reconstruction performance.

Specific Emitter Identification (SEI) is a critical technology for physical layer authentication in wireless communications and the Internet of Things. Leveraging the inherent and hard-to-forge characteristics of Radio Frequency Fingerprinting (RFF), SEI has gained significant attention. Recent advancements in deep learning have propelled SEI methods to new heights of identification performance. However, these methods are often constrained by their reliance on large datasets, posing challenges in real-world scenarios with limited samples. Addressing this issue, this paper proposes an enhanced SEI approach tailored for limited sample environments, employing Double Implicit Regularization (DIR). Our proposed method, DIR-MRAN, utilizes a Multi-Scale Residual Attention Network (MRAN) to extract features effectively from limited samples. The DIR strategy enhances model generalizability by incorporating Sample-wise Implicit Regularization (SIR) and Label-wise Implicit Regularization (LIR), which respectively facilitate sample expansion and label smoothing. We evaluated DIR-MRAN on two real-world datasets, achieving an impressive 95.34% accuracy on the PA dataset and outperforming comparative methods by 26.4% on the ADS-B dataset.

With the development of wireless technology and the Internet of Things (IoT), managing limited spectrum resources has become crucial. As the IoT landscape grows, more effective wireless technique classification (WTC) is imperative. Traditional deep learning (DL) methods for WTC, while robust, suffer from high computational complexity, making them less practical for real-time applications. Addressing this, our article introduces a novel solution, the multifeature fusion broad learning network (MFBLN) for WTC, which employs broad learning (BL). Here, several features of the wireless technique are inputted into a multibranch module to obtain classification information from different perspectives. Then, those features are integrated, which performs better than the typical BL structure. Our simulation results show that our proposed MFBLN method performs well on the classic WTC data sets in the intelligent transportation system (ITS) band. The performance of MFBLN at a 25 Msps sampling rate shows an improvement of approximately 0.67%, coupled with a significant reduction in floating-point operations by 81.93%, and 72.53% decrease in training time. Additionally, the ablation studies further affirm the necessity of each module within the MFBLN framework, underscoring their collective contribution to its enhanced efficiency and effectiveness.

In this article, a hybrid radio frequency-visible light communication and positioning (RF-VLCP) system is designed, which can support high-data rate communication and high accuracy positioning with good energy efficiency (EE) performance. The hybrid system uses two links for downlink communication, namely, radio frequency (RF) and visible light communication (VLC) links, and employs visible light positioning (VLP) technology for positioning. Furthermore, an optimization problem is developed to allocate power for VLC and VLP links and to design beamformer for the RF transmitter. By doing so, the EE of the hybrid system is maximized while the Cramer–Rao Lower bound (CRLB) of the positioning error and the minimum data rate of the communication are guaranteed. A two-step algorithm is proposed to tackle the formulated optimization problem, which first determines the power allocation of the VLP signal and then obtains the power allocation of the VLC signal and the beamformer of the RF transmitter. Numerical results demonstrate the advantages of the proposed two-step algorithm over the existing algorithm in terms of computation speed. In addition, the EE performance of the hybrid system is evaluated under different data rate and positioning accuracy requirements. Besides, we also show that the hybrid RF-VLCP system is more energy efficient compared to standalone RF and VLP technologies.

Unmanned aerial vehicles (UAVs) can be deployed in the areas where traditional network infrastructure is insufficient or absent because of flexibility and collaboration. The deployment of edge intelligence on UAVs in UAV-assisted mobile-edge networks significantly enhance data processing efficiency, which is a critical factor for applications requiring delay-sensitive data processing in the areas mentioned above. However, the limited energy capacity poses a challenge when running complex deployment algorithms. Therefore, lightweight network model is essential for deployment algorithms, as it significantly reduces energy and time consumption. In this article, we propose a cooperative framework-based knowledge distillation to compressed deep neural network (DNN). The subnetworks collaborate to train interactive node parameters, resulting in the optimal evolution of the student network. Then, we introduce a novel result-driven model training approach for simulation data sets. To further enhance efficiency and significantly reduce overall latency, we meticulously refine the internal architecture of the knowledge distillation algorithm. We incorporate a collaborative evolution mechanism into the core of the algorithm, utilizing multinetwork and subnetwork learning to facilitate knowledge transfer, and incorporate some optimization mechanisms into the framework. Finally, we perform a series of experiments to acquiredata sets and conduct algorithm simulation analysis to evaluate the proposed method. The results demonstrate that our work achieves good research results.

Deep learning (DL), renowned for its superior feature extraction capabilities, has remarkably succeeded in specific emitter identification (SEI), especially when supported by high-quality labeled data. However, obtaining accurate signal labels in complex electromagnetic environments is challenging, and manual labeling is prone to errors, underscoring the need for robust DL-based SEI methods that can handle label noise. These methods prevent neural networks from overfitting noisy labels, thereby boosting identification performance. Yet, research in this area is still limited. Our study introduces a robust label-noise SEI approach and the sample selection and regularization (SSR) method. This involves a two-stage adaptive sample selection (ASS) driven by confidence learning. The first stage entails coarse-grained separation of true and false labels through direct deep neural network (DNN) training. In the second stage, semi-supervised learning (SSL) utilizes a regularization-inspired loss, incorporating label smoothing regularization (LSR) and entropy minimization (EM), for fine-grained sample selection. The DNN is ultimately trained on precisely selected true-labeled samples. Comparative experiments on the automatic dependent surveillance-broadcast (ADS-B) and Wi-Fi data sets demonstrate that our SSR method outperforms the existing methods in identification accuracy, particularly at a 20% label-noise ratio, achieving 86.00% accuracy with the ADS-B data set, and 99.38% with the Wi-Fi data set. The code is available at:https://github.com/sleepeach/SSR-SEI.

Thanks to the development of the Internet of Things, a large number of sensors have been deployed, resulting in the collection of abundant time series data. These data series contain potential space-time connection and noise at the same time. Prediction and health management (PHM) aim to provide decision support based on the health state of an entire engineering system. Additionally, the predicting future values also contribute to decision making and fall under the category of time series forecasting. While the existing methods focus on capturing the correlation between the data and reducing the impact of noise, they often fail to fully utilize the noise present in the time series data. In this article, we propose a framework for multivariate time series forecasting called GAGNN. This framework integrates the idea of a generative adversarial network and a graph neural network organically. It adopts the graph neural network as the generator and a multilayer perceptron as the discriminator. Finally, the prediction module is used to obtain the prediction results. The generator, discriminator, and prediction module are trained jointly. Our experimental results demonstrate that our model outperforms the original model on most benchmark data sets and achieves the best results on three out of six benchmark data sets.

Deep learning (DL)-based automatic modulation classification (AMC) is increasingly utilized in wireless applications, particularly within the Internet of Things (IoT) ecosystem. However, the open data collection for these systems can lead to vulnerabilities, as the data sets are susceptible to malicious manipulations, potentially resulting in backdoor attacks. In this article, we propose a novel wavelet domain frequency steganography (WDFS) backdoor attack method to demonstrate this security flaw, designed explicitly for misleading AMC. This method employs discrete wavelet transform and singular value decomposition to segment signals into distinct wavelet domain frequency components. We embed the backdoor trigger directly into these components, ensuring it is sample-specific and undetectable. Extensive testing shows that our WDFS method outperforms existing methods in terms of attack efficiency and stealth and successfully evades several advanced backdoor defense mechanisms, demonstrating its robustness. These findings highlight the urgent need for enhanced security measures in AMC systems within the artificial intelligence domain.

Specific emitter identification (SEI) has emerged as a notable device authentication technology, distinguishing various emitters through the unique radio frequency fingerprint (RFF) inherent in wireless devices. Traditional SEI methods, often hindered by time-consuming manual feature extraction, struggle with complex encrypted signals. The advent of deep learning, with its robust feature extraction capabilities, has significantly advanced SEI, yet it typically demands extensive radio frequency signal samples and falters with limited (i.e., few-shot) samples. Our proposed few-shot SEI (FS-SEI) approach, integrating neural architecture search (NAS) and advanced deep transfer learning (DTL), adeptly identifies few-shot long-range (LoRa) devices. This method begins with NAS to autonomously tailor optimal network architectures for SEI tasks, followed by pre-training on extensive auxiliary datasets to extract general RFF features of LoRa devices. Transfer learning then fine-tunes these features for distinctiveness with compact intra-class distances. By only utilizing few-shot LoRa data for final parameter adjustments, the classifier rapidly assimilates new categories. Simulations confirm our FS-SEI method’s superior accuracy over classical approaches, with visualized feature analysis underscoring its distinguishing and generalizing prowess.

