The rapid increase in wireless devices has raised significant security and privacy concerns, positioning Specific Emitter Identification (SEI) as a crucial physical-layer security technology. Although Deep Learning (DL) methods have been widely applied to SEI due to their powerful end-to-end nonlinear mapping capabilities, they generally require large amounts of high-quality signal examples, which are difficult to obtain in adversarial environments. Moreover, wireless channel perturbations induce a distribution shift between the training and testing signal examples from the same emitter. This shift prevents DL-enabled SEI models from learning emitter-specific, channel-agnostic features, leading to a severe degradation in identification performance. In this work, we propose a cross-channel SEI method based on Meta-Feature Augmentation-Enhanced Few-Shot Learning (MFA-FSL) to efficiently address the aforementioned challenges. To overcome the data scarcity, we use signal examples from base emitters with physical-layer characteristics similar to target emitters for pre-training. To overcome the channel perturbations, we employ meta-learning as the pre-training technique to learn a channel-agnostic feature embedding function. Considering that the function does not perform well in scenarios where signal examples of target emitters are extremely scarce, we approximate the target emitter’s feature distribution and sample augmented features from it. These augmented features, together with the raw features extracted from a few signal examples of target emitters, provide sufficient supervision to train a simple classifier. Experiments conducted on a Wi-Fi dataset comprising 16 emitter categories—10 as base emitters and 6 as target emitters—demonstrate that our proposed method achieves more than 85.63% identification accuracy with only 5 signal examples per target emitter, maintaining more than 83.35% accuracy even under varying wireless channel conditions. The code can be downloaded from https://github.com/lovelymimola/MFA-FSLIoTJ-Version.

Federated learning (FL) offers significant advantages in preserving data privacy and enhancing communication efficiency, making it especially suitable for Internet of Things (IoT) networks supported by unmanned aerial vehicles (UAVs). However, most existing FL approaches rely on assumptions of uniformly distributed, well-labeled, and large-scale datasets-conditions that rarely hold in practical UAV-based IoT scenarios. These environments typically feature small-scale, non-independent and identically distributed (non-IID), and dynamically changing data. To address these challenges, we propose a novel self-supervised federated unsupervised learning (FUL) framework tailored for UAV-assisted IoT systems. The proposed framework comprises three key components: (1) a realistic UAV data collection model that considers limited onboard storage and mobility constraints; (2) a robust local training strategy that incorporates self-supervised regularization and a centered kernel alignment (CKA)-based similarity loss to mitigate the effects of data heterogeneity and rapid distribution shifts; and (3) an importance-aware hybrid normalized aggregation method at the global server, which leverages model divergence-based metrics to evaluate local model reliability and integrates both current and historical gradient information for stable model updates. Experimental results demonstrate that our framework achieves classification accuracies of 30.5%, 62.8%, and 70.5% under memory constraints of 500, 1000, and 2000 samples, respectively—outperforming the best baseline by 18.1%, 26.5%, and 9.1% under the same conditions. These results highlight the effectiveness of the proposed FUL framework in handling data heterogeneity and dynamic sample variations inherent in realistic UAV-enabled IoT applications.

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.

Human activity recognition (HAR) with WiFi channel state information (CSI) is attractive for privacy-preserving, device-free sensing, yet real deployments still struggle with three coupled issues: robustness across rooms and bands, efficiency on edge hardware, and unified support for multiple tasks. We present UN-2DCNN, a lightweight 2D-CNN pipeline tailored to indoor, multi-user CSI sensing. The design reduces temporal redundancy via a simple temporal skipping augmentation, learns a compact 128-D representation with a small CNN+GAP backbone, and injects reliability feedback through uncertainty-aware feature scaling (UAFS): Stage-1 predictive entropy is mapped to a gating weight that rescales features before a second decision head. A channel-attention MLP further suppresses spurious subcarrier responses. Evaluated on a recent multi-user CSI benchmark across classrooms, meeting rooms, and empty environments at 2.4/5 GHz, UN-2DCNN consistently outperforms competitive RNN/Transformer baselines while using only ∼1M parameters and maintaining sub-2 s test-time latency. Beyond higher accuracy, the model exhibits faster, smoother convergence and improved calibration (fewer overconfident errors). Ablations confirm that removing attention, UAFS, or the second-stage head yields consistent drops, and simple temporal skipping on the data side complements model-side selectivity. These results indicate that reliability-aware, lightweight designs can deliver practical accuracy–efficiency trade-offs for CSI-based perception on edge/IoT platforms.

Wi-Fi Channel State Information (CSI)-based human activity recognition (HAR) leverages rich channel propagation characteristics to enable non-intrusive, privacy-preserving, and device-free sensing. In multi-user wireless environments, however, HAR faces significant challenges, including multi-path interference, signal overlap, label ambiguity, cross-domain channel variability, and constraints imposed by real-time deployment on resource-limited edge devices. This paper presents MuECNet (Multi-user Enhanced Convolutional Network), a lightweight and modular deep learning framework designed to operate under realistic multi-user, multi-activity CSI sensing conditions. MuECNet integrates three key components: (i) an Enhanced Convolutional Encoding Module (ECEM) for fine-grained temporal–spectral feature extraction that preserves channel propagation signatures; (ii) a Branch-wise Feature Normalization (BFN) module for user-specific channel representation learning; and (iii) an adaptive Decision Module for multi-label activity inference. To improve robustness under diverse and dynamic channel conditions, we introduce MixUp-based data augmentation to emulate activity overlap and reduce label ambiguity. Evaluations on the WiMANS dataset show that MuECNet achieves 64.46% (2.4 GHz) and 64.15% (5 GHz) accuracy with only 1.19M parameters, 1.74G FLOPs, and 0.28 s inference latency, outperforming baseline models such as ABLSTM and THAT while reducing model size by up to 75%. Ablation studies confirm the contribution of each module, with accuracy drops of up to 6.41% when removed. These results demonstrate that MuECNet provides a robust and communication-efficient solution for integrating CSI-based sensing into future wireless networks and IoT systems.

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.

Laser-based Simultaneous Localization and Mapping (SLAM) is fundamental to autonomous navigation systems. However, conventional frameworks such as Lightweight and Ground-Optimized LiDAR Odometry and Mapping (LeGO-LOAM) face challenges in geometric segmentation robustness, feature extraction accuracy, and loop closure reliability, especially in complex and dynamic environments. To overcome these limitations, this paper proposes LeGO-LOAM-RAS, a semantic-aware, graph-based LiDAR SLAM framework that integrates RandLA-Net for multi-class semantic segmentation, a depth-guided AFE strategy, and a semantic-contextual loop closure mechanism. In the proposed system, RandLA-Net replaces traditional geometry-based segmentation with a deep learning approach, enabling fine-grained scene understanding and the effective discrimination of objects such as roads, vehicles, and buildings. This enhances both local contextual awareness and global structural representation. The AFE module dynamically adjusts neighborhood configurations and angular resolutions based on depth cues, employing depth-error-based noise suppression and curvature refinement to improve the reliability of planar and edge features. For loop closure, a semantic-contextual descriptor is constructed by fusing geometric features with semantic histograms in a polar grid representation, introducing joint geometric-semantic constraints. This design improves loop closure robustness by mitigating ambiguity in perceptually similar environments and suppressing the impact of dynamic elements. Extensive evaluations on publicly available benchmark datasets validate the effectiveness of LeGO-LOAM-RAS, demonstrating substantial improvements in localization accuracy and overall system robustness compared to state-of-the-art methods.

In recent years, semantic segmentation of large-scale point clouds has garnered significant attention due to its critical role in 3D scene understanding. However, the inherent complexity and uneven distribution of large-scale point clouds, coupled with substantial inter-class similarity, significantly hinder the discriminative power of existing segmentation approaches. RandLA-Net has shown strong capabilities in directly inferring semantic information. Building upon this foundation, we proposed three redesigned modules to improve the accuracy of point cloud segmentation: a Local Contextual Feature (LCF) module, a Global Contextual Feature (GCF) module and, a Contextual Feature Enhancement (CFE) module. The LCF module preserves the local spatial encoding unit and introduces an improved dual attention mechanism that independently computes geometric and feature-based attention scores. This facilitates more effective local feature aggregation and overcomes the segmentation artifacts caused by the difficulty in distinguishing similar classes. To complement local representations, the GCF module is integrated to capture scene-level semantics across all 3D points by using the spatial position volume ratio, thereby addressing feature extraction from both local and global perspectives. The CFE module is designed as a plug-and-play component, which enhances feature representations by integrating richer contextual cues from both explicit 3D geometry and implicit feature spaces, along with global bilinear interactions. Comprehensive experiments on the S3DIS (indoor) and Semantic3D (outdoor) datasets show that our method attains Overall Accuracy (OA) scores of 89.8% and 95.3%, and mean Intersection over Union (mIoU) scores of 73.3% and 78.0%, respectively, outperforming existing methods and providing new perspectives for large-scale point cloud semantic segmentation across diverse environments.

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.

Intelligent reflecting surfaces (IRS) enable radar sensing in blocked environments by reconfiguring propagation and creating virtual apertures, which is crucial for non-line-of-sight (NLoS) localization. This work addresses high-accuracy direction-of-arrival (DoA) estimation in semi-passive IRS-assisted sensing. We introduce a virtual-domain lifting that vectorizes the received echoes and induces a structured atomic set, leading to an atomic norm minimization (ANM) formulation. The ANM estimator is formulated as a semidefinite program (SDP) via convex relaxation, and we develop an accelerated proximal gradient (APG) solver that leverages the problem structure and avoids interior-point steps, resulting in substantial computational savings. Compared with spatial-domain and grid-based approaches, the transformed-domain estimator delivers an optimal accuracy-complexity tradeoff. It achieves gridless (ANM-level) high resolution while reducing runtime. Extensive simulations across array sizes, transmit power, and IRS configurations confirm accuracy, robustness to off-grid mismatch, and scalability, demonstrating the practicality of the proposed method for IRS-enabled NLoS sensing in complex environments.

Specific emitter identification (SEI) exploits device-dependent RF fingerprints to distinguish individual transmitters and is important for securing large-scale Internet-of-Things (IoT) deployments. While deep SEI can achieve near-perfect accuracy under same-day evaluation, real deployments rarely satisfy this assumption. At scale, per-day labeling is infeasible; models must therefore generalize from a labeled source day to an unlabeled target day, where day-to-day propagation drift induces distribution shifts and can substantially degrade performance under direct transfer (without adaptation). To address this challenge, we propose a unified unsupervised domain adaptation (UDA) framework for cross-day SEI that requires neither hardware calibration nor handcrafted features. The proposed objective integrates adversarial domain alignment, confidence-aware pseudo-labeling to exploit high-confidence target samples safely, and a cross-domain contrastive regularizer to preserve class-discriminative geometry. We further provide an analysis offering insight into how each component contributes to target-domain generalization. Experiments on two public RF benchmarks from different wireless technologies demonstrate robust cross-day performance across diverse transfers. On WiSig–ManySig, our method achieves 99.78% mean cross-day accuracy over six source-to-target day transfers, ranking best in five cases and remaining within 0.04% of the best in the remaining case. On a LoRa benchmark, it achieves 90.64% mean cross-day accuracy over ten day-transfer pairs, validating the framework beyond Wi-Fi and under larger transfer diversity.

Conventional multi-unmanned aerial vehicle (UAV) assisted non-orthogonal multiple access (NOMA) wireless caching networks (WCNs) usually operate in a distributed and non-collaborative manner, where each UAV serves users independently without coordination or relay support. When UAVs move beyond the communication range of ground base stations (BSs), backhaul disruption occurs, leading to high user latency and limited system scalability. To address these issues, we propose a multi-layer UAV-assisted NOMA WCN architecture, where a primary UAV (PUAV) communicates with the BS and cooperates with multiple secondary UAVs (SUAVs). The PUAV not only acts as a control and coordination hub but also serves as a relay for content transmission to SUAVs when necessary. To minimize user transmission latency, we propose a joint iterative algorithm that integrates user clustering, user pairing, power allocation, and UAV deployment. First, we develop an Advanced Balanced K-Means++ (ABKM) algorithm to ensure that each cluster contains a balanced number of users and to reduce the distance between users and their serving SUAVs. Next, we derive the NOMA power allocation factor that minimizes user transmission latency, ensuring efficient resource distribution among all paired users. Furthermore, we analyze the impact of PUAV and SUAV placement on user latency and propose a two-stage particle swarm optimization (PSO)-based algorithm to iteratively optimize the deployment of all UAVs. Finally, the user pairs and power allocation are jointly optimized based on the updated deployment of all UAVs to further reduce user latency. Simulation results show that, compared with a single-layer UAV architecture and benchmark schemes, the proposed multi-layer design with joint optimization achieves lower user latency. Additionally, comparisons with the optimal power allocation search method confirm the validity of the derived NOMA power allocation factor.

Radio Frequency Fingerprint (RFF) identification plays a critical role in physical-layer security by enabling the identification of wireless devices. Recent advances have leveraged deep learning (DL) to enhance performance and robustness. However, existing DL-based RFF identification methods rely heavily on large-scale labeled signal datasets, making data annotation costly and challenging, particularly in complex electromagnetic environments. To address this limitation, we propose a self-supervised RFF identification method based on Time-Frequency Contrastive Learning (TFCL), designed to operate on unlabeled signal samples. The framework consists of two key modules: (1) a time-frequency contrastive self-supervised learning module, which constructs robust RFF feature embeddings from unlabeled signals, and (2) a CutMix-based regularized finetuning module, which enhances robustness through regularized training. Moreover, we introduce parameter freezing integrated with CutMix to adapt to diverse downstream scenarios. Extensive experiments demonstrate that the proposed TFCL-based method achieves superior feature embedding quality and identification accuracy compared to four competitive baselines, highlighting its effectiveness in real-world applications.