Automatic modulation classification (AMC) holds a significant position in physical-layer security, offering an innovative method to enhance the security of data transmission and anti-interference ability. Recently, deep learning (DL) has seen extensive application in radar and communication signal classification, which requires sufficient labeled training data to ensure great classification performance. However, obtaining a significant amount of labeled samples is extremely challenging in complex and ever-changing electromagnetic environments. Therefore, we propose a novel few-shot AMC method using architecture search and knowledge transfer. This method first utilizes an advanced neural architecture search algorithm,$\Lambda $-DARTS, to automatically search for the optimal network structure (i.e., Auto-MCNet) based on the auxiliary sample set. Then, the Auto-MCNet model is pretrained on the auxiliary data set to explore prior knowledge about signal classification. Finally, we transfer the knowledge to a few-shot training data set and fine-tune the Auto-MCNet model to enhance its generalization ability. The simulation results indicate that when the signal-to-noise ratio (SNR) is greater than 0 dB and the shot of each class is 3 and 10, the average accuracy of the proposed Auto-MCNet is higher than 81% and 90%, respectively. Moreover, compared to advanced competitors, Auto-MCNet achieves higher classification performance with lower model complexity.

In cognitive radio networks, cooperative spectrum sensing (CSS) is a key approach to effectively discover spectrum opportunities for secondary users. However, due to the presence of malicious nodes, CSS faces significant challenges in the trust issue of sensing results caused by spectrum sensing data falsification and the privacy leakage of sensing nodes. In this article, we develop a trustworthy and privacy-preserving CSS solution based on blockchain, TaP2-CSS. It achieves the transparency and trustworthiness in exchanging and fusing sensing reports and preserves privacy of sensing nodes. More specifically, a fusion scheme is proposed to realize the high defense capability against the spectrum sensing falsification attack launched by lurking and persistent malicious nodes. Furthermore, to address privacy threats of sensing nodes, we propose a privacy-preserving sensing scheme based on dynamic sensing time for resource-constrained sensing nodes. It effectively limits the location information leaked by sensing reports without the need for complex cryptographic computation and protocol interaction. Comprehensive evaluation and comparison show that the proposed solution achieves high sensing accuracy in the presence of malicious nodes while preserving the privacy of sensing nodes.

Real-time monitoring and prediction of damages form the basis of Artificial Intelligence for IT Operations (AIOps) in mechanical equipment, relying on the Internet of Things (IoT). Acoustic emission technology is widely used in Prognostic and Health Management (PHM) to monitor the growth of fatigue cracks online. Extracting and selecting high-quality acoustic emission features are crucial to the accuracy of fatigue crack prediction, as it helps establish the relationship between these features and fatigue crack growth (FCG). However, traditional artificially selected acoustic emission features are seriously affected by the signal amplitude threshold. To solve the above problems, we proposed a fatigue crack prediction model based on the improved stacked autoencoder and attention mechanism (SSAE-AM). The model can adaptively extract acoustic emission features that are strongly correlated with FCG by adding a supervision module to the stacked autoencoder (SAE) and using the attention mechanism (AM)to weight the fusion features. On this basis, the relationship model between acoustic emission features and FCG is established for crack prediction. Finally, we verify the validity of the model through experiments that monitor fatigue crack growth under different loading stresses. Compared with models that use other acoustic emission statistical features for crack prediction, the model proposed in this paper can achieve better prediction accuracy.

Specific emitter identification (SEI) plays a crucial role in the security of the Industrial Internet of Things (IIoT). In recent years, research on applying deep learning (DL) methods for signal identification has mushroomed. However, DL-based SEI methods rely on a huge amount of training data and powerful computing devices, limiting their application scenarios. In addition, DL models are considered black box models with poor interpretability. To solve the above problems, this paper proposes a novel few-shot SEI solution using knowledge graph-driven incremental broad learning (KG-IBL). Specifically, this paper uses a deep belief network (DBN) to dig deep into features and expand the broad structure with additional enhancement nodes. Furthermore, the proposed KG-IBL does not need to retrain all data to achieve dynamic incremental update learning. To our knowledge, this is the first endeavor to integrate KG with broad learning for addressing the few-shot SEI problem. The experimental results demonstrate that the proposed KG-IBL surpasses existing incremental methods in both identification performance and computational overhead. Last but not least, the accuracy of the proposed KG-IBL is 97.5%, which is only 1.67% lower than the theoretical upper limit, and the training time is nearly 267 times lower than that of deep learning models. The code and dataset are available for download athttps://github.com/Lollipophua/KG-IBL.

Specific emitter identification (SEI) based on radio frequency fingerprinting (RFF) is a physical layer authentication method in the field of wireless network security. RFFs are unique features embedded in the electromagnetic waves, which come from the hard imperfections in the wireless devices. Deep learning has been applied to many SEI tasks due to its powerful feature extraction capabilities. However, the success of most methods hinges on massive and labeled samples, and few methods focus on a realistic scenario, where few samples are available and labeled. In this paper, to overcome data limitations, we propose a few-shot SEI (FS-SEI) method based on self-supervised learning and adversarial augmentation (SA2SEI). Specifically, to overcome the limitation of label dependence for auxiliary dataset, a novelty adversarial augmentation (Adv-Aug)-powered self-supervised learning is designed to pre-train a RFF extractor using unlabeled auxiliary dataset. Subsequently, to overcome the limitation of sample dependence, knowledge transfer is introduced to fine-tune the extractor and a classifier with target dataset including few samples (5-30 samples per emitter in this paper) and corresponding labels. In addition, auxiliary dataset and target dataset are come from different emitters. An open-source large-scale real-world automatic-dependent surveillance-broadcast (ADS-B) dataset and a Wi-Fi dataset are used to evaluate the proposed SA2SEI method. The simulation results show that the proposed method can extract more discriminative RFF features and obtain higher identification performance in the FS-SEI. Specifically, when there are only 5 samples per Wi-Fi device, it can achieve$83.40\%$identification accuracy, in which$38.63\%$identification accuracy improvement comes from the Adv-Aug of pre-training process. The codes are available athttps://github.com/LIUC-000/SA2SEI.

The evolution of wireless communication technologies has brought significant conveniences but also raised security concerns. Radio frequency fingerprint (RFF) is a potential feature, which can uniquely identify a specific emitter. The integration of Deep Learning (DL) has further enhanced the reliability of RFF identification. However, DL methods often struggle in dynamic communication environments. In this paper, we propose a dynamic adaptive RFF identification method leveraging Cognitive Representation Learning (CRL). Our proposed method is capable of recognizing and storing cognitive knowledge from historical environments. Furthermore, it dynamically adapts to current situations through its cognitive module, offering enhanced adaptability in dynamic environments. Specifically, we analyze the causes of RFF and define the RFF identification problems at first. Secondly, our cognitive module evaluates current data by examining both data distribution and feature distribution distances. Concurrently, our representation learning strategy enhances feature reuse and focuses on feature space. Finally, we implement an unsupervised ensemble module, combining unsupervised clustering with model ensemble techniques to boost performance. Simulation results validate our method’s robust generalization in dynamic settings, with an improvement of 7.66% in controlled environments and 5.98% in more challenging scenarios on PA dataset. Furthermore, the high identification ratio and ablation study results underscore the efficacy and necessity of each module in our approach.

Radio frequency fingerprinting (RFF) serves as a distinctive hardware trait in transmitters, forming the cornerstone of transmitter identification. While recent advancements led to significant improvements in identification accuracy, these developments also inadvertently simplify the process for adversaries to detect our transmitters. This vulnerability is particularly concerning in secure communications, as the exposure of device information could potentially result in the compromise of communication content, posing significant security threats. To counteract such risks and safeguard transmitters against unauthorized identification, this paper proposes a novel RFF concealment (RFFC) method based on IQ imbalance compensation and digital pre-distortion (DPD) techniques. This method not only effectively conceals the RFF, preventing malicious detection of the transmitter, but also enhances the system’s linearization performance. The effectiveness of the proposed RFFC framework is validated through MATLAB Simulink and a software and hardware test platform. Experimental results show that using the blind generalized linear structure-based IQ imbalance and deep neural network (DNN)-based PA nonlinearity joint concealment method performs best, reducing transmitter identification accuracy to only 17% under various signal-to-noise ratio conditions. Additionally, this method performs the best in system linearization performance.

Automatic Modulation Classification (AMC) is crucial for monitoring the legitimacy of user frequency behavior and identifying potential sources of interference in spectrum monitoring. Deep learning-based AMC models have shown excellent performance, however, it has been proven susceptible to adversarial attacks. To address the problem, we propose a Disentangled Hilbert-Schmidt Information Bottleneck Adversarial Defense (DIBAD) method to enhance the adversarial robustness of AMC models. Specifically, we firstly analyze the task-relevant and task-irrelevant features in the intermediate representations of modulation signals from the perspective of mutual information theory. Secondly, a training framework consisting of a classification feature extractor, a supplementary feature extractor, and a classifier is designed. Under the information bottleneck constraint, the classification feature extractor and supplementary feature extractor are used to extract task-relevant and task-irrelevant features, respectively. The information bottleneck constraint is employed to reduce task-irrelevant features, thus improving the model’s adversarial robustness. Experiments on the RML2016.10a and DMRadio09.real datasets, along with comprehensive analysis, demonstrate the superiority of the DIBAD method terms of adversarial robustness.

Cyber security has always been an important issue in the Internet of Everything topic. In the physical layer of the Internet, specific emitter identification (SEI) technology is widely researched as a simple and effective intrusion prevention technology. Existing SEI research only focused on radio frequency (RF) signals from a single receiver. However, in real scenes such as the Industrial Internet of Things (IIoT), vehicle-to-everything applications, and intelligent sensing systems, etc., RF signals are received from different types of sensors deployed at different locations. Therefore, this paper proposes a multisource heterogeneous SEI (MH-SEI) method and proposes a multi-source heterogeneous attention-based feature fusion network (MHAFFN) to achieve excellent identification performance. The proposed MHAFFN utilizes a multi-channel convolutional network as the RF fingerprinting (RFF) extraction module for multisource heterogeneous RF signals and equips an attention-based RFF fusion module to obtain mixed RFF for the automatic classifier. The experimental results show that the identification accuracy of MHAFFN is 99.196% in a perfect environment. Furthermore, robustness verification has proved that MHAFFN keeps advantages in noisy environments. Through fault tolerance mechanism verification experiment, it is proved that MHAFFN is able to work stably in real-world complex scenarios.

In the case of COVID-19, which requires stable and reliable tracking of personnel movement, aircraft identification by specific emitter identification (SEI) is a hot-button issue. It refers to the process of identifying individual aircraft by comparing features extracted from the Radio Frequency (RF) signal of a given aircraft. Deep learning (DL) has been widely used in SEI research due to its excellent feature extraction capability, but in the actual low-resource reception scenario, the aircraft signal data acquired for training are long-tailed in distribution, and the imbalance of the signal data increases the challenge of training the network. In this paper, we propose a novel long-tailed specific emitter identification (LT-SEI) method using decoupled representation (DR) learning. Specifically, we separate the learning process into two stages: representation learning and classification, which includes unbalanced training and balanced classifier learning. The proposed DR-based LT-SEI approach is assessed using aircraft Automatic Dependent Surveillance Broadcast (ADS-B) data collected in the real world and compared to state-of-the-art methods. Experiment results show that the method has better long-tail recognition performance than the existing methods. When the data imbalance factor is 0.01, the F1 score of the model for the recognition result can reach 71.2%, which is 9% higher than that of the baseline model.

Vehicular Edge Computing (VEC) is the transportation version of Mobile Edge Computing (MEC). In VEC, task offloading enables vehicles to offload computing tasks to nearby Roadside Units (RSUs), thereby reducing the computation cost. Recent trends in task offloading cause a proliferation of studies in academia. However, the existing offloading schemes still face many challenges, such as high-dynamic network topology, massive and complex data, dynamic scenes with high-speed vehicles and low-latency requirements. Digital Twin (DT)-based VEC is emerging as a promising solution. It monitors the state of the VEC network in real time through mappings and interactions between the physical and virtual entities. Consequently, the task offloading scheme can make more reasonable offloading decisions at the physical layer and further improve the efficiency of VEC. Above all, we propose a VEC computing offloading scheme, namely, AdaptiveSwarm Intelligent Offloading Scheme Based on Digital-Twin-Assisted PRedictionInVEC (STRIVE). The VEC network architecture is established to combines DT with an improved Generative Adversarial Network (GAN). The powerful prediction ability of GAN is used to assist in constructing DT in the pre-processing phase, reducing the size of the decision space. To adapt to the dynamic nature of VEC, we establish an adaptive model to adjust the real-time parameter under various scenarios. Then, we deploy an improveDgenetIc simulatEd annealing-baSEd particLe swarm optimization (DIESEL) algorithm to task offloading decision-making, which can provide reliable computing services for vehicles at a lower cost. The simulation results demonstrate that the proposed scheme can effectively reduce computing delay and energy consumption compared with its counterparts.

Specific emitter identification (SEI) uses advanced techniques to identify radio equipment by analyzing unique characteristics in radio frequency signals. Recently, deep learning (DL) has been considered a promising tools for designing various intelligent SEI methods. This is primarily due to its ability to fully exploit hidden data features and make autonomous classification decisions, leading to effective performance. The existing DL-SEI methods are based on the availability of extensive labeled datasets, however, collecting and annotating such data is challenging and time-consuming in real-world scenarios. Furthermore, these datasets often contain both device-specific and irrelevant features, which limits the adaptability of models to fixed channels. To overcome these challenges, we propose a robust variable-channel SEI (VC-SEI) method. This method uses semantic consistency-powered semi-supervised domain adaptation (SSDA). We introduce domain adversarial training to ensure global semantic consistency (GSC), allowing the extraction of channel-irrelevant features. Additionally, we design two loss functions to maintain local semantic consistency (LSC) for extracting category-relevant features. This approach enables effective domain adaptation. Our SSDA-based VC-SEI method has been rigorously evaluated using the ORACLE RF fingerprinting datasets from 16 USRP X310 radios. When only 1% of training samples in the target domain are labeled, our method achieves 84.20% identification accuracy in the target domain and 92.00% identification accuracy in the source domain. These results surpass those of current state-of-the-art methods. Simulation results confirm the robust identification performance of our proposed VC-SEI method in both source and target domains across all scenarios. Our code can be downloaded fromhttps://github.com/frownean/VC-SEI-based-SSDA.

Recently, with the explosive growth of the mobile devices, spectrum sensing for wireless devices has become an attractive research. Automatic modulation classification (AMC) is an important task in spectrum sensing and plays an important role in blind signal recognition, and deep learning has been shown to greatly improve the performance of AMC networks. However, deep learning models for AMC are considered vulnerable against adversarial attacks, resulting in unreliable sensor systems. In this paper, we study how to deal with the threats of adversarial attacks by optimizing neural networks. We propose an adversarial defense method based on genetic algorithm (GA) to optimize adversarial training. The optimizations are performed between the layers of the neural networks to obtain the weights with maximum fitness, to improve the adversarial robustness of the models. In addition, an indicator to quantitatively evaluate the adversarial robustness of the models is also proposed. We conduct experiments in the different perturbation-to-noise ratios (PNRs) to verify the effectiveness of the defensive models. The results show that the GA-optimized approach can greatly improve the classification accuracy of the models to adversarial examples, and provides a better fitting ability than the mainstream adversarial training methods.

Specific emitter identification (SEI) refers to a process to determine the category of emitters by extracting, analyzing and matching the characteristics of received emitter signals. With the increasingly complex environment, traditional SEI methods, such as parameter matching, become difficult to meet the needs of robust and effective signal identification. Deep learning (DL) possesses powerful feature extraction ability and has been widely used in SEI. The superior performance of DL-based SEI methods also brings problems of redundant model parameters and high feature dimensionality, which further causes slow convergence rate, high storage requirements, and ever-increasing computational complexity. In this paper, we propose an SEI method based on end-to-end sparse feature selection (SFS) to make model pay more attention to features with good identification performance. Specifically, we add sparse parameters to features and design loss function composed of cross-entropy loss and sparse regularization. Several experiments are conducted on ADS-B, WiFi and LoRa datasets. From the simulation results, our proposed SFS-SEI method improves feature sparsity, speeds up loss convergence, reduces model parameters on the premise of ensuring accuracy. Code is available at: https://github.com/sleepeach/SFS-SEI.