Millimeter-wave (mmWave) radar has emerged as a powerful sensing modality for human activity recognition (HAR) owing to its capability to capture 3D point cloud sequences without privacy concerns. However, effectively modeling the sparse, irregular, and non-uniform nature of radar data remains a major challenge. Existing approaches often rely on highly complex network architectures to improve accuracy, which leads to excessive computational overhead and poor scalability. To overcome these limitations, this paper proposes a compact hybrid feature extraction network for voxelized radar point cloud classification, which performs early-stage spatio-temporal fusion and is termed STFusionNet (Spatial-Temporal Fusion Network). The STFusionNet comprises (i) a lightweight 3D convolutional front-end, which treats consecutive temporal frames as input channels to encode motion dynamics into a compact volumetric representation and further aggregates features along the depth axis; (ii) a minimalist 2D convolutional backbone after a Depth-to-Channel Folding operation, which captures spatial features with minimal computational cost. Extensive experiments on the public MMActivity and MiliPoint datasets demonstrate that our model achieves competitive accuracy (e.g., 92.20% on MMActivity and 72.86% on MiliPoint) with only about 50K parameters and 46 MMac, outperforming or matching representative spatio-temporal baselines under a much lower computational budget. Extensive ablation experiments verify the contribution of key components, while statistical significance tests confirm the reliability of the performance improvements. These results confirm that STFusionNet offers a robust, efficient, and generalizable solution for mmWave radar-based HAR in Internet of Things (IoT) applications.

Traditional covert ambient backscatter communication (AmBC) systems suffer from a fundamental throughput limitation governed by the square root law (SRL), restricting reliable covert transmission toO(√n) bits overnchannel uses. To overcome this limitation, we introduce a non-colluding replay node that retransmits ambient radio frequency (RF) signals with randomized power, significantly increasing channel uncertainty faced by an adversarial warden (Willie) while preserving compatibility with low-power AmBC architectures. Through rigorous theoretical analysis, we demonstrate that this approach enables linear scaling of covert throughput without necessitating power reduction or prior knowledge of ambient RF signal characteristics. Furthermore, it guarantees that Willie’s total detection error probability can be driven arbitrarily close to 1, specificallyPFA+PMD= 1 − ϵ for any ϵ > 0, simultaneously achieving an arbitrarily low decoding error probability at the legitimate receiver (Bob). Unlike conventional jamming-based solutions requiring stringent synchronization or complex multi-antenna configurations, our replay mechanism operates independently from covert communication participants, substantially simplifying the decoding architecture for the legitimate receiver and reducing synchronization overhead. By increasing the ambient signal power uncertainty, the proposed architecture provides a robust, scalable framework suitable for high-rate covert communication scenarios in IoT and privacy-sensitive applications, achieving an effective balance among covertness, energy efficiency, and system robustness.

Auditory stimuli strongly shape emotional and physiological states, making them central to affective computing and mental health technologies. We present the study of three auditory conditions, spiritual meditation (SM), music (M), and natural silence (NS), using acoustic time-series signals. To support this, we introduce the Spiritual, Music, Silence Acoustic Time Series (SMSAT) dataset, a benchmark of controlled acoustic recordings with demographic diversity. We develop a contrastive learning-based SMSAT encoder that learns discriminative embeddings from ATS data, achieving 99% accuracy. In addition, we propose the Calmness Analysis Model (CAM), integrating multi-domain features for affective state classification, achieving a 99% accuracy in the three-stimulus classification task. Inter & intra-class feature space separability, calmness evaluation using Temporal Segmented Response Profiling (TSRP) confirm significant physiological differences across auditory conditions, with SM showing stronger effects on cardiac response characteristics (CRC).WaveGAN is used to generate additional dataset. Under subject-wise evaluation, CAM reached$98.4\%$accuracy, and the SMSAT Encoder achieved$96.5\%$accuracy. This work provides a validated dataset and scalable deep learning framework for stress monitoring, well-being, and therapeutic audio interventions.

With the rapid proliferation of unmanned aerial vehicles (UAVs) in civilian and industrial applications, the risk of malicious or unauthorized UAV use has become a critical security concern. Existing machine learning (ML)-based UAV recognition methods offer a certain degree of interpretability, but their performance is often limited in complex environments and across diverse UAV types. In contrast, deep learning (DL)-based methods exhibit strong representation capability, yet they generally lack physical interpretability. To address this issue, we propose an interpretable UAV recognition framework, termed frequency-aware network for UAV recognition (FANet-UAV), which performs coarse-to-fine feature learning in the frequency domain. Specifically, a multiplication filter module (MFM) is first designed to capture coarse-grained spectral patterns by exploiting multi-mode and multi-scale frequency characteristics of UAV signals. Based on these coarse representations, a convolutional neural network (CNN) is further employed to extract fine-grained discriminative features for accurate classification. Experimental results on two public UAV datasets demonstrate the effectiveness of the proposed method. In particular, FANet-UAV improves the recognition accuracy from 90.45% to 96.82% on DroneRFa and from 94.15% to 98.83% on DroneRF. Moreover, visualization results and channel-wise SHAP analysis provide both pre-hoc and post-hoc interpretability, revealing that FANet-UAV mainly relies on flight control signal (FCS) features for decision-making, while video transmission signal (VTS) features contribute less to the final recognition results.

With the growing adoption of Internet of Things (IoT) devices, ensuring the security of wireless communications has become increasingly critical. Radio frequency fingerprint identification (RFFI) has shown promise in this regard due to its capability of uniquely identifying devices. Although deep learning (DL) approaches have significantly improved RFFI performance, they typically rely on large-scale centralized data. This poses challenges in terms of privacy preservation and heterogeneous data distributions. To address the performance degradation caused by non-independent and identically distributed (non-IID) data in cross-receiver scenarios, this paper proposes a feature alignment strategy based on federated learning (FL) for RFFI. In such scenarios, due to differences in receiver hardware characteristics, deployment locations, and channel conditions, the signals captured by different receivers often exhibit distribution shifts, resulting in misaligned feature spaces across clients. The proposed method guides each client to learn aligned intermediate feature representations during local training, effectively mitigating the resulting adverse impact on model generalization. Experiments conducted on a real-world RF dataset demonstrate that the proposed method achieves higher identification accuracy and improved stability compared with representative federated baselines, including FedAvg and FedProx. The highest identification accuracy reaches 90.83%, and the performance gains are accompanied by generally reduced variance across different client configurations, highlighting the robustness and generalization capability of the proposed approach in heterogeneous wireless environments.

Specific Emitter Identification (SEI) leverages unique hardware-induced Radio Frequency Fingerprints (RFFs) for secure physical-layer authentication. However, under cross-receiver scenarios where training and testing data exhibit hardware-induced distribution shifts, deep learning models are prone to shortcut learning. In such cases, networks inadvertently exploit spurious, receiver-specific artifacts as ”shortcuts” for identification rather than extracting the genuine, intrinsic fingerprints of the transmitter. To overcome this challenge, we propose a robust multi-task learning framework, termed MTL-SEI. This framework synergizes spectrum-based feature extraction with receiver-invariant adversarial training and channel-aware auxiliary supervision. Specifically, a gradient reversal layer (GRL) is employed to suppress receiver-dependent features, while an equalization-state prediction task provides semantic guidance to disentangle channel-induced distortions. Furthermore, an uncertainty-guided task weighting mechanism is introduced to dynamically balance the multiple optimization objectives based on predictive variance. Evaluations conducted on the ManySig dataset under a rigorous receiver-disjoint protocol demonstrate the superior generalization capability of MTL-SEI. Notably, our method achieves a transmitter identification accuracy of 88.50% —representing a 37.7% improvement over the 1D-CNN baseline—and yields an average performance gain of over 6.92% compared to state-of-the-art domain generalization methods. These results validate the effectiveness of the proposed feature disentanglement mechanism in mitigating receiver-induced biases.

Indoor location-based services (LBS) have witnessed rapid growth in applications such as user tracking, healthcare monitoring, and smart facility management, driving the critical need for efficient and pervasive indoor localization. Traditional WiFi fingerprinting methods face significant challenges: multi-site localization (MSL) relies on densely deployed static WiFi sites, incurring high infrastructure costs and conflicting with the Integrated Sensing and Communication (ISAC) paradigm; single-site localization (SSL) requires complex hardware; and single mobile site localization (SMSL) suffers from poor real-time performance due to long traversal paths. To address these limitations, this paper proposes a Multi-Agent Deep Reinforcement Learning-based Collaborative Indoor Localization (MADRL-CIL) framework. MADRL-CIL leverages multiple collaborative mobile sites to dynamically acquire Received Signal Strength (RSS) fingerprints. By modeling each mobile site as an agent, the framework formulates the path selection and fingerprint acquisition task as a Multi-Agent Deep Reinforcement Learning (MADRL) problem under a Centralized Training with Decentralized Execution (CTDE) paradigm, facilitating effective collaboration among multiple mobile sites to optimize localization accuracy while minimizing localization time. Additionally, a Multi-Site Fingerprint Matching (MS-FM) model is specifically designed to process collaboratively collected RSS fingerprints, enabling fine-grained localization accuracy. Experimental evaluations in a real-world indoor environment demonstrate that MADRL-CIL achieves localization accuracy comparable to dense multi-static site deployments while provides good real-time performance.

This work is concerned with robust distributed multi-view image transmission over a severe fading channel with imperfect channel state information (CSI), wherein the sources are slightly correlated. In contrast to point-to-point deep joint source-channel coding (DJSCC), the distributed setting introduces the key challenge of exploiting inter-source correlations without direct communication, especially under imperfect CSI. To tackle this problem, we leverage the complementarity and consistency characteristics among the distributed, yet correlated sources, and propose an robust distributed DJSCC, namely RDJSCC. In RDJSCC, we design a novel cross-view information extraction (CVIE) mechanism to capture more nuanced cross-view patterns and dependencies. In addition, a complementarity-consistency fusion (CCF) mechanism is utilized to fuse the complementarity and consistency from multi-view information in a symmetric and compact manner. Theoretical analysis and simulation results show that our proposed RDJSCC can effectively leverage the advantages of correlated sources even under severe fading conditions, leading to an improved reconstruction performance.

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.

Massive multiple-input multiple-output (MIMO) array systems are a cornerstone technology for beyond fifth-generation (B5G) and sixth-generation (6G) wireless communications. This paper proposes a novel algorithm for the joint estimation of direction-of-departure (DOD) and direction-of-arrival (DOA) in massive MIMO systems under unknown gain-phase errors. The proposed method first exploits a normalized rotational invariance property to extract the relative amplitude-phase difference vectors between adjacent antenna elements. By incorporating the prior knowledge that the transmitter and receiver phase errors follow a zero-mean distribution, we formulate two decoupled cost functions to enable joint DOD and DOA estimation. We then obtain that the corresponding angular parameters efficiently through low-complexity spectral searches. Notably, the proposed method requires only one well-calibrated transmitter and one well-calibrated receiver, thereby substantially reducing the calibration effort compared with existing approaches. The gain errors are directly estimated from the amplitude-phase difference vectors, while the phase error vectors are reconstructed using the estimated DOD and DOA values. The proposed framework accommodates general conformal transceiver array geometries and effectively mitigates error accumulation in gain-phase calibration. Simulation results verify that the proposed algorithm achieves superior angular estimation accuracy and calibration precision compared with state-of-the-art techniques.

With the increasing demand for secure communication in 5G and beyond, authentication of wireless devices has become a crucial task for communication security. Radio frequency fingerprint identification (RFFI) leverages the hardware-specific features in radio frequency (RF) signals, known as radio frequency fingerprints (RFF), to achieve highprecision device identification. However, the dependence of RFFI on the physical characteristics of devices makes it vulnerable to physical spoofing attacks. This paper proposes an innovative physical spoofing attack framework that combines spoofed transmitter and legitimate transmitter models. It performs RFF modeling, RFF concealment (RFFC), and RFF spoofing (RFFS) sequentially to achieve precise spoofing of the original baseband signal. We validate the effectiveness of the proposed physical spoofing mechanism through simulations of seven types of transmitters using MATLAB Simulink. The performance is further evaluated on an RFFI model based on complexvalued convolutional neural networks (CVCNN). Experimental results show that neural networks (NN) significantly outperform the generalized memory polynomial (GMP) model in nonlinear data fitting and temporal relationship modeling. Consequently, NN-based physical spoofing methods exhibit superior attack effectiveness. Specifically, under the signal-to-noise ratio (SNR) of 15 dB, the NN-based physical spoofing method achieves a target attack success rate (TSR) as high as 98%, which is superior to adversarial attack methods. NN-based methods also enhanced performance in terms of stealthiness metrics.

Automatic modulation classification (AMC) is a key technique for identifying the modulation schemes of wireless signals, enabling improved performance and security in communication systems by accurately classifying signal types. However, most existing AMC research assumes modulation classes are part of a closed set, which can cause classifiers to misidentify unknown modulation schemes as known ones, undermining both the security and reliability of communication systems. To address this, we propose a novel open set AMC (OS-AMC) method based on deep metric learning and OpenMax (M-OpenMax). The proposed M-OpenMax-based OS-AMC method utilizes crossentropy loss and center loss to extract separable and discriminative signal features and uses OpenMax to adjust the nonnormalized score output of the model to achieve the classification of known signals and removal of unknown signals. Experimental results demonstrate that the proposed M-OpenMax-based OSAMC method outperforms other open-set AMC techniques, particularly in its ability to handle unknown modulation types.

With unmanned aerial vehicles (UAVs) widely applied in diverse fields, their potential safety risks are more prominent. Accurate UAV identification is crucial. This paper presents a method combining wavelet decomposition and the channel-enhanced attention mechanism. Two-dimensional discrete wavelet transform (2D-DWT) analyzes UAV radio frequency (RF) signal spectrograms for multi-resolution, extracting key information while decomposition data volume and computational complexity. The efficient channel attention (ECA) mechanism boosts the model’s expressiveness. Together with attention-based multi-scale convolution network (AMSCNet), it extracts multi-scale features, reducing information loss and enhancing identification. Experimental results show an average accuracy of 97.00%, outperforming residual network (ResNet) and efficient neural network (EfficientNet). It also has low computational complexity and stable performance across various scenarios, offering an efficient and reliable UAV identification solution.