Rogue emitter detection (RED) is a crucial technique to maintain secure internet of things applications. Existing deep learning-based RED methods have been proposed under friendly environments. However, these methods perform unstably under low signal-to-noise ratio (SNR) scenarios. To address this problem, we propose a robust RED method, which is a hybrid network of denoising autoencoder and deep metric learning (DML). Specifically, denoising autoencoder is adopted to mitigate noise interference and then improve its robustness under low SNR while DML plays an important role to improve the feature discrimination. Several typical experiments are conducted to evaluate the proposed RED method on an automatic dependent surveillance-Broadcast dataset and an IEEE 802.11 dataset and also to compare it with existing RED methods. Simulation results show that the proposed method achieves better RED performance and higher noise robustness with more discriminative semantic vectors than existing methods.

Specific emitter identification (SEI) plays an increasingly crucial and potential role in both military and civilian scenarios. It refers to a process to discriminate individual emitters from each other by analyzing extracted characteristics from given radio signals. Deep learning (DL) and deep neural networks (DNNs) can learn the hidden features of data and build the classifier automatically for decision making, which have been widely used in the SEI research. Considering the insufficiently labeled training samples and large-unlabeled training samples, the semi-supervised learning-based SEI (SS-SEI) methods have been proposed. However, there are few SS-SEI methods focusing on extracting the discriminative and generalized semantic features of radio signals. In this article, we propose an SS-SEI method using metric-adversarial training (MAT). Specifically, pseudo labels are innovatively introduced into metric learning to enable semi-supervised metric learning (SSML), and an objective function alternatively regularized by SSML and virtual adversarial training (VAT) is designed to extract discriminative and generalized semantic features of radio signals. The proposed MAT-based SS-SEI method is evaluated on an open-source large-scale real-world automatic-dependent surveillance–broadcast (ADS-B) data set and Wi-Fi data set and is compared with the state-of-the-art methods. The simulation results show that the proposed method achieves better identification performance than existing state-of-the-art methods. Specifically, when the ratio of the number of labeled training samples to the number of all training samples is 10%, the identification accuracy is 84.80% under the ADS-B data set and 80.70% under the Wi-Fi data set. Our code can be downloaded from https://github.com/lovelymimola/MAT-based-SS-SEI .

Deep learning (DL)-based specific emitter identification (SEI) is a potential physical layer authentication technique for Industrial Internet-of-Things (IIoT) Security, which detects the individual emitter according to its unique signal features resulting from transmitter hardware impairments. The success of DL-based SEI often depends on sufficient training samples and the integrity of samples’ labels. The extensive deployment of wireless devices generates a huge amount of signals, but signals labeling is quite difficult and expensive with the high demand for expertise. In this article, we present an SEI method based on dual consistency regularization (DCR), which enables feature extraction and identification using a few labeled samples and a large number of unlabeled samples. With the help of pseudo labeling, we leverage consistency between the predicted class distribution of weakly augmented unlabeled training samples and that of strongly augmented training unlabeled samples, and consistency between semantic feature distribution of labeled samples and that of pseudo-labeled samples, which takes the unlabeled samples into account to model parameter tuning for a more accurate emitter identification. Extensive numerical results demonstrate that compared with well-known semi-supervised learning-based SEI methods, our method obtains 99.77% identification accuracy on a WiFi data set and 90.10% identification accuracy on an automatic dependent surveillance-broadcast (ADS-B) data set when only 10% of training samples are labeled, and improves the identification accuracy on the WiFi data set and the ADS-B data set by more than 19.07% and 5.30%, respectively. Our codes are available athttps://github.com/lovelymimola/DCR-Based-SemiSEI.

Wi-Fi-based passive sensing is considered as one of the promising sensing techniques in advanced wireless communication systems due to its wide applications and low deployment cost. However, existing methods are faced with the challenges of low sensing accuracy, high computational complexity, and weak model robustness. To solve these problems, we first propose a robust channel state information (CSI)-based Wi-Fi passive sensing method using attention mechanism deep learning (DL). The proposed method is called as convolutional neural network (CNN)-ABLSTM, a combination of CNNs and attention-based bi-directional long short-term memory (LSTM). Specifically, CSI-based Wi-Fi passive sensing is devised to achieve the high precision of human activity recognition (HAR) due to the fine-grained characteristics of CSI. Second, CNN is adopted to solve the problems of computational redundancy and high algorithm complexity which are often occurred by machine learning (ML) algorithms. Third, we introduce an attention mechanism to deal with the weak robustness of CNN models. Finally, simulation results are provided to confirm the proposed method in three aspects, high recognition performance, computational complexity, and robustness. Compared with CNN, LSTM, and other networks, the proposed CNN-ABLSTM method improves the recognition accuracy by up to 4%, and significantly reduces the calculation rate. Moreover, it still retains 97% accuracy under the different scenes, reflecting a certain robustness.

Radio frequency fingerprint (RFF), which comes from the imperfect hardware, is a potential feature to ensure the security of communication. With the development of deep learning (DL), DL-based RFF identification methods have made excellent and promising achievements. However, on one hand, existing DL-based methods require a large amount of samples for model training. On the other hand, the RFF identification method is generally less effective with limited amount of samples, while the auxiliary dataset and the target dataset often needs to have similar data distribution. To address the data-hungry problems in the absence of auxiliary datasets, in this paper, we propose a supervised contrastive learning (SCL)-based RFF identification method using data augmentation and virtual adversarial training (VAT), which is called “SCACNN”. First, we analyze the causes of RFF, and model the RFF identification problem with augmented dataset. A non-auxiliary data augmentation method is proposed to acquire an extended dataset, which consists of rotation, flipping, adding Gaussian noise, and shifting. Second, a novel similarity radio frequency fingerprinting encoder (SimRFE) is used to map the RFF signal to the feature coding space, which is based on the convolution, long-short-term-memory, and a fully connected deep neural network (CLDNN). Finally, several secondary classifiers are employed to identify the RFF feature coding. The simulation results show that the proposed SCACNN has greater identification ratio than the other classical RFF identification methods. Moreover, the identification ratio of the proposed SCACNN achieves an accuracy of 92.68% with only 5% samples.

Emerging wireless networks may suffer severe security threats due to the ubiquitous access of massive wireless devices. Specific emitter identification (SEI) is considered as one of the important techniques to protect wireless networks, which aims to identifying legal or illegal devices through the radio frequency (RF) fingerprints contained in RF signals. Existing SEI methods are implemented with either traditional machine learning or deep learning. The former relies on manual feature extraction which is usually inefficient, while the latter relies on the powerful graphics processing unit (GPU) computing power but with limited applications and high cost. To solve these problems, in this article, we propose a GPU-free SEI method using a signal feature embedded broad learning network (SFEBLN), for efficient emitter identification based on a single-layer forward propagation network on the central processing unit (CPU) platform. With this method, the original RF data is first preprocessed through external signal processing nodes, and then processed to generate mapped feature nodes and enhancement nodes by nonlinear transformation. Next, we design the internal signal processing nodes to extract effective features from the processed RF signals. The final input layer consists of mapped feature nodes, enhancement nodes, and internal signal processing nodes. Then, the network weight parameters are obtained by solving the pseudo inverse problem. Experiments are conducted over the CPU platform and the results show that our proposed SEI method using SFEBLN achieves a superior identification performance and robustness under various scenarios.

A time-frequency diagram is a commonly used visualization for observing the time-frequency distribution of radio signals and analyzing their time-varying patterns of communication states in radio monitoring and management. While it excels when performing short-term signal analyses, it becomes inadaptable for long-term signal analyses because it cannot adequately depict signal time-varying patterns in a large time span on a space-limited screen. This research thus presents an abstract signal time-frequency (ASTF) diagram to address this problem. In the diagram design, a visual abstraction method is proposed to visually encode signal communication state changes in time slices. A time segmentation algorithm is proposed to divide a large time span into time slices. Three new quantified metrics and a loss function are defined to ensure the preservation of important time-varying information in the time segmentation. An algorithm performance experiment and a user study are conducted to evaluate the effectiveness of the diagram for long-term signal analyses.

With the rapid development of the cognitive radio networks, the number of terminal devices has exploded. Massive devices generate a large amount of privacy-sensitive data, typically WiFi signals. This paper proposes a method for Radio frequency (RF) fingerprinting identification of WiFi signals based on federated learning, which trains a cooperative model to complete RF fingerprinting identification without transmitting privacy-sensitive data. The experimental findings on a real-world dataset validate that the strategy described in this study increases the RF fingerprinting identification accuracy in a variety of size circumstances, and ensures that data privacy will not be compromised.