With the rapid advancement of wireless communication technologies, WiFi signals have become essential for modern connectivity across diverse applications. However, their widespread deployment introduces significant security vulnerabilities, including unauthorized access, data leakage, and interference. Accurate identification of WiFi transmitters is crucial for mitigating these threats. While existing methods perform well in ideal conditions, their effectiveness degrades in real-world scenarios, particularly in environments with low signal-to-noise ratios (SNRs). To address this limitation, we propose a novel transmitter identification framework that integrates blueprint separable convolution (BSC) and a squeeze-and-excitation (SE) module. The BSC extracts critical features efficiently, while the SE module dynamically enhances feature representations. Simulation results demonstrate that the proposed approach achieves competitive or superior accuracy compared to state-of-the-art models. Moreover, the framework exhibits strong robustness, maintaining high recognition performance even in challenging transmission conditions with low SNRs.

Wi-Fi-based Human Activity Recognition (HAR) using Channel State Information (CSI) has received significant attention due to its non-intrusive nature and wide applicability in smart cities, healthcare, and smart home systems. Despite its potential, real-world deployment faces a major challenge: ensuring the model’s ability to generalize across different users, who exhibit distinct behaviors and encounter diverse environmental factors. This issue, termed Cross-User Generalization (CUG), arises from distribution shifts caused by variations in users’ body shapes, postures, movements, and environmental conditions. To address this challenge, we propose a cross-domain generalization framework based on an Attention-based Bidirectional Long Short-Term Memory (ABLSTM) network. The proposed framework enhances the generalization capabilities of HAR models by leveraging multi-source training and incorporating attention mechanisms for effective temporal feature learning. Specifically, the model learns user-invariant features across diverse training users and adapts to new users without requiring direct exposure to their data. Extensive experiments on a multi-user CSI dataset demonstrate that the ABLSTM model improves average test accuracy by 2.0%–6.7% compared to BiLSTM and GRU models, and over 18.0% compared to MLP-based models, while achieving the lowest training and testing loss. This methodology offers a robust and scalable solution for Wi-Fi-based HAR, promoting reliable deployment in complex, multi-user environments encountered in smart cities, healthcare monitoring, and security surveillance.

Specific emitter identification (SEI) is a crucial technique for recognizing individual emitters based on the unique characteristics of their radio frequency signals. Deep learning (DL)-based SEI has become the dominant method for identifying and authenticating wireless devices. However, in real-world applications, electromagnetic signals are subject to dynamic channel conditions and variations across different receivers, leading to significant performance degradation when models trained on specific datasets are applied to new, unseen environments. This variability challenges traditional DL methods, making domain generalization (DG) an essential approach to tackle this issue. In this paper, we propose a robust SEI method, latent distribution mixing (LDM), to enhance model generalization in receiver-agnostic scenarios. Our approach first applies the Fourier transform to convert time-domain signals into frequency-domain representations. Then, it mixes latent feature distributions across domains in the feature space to improve robustness, enabling the model to adapt to domain shifts effectively. We evaluated our method on a cross-receiver dataset, achieving a peak performance of 88.52%, surpassing other domain generalization methods. The experimental results demonstrate that the proposed LDM method offers a promising solution for SEI tasks in cross-receiver scenarios. Our code can be downloaded from https://github.com/frownean/LDM.

In this paper, we propose a new scheme for uplink transmission of low bit rate local data in wireless systems assisted by reconfigurable intelligent surface (RIS) arrays. With an incoming user signal that has a plane polarization (horizontal or vertical), the RIS array dynamically changes the reflected signal polarization and maps the local data on the polarization state. The base station employs two antennas, one with horizontal polarization and the other with vertical polarization, and detection of the RIS data is performed using a simple power comparator. Our results show that a bit error rate (BER) floor appears when the local data is transmitted at the user symbol rate, but the BER floor vanishes when the local data rate is reduced. The proposed technique thus turns out to be particularly suitable for transmission of low bit rate local data, and it features strong robustness to imperfections of the signal polarization.

Radio frequency fingerprinting (RFF) presents a promising solution for advancing specific emitter identification (SEI) methods, which are crucial for securing the Internet of Things (IoT). While deep learning (DL)-based SEI approaches have demonstrated strong potential, they heavily depend on large, labeled datasets, which are often difficult to obtain in real-world scenarios. This reliance limits the robustness of existing SEI methods. To overcome this challenge, we propose a robust few-shot SEI (FS-SEI) method leveraging multi-view feature fusion with attention (MFFA). By integrating interpretable signal processing (SP) features with DL features and incorporating an attention mechanism for adaptive multi-view fusion, the proposed approach enhances both identification accuracy and robustness in few-shot scenarios. Experimental results validate the effectiveness of the method, showing consistent robustness under noisy conditions and significant gains in identification accuracy. These findings highlight its strong potential for practical applications in dynamic and challenging environments.

Radio Frequency Fingerprinting (RFF) is a critical technology for enhancing physical-layer security by leveraging the unique RF characteristics of hardware, enabling authentication and anti-counterfeiting for wireless communication devices. In recent years, Deep Learning (DL) has been extensively applied in$R$FF, significantly improving identification accuracy and efficiency. However, DL- based RFF methods still encounter challenges regarding robustness, particularly in cross-channel scenarios. To address these challenges, we propose a channel-robust RFF method based on a Multi-Scale Convolutional Attention Network (MSCAN) with Random Overlay Augmentation (ROA). Specifically, MSCAN extracts and fuses features at different scales, allowing it to capture more comprehensive signal characteristics. Additionally, ROA is a combinatorial data augmentation (DA) strategy designed to simulate diverse characteristics of wireless propagation environments, thereby enhancing the adaptability and robustness of RFF in complex channel conditions. Experiments conducted on the ORACLE dataset demonstrate that our proposed method achieves over 92 % accuracy in cross-channel scenarios, outperforming the previously proposed DA strategy. The codes will be published in GitHub11https://github.com/BeechburgPieStar/SDG-for-Robust-SEI

The rapid increase in wireless devices has raised significant security and privacy concerns, positioning Specific Emitter Identification (SEI) as a crucial physical-layer security technology. While Deep Learning (DL) has been widely applied to SEI, it often requires large amounts of high-quality signal examples, which are laborious and expensive to obtain. Moreover, the DL-enabled SEI models have difficulties in extracting features from the signal examples in the testing process that are consistent with those from the signal examples in the training phase due to the wireless channel variations, further resulting in a significant reduction in identification performance. To address these challenges, we propose a channel-robust Few-Shot SEI (FS-SEI) method based on Meta-Feature Augmentation (MFA). Our approach utilizes datasets from base emitters to construct a meta-feature embedding function that can extract generalizable features from a few signal examples of target emitters. We then calculate and calibrate the statistics of these extracted features to describe the feature distribution of target emitters. A Multi-Layer Perceptron (MLP) is subsequently trained on both original and augmented features derived from this distribution, achieving a robust FS-SEI model. Experiments conducted on a Wi-Fi dataset comprising 16 emitter categories - 10 as base emitters and 6 as target emitters - demonstrate that our method achieves 93.75% identification accuracy with only 5 examples per target emitter, maintaining 92.56% accuracy even under varying wireless channel conditions. Code is available at https://github.com/lovelymimola/MFA-based-FS-SEI.

Multi-dimensional spectrum prediction is essential for spectrum sharing and dynamic spectrum access (DSA), tack-ling spectrum scarcity and improving wireless communication. Traditional methods often use machine learning (ML), which requires manual feature extraction, or deep learning (DL), which demands high computational resources. This paper proposes a lightweight multi-dimensional spectrum prediction model using an adaptive broad learning network (ABLN). The model employs a sliding window to preprocess data and establishes input layers using randomly generated feature and enhancement nodes. The weights of broad learning are determined by solving the pseudo-inverse, and the structure is incrementally extended without retraining, reducing computational complexity. An adaptive node increment module optimizes hyperparameters efficiently. Experimental results demonstrate that ABLN reduces computational overhead while maintaining robust prediction performance across various scenarios.

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.

WiFi-based passive noncontact sensing is widely regarded as a leading technology in wireless sensing, owing to its extensive application scope and favorable growth outlook. Nevertheless, although current WiFi-based sensing techniques attain remarkable accuracy in identifying activities within particular scenarios, they need stronger generalization capabilities across different targets and environments, hindering further commercial development. To address this issue, this article uses convolutional neural network (CNN), BLSTM, and attention layers to propose a cross-subject transfer learning method based on the CNN-ABLSTM algorithm model. This method combines widely used transfer learning methods with deep neural network algorithms in cross-domain sensing. Specifically, this method leverages the performance advantages of the CNN-ABLSTM algorithm model in processing time-series data like channel state information (CSI) and utilizes transfer learning to fine-tune the pretrained model from the source domain for application in the target domain with different subjects. This enables faster and more accurate achievement of cross-subject tasks. The simulated results show that the proposed new approach achieves higher recognition accuracy and shorter training times than traditional transfer learning methods for cross-subject tasks. In testing with the dataset used, it achieves up to around 85% performance of activity recognition accuracy in cross-subject tasks.

WiFi-based wireless sensing has emerged as a promising passive sensing technology that is precious for human activity recognition (HAR) across diverse applications. However, achieving robustness across varying scenarios presents a significant challenge, limiting its broader adoption. To address this issue, we propose a robust cross-scenario incremental learning (IL) method for WiFi-based wireless sensing that leverages WiFi channel state information (CSI) and elastic weight consolidation (EWC) loss. Our approach integrates a convolutional neural network and attention-based long short-term memory (CNN-ABLSTM) framework, which effectively captures the spatial and temporal features of CSI data. The IL strategy enhances model adaptability across dynamic environments, while EWC minimizes catastrophic forgetting by preserving critical weights from prior tasks. The method’s integration of a memory set and EWCLoss enables it to balance the retention of learned features with adaptation to new scenarios, effectively mitigating performance degradation across tasks. Experimental results on the MM-Fi dataset demonstrate robust cross-scenario performance: starting with initial training on scene E01, the model achieves incremental recognition in new scenes E02, E03, and E04 with cross-scenario accuracies of 88.01%, 80.16%, and 70.93%, respectively. The proposed approach substantially improves cross-scenario adaptability and test accuracy compared to traditional and cross-domain methods such as transfer learning. This work marks a significant advancement toward robust and scalable WiFi-based wireless sensing for diverse real-world applications.

Specific Emitter Identification (SEI) is pivotal for ensuring the security of the Internet of Things (IoT). Traditional deep learning-based SEI techniques often falter in real-world applications, particularly when distinguishing between legitimate and rogue devices amid noisy conditions and low Signal-to-Noise Ratios (SNR). To surmount these challenges, we propose a novel open-set SEI (OS-SEI) strategy that utilizes a Metric-enhanced Denoising Auto-encoder (MeDAE) architecture. This advanced framework incorporates a deep residual shrinkage network, significantly augmenting the denoising autoencoder’s capability, thereby bolstering its resilience against noisy environments. Further, the integration of discriminative metrics, such as center loss, markedly enhances feature discrimination, resulting in heightened accuracy of device identification. Our comprehensive experimental assessments, conducted on an Automatic Dependent Surveillance-Broadcast (ADS-B) dataset, underscore the superiority of our proposed OS-SEI method over existing models. The findings confirm our approach’s enhanced robustness to noise and its superior accuracy in device identification within open-set scenarios.

Road damage detection is essential for timely pavement maintenance and transportation safety. Traditional approaches, which rely on manual inspection, are both timeconsuming and labor-intensive. Although deep learning-based computer vision techniques have shown remarkable potential to surpass conventional methods, their real-world deployment remains challenging, primarily due to limitations in dataset diversity and the computational demands of complex models on resource-constrained hardware. To address these challenges in Internet of Things (IoT) environments, we propose an end-to-end road damage detection system optimized for edge deployment. Our approach begins with systematic video data collection using an industrial camera mounted on a moving vehicle. Experts then extract and manually annotate 13,528 frames, encompassing nine distinct categories of road damage and assets. Utilizing this dataset, we train a lightweight YOLOv5s network tailored for real-time detection. The model is subsequently quantized and deployed on an NVIDIA Jetson Xavier NX edge device. The detection results are transmitted to the cloud in real time, leveraging IoT infrastructure to enable scalable storage and analysis. The proposed system demonstrates a practical, efficient, and scalable solution for real-time road condition monitoring in industrial applications.

The early detection of ocular disorders, including Graves’ disease, myasthenia gravis, conjunctival hyperemia, conjunctivitis, and keratitis, which critically impair the vision of millions worldwide, necessitates large-scale screening predicated on ocular appearance measurements as a crucial diagnostic component. The emerging Internet of Medical Things (IoMT) introduces new avenues for local clinics to embrace portable and extensive diagnostics. However, the inherent heterogeneity and blurriness of ocular images, compounded by environmental noise, and the computational resource constraint hinder the high-precision diagnostics on IoMT devices. In response to these challenges, a linguistic-guided generative large vision model (LiGu-LVM) has been formulated to assist and enhance the diagnostic capability of IoMT-enabled ocular scanners, integrating a dynamically allocated high-speed quantization system (DAHSQS), a linguistic-guided generative local-isolation module (LiGu), an oculo visio transformatrix segmentum-analytica modulorum (OVT-SAM), and a multiscale recursive attention segmentation engine (MuRASE). DAHSQS enables the flexible aggregation and transmission of patient imagery to shift heavy diagnostic tasks from IoMT-enabled mobile ocular scanners to computational clusters, facilitating rapid facial measurements and preliminary screening via dynamic task allocation and scalable server clusters. The LiGu module employs natural language guidance to generate key image locations, using extensive prior knowledge embedded within linguistic models for precise semantic isolation. OVT-SAM synthesizes multilevel features from the large vision model, extracting intermediate characteristic information and addressing global features alongside deep semantic understanding in natural images collected from IoMT-enabled ocular scanners. MuRASE achieves high-fidelity segmentation of ocular images by incorporating contextual recursive attention mechanisms and skip connections with layer-wise reverse connectivity. Extensive experiments show proposed method surpassing 80% Intersection Over Union (IoU) in ocular semantic segmentation on the CelebA-HQ dataset, achieving an IoU of 82.9%, thus exceeding the performance of existing models by 4.9%.

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.

As the global population continues to age and technologies such as the Internet of Things (IoT) and edge computing advance rapidly, indoor human activity recognition (HAR) based on Wi-Fi channel state information (CSI) has gained significant research attention. However, the high computational complexity of existing HAR methods limits their deployment on resource-constrained devices. To address this challenge, we propose a lightweight HAR method using branch decision lightweight two-stream convolution-augmented transformer (BLTHAT) model, which integrates depthwise separable convolutions (DSC) and an improved framework structure to enhance computational efficiency. Additionally, we introduce the branch fusion network (BFN), a decision-making module designed to optimize feature processing and improve model robustness. Further enhancements in attention mechanisms and regularization strategies contribute to reducing complexity while maintaining high recognition accuracy. Comprehensive experiments were conducted on a multi-label dataset. The results demonstrate that our proposed HAR method achieves high computational efficiency with minimal complexity, making it well-suited for IoT applications. Ablation studies further confirm that the multi-branch structure of the BFN module enhances feature extraction without significantly increasing computational overhead.

The rapid growth of Internet of Things (IoT) devices poses new challenges for secure and scalable device authentication. Deep learning-based specific emitter identification (SEI) has shown promise by extracting unique features from radio frequency (RF) signals. However, its performance often degrades under varying channel conditions, as models trained on channel-specific data exhibit poor generalization. To address this, we propose a channel-distortion-agnostic SEI framework based on decentralized learning. The method enables multiple distributed clients to collaboratively train a global model without sharing raw RF data, thereby preserving privacy and reducing communication overhead. An adaptive model aggregation strategy is introduced to mitigate client heterogeneity by weighting local updates based on data characteristics. Additionally, we incorporate realistic RF impairments, including DC offset, IQ imbalance, and power amplifier nonlinearity, to simulate practical transmitter conditions. Extensive experiments under diverse wireless channels demonstrate that the proposed approach outperforms baselines, achieving superior accuracy and robustness across heterogeneous environments.

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.

Owing to the growing population and rapid urbanization, intersections, where traffic converges from various directions, have become major bottlenecks for road capacity due to frequent congestion. Recent advances in Connected and Autonomous Vehicle (CAV) technology enable signal-free intersections, where CAVs collaborate to cross intersections without collisions. Most existing signal-free intersection control methods focus on accommodating conflicts among vehicles inside the intersection and fixed-direction lanes are commonly adopted. However, the use of fixed-direction lanes is a legacy from conventional signalized intersections, where turning lanes are predetermined and fixed, so as to direct vehicles with different turning intentions to different lanes and avoid collisions. In this paper, we aim to make full utilization of the capacity of signal-free intersections by making use of free-direction lanes, which allow vehicles to make right, straight or left turns from any lane. To this end, we propose a cooperative multi-agent Deep Reinforcement Learning (DRL)-based control method for signal-free intersections with free-direction lanes. Specifically, we first study the problem of cooperatively determining coordination of vehicles inside the intersection and lane changes of vehicles on the incoming arms. Then, a multi-agent DRL-based control method for cooperatively determining coordination and lane-change of vehicles for signal-free intersections with free-direction lanes, named CD-CLC, is proposed for maximizing non-conflicting vehicles crossing the intersection simultaneously while taking vehicle fairness into consideration, to minimize travel delays of vehicles and improve traffic efficiency. Extensive experiments have been conducted to compare CD-CLC with other state-of-the-art methods to demonstrate the effectiveness of the proposed approach.

The utilization of Wi-Fi-based technology for pervasive indoor user identification has gained prominence due to its cost-effective nature and compatibility with user devices. Previous works proposed capturing the media access control (MAC) address emitted from a user’s device and using information element (IE)-based MAC de-randomization methods to mitigate the impairment caused by random MAC. However, IE types of different Wi-Fi devices are not consistently differentiated, leading to identification errors in IE-based methods. Additionally, typical Wi-Fi fingerprinting approaches require densely predeployed Wi-Fi stations, contradicting the principle of pervasive localization. To address these challenges, we propose the mobile single-station-based user identification (MS.Id) technique, which leverages Wi-Fi mobile single stations for pervasive indoor user identification. MS.Id includes mobile single-station localization (MSL) and MAC de-randomization based on users’ spatiotemporal location and IE information (DR.LIE). MSL can be implemented on a standard mobile Wi-Fi station without extensive predeployment. DR.LIE performs MAC de-randomization using the LIC algorithm to identify users with random MAC addresses. Experimental results demonstrate that MS.Id outperforms previous IE-based user identification methods and multistation localization techniques. MSL achieves a localization error of 1.15 m which is better than multistation with 12 APs of 1.40 m. DR.LIE demonstrates an identification accuracy of 95.24% which is better than AIMAC of 85.48%.

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.

Automatic modulation classification (AMC) is a fundamental technology for identifying modulation types in non-cooperative communication systems. It plays a crucial role in various applications, including spectrum monitoring, cognitive radio, and signal intelligence. Recently, deep learning (DL) based AMC methods have achieved remarkable classification accuracy. However, their practical deployment in resource-constrained edge devices remains challenging due to their high computational complexity and excessive model size. To address this limitation, we propose an ultra-lightweight AMC method based on filter pruning via geometric median (FPGM). The key idea is to leverage the geometric median as a robustness-driven filter selection criterion, effectively eliminating redundant convolutional kernels while preserving essential model representations. Specifically, we first determine the geometric median of the filters in each layer, which effectively represents the distribution of filters within that layer. Then, filters near the geometric median are identified and filtered out through the characteristics of the geometric median. Finally, the performance degradation of the model caused by the removal of filters can be restored through fine-tuning. Experimental results demonstrate that the proposed AMC method achieves a 99% reduction in model size while limiting the classification accuracy drop to merely 1.61%, significantly outperforming other lightweight AMC techniques. These results highlight the feasibility of deploying the proposed AMC model on edge Internet of Things (IoT) devices, enabling efficient real-time modulation classification with minimal computational overhead.

In dynamic and cluttered environments, traditional Simultaneous Localization and Mapping (SLAM) systems often suffer from degraded localization accuracy and unstable map construction due to the presence of moving objects and occlusions. To address these challenges, we propose DFusion-SLAM, a lightweight and robust SLAM framework that integrates an enhanced object detection module into ORB-SLAM3. The detection module is based on an improved D-Fine architecture, in which the original Transformer is replaced with a more efficient PolaLinear Attention mechanism. Furthermore, a MetaFormer-based semantic fusion structure is introduced to strengthen multi-scale feature representation. These architectural improvements jointly enhance detection accuracy while reducing model complexity, achieving a performance increase from 42.8% to 43.7% mean Average Precision (mAP). Experimental evaluations on dynamic RGB-D sequences from the TUM and Bonn datasets demonstrate that DFusion-SLAM significantly improves localization accuracy and mapping stability under dynamic conditions, while maintaining high computational efficiency. These results highlight the framework’s strong potential for real-time deployment in IoT-oriented mobile and robotic platforms operating in complex environments.

Accurate streamflow (SF) forecasting is crucial for effective water-resource management amid global climate change. Traditional ensemble SF-forecasting methods, relying on historical data and watershed characteristics, often produce uncertainties in their input, structure, and parameters, reducing their forecasting accuracy. This study introduces a variance-combined bias-correction (VCB) method, integrated with Internet of Things (IoT) technology to improve ensemble SF forecasts’ accuracy and responsiveness. The VCB method significantly improves the SF-forecasting performance by incorporating variance information from ensemble forecasts along with the ensemble mean. We apply the method to the Shiquan Reservoir in China’s Han River basin, and the results show that the VCB method outperforms the Bayesian joint probability (BJP) method, achieving an increases of 8.8% in the Nash-Sutcliffe efficiency (NSE), 0.7% in the Pearson correlation coefficient (PCC), 2.1% in the qualified rate (QR), and a 7.2% reduction in the mean absolute percentage error (MAPE). Furthermore, IoT technology integration improves method inputs’ accuracy and timeliness, showing the strongest performance during extreme weather events. Thus, by improving uncertainty management and forecasting accuracy, the IoT-integrated VCB method provides more effective support for water-resource management. Future research should apply this approach to diverse hydrological contexts and explore deeper integration with machine-learning techniques.

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 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.

Network intrusion detection (NID) is a critical area of research in network security. While deep learning based NID methods have recently achieved advanced detection performance, they often struggle with limited labeled traffic and the resource constraints of edge Internet of Things (IoT) devices. To address these challenges, we propose an advanced few-shot NID method using lightweight transfer learning (LTL), termed NID-LTL. Our approach begins by pre-training a detection model on the large-scale auxiliary dataset to learn universal representations of network traffic characteristics. Then, an automatic pruning strategy is crafted to prune the pre-trained model, which uses a kernel based nonlinear traffic feature selection algorithm to filter out the key information most relevant to the original traffic. Finally, the layer-wise knowledge distillation method is combined to transfer the useful knowledge learned by the pre-trained model to a lightweight student model. This method can not only quickly adapt to novel few-shot NID tasks, but also further compress the model size, reduce computational and storage overhead. Experimental results demonstrate that the proposed NID-LTL method has excellent classification performance with small model sizes, low parameter counts, and low floating point operations (FLOPs). Especially, in the 1-shot scenario, the NID-LTL method achieves 89.38% classification accuracy with only 1.41% of the parameters in the original model.

In this article, a novel multiuser multiple-input-multiple-output (MIMO) communication system for Internet of Things (IoT) is proposed, where the aerial reconfigurable intelligent surface (ARIS) and nonorthogonal multiple access (NOMA) are used as the sum rate enhancement pathway. The base station (BS) has multiple antennas that transmit superimposed signals to multiple users. The passive ARIS serves as a flexible transmit relay to reduce path loss and improve channel gains. Users are divided into several groups based on their channel status, each sharing a radio frequency (RF) chain. To maximize the sum rate of all users, the placement of ARIS, the passive/active beamforming design and the power allocation among users are jointly optimized. As the joint optimization for user grouping, passive/active beamforming and power distribution is formulated as a mixed-integer nonlinear program (MINLP) which is nonconvex and coupled and hence, obtaining an optimal solution is challenging. In this article, the problem is decoupled into three subproblems and solved alternately efficiently. The numerical results demonstrate that the suggested MIMO-ARIS-NOMA system can achieve higher sum rate performance than traditional schemes.

In millimeter-wave and terahertz band communication systems, precise beam prediction is crucial for optimizing network performance and enhancing signal transmission efficiency. Traditional beam prediction methods have primarily relied on single-modal data, which often fails to capture the comprehensive environmental information necessary for optimal accuracy. In contrast, multi-modal data-based approaches offer a more promising solution by leveraging the strengths of diverse data sources. However, many existing fusion methods are static, inadequately accounting for variations in information content across different modalities, which can hinder the full utilization of each modality’s advantages. To address these limitations, this paper proposes an advanced multi-modal beam prediction method that integrates multipath-like data augmentation (MLDA), cross-modal feature enhancement (CMFE), and an uncertainty-aware dynamic fusion mechanism. Our approach combines image and radar data to predict beam indices, dynamically adjusting the weights of different modalities to accommodate varying information densities. The proposed method employs ResNet34 for feature extraction from the multi-modal data, followed by a cross-modal feature enhancement module that aggregates complementary information from the image and radar data. Finally, the dynamic fusion mechanism integrates the predictions from the single-modal data. Experimental results demonstrate that our method significantly improves the accuracy and robustness of beam prediction, achieving an overall accuracy of 89.72%. The performance of the proposed method is further validated through comparisons with various existing methods and comprehensive ablation studies, highlighting its superiority in multi-modal assisted beam prediction scenarios.

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.

Radio frequency fingerprint identification (RFFI) is regarded as one of the most promising techniques for managing and regulating Internet of Things (IoT) devices. This technology analyzes the unique electromagnetic signals emitted by wireless devices to enable precise identification and authentication. Most existing RFFI methods focus on RF signals collected in specific scenarios. However, in real-world applications, signals are often collected at different times or from varying deployment locations, leading to differences between the training and testing distributions. The study of RFFI methods under these conditions remains underexplored. To address this gap, this paper introduces a cross-domain RFFI framework centered on adaptive semantic augmentation (ASA). The framework integrates a computationally efficient multi-resolution spectrogram decomposition strategy with a feature-sensitive multi-scale network. The ASA method enhances RFFI accuracy in cross-domain settings by linearly interpolating between two distinct semantic features to create new semantics for further identification. The proposed approach leverages two-dimensional discrete wavelet transform (2D-DWT) to decompose the raw spectrogram into four sub-bands, followed by a multi-scale network to extract critical semantic features for the ASA method. Simulation results show that the proposed ASA method significantly improves Unmanned Aerial Vehicle (UAV) identification performance, achieving accuracies of 93.05% and 98.90% on two different cross-domain datasets, respectively, outperforming existing data augmentation (DA) methods. Furthermore, generalizability validation demonstrates that the proposed method performs outstandingly across other Internet of Things (IoT) applications.

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.