Radio frequency fingerprint (RFF) identification is an emerging physical layer security technique, which provokes many promising applications in the internet of things (IoT). However, traditional machine learning-based RFF identification methods rely on complex manual feature extraction, while it is difficult for methods based on deep learning to deal with RFF identification under different channel environments. To solve these problems, we propose three different transfer learning-based RFF identification methods based on ConvMixer network, which is a mixture of different convolutional layers, using pre-trained model in the previous channel environment to assist in training under the new channel environment. Experimental results show that, compared with the previous retraining method, our proposed method reduces the number of training parameters and improves the identification performance at low SNR. Moreover, the proposed method can still have a certain performance guarantee with less training data.

Artificial intelligence (AI) has emerged as the most promising solution expected to overcome the high degree of abstraction of radio signals and achieve accurate automatic modulation classification (AMC). To further improve the classification performance of the AMC model and enhance its interpretability, the network output layer is modeled as a decision space into which the input data is projected. In this paper, we expand the inter-class angle between the classes with the largest confusion rate to increase the decision space. In addition, we extend the perspective to the softmax layer and evaluate the negative impact of the output distribution range on the confidence difference in the AMC problem. We further propose constraining the norm of the input data to the output layer in combination with prior knowledge of the distribution of modulation signal data. Combining the above two aspects, a Maximum Focal Inter-Class Angular Loss with Norm Constraint (MFICAL-NC) scheme is proposed. The experimental results show that the method can guide the model to obtain a better fitting state and a stronger generalization ability.

With the application of deep learning (DL) in signal detection, improving the robustness of classification models has received much attention, especially in automatic modulation classification (AMC) of electromagnetic signals. A large amount of electromagnetic signal data is required to obtain robust models in the training and testing process. However, the high cost of manual collection and the issue of low quality of automatically generated data contribute to the AMC model’s defects. Therefore, it is essential to generate electromagnetic data by data augmentation. In this paper, we propose a novel electromagnetic data augmentation tool, namely ElecDaug, which directs the metamorphic process by electromagnetic signal characteristics to achieve automatic data augmentation. Based on electromagnetic data pre-processing, transmission or time-frequency domains characteristic metamorphic, ElecDaug can augment the data samples to build robust AMC models. Preliminary experiments show that ElecDaug can effectively augment available data samples for model repair. The video is at https://youtu.be/x5g6IVX_Q3s. Documentation and source code can be found here: https://github.com/ehhhhjw/tool_ElecDaug.git.

Specific emitter identification (SEI) is developed as a potential technology against attackers in cognitive radio networks and authenticate devices in Internet of Things (IoT). It refers to a process to discriminate individual emitters from each other by analyzing extracted characteristics from given radio signals. Due to the strong capability of deep learning (DL) in extracting the hidden features of data and making classification decision, deep neural networks (DNNs) have been widely used in the SEI. Considering the insufficiently labeled training dataset and large unlabeled training dataset, we propose a novel SEI method using semi-supervised (SS) learning framework, i.e., metric-adversarial training (MAT). Specifically, two object functions (i.e., cross-entropy (CE) loss combined with deep metric learning (DML) and CE loss combined with virtual adversarial training (VAT)) and an alternating optimization way are designed to extract discriminative and generalized semantic features of radio signals. The proposed MAT-based SS-SEI method is evaluated on an open source large-scale real-world automatic-dependent surveillance-broadcast (ADS-B) dataset. The simulation results show that the proposed method achieves a better identification performance than four latest SS-SEI methods.

Specific emitter identification (SEI) is a promising physical layer authentication technique based on unintentionally hardware impairments of transmitters. These impairments are independent of the data’s content, so they are difficult to forge and analyze. Recently, most deep learning (DL) based SEI methods have been proposed, and have shown their great performance. However, these methods are big data-driven which means they have poor performance with limited training samples, and the vulnerability of neural networks to adversarial attacks is also a problem worth considering. In this paper, we propose an innovative few-shot SEI method based on class-reconstruction classification network and adversarial training (CRCN-AT) without the support of auxiliary dataset. Simulation results show that the proposed method achieves better identification performance and robustness in few-shot scenarios compared to traditional methods. The Pytorch code is released at https://github.comLIUC-000/CRCN-AT.

Specific emitter identification (SEI) extracts the fingerprint characteristics of emitters according to the subtle differences of transmitted signals, to distinguish different emitter individuals and prevent unauthorized network access. Deep learning (DL) based SEI methods have been proposed to achieve a good identification performance in recent years. However, the existing methods need a massive specific emitter dataset to alleviate model overfitting during the training stage. In this paper, we propose data augmentation (DA) aided few-shot learning method and validate the proposed method using automatic dependent surveillance-broadcast (ADS-B) signals. Specifically, according to the characteristics of ADS-B signals, four DA methods, i.e., flip, rotation, shift, and noise are studied for the proposed method. Experimental results are provided to show that the proposed method improves the recognition accuracy and the model robustness.

Radio frequency fingerprint (RFF) is regarded as a key technology in physical layer security in various wireless communications systems. Deep learning (DL) has achieved great success in the field of signal identification, particularly in improving performance and eliminating manual feature extraction. However, the training cost of these DL-based methods is usually large. It is unwise to retrain the network with whole data when it comes to new data. Therefore, we propose a novel RFF identification method based on incremental learning (IL), which uses continuous data stream to update the identification model, constantly. Experimental results show that with the increase of increment times, the accuracy of the proposed IL-based method gradually approaches the performance of joint training, and finally reaches 96.79%, which is only 1.9% lower than the performance upper bound.

Specific emitter identification (SEI) is a highly potential technology for physical-layer authentication that is one of the most critical supplements for the upper-layer authentication. SEI is based on radio frequency (RF) features from circuit difference, rather than cryptography. These features are inherent characteristics of hardware circuits, which are difficult to counterfeit. Recently, various deep learning (DL)-based conventional SEI methods have been proposed, and achieved advanced performances. However, these methods are proposed for close-set scenarios with massive RF signal samples for training, and they generally have poor performance under the condition of limited training samples. Thus, we focus on few-shot SEI (FS-SEI) for aircraft identification via automatic dependent surveillance-broadcast (ADS-B) signals, and a novel FS-SEI method is proposed, based on deep metric ensemble learning (DMEL). Specifically, the proposed method consists of feature embedding and classification. The former is based on metric learning with a complex-valued convolutional neural network (CVCNN) for extracting discriminative features with compact intracategory distance and separable intercategory distance, while the latter is realized by an ensemble classifier. Simulation results show that if the number of samples per category is more than 5, the average accuracy of our proposed method is higher than 98%. Moreover, feature visualization demonstrates the advantages of our proposed method in both discriminability and generalization. The code and the dataset can be downloaded fromhttps://github.com/BeechburgPieStar/FS-SEI.

With the rapid development of the information technology, the number of devices in the Internet of Things (IoT) is increasing explosively, which makes device identification a great challenge. Deep neural networks (DNNs) have been used for device identification in IoT due to their superior learning ability. However, DNNs are susceptible to adversarial attacks, which can greatly degrade the accuracy of deep learning (DL) models for device identification. The adversarial attack is one of the fundamental security concerns for DNNs, and it is of great importance to study the generation of adversarial examples and to examine the attack effects for the design of robust DNN-based device identification schemes. In this article, we examine the effects of nontargeted and targeted adversarial attacks on convolutional neural network (CNN)-based device identification and propose combined evaluation indicators of logits to enrich the evaluation criteria. Our experimental results demonstrate that the identification accuracy degrades with the increase of the perturbation level and iteration step size, and the proposed combined evaluation indicators are effective to show the individual device signal differences. The insights from this study will be useful for the design of robust DL-based IoT systems.

With the development of the Internet of Things (IoT), the IoT devices are increasing day by day, resulting in increasingly scarce spectrum resources. At the same time, many IoT devices are facing inevitable malicious attacks. The cognitive Radio-enabled IoT (CR-IoT) is proposed as an effective method for spectrum resource allocation and risk monitoring in the IoT. The signal detection and modulation recognition are the key technologies for CR-IoT, addressing the problem of multisignal detection and automatic modulation classification (AMC) is one of the prerequisites for realizing secure dynamic spectrum access. Based on sliding window and deep learning (DL), this study proposes a multisignal frequency domain detection and recognition method. The frequency spectrum of the time-domain overlapping signal is obtained through the fast Fourier transform (FFT), and the frequency spectrum is segmented based on the signal energy detection method. Finally a complex convolutional neural network (CNN) is constructed for the identification of signal spectrum information. The proposed method can recognize 264 time-domain aliasing and frequency-closed signals with an accuracy of 97.3% under the influence of −2 dB corresponding to the noise of the calibration signal. In addition, the proposed method eliminates the influence of bandwidth, which can effectively detect and recognize the signal types of each component in the frequency band. This method has wide applicability and provides an effective scheme for the IoT cognitive technology.