Specific emitter identification (SEI), a crucial technology at the physical layer of communication protocols, exploits unique radio frequency fingerprints (RFFs) to distinguish between individual emitters. Deep learning (DL) has been widely applied to SEI due to its remarkable capability in uncovering hidden features and distinguishing between different devices. However, DL-based SEI approaches typically require extensive labeled datasets, which are difficult to obtain in real-world scenarios, thus limiting their practical applicability. To address this challenge, we propose a novel few-shot SEI (FS-SEI) method based on bi-interpolative metric learning (Bi-InterML), highly reducing the amount of data needed to adapt the algorithm to a new environment and simultaneously avoiding pretraining. Our approach enhances data quality through wavelet coefficient-based and sequence bi-interpolation, generating enriched data used alongside the original dataset for classification via a complex-valued convolutional neural network (CVCNN). Additionally, interpolative metric learning (IML) is employed to constrain feature distances, enhancing feature discriminability. Experimental results on a real-world Wi-Fi dataset demonstrate the effectiveness of the proposed Bi-InterML-based FS-SEI method, achieving an identification accuracy of 91.48% with 10 samples per category, while it outperforms comparative methods by a margin of 9.64% to 43.18% in the case of 1 sample per category. Furthermore, its generalizability is validated on the base station (BS) dataset, where the proposed method consistently outperforms existing approaches in few-shot scenarios.

Specific Emitter Identification (SEI) is crucial for ensuring the security of physical layer communication. However, signal characteristics can be affected by various factors such as environmental and equipment variations. An effective SEI system must continuously learn and adapt to these changes to maintain accurate signal recognition. This study proposes an advanced domain incremental learning (DIL) framework for SEI, named Adaptive Domain-Incremental Learning with Knowledge Replay and Domain Alignment (ADIRA). ADIRA employs knowledge replay and distillation strategies, along with adaptive coefficients, to balance the model’s performance in recognizing signals across both new and old domains. To address the variations in signal data feature distributions across different domains, we introduce a domain alignment strategy based on adversarial training. This approach integrates embedding distillation loss with supervised contrastive loss, significantly enhancing the model’s adaptability to domain changes. Experimental results on two benchmark datasets demonstrate that ADIRA achieves performance only 0.42% and 1.71% lower than joint training, with replay samples constituting just 1.1% and 1.5% of the training set, effectively mitigating catastrophic forgetting.

In this paper, authentication for mobile radio frequency identification (RFID) systems with low-cost tags is investigated. To this end, an adaptive modulus (AM) encryption algorithm is first proposed. To further enhance security without requiring additional storage for new key matrices, a self-updating encryption order (SUEO) algorithm is designed. Furthermore, a diagonal block local transpose key matrix (DBLTKM) encryption algorithm is presented, which effectively expands the feasible domain of the key space. Building upon these three algorithms, a novel joint AM-SUEO-DBLTKM encryption algorithm is constructed. Making full use of the strengths of the proposed joint algorithm, a two-way RFID authentication protocol, named AM-SUEO-DBLTKM-RFID, is proposed specifically for mobile RFID systems. In addition, the Burrows-Abadi-Needham (BAN) logic and security analysis indicate that the proposed AM-SUEO-DBLTKM-RFID protocol can effectively combat various typical attacks. Numerical results demonstrate that the proposed AM-SUEO-DBLTKM algorithm can save 99.59% of tag storage over traditional algorithms. Finally, the proposed AM-SUEO-DBLTKM-RFID protocol achieves both low computational complexity and low storage overhead, making it well-suited for deployment in resource-constrained, low-cost RFID tags.

Physical Layer Authentication (PLA) emerges as a promising security solution, offering efficient identity verification for the Internet of Things (IoT). The advent of 5G/6G technologies has ushered in an era of extensive device connectivity, diverse networks, and complex application scenarios within IoT ecosystems. These advancements necessitate PLA systems that are highly secure, robust, capable of online processing, and adaptable to unknown channel conditions. In this paper, we introduce a novel two-stage PLA framework that synergizes channel prediction with power-delay attributes, ensuring superior performance in mobile and time-varying channel environments. Specifically, our approach employs Sparse Variational Gaussian Processes (SVGP) to accurately model and track real-time channel variations, leveraging historical data for online predictions without incurring significant computational or storage overhead. The second stage of our framework enhances the robustness of the authentication process by incorporating power-delay features, which are inherently resistant to temporal fluctuations, thereby eliminating the need for additional feature extraction in noisy settings. Moreover, our authentication scheme is designed to be distribution-agnostic, utilizing Kernel Density Estimation (KDE) for non-parametric threshold determination in hypothesis testing. Theoretical analysis underpins the generalization capabilities of our proposed method. Simulation results in mobile scenarios reveal that our two-stage PLA framework reduces complexity and significantly improves identity authentication performance, particularly in scenarios with low signal-to-noise ratios.

Radio frequency fingerprint identification (RFFI) is essential for ensuring device security in ubiquitous wireless communications and the Internet of Things (IoT). Although deep learning (DL) and self-supervised learning (SSL) techniques have significantly enhanced RFFI system performance, they often depend on data sourced from open internet datasets or collected in uncontrolled environments. This dependency heightens the risk of malicious data tampering, particularly in adversarial environment, thereby exacerbating security vulnerabilities. To address this issue, this paper investigates the vulnerability of SSL-based RFFI systems to backdoor attacks and introduces a novel method utilizing a spectrum-enhanced insensitive perturbation (SEIP) trigger. We develop an SSL-based RFFI backdoor attack framework, providing new insights into SSL security within the signal processing domain. The SEIP trigger introduces subtle perturbations in the frequency domain, enabling highly effective and covert backdoor attacks. Experimental results demonstrate that the SEIP trigger outperforms existing triggers regarding attack effectiveness across various channel conditions while maintaining strong stealthiness against backdoor defense mechanisms. These findings confirm that the SEIP trigger achieves an optimal balance between attack effectiveness and stealthiness. Moreover, this paper offers a new perspective for evaluating the security of RFFI systems and the resilience of backdoor defense strategies.

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.

Malware traffic classification (MTC) is a crucial step in network intrusion detection, which is significant for network security and management. With the continuous evolution of malware traffic, traditional MTC methods are difficult to adapt efficiently to new traffic categories, and manually designed neural network structures suffer from performance bottlenecks and low design efficiency. Hence, we propose an enhanced MTC method based on expandable class incremental learning (CIL) with architecture search. The architecture search can automatically design the optimal neural network structure tailored to different network traffic characteristics, avoiding the limitations of manually designing network structures and improving classification performance. Meanwhile, expandable CIL allows the MTC model to gradually learn new traffic categories without forgetting previous knowledge, avoiding the computational overhead and efficiency loss caused by frequent retraining of the model. The experimental results demonstrate that the proposed CIL-MTC approach surpasses advanced incremental learning methods on both the Edge-IIoTset and ISCX VPN-nonVPN datasets, achieving superior classification performance while maintaining lower average trainable parameters and training costs. Especially, it achieves an average incremental accuracy of 98.55% and 99.09% on the Edge-IIoTset dataset with incremental tasks of 5 and 2, respectively.

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.

By extracting radio frequency (RF) fingerprints from received signals, specific emitter identification (SEI) becomes a promising technique for physical layer identification of wireless devices. Recently, channel-robust SEI has attracted increasing attention due to the weak robustness exhibited by deep learning (DL)-based SEI methods in cross-channel conditions. To address these limitations, we propose a novel channel-robust SEI framework based on single-source domain generalization (SDG). Initially, we analyze the weak robustness of existing SEI methods from the perspective of the “shortcut learning” phenomenon in DL. Shortcut learning may lead traditional SEI methods to prioritize easily-mined, yet transient, channel characteristics in signal samples, rather than focusing on the more stable RF fingerprints derived from hardware differences. Next, from the perspective of SDG, we outline the optimization goal to rectify the shortcut learning in SEI. Inspired by this optimization goal, we then propose a channel-robust SEI method. This method consists of feature embedding through a multi-scale convolutional attention network (MSCAN), domain expansion using random overlay augmentation (ROA) to generate multiple virtual domains, and dual alignment strategy based on contrastive learning. Specifically, supervised contrastive learning is implemented for category-wise alignment, while supervised contrastive adversarial learning is utilized for domain-wise alignment. This dual alignment strategy can optimize the MSCAN to learn discriminative and domain-invariant feature representations, thereby enhancing the robustness of SEI. Simulation experiments on the ORACLE dataset and the WiSig dataset have demonstrated the superiority of our method compared to state-of-the-art techniques. The codes can be downloaded from GitHub (https://github.com/BeechburgPieStar/SDG-for-Channel-Robust-SEI).

User clustering presents a significant design challenge when implementing non-orthogonal multiple access (NOMA) in multiple-input multiple-output (MIMO) systems. To fully exploit the potential of power domain multiplexing and achieve better performance of NOMA, users must possess significant variations in their channel gains. Consequently, it becomes necessary to cluster users based on their distinct channel gain characteristics. However, using random user clustering often leads to suboptimal outcomes, while the exhaustive search method is burdened with exorbitant complexity. To achieve the balance between system performance and complexity, this paper proposes a user clustering scheme that relies on Jaccard coefficient, which is a measure of differences in user channels, ranging from 0 to 1. A value of 0 indicates complete dissimilarity, while a value of 1 indicates complete similarity. By calculating the Jaccard coefficient, we can identify users who are dissimilar to the centroid as a cluster. Additionally, a new power allocation algorithm is developed to maximize the sum spectral efficiency by employing successive convex approximations (SCA), taking into account both spectral efficiency and user quality of service. The simulation results demonstrate that the algorithm proposed for maximizing the sum spectral efficiency exhibits a higher convergence rate and can substantially enhance the sum spectral efficiency in comparison to the full power control (FPC) scheme.

As widely deployed WiFi sensors in indoor scenarios, e.g., WiFi access points and WiFi monitors, WiFi signal-based indoor localization has attracted increasing attention from research communities in the past decade. Among various WiFi-based localization techniques, received signal strength (RSS) fingerprinting based on multiple sensors reveals its superiority and effectiveness in complex indoor environments. Existing multi-sensor-based techniques mainly focus on designing efficient algorithms to improve localization performance. However, the limitations of 1) densely pre-deployed WiFi sensors and, 2) sensitivity to changing sensors are not considered appropriately. In this paper, we propose a novel technique called Single Mobile Sensor (SMS) localization, which leverages a single mobile sensor for indoor localization. The SMS localization technique employs a fingerprinting technique with a custom-designed model, named SMS Fingerprint Matching (SMSFM) model, which is responsible for matching fingerprints constructed by a single mobile sensor to estimate targets' location. Numerous experiments conducted on a practical testbed have revealed that the SMSFM model surpasses conventional models, leading to SMS localization delivering competitive localization accuracy compared to previous multi-sensor-based technologies, despite relying solely on a single sensor.

As unmanned aerial vehicles (UAVs) become increasingly prevalent in various environments, their detection is essential for ensuring safety and effective management. For non-standard transmitter waveforms, identifying a specific model poses challenges, and most researchers focus on developing deeper and broader architectures to improve performance at the expense of computational burden and speed, which is not suitable for the deployment of UAV radio frequency (RF) fingerprinting identification. In this paper, we propose a novel multi-resolution analysis-based method for UAV identification. We develop a lightweight, multi-scale convolutional network that utilizes various receptive fields to extract unique hardware intrinsic features. We employ the two-dimensional Discrete Wavelet Transform (2D-DWT) to innovatively decompose the low-frequency and the high-frequency components of the RF signal spectrogram into four distinct sub-bands. Simulation results indicate that our proposed methods outperforms other state-of-the-art UAV identification methods in terms of both performance and computational complexity.

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).

As economic development and social well-being demands grow, road maintenance and safety have become paramount. This study introduces an intelligent road damage detection system using the You Only Look Once v5s (Yolov5s) network, aimed at improving the efficiency and accuracy of road condition assessments through advanced deep learning techniques. A comparative analysis of object detection algorithms, including You Only Look Once version 3 (Yolov3), Single Shot MultiBox Detector (SSD), and YOLOv5$s$, highlights YOLOv5s's superior speed and accuracy balance. Experimen-tal results demonstrate YOLOv5s's exceptional performance in accuracy, recall, and mean Average Precision (mAP) metrics. This intelligent system offers a robust technical solution to the global challenge of road maintenance, significantly enhancing road safety and maintenance effectiveness.

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 this paper, we investigate the effect of spatial correlation on the performance of wireless systems with reconfigurable intelligent surface (RIS) arrays using pilot-aided channel estimation. The RIS array is partitioned into several tiles, a pilot is inserted at or near the center of each tile, and the phase of the channel coefficient estimate at the pilot location is used to determine a common phase shift for configuring all RIS elements of that tile. The analysis shows that while a large number of pilots are needed in the absence of spatial correlation to approach the performance of optimally configured RIS arrays, a small number is sufficient in the presence of spatial correlation. The implication of this is that spatial correlation between the RIS array elements appears as a desirable feature, which not only reduces the number of pilots needed for channel estimation at the base station and the receiver complexity, but also the overhead involved in the feedback of the phase information for configuring the elements of the RIS array.

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.

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 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.

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.

The rapid changes in high-mobility vehicle environments make it challenging for base stations (BS) to obtain comprehensive channel state information. Furthermore, road and traffic safety require communication with low latency and high reliability, posing significant challenges to spectrum resource allocation in vehicular networks. To address these challenges, this paper proposes a method combining dueling double deep-Q network (D3QN) reinforcement learning (RL) with long short term memory (LSTM) network. By using a Manhattan Grid Layout City Model as the foundational environment, a multi-agent model is constructed, with each vehicle-to-vehicle (V2V) link acting as an individual agent. These agents collaborate and interact with the environment, receiving feedback, and then determining the optimal resource allocation to ensure both superior mobile service and a safe driving environment. The experimental results indicate that our proposed method outperforms the conventional D3QN network in both the vehicle-to-infrastructure (V2I) links and the V2V links.

Malware traffic classification (MTC) plays an important role in cyber security and network resource management for the secure Internet of Things (IoT). Many deep learning (DL)-based MTC methods have been proposed due to their robustness and effectiveness with self-designed model architecture. However, to completely adjust complex parameters in the DL model, the architecture design of the DL model requires substantial professional knowledge and effort from human experts. To solve these problems, we propose an automatic and efficient MTC method using neural architecture search via proximal iterations (NASP), which can automatically and efficiently search the optimal model architecture according to the network traffic in the realistic environment. Specifically, we first describe NAS as a constrained optimization problem by keeping the search space differentiable and forcing the architecture to be discrete in the search process. Second, a suitable regularizer is introduced to balance the complexity and performance of the model architecture. Finally, the simulation results show that the proposed NASP-aided MTC method not only can efficiently and accurately search the optimal classification model architecture on the USTC-TFC2016 data set and the Egde-IIoTset data set but also compared with the typical MTC methods it can achieve the optimal classification performance with the fewer parameters as well as the floating-point operations (FLOPs).

The inherent flexibility of small unmanned aerial vehicles (UAVs) enables their deployment across various emerging markets. Unauthenticated UAVs pose a significant threat if they intrude into aviation-sensitive areas. To address this issue, deep learning (DL)-based radio frequency fingerprint identification (RFFI) has been developed as a promising approach for identifying illegal UAVs. However, these commonly used DL-based methods demand high computation and storage requirements, which are not suitable for the deployment of RFFI. In this paper, we propose an efficient and low-complexity RFFI method for UAV identification. Specifically, we design a lightweight backbone network consisting of lightweight multi-scale convolution (LMSC) blocks that can significantly reduce the model size and enhance the feature extraction ability. The simulation results indicate that our proposed UAV RFFI method outperforms other state-of-the-art and popular DL-based RFFI methods in terms of both identification performance and complexity. The identification accuracy surpasses that of all other methods at low signal-to-noise ratios (SNRs) and achieves nearly 100% accuracy at high SNRs. To further enhance model efficiency, we employ data truncation in our experimental simulations, demonstrating that a sample length of 2000 is sufficient to retain high identification performance. Additionally, we incorporate the Mixup regularization strategy, which improves accuracy without increasing the complexity, especially as sample length decreases.

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.

Specific emitter identification (SEI) plays an important role in secure Industrial Internet of Things (IIoT). In recent years, many SEI methods based on machine learning (ML) and deep learning (DL) have been proposed due to their great performance. However, DL-based SEI methods are accompanied by huge computation overhead, which is not suitable for IIoT applications. In addition, the existing ML-based SEI methods rely on feature extraction and a heavy and redundant classifier, which do not ensure optimal feature combination and efficient computation. To solve the above problem, we propose an improved DL-based SEI method using a signal feature embedded knowledge graph (KG) composed of universal features. To the best of our knowledge, this is the first attempt to apply KG for SEI technology. Specifically, we explore an adaptive feature combination (AFC) strategy through the attention mechanism to realize an efficient SEI classifier. The simulation results show that the proposed KG-AFC algorithm outperforms existing SEI methods in identification performance and computation overhead. At the same time, under the optimal compression rate, the average accuracy of the proposed SEI algorithm is higher than 99.2% and can effectively reduce complexity. The code and the data set can be downloaded fromhttps://github.com/Lollipophua/KG-AFC.

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.

The implementation of Scenario Classification (SC) plays a pivotal role in various edge intelligence applications, notably in fields such as autonomous driving, navigation, and remote sensing. With recent advancements, deep learning (DL) techniques have substantially improved SC, delivering remarkable results in classification tasks. However, the integration of DL in SC brings significant computational demands, posing challenges for deployment on edge devices where resources are constrained. Addressing this issue, we propose a novel Low-Resource Scenario Classification (LR-SC) approach, primarily focused on model pruning. This strategy aims to reduce computational power and storage needs, thus optimizing resource utilization in edge intelligence applications. Our approach involves the application of an ℓ2 regularization and a threshold-based pruning method, which selectively eliminates non-essential connections. This is followed by a systematic process of alternating pruning and fine-tuning to mitigate any performance loss due to the pruning. Experimental evaluations of the LR-SC method have shown its effectiveness; it substantially lowers the parameter count to merely 24% of the original model, while simultaneously achieving a 0.42% increase in classification accuracy.

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.

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.

Direction-of-arrival (DOA), also referred to as angle-of-arrival (AOA), is an excellent choice for unmanned aerial vehicle (UAV) localization and has garnered significant attention recently. In this article, we propose a novel two-dimensional (2D)-DOA auxiliary framework for anonymous UAV localization. At its core, this framework relies on measuring 2D-DOA using a monostatic multiple-input–multiple-output (MIMO) radar configured with electromagnetic vector sensors (EMVSs). Differing from existing mainstream methods, the multipath effect of the UAV is taken into account. A rearrangement multiple signal classification (R-MUSIC) algorithm is developed. The algorithm recovers the covariance matrix rank by connecting spatial responses from both transmitting (Tx) or receiving (Rx) arrays with radar cross-section (RCS) coefficients. Subsequently, rough 2D-DOA estimates are obtained using the vector cross-product (VCP) technique. These rough estimates are then used to establish good initialized values for refined 2-D spectral peak searching. Finally, leveraging the relationship between 2D-DOA and Tx/Rx array coordinates, a UAV’s 3-D position can be directly computed. This framework remains insensitive to the geometric configuration of Tx/Rx arrays while striking a balance between complexity and accuracy. Numerical simulation experiments confirm the improvements of our developed R-MUSIC algorithm.

Malware traffic classification (MTC) is one of the important techniques to ensure the security of cyberspace, which aims to detect anomalies and classify different types of network traffic. Recently, MTC methods based on deep learning (DL) have shown their excellent performance. However, these DL-based methods rely on datasets with manually labeled samples for training, which are costly and hard to obtain. To address this problem, this paper proposes a novel self-supervised MTC method based on the framework of masked auto-encoder (MAE). Specifically, MAE first constructs a reasonable unsupervised pretext task with a random masking strategy, which reduces the redundant information in samples and speeds up the pre-training process. The transformer-based backbone network then efficiently extracts features from the non-redundant traffic data efficiently. The proposed MTC-MAE method employs self-supervised learning on a large-scale unlabeled dataset to acquire unbiased features, and fine-tunes on specific datasets to adapt to diverse traffic classification scenarios. Simulation experiments show that our proposed MTC-MAE method is able to learn universal features with high quality and has excellent classification performance on various downstream datasets. The datasets we used, code implementation, and pre-trained models are available on GitHub.

Ensuring network security, effective malware detection is of paramount importance. Traditional methods often struggle to accurately learn and process the characteristics of network traffic data, and must balance rapid processing with retaining memory for previously encountered malware categories as new ones emerge. To tackle these challenges, we propose a cutting-edge approach using self-paced class incremental learning (SPCIL). This method harnesses network traffic data for enhanced class incremental learning (CIL). A pivotal technique in deep learning, CIL facilitates the integration of new malware classes while preserving recognition of prior categories. The unique loss function in our SPCIL-driven malware detection combines sparse pairwise loss with sparse loss, striking an optimal balance between model simplicity and accuracy. Experimental results reveal that SPCIL proficiently identifies both existing and emerging malware classes, adeptly addressing catastrophic forgetting. In comparison to other incremental learning approaches, SPCIL stands out in performance and efficiency. It operates with a minimal model parameter count (8.35 million) and in increments of 2, 4, and 5, achieves impressive accuracy rates of 89.61%, 94.74%, and 97.21% respectively, underscoring its effectiveness and operational efficiency.

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.

Automatic dependent surveillance-broadcast (ADS-B) has been widely deployed on aircraft to facilitate aviation information exchange and improve air traffic safety. However, its broadcast nature and lack of security considerations like encryption and authentication have caused the counterfeit of ADS-B messages to be straightforward. Flooding forged messages to legitimate aircraft, denial-of-service (DoS) attacks threaten flight security severely. In this paper, we propose a practical security solution against DoS attacks on ADS-B based on high-precision timestamp and position information. The solution achieves high feasibility and reliability by accommodating measurement errors of physical quantities. Besides, it preserves ADS-B frame size and ensures efficient computation in frame generation and verification. Comprehensive security analyses demonstrate robust filtrations of the proposed solution on malicious messages from DoS adversaries with different capabilities. Further simulations on real-world aviation data exhibit significant defensive performance realized by the DoS-immune ADS-B security solution. Whether adversaries can only intercept ciphertext, or they have opportunities to acquire decrypted messages, all DoS attacks on ADS-B are successfully thwarted by the solution. Even for adversaries with victim aircraft location estimation capacity, the solution resists all DoS attacks transmitting less than 50 forged messages per second.

The increasing significance of unmanned aerial vehicles (UAVs) in mobile edge computing (MEC) has captured considerable attention. Nevertheless, the effectiveness of UAVs-assisted MEC networks is hampered by challenges, such as limited communication capacity and onboard power. To tackle these issues, this study develops a constrained multiobjective optimization model designed to enhance the performance of UAVs-assisted MEC networks, focusing on system capacity, energy consumption, and task latency. As a result, this problem manifests as a complex constrained multiobjective optimization problem. The study then proposes a constrained multiobjective decomposition evolutionary algorithm (CMODEA) with low-computational complexity. This algorithm employs an adaptive individual comparison strategy, balancing diversity and convergence, and integrates an optimally guided differential evolution strategy for efficiently approximating optimal solutions. Additionally, it incorporates an adaptive constraint handling method, effectively managing existing constraints. The CMODEA aims to simultaneously optimize system capacity, energy consumption, and task latency while meeting the computational resource requirements of UAVs and ensuring acceptable user task latency levels. Simulation results demonstrate the algorithm’s effectiveness in significantly enhancing capacity, reducing energy consumption and latency, without greatly increasing algorithm complexity.

This article proposes a new framework of aerial reconfigurable intelligent surface (ARIS) enhancing the nonorthogonal multiple access (NOMA) system. The base station (BS) transmits superimposed signals to multiple users with different channel gains through ARIS which can flexibly change channel conditions and perform intelligent NOMA operations. It ensures that our system can perform well in providing services to multiple users simultaneously. In this system, the placement of the unmanned aerial vehicle (UAV) is jointly optimized along with the AIRS passive beam and the multiuser power allocation in order to maximize the communication sum rate. Since the joint optimization problem is nonconvex and coupled, it is hence disintegrated into three subproblems and it is solved alternately through the successive convex approximation (SCA). Moreover, semi definite programming (SDP) is used to deal with the rank one constraint of RIS reflection matrix and comparisons are made using particle swarm optimization (PSO). The numerical results show that the proposed ARIS-NOMA framework can achieve better sum rate performance than traditional NOMA with fixed RIS and OMA-ARIS.

Specific emitter identification (SEI) is important to guarantee the security of device administration. Recently, to increase the effectiveness of the recognition, traditional SEI employing only one sensor has been extended to the scenario with multiple sensors. However, the inherent distortion at different sensors impacts the radio frequency fingerprints (RFFs) of the emitter independently, which inevitably leads to the non-universalization of the features extracted at different sensors. Besides, variational modal decomposition (VMD), which is an effective preprocessing in SEI, has not been well investigated in noisy scenarios. To combat the environment noise, this paper proposes two joint VMD (JVMD) algorithms, i.e., JVMD for ignoring the distortions at sensors (I-JVMD) and JVMD for considering the distortions at sensors (C-JVMD). Specifically, I-JVMD exploits the consistency of the central frequencies and intrinsic modal functions (IMFs) of multiple sensors, and C-JVMD further estimates and filters out the phase noise at each sensor that may distort the RFFs of the emitter. Simulations of the proposed JVMD algorithms and their corresponding applications in SEI are provided on two real-world datasets. When compared with the traditional VMD, the proposed ones improve the accuracy of device classification and the robustness towards noise.

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.

Malware traffic classification (MTC) is one of the important research topics in the field of cyber security. Existing MTC methods based on deep learning have been developed based on the assumption of enough high-quality samples and powerful computing resources. However, both are hard to obtain in real applications especially in availability of IoT. In this paper, we propose a few-shot MTC (FS-MTC) method combining knowledge transfer and neural architecture search (i.e. NAS-based FS-MTC) with limited training samples as well as acceptable computational resources, in order to mitigate the identified challenges. Specifically, our proposed method first converts the raw network traffic into traffic images through data pre-processing to serve as input data for the neural network. Second, we use neural architecture search to adaptively search for the effective feature extraction model on the source domain (including Edge-IIoTset, Bot-IoT, and benign USTC-TFC2016). Third, the searched model is pre-trained on source task to achieve the generic feature representation of malware traffic. Finally, we only use few-shot malware traffic samples to fine-tune the pre-trained model to quickly adapt to new types of MTC tasks in realistic network environments. The experimental results show that the proposed NAS-based FS-MTC method has great scalability and classification performance in different FS-MTC tasks, including 5-wayK-shot USTC-TFC2016 dataset and 10-wayK-shot CIC-IoT dataset. Compared with state-of-the-art methods in the field of malware classification, the proposed NAS-based FS-MTC has higher classification accuracy. Especially in the 1-shot case of the USTC-TFC2016 dataset, its average accuracy is as high as 86.91%.

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.

Reconfigurable intelligent surface (RIS) is a promising paradigm for implementing intelligent reconfigurable wireless propagation environments in the 6G era. However, most of the existing studies focus on utilizing RIS deployed on buildings to provide services to users or constructing a RIS-assisted system framework for static users, which greatly limited application in real-time changing vehicular communication environments. As a result, combining unmanned aerial vehicles (UAVs) with RIS (RIS-UAV) plays a crucial role in various wireless networks due to their high mobility. To maximize the communication rate between base station (BS) and mobile vehicle, we propose a position prediction strategy for vehicles that facilitates real-time adjustment of UAV trajectories and RIS phase shifts, enhancing communication in dynamic environments. Deep reinforcement learning (DRL) algorithm is utilized to solve the above question, which achieves a good effect on convergence in continuous action space. Simulation results demonstrate that compared with benchmark schemes, the algorithm we suggested has significant performance gains, that is to maximize the communication rate under system constraints and guarantee the reliability of the communication.