With the rapid growth of the number of flights, the traditional radar system has been unable to meet the needs of flight supervision. At the same time, it also puts forward higher requirements for air traffic management (ATM). Automatic dependent surveillance-broadcast (ADS-B) is a promising technology in the next generation of air traffic control (ATC). However, the openness of ADS-B system brings the opportunities for terrorists to tamper with data. In this paper, we propose a novel aircraft coordinate prediction hybrid model based on deep learning. The proposed model combines inception modules and long short-term memory (LSTM) modules. Inception modules are used to extract the spatial features of dataset, and LSTM modules are used to extract the temporal features of dataset. In addition, we use the ADS-B signal strength instead of its specific information to obtain aircraft coordinates. Signal strength is not easily tampered with, but it carries limited information. Therefore, this scheme sacrifices a certain precision for reliability. Inception modules and LSTM modules are combined in different ways to perform experiments on the real-world ADS-B datasets from OpenSky network. The experimental results show that the proposed 2-Inception-LSTM is the local optimal model. The prediction error is within 10 km. It can be suitable for situations where the positioning accuracy of aircraft coordinates is not pursued, but the positioning reliability must be guaranteed.

In this article, interferencequality assessment is of great significance to reflect the communication environment and improve speech communication performance. However, most traditional assessment approaches aimed at the degraded speech produced in the communication telephone network, but lacking of methods in extreme communication environment with ultralow SNR. Therefore, in this article, we proposed a convolutional neural network (CNN) model evaluation method based on Log-Mel spectrogram to evaluate interfered speech quality. In this method, the Mel frequency cepstrum coefficients of interference speech are converted into images, which are used as input of CNN. In order to verify the performance of this method, we collected a speech dataset in real interfered communication scenarios and finished manual annotation. Experiments are carried out on this dataset to evaluate the interference speech, and the performance of this method is compared with that of machine learning evaluation method under different features. Experimental results show that the proposed method gives the better evaluation accuracy. Compared with the previous machine learning methods, the accuracy is improved by 12.5% from 75% to 87.5%.

Reliable positioning services are extremely important for users in mountainous environments. However, in such environments, the service reliability of conventional wireless positioning technologies is often disappointing due to frequent non-line-of-sight (NLoS) propagation and poor geometry of available anchor nodes. Hence, we propose a unmanned aerial vehicle (UAV)-enabled positioning system that utilizes UAV’s mobility to overcome the above challenges. In this article, we first analyze and model the major causes of service failures in the proposed system. In particular, a geometry-based NLoS probability model is established based on the digital elevation models (DEMs) of realistic terrain for reliability analysis. Subsequently, we propose a reliability-prediction method and derive the corresponding metric to evaluate the system’s ability to provide reliable positioning services. Moreover, we also develop a voting-based method for the further enhancement of service reliability. Monte Carlo simulations show that in mountainous environments, the proposed reliability-prediction method could achieve a prediction accuracy that is at least 36.8$\%$higher than that of the existing technique. In addition, in the experiments conducted in two typical valley scenarios, the proposed reliability-enhancement method improves the service reliability of the proposed system by 23$\%$and 29$\%$, respectively. These numerical results demonstrate the strong potential of the proposed system and methods for reliable positioning.

Compared with the fixed frequency signal, the carrier frequency of frequency hopping (FH) signal is controlled by the pseudo-random codes, so it has better concealment and anti-interference. As an important parameter of FH communication, the modulation mode of FH signal can provide powerful support for combat response, such as identification of friend or foe attribute, positioning and jamming guidance, intelligence information extraction, etc. However, there is still a big gap in modulation recognition of FH signals at the domestic and foreign countries. In this paper, a modulation recognition method of FH signal based on time-frequency transform is proposed. The time-frequency images of different modulation types of FH signals are obtained by SPWVD time-frequency transform, and then the time-frequency images are denoised by convolution autoencoder. Finally, the denoised images are sent to convolution neural network for feature extraction and classification recognition. Simulation experiments prove that the proposed method achieves a good classification effect at low signal-to-noise ratios (SNRs), and achieves a recognition rate of 93.67% at -2dB.

With the development of network, network security has become a topic of increasing concern. Recent years, machine learning technology has become an effective means of network intrusion detection. However, machine learning technology requires a large amount of data for training, and training data often contains privacy information, which brings a great risk of privacy leakage. At present, there are few researches on data privacy protection in the field of intrusion detection. Regarding the issue of privacy and security, we combine differential privacy and machine learning algorithms, including One-class Support Vector Machine (OCSVM) and Local Outlier Factor(LOF), to propose an hybrid intrusion detection system (IDS) with privacy protection. We add Laplacian noise to the original network intrusion detection data set to get differential privacy data sets with different privacy budgets, and proposed a hybrid IDS model based on machine learning to verify their utility. Experiments show that while protecting data privacy, the hybrid IDS can achieve detection accuracy comparable to traditional machine learning algorithms.

In energy harvesting Ad-hoc networks, a multi-hop D2D link is made available for long-distance communication, which will cause interference with adjacent D2D nodes. The paper proposes a relay selection algorithm based on machine learning to maintain the supply of communication energy and reduce interference with other D2D nodes. First, the closed-form solution of the outage probability is analyzed. Then, the distance ratio factor (DRF) which affects the outage performance is derived. Based on the factor, the mapping DRF matrix is obtained and a support vector machine (SVM) is utilized to decrease the outage probability. Finally, the relay nodes are selected by the SVM - Dijkstra algorithm. Simulation experiments verify the performance of the proposed algorithm. The proposed algorithm outperforms the shortest path algorithm, the direct transmission method, and the DRF-Dijkstra algorithm.

Unmanned aerial vehicle (UAV) is considered as a promising technique to enhance future wireless mobile communication. In this paper, the UAVs serve as aerial base stations (UBSs) to provide reliable service for terminal users (TUs). We construct the physical model and air-ground link model to formulate an optimization problem, aiming to maximize the total channel capacity of the network. To address this non-convex problem, we proposed a multi-agent deep reinforcement learning algorithm (MADRL) based on deep deterministic policy gradient (DDPG) to optimize the trajectory design and bandwidth assignment dynamically. Proper reward function is well designed to guide the agents to exploit the potential of the aerial network. Simulations demonstrate that our scheme can adapt the rapidly changing environment and obtains 29.49% performance improvement comparing to the baseline scheme.

Deep learning (DL) models are vulnerable to adversarial attacks, by adding a subtle perturbation which is imperceptible to the human eye, a convolutional neural network (CNN) can lead to erroneous results, which greatly reduces the reliability and security of the DL tasks. Considering the wide application of modulation recognition in the communication field and the rapid development of DL, by adding a well-designed adversarial perturbation to the input signal, this article explores the performance of attack methods on modulation recognition, measures the effectiveness of adversarial attacks on signals, and provides the empirical evaluation of the reliabilities of CNNs. The results indicate that the accuracy of the target model reduce significantly by adversarial attacks, when the perturbation factor is 0.001, the accuracy of the model could drop by about 50% on average. Among them, iterative methods show greater attack performances than that of one-step method. In addition, the consistency of the waveform before and after the perturbation is examined, to consider whether the added adversarial examples are small enough (i.e., hard to distinguish by human eyes). This article also aims at inspiring researchers to further promote the CNNs reliabilities against adversarial attacks.

In the coming 6G communications, network densification, high throughput, positioning accuracy, energy efficiency, and many other key performance indicator requirements are becoming increasingly strict. In the future, how to improve work efficiency while saving costs is one of the foremost research directions in wireless communications. Being able to learn from experience is an important way to approach this vision. Transfer learning (TL) encourages new tasks/domains to learn from experienced tasks/domains for helping new tasks become faster and more efficient. TL can help save energy and improve efficiency with the correlation and similarity information between different tasks in many fields of wireless communications. Therefore, applying TL to future 6G communications is a very valuable topic. TL has achieved some good results in wireless communications. In order to improve the development of TL applied in 6G communications, this article performs a comprehensive review of the TL algorithms used in different wireless communication fields, such as base stations/access points switching, indoor wireless localization and intrusion detection in wireless networks, etc. Moreover, the future research directions of mutual relationship between TL and 6G communications are discussed in detail. Challenges and future issues about integrate TL into 6G are proposed at the end. This article is intended to help readers understand the past, present, and future between TL and wireless communications.

With the development of IoT in smart cities, the electromagnetic environment (EME) in cities is becoming more and more complex. A full understanding of the characteristics of past spectrum resource utilization is the key to improving the efficiency of spectrum management. In order to explore the characteristics of spectrum utilization more comprehensively, this paper designs an EME portrait model. By checking the statistical information of the spectrum data, including changes in the noise floor and channel utilization in each individual wireless service, the correlation between the spectrum and time or space of different channels and the information is merged into a high‐dimensional model through consistency transformation to form the EME portrait. The portrait model is not only convenient for storage and retrieval but also beneficial for transfer and expansion, which will become an important foundation for intelligent electromagnetic spectrum management.

The discovery of adversarial examples poses a serious risk to the deep neural networks (DNN). By adding a subtle perturbation that is imperceptible to the human eye, a well-behaved DNN model can be easily fooled and completely change the prediction categories of the input samples. However, research on adversarial attacks in the field of modulation recognition mainly focuses on increasing the prediction error of the classifier, while ignores the importance of decreasing the perceptual invisibility of attack. Aiming at the task of DNNbased modulation recognition, this study designs the Fitting Difference as a metric to measure the perturbed waveforms and proposes a new method: the Nesterov Adam Iterative Method to generate adversarial examples. We show that the proposed algorithm not only exerts excellent white-box attacks but also can initiate attacks on a black-box model. Moreover, our method decreases the waveform perceptual invisibility of attacks to a certain degree, thereby reducing the risk of an attack being detected.

With the development of the Internet of Things (IoT) technology and the rapid deployment of 5G wireless, more and more radiation devices are appearing in the increasingly complex electromagnetic environment. To be able to manage these devices in a unified manner, accurate identification of the devices has become a top priority. Specific emitter identification (SEI) is to effectively solve this problem. In this paper, both power spectral density (PSD) and fractional Fourier transform (FrFT) methods are used to extract the characteristics of transient signals. The characteristics of steady-state signals are analyzed by the bispectrum method. The SEI system model in this paper is constructed based on these techniques. Our experiments results show that when the SNR is 16dB, the SEI system can achieve a recognition accuracy of over 97% by exploiting the characteristics of the transient signal. Since the characteristics of the steady-state signal can better suppress noise, the SEI system can achieve a nearly 90% classification recognition accuracy under extremely low SNR.

Nowadays, network intrusions have brought greater impact in a large scale. Intrusion Detection Systems (IDS) have been a recent research hotspot for both the industry and the academic. However, due to the dynamic characteristics of network traffic, it is challenging to extract significant features and identify the traffic types. This paper focuses on applying deep learning methods to feature extraction. Specifically, an IDS model is proposed based on autoencoder and long short-term memory (LSTM) cell. The overall architecture of the intrusion detection model includes a feature extractor, a classifier, and an evaluation block. Different structures of the feature extraction model have been discussed and researched. Experiments conducted on the UNSW-NB15 dataset produce satisfactory result. A number of selected metrics such as accuracy and false alarm rate are adopted to evaluate the detection performance. Simulation results indicate that our model works better than competing machine learning methods and achieves accuracy of over 92%.

To meet the future needs of increasingly crowded airspace, the International Civil Aviation Organization (ICAO ) proposed to use the Automatic Dependent Surveillance-Broadcast (ADS-B ) to provide navigation and surveillance technology to solve the problems of security and capacity in the airspace. But ADS-B does not offer any authentication and encryption. So it is vulnerable to attacks by various illegal devices. A novel radiofrequency fingerprint (RFF ) recognition method of aircraft identity verification based on deep learning is proposed. The ADS-B signal captured by RTL-SDR is used for confirmation. The experimental results show that the fingerprint is called the Contour Stellar Images with a better recognition effect under different networks and different SNR.

With the emergence of the information age, mobile data has become more random, heterogeneous and massive. Thanks to its many advantages, deep learning is increasingly applied in communication fields such as modulation recognition. However, recent studies show that the deep neural networks (DNN) is vulnerable to adversarial examples, where subtle perturbations deliberately designed by an attacker can fool a classifier model into making mistakes. From the perspective of an attacker, this study adds elaborate adversarial examples to the modulation signal, and explores the threats and impacts of adversarial attacks on the DNN-based modulation recognition in different environments. The results show that, regardless of a white-box or a black-box model, the adversarial attack can reduce the accuracy of the target model. Among them, the performance of the iterative attack is superior to the one-step attack in most scenarios. In order to ensure the invisibility of the attack (the waveform being consistent before and after the perturbations), an appropriate perturbation level is found without losing the attack effect. Finally, it is attested that the signal confidence level is inversely proportional to the attack success rate, and several groups of signals with high robustness are obtained.

The V2V (Vehicle to Vehicle) communication system in the Internet of vehicular networking is an important part of the future intelligent vehicle network, and it is extremely important to study the quality of the V2V communication channel. The double-Rayleigh fading model can better reflect the small-scale fading characteristics of the V2V channel. Therefore, this paper conducts experimental verification in this channel environment. First, using the gain matrix constructed by CSI, the images of time, frequency and related domain are obtained through the transformation of contour line, waterfall map and related diagram. Then, The image features transformed by the channel state information are extracted based on the improved multi-texton histogram. Finally, the V2V channel quality under slow fading conditions is discriminated under the SVM. The results show that the method not only simplifies the difficulty of channel state feature extraction, but also can effectively and reliably predict the instantaneous channel state.

In the era of 5G and Internet of Things, the number of connected devices has increased dramatically, which has placed a heavy burden on the network. So it is worthwhile to study the intelligent and accurate identification and control of devices. Radio Frequency (RF) fingerprinting technology has been widely used in wireless device identification. RF fingerprint contains rich nonlinear characteristics that reflect the uniqueness of wireless devices. However, redundant or irrelevant information in the features will result in poor recognition performance. In response to the problem, a novel integration feature selection method is proposed in this paper. The principle is to improve the identification performance through extracting the best-performing feature subset from the initial features. Signals from seven power amplifiers are collected as the dataset. The covariance feature is extracted as RF fingerprint and K-Nearest Neighbor (KNN) classifier is used for classification. The stability of the proposed method is evaluated by the Spearman correlation coefficient. The robustness is evaluated under the varying Signal-to-Noise Ratio (SNR). The identification results demonstrate the excellent performance of the proposal.

The arrival of 5G has accelerated the development of the Internet of things and vehicular technology, which often need to transmit large amounts of data through wireless networks. Modulation classification plays an important role in wireless communication. Recent years, deep learning has been applied to solve the modulation classification problem and achieved good classification results. At present, almost all the papers that use deep learning to solve modulation classification are in Gaussian White noise environment. However, the error source mainly comes from non-Gaussian noise in practical wireless communication. In this paper, a modulation classification method in non-Gaussian environment based on Deep Learning is proposed. The proposed algorithm can effectively suppress the sharp pulse in non-Gaussian noise and improve the modulation recognition accuracy. MPSK and MQAM signals which are difficult to distinguish are adopted in the simulation experiment. The simulation results show that validity of the proposed method. At the same time, experiments show that this method is robust to the characteristic exponent of noise.

Fifth generation with high dimensions and capabilities is expected to fulfil the requirements of the Tactile Internet. Tracking provides strong support for intuitive interaction with interfaces by hands, eyes, bodies, etc. Such interfaces can be used in the Tactile Internet for interaction with real and virtual objects. The trackers based on tracking-by-detection framework rely on manual feature detectors for robust tracking, which is particularly useful for specific objects like humans but cannot handle generic tracking problems. Therefore, a sparse feature learning method beyond manual design is proposed to learn features from the samples sampled during tracking. The basic idea is to learn a dictionary from the samples in the previous frames and construct feature representations to represent the object for detection of the location in the current frame. The samples are patches centered at the keypoints based on an adaptive features from accelerated segment test (FAST) detector with local threshold. The dictionary is learned with sparse coding for sparse representations and atoms of the dictionary are grouped to describe the local orientation of these samples. The integrated features are built after rectification of the sparse representations. The correlation filter is used to infer the object location from the sparse features. The qualitative and quantitative experimental results on OTB100 show the advantage of the proposed tracker against current state-of-the-art trackers in terms of accuracy.