Traffic classification is a critical task in network security and management. Recent research has demonstrated the effectiveness of the deep learning-based traffic classification method. However, the following limitations remain: (1) the traffic representation is simply generated from raw packet bytes, resulting in the absence of important information; (2) the model structure of directly applying deep learning algorithms does not take traffic characteristics into account; and (3) scenario-specific classifier training usually requires a labor-intensive and time-consuming process to label data. In this paper, we introduce a masked autoencoder (MAE) based traffic transformer with multi-level flow representation to tackle these problems. To model raw traffic data, we design a formatted traffic representation matrix with hierarchical flow information. After that, we develop an efficient Traffic Transformer, in which packet-level and flow-level attention mechanisms implement more efficient feature extraction with lower complexity. At last, we utilize MAE paradigm to pre-train our classifier with a large amount of unlabeled data, and perform fine-tuning with a few labeled data for a series of traffic classification tasks. Experiment findings reveal that our method outperforms state-of-the-art methods on five real-world traffic datasets by a large margin. The code is available at https://github.com/NSSL-SJTU/YaTC.

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.

Contactless Wi-Fi sensing, using channel state information (CSI) fingerprints, plays a pivotal role in communication, smart healthcare, and industrial automation. Deep learning has revolutionized the efficiency of non-contact sensing technology. Owing to its robust feature extraction capabilities and the interconnectedness of diverse sensing tasks, methods that address multiple tasks at once, like joint activity recognition and indoor localization (JARIL), have gained prominence. The primary goal of JARIL is to improve performance while reducing computational demands. Nevertheless, there remains substantial potential for enhancing its effectiveness through additional refinement and optimization measures. To address this, we introduce a regularized multi-label learning (RML) framework specifically designed for JARIL. This framework combines a parameter-efficient backbone network based on multi-scale separable convolution with residual connections, and a regularization training strategy. The latter strategy boosts performance by linearly combining two distinct CSI samples with their labels, creating new training instances in the training process. Simulation results show that the proposed method boasts a recognition accuracy of 91.73% and a localization precision of 99.64%. This marks an improvement of 4.32% and 3.60% respectively, in comparison to the prior ResNet1D+-based JARIL method. The codes can be downloaded fromhttps://github.com/BeechburgPieStar/JARIL.

Intelligent Reflecting Surface (IRS) represents a significant breakthrough in wireless communications, allowing the reconstruction of wireless channels even for occluded users to the base station (BS). Estimating the Direction-of-Arrival (DOA) of a source oriented toward Non-Line-of-Sight (NLOS) propagation is an intriguing topic in an IRS-aided wireless communication scenario. However, the existing optimization-based approaches are overly complex to be practically implemented. In this paper, we propose a polarized IRS architecture, in which both IRS and BS are equipped with arbitrarily placed Electromagnetic Vector Sensor (EMVS) arrays. A Normalized Vector-Cross Product (NVCP) estimator is developed for DOA estimation, which avoids the need for complicated data recovery or exhaustive grid search. The proposed framework enables Two-Dimensional (2D) DOA estimation for NLOS signals without requiring prior knowledge of the BS-IRS channel. Numerical simulations have been conducted to verify its effectiveness.

Traffic classification is a critical task in network security and management. Recent research has demonstrated the effectiveness of the deep learning-based traffic classification method. However, the following limitations remain: (1) the traffic representation is simply generated from raw packet bytes, resulting in the absence of important information; (2) the model structure of directly applying deep learning algorithms does not take traffic characteristics into account; and (3) scenario-specific classifier training usually requires a labor-intensive and time-consuming process to label data. In this paper, we introduce a masked autoencoder (MAE) based traffic transformer with multi-level flow representation to tackle these problems. To model raw traffic data, we design a formatted traffic representation matrix with hierarchical flow information. After that, we develop an efficient Traffic Transformer, in which packet-level and flow-level attention mechanisms implement more efficient feature extraction with lower complexity. At last, we utilize the MAE paradigm to pre-train our classifier with a large amount of unlabeled data, and perform fine-tuning with a few labeled data for a series of traffic classification tasks. Experiment findings reveal that our method outperforms state-of-the-art methods on five real-world traffic datasets by a large margin. The code is available at https://github.com/NSSL-SJTU/YaTC.

Radio frequency fingerprint (RFF) has been widely used in wireless transceivers as an additional physical security layer. Most of the existing RFF extraction methods rely on a large number of labeled signal samples for model training. However, in real communication environments, it is usually necessary to process timely received signal samples, which are limited in quantity and are difficult to obtain labels, the performance of most RFF methods is generally poor. To effectively extract features from the limited and unlabeled signal samples, we propose an efficient RFF extraction method using an asymmetric masked auto-encoder (AMAE). Specifically, we design an asymmetric extractor-decoder, where the extractor is used to learn the latent representation of the masked signals and the decoder as light as a convolution layer reconstructs the unmasked signal from the latent representation. Using commercial off-the-shelf LoRa datasets and WiFi datasets, we show that the proposed AMAE-based RFF extraction method achieves the best performance compared with four advanced unsupervised methods whether in the case of large data size or small data size, or under line of sight (LOS) and non line of sight (NLOS) channel scenarios. The codes of this paper can be downloaded from Github: https://github.com/YZS666/AnEfficient-RFF-Extraction-Method.

In frequency division duplexing (FDD) massive multiple-input multiple-output (MIMO), the downlink channel state information (CSI) feedback method based on deep transfer learning (DTL) has been proposed to obtain the downlink CSI at the Base Station (BS). In the CSI feedback method based on DTL, a target model for one channel environment is obtained by fine-tuning the parameters of a source model trained on a large number of the CSI dataset (source data) of another channel environment. The fine-tuning is done with a small number of the CSI dataset (target data) of the target channel environment. Thus, a target model can be obtained at a low learning cost. However, the performance of the target model could highly depend on the source data. In this paper, we investigate two metrics as criteria for selecting source data to obtain a target model with a high CSI reconstruction performance: (i) Jensen-Shannon Divergence (JSD), which represents the similarity between target and source data, and (ii) entropy, which represents the diversity of source data. The simulation results showed when the target channel model is non line-of-sight (NLOS), the source data with high entropy and low JSD tend to provide higher CSI reconstruction performance of the target model. These results indicate that the JSD and the entropy could be a source data selection metric.

Reconfigurable intelligent surfaces (RIS) are currently drawing a lot of attention in the research community as a key technology for future wireless networks. In addition to boosting the signal-to-noise ratio and improving coverage for cellular users, they can also be used to transmit locally collected data either by partitioning the RIS array into tiles and mapping the local data to the indexes of the activated tiles (or groups of tiles) following the concept of spatial modulation (SM), or by activating all RIS elements and mapping the local data onto a set of common phase shifts. The problem of the first technique, which we refer to as RIS-SM, is that spatial correlation between elements of the RIS array strongly degrades the bit error rate performance. In this paper, we focus on the second technique, and we investigate the transmission of low bit rate local data using the concept of hierarchical transmission. The basic idea behind this technique is that the magnitude of the common phase shifts must be maintained at a very small value in order to keep the performance degradation caused by the local data on the user data within an acceptable limit. For the local RIS data, this constraint leads to a small minimum Euclidean distance in the signal constellation plane, but despite this small minimum distance, the desired performance is achieved by limiting the speed of the local RIS data to a fraction of the user symbol rate. Analytic minimum distance calculations and simulation results are provided to demonstrate the efficiency of the proposed hierarchical transmission technique.

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.

To reduce the outage of the connection between unmanned aerial vehicles (UAVs) and cellular networks in complex real-time channel state, and reduce the energy consumption of UAV during flight mission, an online trajectory optimization scheme of UAV based on outage probability knowledge map reconstruction is proposed. The outage probability knowledge map is a database that simulates the connection between UAV and the cellular network during real hovers. The UAV first samples sparsely from the target area and calculates the outage probability of the sampling point, and then uses the Kriging algorithm to reconstruct the outage probability knowledge map. Based on the reconstructed outage probability knowledge map, with the goal of minimizing the energy consumption of UAV task execution, the UAV trajectory optimization problem is established, and a trajectory optimization algorithm based on deep reinforcement learning (DRL) is proposed to solve it. Numerical results show that the proposed online trajectory optimization scheme based on outage probability knowledge map can obtain great returns in terms of maintaining connectivity, reducing task completion time and energy consumption.

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, these methods highly rely on expert experience to design network structures. These hand-designed fixed network structures lack flexibility, which often leads to insufficient model generalization. Neural architecture search (NAS) can be seen as a subdomain of automatic machine learning (AutoML), which can automatically adjust network structure and parameters according to a specific task. In this paper, we propose a neural architecture search-based SEI method, which can achieve an efficient search of the architecture with the use of a gradient descent algorithm. Experimental results show that the proposed NASEI method both improves the accuracy and reduces the parameter quantity when compared with state-of-the-art methods. Code available at https://github.com/huangyuxuan11/NASEI.git.

Federated Learning is now widely used to train neural networks under distributed datasets. One of the main challenges in Federated Learning is to address network training under local data heterogeneity. Existing work proposes that taking similarity into account as an influence factor in federated learning can improve the speed of model aggregation. We propose a novel approach that introduces Centered Kernel Alignment (CKA) into loss function to compute the similarity of feature maps in the output layer. Compared to existing methods, our method enables fast model aggregation and improves global model accuracy in non-IID scenario by using Resnet50.

Abstract Energy efficiency (EE) is an important indicator in ultra‐reliable and low‐latency communication (URLLC). Power allocation is considered as an effective method to achieve high EE in URLLC. However, since the EE optimization problem is non‐convex, it is difficult to obtain the analytical solution efficiently. Moreover, to ensure reliable and low‐latency communication within a finite blocklength, the Shannon formula becomes impractical for URLLC. Therefore, finite blocklength coding theory is used to meet the requirements of URLLC. In this paper, the EE problem of URLLC is formulated and the power allocation function is parameterized to be optimized through a deep neural network (DNN). The DNN is trained through the primal‐dual iterative algorithm offline in the unsupervised manner, and can be deployed online to achieve real time power allocation results. The numerical results show the effectiveness of the proposed method.

Regulation of drones is already an important research topic. The drone identification method based on the radio frequency (RF) signal analysis technology is an efficient approach to regulate mainstream civilian drones. However, existing research on drone identification has been conducted under high signal-to-noise ratio (SNR) conditions. In fact, long-range drone identification in urban environments is performed under low SNR conditions. In this article, a global context (GC)-based threshold strategy is proposed to solve the above problem. The threshold is automatically determined during the deep architecture optimization. Meanwhile, the unimportant features in the network are removed by threshold denoising. First, the weight of each feature channel is obtained by modeling cross-channel dependencies, and then a weighted average is performed for each position along the feature channel on the feature map to obtain the thresholds. The method reduces the impact of unimportant features on performance without complex data preprocessing. In the experiments, the performance and complexity of the proposed method are extensively evaluated by 11 different drone RF signals. The experimental results show that in comparison with other deep learning-based threshold calculation methods, the proposed method has a more outstanding performance and lower computational complexity for drone RF signal identification under the low SNR condition.

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.

Federated learning (FL) is a machine learning technique that allows for on-site data collection and processing without sacrificing data privacy and transmission. Heterogeneity is a key challenge in federated settings. Recently, cross-technology communication (CTC) has emerged as a solution for Internet of Things (IoT) heterogeneity, enabling direct communication between different wireless devices without the need for hardware modifications or gateway intervention. For example, a sophisticated WiFi device can serve as a central coordinator for other heterogeneous devices, such as LoRa, ZigBee, Bluetooth, and LTE, leading to more efficient and ubiquitous cross-network information exchange. However, heterogeneous wireless technologies present different data transmission rates and computing resources, making it difficult to achieve high accuracy in predictions due to large amounts of multidimensional data, communication delays, transmission latency, limited processing capacity, and data privacy concerns. In this work, we propose an FL framework based on CTC for heterogeneous IoT applications, called FLCTC. To demonstrate the usability of FLCTC, we implemented FLCTC and a specific solution for forest fire prediction. FLCTC was concretely implemented as a federal deep learning based on long and short-term memory and used for forest fire prediction, addressing the challenge of data characterization in heterogeneous IoT networks. FLCTC promises to improve communication efficiency and prediction accuracy. Our platform-based evaluation results show that FLCTC is feasible, with a recall of 96% and an accuracy of 88%, offering valuable insights into the use of FL with CTC for heterogeneous IoT applications.

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.

The topic of anonymous unmanned aerial vehicle (UAV) localizing based on angle estimation has been frequently discussed in the past few years. However, the existing methodologies are inefficient in a massive sensor arrays scenario. To avoid such drawback, a cooperative 3-D positioning methodology is introduced. The critical idea of the proposed localizing method is to estimate the 2-D angle of the anonymous UAV via a polarized massive–multi-input multi-output (MIMO) system. To reduce the computational burden and explore the nature of the multidimensional data, a tensor compressive sampling (TCS) framework is proposed. Moreover, a closed-form estimation strategy is developed for 2-D direction finding. Our framework is shown to be more efficient than the existing algorithm in terms of hardware/software complexity. Besides, it is suitable for a polarized MIMO system with an arbitrary array geometry. Several simulation examples are provided to show its improvement of the new methodology.