In indoor localization, reliability and optimization analysis are the most vital factors to be considered. Numerous modern-day services require precise location information for their application. Location fingerprinting using WLAN is the most acknowledged technique for indoor localization purposes. Both accuracy and coverage can be enhanced by deploying the WLAN access points (APs) appropriately. In this article, an optimization problem is formulated for reliable localization systems. An AP deployment strategy ensuring coverage along with a selection strategy to choose an optimal configuration for reducing the localization error has been implemented. A hybrid technique is proposed to select the optimal APs configuration that merges the traditional fingerprint difference and geometric dilution of precision-based methods. A distinguishing feature of this work is the inclusion of two significant constraints, which are the consideration of walls and people attenuation factor in the optimization process. Simulations are conducted to test and verify the practicality of the proposed technique through a number of comparison test cases. The results demonstrate that our proposed technique outperforms the previously existing techniques.

Network Intrusion Detection Systems (NIDS) have become a strong tool to alarm attacks in computer and communication systems. Machine learning, especially deep learning, has made huge success in fields of industry and academic. Network intrusion activity can be a time series event. In this paper, we adopt a time-related deep learning approach to detect network intrusions. A stacked sparse autoencoder (SSAE) is first built to extract the features with the greedy layer-wise strategy. And then, we propose a time- related intrusion detection system based on the variants of Recurrent Neural Network (RNN). We study the performance of proposed approach on the binary classification with a benchmark dataset UNSW- NB15. Based on the study of parameter time steps, it is proved that our time- related model is effective for intrusion detection. The experiment results show that the accuracy of the proposed approach reaches over 98% and the false alarm rate is as low as 1.8%. The performance of our model is superior to that of the standard RNN- based approach and approaches based on Deep Neural Network and shallow machine learning.

It has been recognized that fixed spectrum and channel allocation will lead to waste of spectrum resources when multiple agents communicate at the same time. Dynamic allocation of channels is proposed to maximize the utilization of spectrum resources. In the environment of multiple unmanned aerial vehicles (UAVs), it is necessary to ensure that each UAV can communicate successfully without interfering with other UAVs. Dynamic allocation of channels plays an important role in such systems. In this paper, we propose a dynamic channel allocation scheme based on deep reinforcement learning for multi-UAV systems. A slotted time system is used by all the UAVs. Di2642erent from the traditional method, the occupancy of each channel is scanned first in each time slot. Then a channel will be selected for data transmission, with feedback from the environment when the transmission is over. The proposed channel allocation scheme incorporates a long short-term memory (LSTM) into the deep reinforcement learning framework, to better learn from the past experience and better adapt to the the highly dynamic environment in a multi-UAV system. The experimental results show that compared with the traditional reinforcement learning method (Q- learning and Deep Q Network (DQN)), the proposed method achieves faster convergence and better performance with respect to average collision rate, average reward, and average successful communication rate.

Nowadays, the serious security threat of industrial control system and sensors has become a major challenge with the rapid development of Industrial Internet of Things (IIoT). Man-in-the-middle (MITM) attack is a very common intrusion method, which will make a great security threat in the application of IIoT. In IIoT scenario, the lightweight safety certification can play a very important role in the development of data-intensive and decentralized applications running on billions of sensors and devices, preserving their security. Therefore, in this paper, a low-latency high-reliability security mechanism is proposed to avoid the MITM attack in IIoT scenario. First, combining the radio frequency fingerprint (RFF) technology with IIoT applications, a lightweight IIoT security architecture is proposed. Based on the proposed IIoT security architecture, the process of device access authentication and communication service is illustrated. Second, according to the requirement of IIoT identification method, an access authentication method of the device is proposed based on the RFF. The method of feature extraction, classifier designing, and the access authentication process is discussed in detail. Finally, the simulation results show that the identification rate of devices can reach 95% under SNR = 6 dB, and can nearly reach 100% under SNR = 15 dB. Through the new process of access authentication, the access authentication rate can reach 95% under SNR = 15 dB. Therefore, according to the simulation results, the new security mechanisms based on RFF can be used to avoid the MITM attack in IIoT scenario.

Non-orthogonal multiple access (NOMA) has been developed as a key multi-access technique for 5G. However, secure transmission remains a challenge in NOMA. Especially, the user with weakest channel is most threatened by eavesdropping, due to its highest transmit power. Two schemes are proposed to generate artificial jamming at the NOMA base station (BS), aiming at disrupting the potential eavesdropping without affecting the legitimate transmission. In the first scheme, the transmit power of artificial jamming is maximized, with its received power at each receiver higher than that of other users. Thus, the jamming signal can be eliminated via successive interference cancellation before others. When the transmit power of the BS is inadequate, the transmit jamming power is maximized with the jamming signal zero-forced at each receiver. Thus, the legitimate transmission is not affected by the jamming, and the eavesdropping can be disrupted effectively. Due to the non-convexity of these two optimization problems, we first convert them to convex ones and, then, provide an iterative algorithm to solve them. Simulation results are presented to show the effectiveness of the proposed schemes in guaranteeing the security of NOMA networks.

While the intersection of blockchain and Industrial Internet of Things (IIoT) has received considerable research interest lately, the conflict between the high resource requirements of blockchain and the generally inadequate performance of IIoT devices has not been well tackled. On one hand, due to the introductions of mathematical concepts, including Public Key Infrastructure, Merkle Hash Tree, and Proof of Work (PoW), deploying blockchain demands huge computing power. On the other hand, full nodes should synchronize massive block data and deal with numerous transactions in peer-to-peer network, whose occupation of storage capacity and bandwidth makes IIoT devices difficult to afford. In this paper, we propose a lightweight blockchain system called LightChain, which is resource-efficient and suitable for power-constrained IIoT scenarios. Specifically, we present a green consensus mechanism named Synergistic Multiple Proof for stimulating the cooperation of IIoT devices, and a lightweight data structure called LightBlock to streamline broadcast content. Furthermore, we design a novel Unrelated Block Offloading Filter to avoid the unlimited growth of ledger without affecting blockchain's traceability. The extensive experiments demonstrate that LightChain can reduce the individual computational cost to 39.32% and speed up the block generation by up to 74.06%. In terms of storage and network usage, the reductions are 43.35% and 90.55%, respectively.

The wireless video transmission environment of unmanned aerial vehicles (UAVs) is complex and unstable given the high mobility and changeable working conditions of UAVs, which lead to burst and consecutive errors and high error rates. A compressed video stream is extremely sensitive to transmission errors, such that even a single bit error sharply degrades the video quality. Hence, we propose an intraframe pixel-row-interleaved error concealment algorithm that interleaves pixel rows to generate high similarity in different parts of a frame, thereby achieving intraframe error resilience. Subsequently, we suggest an interframe time-field-interleaved alternative motion-compensated prediction that allows for automatic error elimination and recovers at least four consecutive frames in wireless video communications. The experiments demonstrate that the proposed algorithms recover frames with excellent subjective and objective effects. Moreover, these algorithms can provide reliable and robust video transmission for UAVs.

Fault diagnosis is a typical multisensor information fusion problem. The information obtained from different sensors, such as sound, pressure, vibration, and temperature, can be considered as a piece of evidence. From the viewpoint of the evidence theory, the problem of multisensor fault diagnosis can be viewed as the problem of evidence fusion and decision. However, the information obtained from different sensors may be inaccurate, uncertain, fuzzy, or even conflict, so how to set up the fault diagnosis architecture of a distributed multisensor system and combine the conflict evidence should be taken into consideration. In this paper, the classical Dempster-Shafer evidence theory is described and the disadvantage of a classical Dempster's combination rule is discussed. In order to solve the counter-intuitive result when using the classical Dempster's combination rule, the Euclidean distance is proposed to characterize the differences between different pieces of evidence, and then the support degree of each evidence is generated and the weighted pieces of evidence can be combined directly using the classical Dempster's combination rule. Numerical simulation examples indicate that the proposed method has a better performance of analyzing the conflict between different pieces of evidence, especially for high conflict evidence. Therefore, compared with the existing methods, it has better applicability. According to the requirement of the Dempster-Shafer evidence theory, the fault diagnosis architecture of a distributed multisensor system is analyzed in detail, and a fault case of a rotating machine is used to illustrate that the proposed model is effective and superior, which can be used in practice.