The Angle-of-Arrival (AoA)-based approach is an appealing solution for unmanned aerial vehicle (UAV) positioning, and has received significant interest recently. In this article, we propose a novel framework for UAV three-dimensional (3-D) positioning, the core of which is to measure the two-dimensional (2-D) Angle-of-Departure (2D-AoD) and 2D-AoA via a bistatic multiple-input multiple-output (MIMO) radar. Unlike the existing positioning architectures, the MIMO radar is equipped with polarized array antennas. An estimator based on the parallel factor (PARAFAC) decomposition is developed. It first obtains the direction matrices via performing the PARAFAC decomposition of the array data. Thereafter, the rotational invariance characteristic is utilized to form a normalized polarization response vector, from which the 2D-AoD, 2D-AoA, and polarization status of the UAVs are achieved via incorporating the vector cross-product method and the least squares (LSs) technique. Finally, the 3-D positions of the UAVs are easily calculated via the location relationship between the 2D-AoD, 2D-AoA, and the coordinates of transmitting/receiving (Tx/Rx) array. The proposed framework is computationally friendly, and is capable of positioning anonymous UAV. Moreover, it is insensitive to the geometry of the Tx/Rx array, indicating that the proposed framework supports configurable Tx/Rx antennas. Simulation results are provided to verify our theoretical advantages.

Malware traffic classification (MTC) plays an important role for securing the Internet of Things (IoT). Many machine learning (ML) and deep learning (DL)-based MTC methods have been proposed in recent years. However, the former still requires human intervention, while the latter incurs considerable computation overheads. To address these problems, we propose a broad learning (BL)-aided MTC method (BL-MTC), which is a lightweight and graphics processing unit-free solution with good performance and extremely low cost. The simulation results show that the proposed BL-MTC method not only achieves superior results on the USTC-TFC2016 data set but also exhibits an exponential advantage in computation overhead.

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.

Federated learning (FL) has become an increasingly popular solution for intrusion detection to avoid data privacy leakage in Internet of Things (IoT) edge devices. Existing FL-based intrusion detection methods, however, suffer from three limitations: 1) model parameters transmitted in each round may be used to recover private data, which leads to security risks; 2) not independent and identically distributed (non-IID) private data seriously adversely affect the training of FL (especially distillation-based FL); and 3) high communication overhead caused by the large model size greatly hinders the actual deployment of the solution. To address these problems, this article develops an intrusion detection method based on a semisupervised FL scheme via knowledge distillation. First, our proposed method leverages unlabeled data via distillation method to enhance the classifier performance. Second, we build a model based on convolutional neural networks (CNNs) for extracting deep features of the traffic packets, and take this model as both the classifier network and discriminator network. Third, the discriminator is designed to improve the quality of each client’s predicted labels, and to avoid the failure of distillation training caused by a large number of incorrect predictions under private non-IID data. Moreover, the combination of the hard-label strategy and voting mechanism further reduces communication overhead. The experiments on the real-world traffic data set with three non-IID scenarios show that our proposed method can achieve better detection performance as well as lower communication overhead than state-of-the-art methods.

The polarized massive multiple-input multiple-output (MIMO) technique has been regarded as a promising solution to millimeter wave (mmWave) communication systems, because it experiences more degrees-of-freedom than the scalar configuration, and it represents a significant opportunity for secure communication. To deliver smart service to terminals, it is essential to provide base stations (BS) with the capability of terminal’s direction-of-arrival (DOA) awareness. In this paper, a compressive sampling (CS) framework is proposed for two-dimensional (2D) DOA and polarization estimation in mmWave polarized massive MIMO systems. The proposed approach first reduces the data volume via a reduced-dimension matrix. Then it computes the signal subspace via the eigendecomposition of the compressed array measurement. Thereafter, the rotational invariance characteristic is utilized to form a normalized polarization steering vector. Finally, 2D-DOA and polarization are estimated by incorporating the Poynting vector and the least squares (LS) techniques. The proposed architecture is computationally much more economical than existing algorithms. Besides, it allows a mmWave BS to provide comparable estimation performance with arbitrary sensor geometry, which is more flexible than most of the existing architectures. Furthermore, it is robust to the sensor position error. Numerical simulations verify the advantages of the proposed framework.

With the explosive growth of advanced wireless technologies and computing device platforms, mobile sensing has gained huge attention. Indoor localization is actually considered as one of most valuable techniques in the field of contactless sensing. In this paper, we propose a novel graph convolutional network (GCN) empowered indoor localization method, which aggregates channel state information (CSI) features extracted from multiple multiple-input multiple-output (MIMO) links. CSI features from multiple antennas are basically converted into graph nodes in order to adopt GCN classification model. At the same time, graph attention mechanism is introduced to study and transfer spatial and frequency of CSI features. Eventually, output of graph is mapped with multiple measurement points through prediction network to provide final estimate position. 5GHz commercial Wi-Fi equipment is respectively utilized for data collection and experimental evaluation in two representative indoor scenarios. Experimental result shows that the proposed method has better performance in robust localization compared to other state-of-the-art deep learning methods.

Radio frequency-based device-free passive perception (RF-DFPP) is considered as one of the most promising techniques for ubiquitous smart applications in the WiFi field due to its extremely low deployment cost. Existing RF-DFPP methods typically employ received signal strength indicator (RSSI), ignoring the potential benefits of fine-grained sensing accuracy of channel state information (CSI). In addition, the robustness of such sensing methods is not good at present. To solve the problem, in this paper, we propose a robust CSI-based RF-DFPP method using a combination network of convolutional neural networks (CNN) and attention-based bi-directional long short term memory (LSTM). The combined network can extract the signal features of the collected CSI through CNN, and then realize RF-DFPP recognition through the training of LSTM and attention layers. Simulation results show that the proposed method significantly improves the recognition accuracy compared with the existing methods. Moreover, it performs robustly even if the model training is done under the different datasets.

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.

With the development of the Industrial Internet of Things (IIoT), more frequent attacks occur to intrude IIoT devices. A reasonably designed intrusion detection method can effectively guarantee the security of IIoT. Over the past decade, different methods of intrusion detection based on deep learning (DL) have been proposed, which helps intrusion detection keep evolving and become more robust. However, these previous researches usually require the participation of a large number of experts, and gradually become invalid with the continuous development of intrusion methods. The limited compute capability of IIoT devices also greatly hinder the deployment of overly complex DL models. To address these challenges, this paper proposes a lightweight semi-supervised learning (LSSL) method based on consistency regularization for intrusion detection. Our proposed method enhances the detection performance by using unlabeled traffic data for consistency training. Besides, we adopt separable convolutions for efficient feature extraction. Experimental results on two widely-used benchmark datasets show that the detection performance of our model is significantly improved by the consistency training, and it can effectively detect various attacks in complex networks.

Federated learning (FL) has become an increasingly popular solution for intrusion detection to avoid data privacy leakage in Internet of Things (IoT) edge devices. However, most of the current FL-based intrusion detection methods still suffer from three limitations: (1) model parameters transmitted in each round may be used to recover private data which leads to security risks, (2) not independent and identically distributed (non-IID) private data seriously adversely affects the training of FL (especially distillation-based FL), and (3) high communication overhead caused by the large model size greatly hinders the actual deployment of the solution. To address these problems, this paper develops an intrusion detection method based on semi-supervised FL scheme via knowledge distillation. First, our proposed method leverages unlabeled data via distillation method to enhance the classifier performance. Second, we build a CNN-based model for extracting deep features of the traffic packets, and take this model as both the classifier network and discriminator network. Third, discriminator is designed to improve the quality of each client’s predicted labels, to avoid the failure of distillation training caused by a large number of incorrect predictions under private non-IID data. Moreover, the combination of hard-label strategy and voting mechanism further reduces communication overhead. Experimental results on the real-world traffic dataset show that our proposed method can achieve better classification performance as well as lower communication overhead than state-of-the-art methods.

Due to the computing capability and memory limitations, it is difficult to apply the traditional deep learning (DL) models to the edge devices (EDs) for realizing automatic modulation classification (AMC). In this paper, a lightweight neural network for decentralized learning-based automatic modulation classification (DecentAMC) method is proposed. Specifically, group convolutional neural network (GCNN) is designed by replacing the standard convolution layer with the group convolution layer, replacing the flatten layer with the global average pooling (GAP) layer and removing part of fully connected layers. DecentAMC method is achieved by the cooperation in which multiple EDs update and upload the model weight to a central device (CD) for model aggregation to avoid the data privacy disclosure. Experimental results show that the proposed GCNN-based DecentAMC method can improve training efficiency to about 4 times and 57 times than that of GCNN-based centralized AMC (CentAMC) and CNN-based DecentAMC respectively. GCNN-based DecentAMC method can effectively reduce the communication cost and save storage of EDs when compared with CNN-based DecentAMC. Meanwhile, the time complexity and the space complexity of GCNN is significantly decreased when compared with CNN and SCNN, which is suitable to be deployed in EDs.

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.

Accessing the accurate downlink channel state information (CSI) is essential to take full advantage of frequency division duplex (FDD) massive multiple-input multiple-output (MIMO) systems due to its weak channel reciprocity. Meanwhile, great computational burdens will happen, which is accompanied by continuous CSI feedback. The existing compressive sensing (CS)-based and deep learning (DL)-based methods try to solve such problems, but do not achieve desired effect to get ideal CSI feedback or decrease the overhead. An adaptive deep neural network (DNN)-based CSI feedback method is proposed in this paper to address this. A classification block of the compression ratio is adopted and modified to apply to a more complex channel model named Clustered-Delay-Line (CDL), which helps decrease the computational overhead of the network. Besides, the reconstruction accuracy of the CSI feedback is further improved by proposing a new structure of the encoder. Quantization and dequantization modules are also applied to make the whole network more robust and effectively minimize the quantization distortion in the real communication scenario, respectively. The simulation results show that the proposed method performs better than the conventional ones on the CSI reconstruction accuracy in terms of normalized mean square error (NMSE), even though the quantization module is added.

Blind signal recognition (BSR) is a significant research topic in the field of intelligent signal processing. However, existing BSR of space-time block codes (STBC) mainly depends on conventional algorithms, which require priori information and can only identify a relatively limited amount of STBC. Although deep learning (DL) has been widely used in signal recognition, so far there are few studies on BSR of STBC in multiple-input multiple-output (MIMO) systems using DL. In this paper, a blind recognition approach for STBC based on multichannel convolutional neural network (MCNN) is proposed. By leveraging the structure of multiple input channel, the in-phase and quadrature (IQ) channel information of STBC signals can be comprehensively extracted. Simulation results demonstrate that the proposed algorithm extends the recognizable STBC codes to 6, and can also improve the recognition accuracy in comparison to traditional convolutional neural network (CNN). The model proposed in this paper has been validated with two datasets and experimentally proved to be well generalized.

Malware traffic classification (MTC) is a very important component of cyber security, and a number of the MTC techniques are based on deep learning (DL) with a strong capability of feature mining and classification. However, these DL-based MTC methods are heavily dependent on a large amount of network traffic samples. In the few-shot scenarios, these methods usually overfit and have poor classification performance. Considering that the update cycle of malware is faster and faster, and there are more and more types of malware, collecting enough training samples for all malware is very challenging, if not impossible. In this paper, a novel few-shot MTC(FS-MTC) method is proposed based on convolutional neural network (CNN) and model-agnostic meta-learning (MAML) algorithm. Specifically, the CNN is trained on samples from normal softwares by MAML rather than the conventional optimization methods, then the CNN is finetuned by a few samples from malware for MTC. Simulation results show that our proposed MAML-based FS-MTC can outperform the traditional MTC methods. The performance of our proposed method can reach up to 95.69%.

This paper analyzes the power imbalance factor on the uplink of a 2-user Power-domain NOMA system and reveals that the minimum value of the average error probability is achieved when the user signals are perfectly balanced in terms of power as in Multi-User MIMO with power control. The analytic result is obtained by analyzing the pairwise error probability and exploiting a symmetry property of the error events. This result is supported by computer simulations using the QPSK and 16QAM signal formats and uncorrelated Rayleigh fading channels. This finding leads to the questioning of the basic philosophy of Power-domain NOMA and suggests that the best strategy for uncorrelated channels is to perfectly balance the average signal powers received from the users and to use a maximum likelihood receiver for their detection.

To address the problem of spectrum resources and transmitting power for vehicular networks, this paper proposes a resource allocation (RA) method based on dueling double deep-Q network (D3QN) reinforcement learning (RL). Due to the high mobility of the vehicle, the channel changes rapidly which makes it difficult to accurately collect high-accuracy channel state information at the base station and to perform centralized management. In response of this difficulty, we construct a multi-intelligence model, using Manhattan Grid Layout City Model as the basis of environment and with each vehicle-to-vehicle (V2V) link as an intelligence. They work together to interact with the environment, receive appropriate observations, get rewards, and finally learn to improve the allocation of power and spectrum to enable users to achieve a better entertainment experience and a safer driving environment. Experimental results demonstrate that with proper training mechanism and reward function construction, cooperation among multiple intelligence can be performed in a distributed manner, with improvements in both the capacity of total vehicle-to-infrastructure links and the effective payload delivery success rate of the V2V links compared to common Q-network.

Matrix completion-assisted channel estimation is considered one of promising techniques in millimeter wave (mmWave) massive multiple input multiple output (MIMO) system by exploiting the low-rank property of channel matrix in the angle domain. However, existing channel estimation approaches are hard to achieve high accuracy due to the inevitable bias solution caused by nuclear norm based minimization (NNM). To address this problem, this paper proposes a novel matrix completion-assisted mmWave massive MIMO channel estimation method. We employ an effective and flexible rank function named joint weighted and truncated nuclear norm as relaxation of nuclear norm, and then construct an novel matrix completion model for channel estimation problem. Moreover, a popular framework of alternating direction method of multipliers (ADMM) is derived for minimization of the resulting optimization problem. Simulation results are provided to verify the proposed method that can flexibly and effectively improve the channel estimation accuracy with reliable convergence.

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.

With the increasing popularity of Internet of things (IoT), the emergence of many IoT devices has led to security vulnerabilities. The classification of wireless signals is very important for secure communications. Most of existing signal classification tasks only focus on single signal classification task, while ignoring the relationship between radio frequency fingerprinting identification (RFFI) and automatic modulation classification (AMC). To solve the multi-task classification problem, this paper designs a multi-task learning convolutional neural networks (MTL-CNN). Real-radio datasets are generated by Signal Hound VSG60A and collected by Signal Hound BB60C to solve the lack of RFF samples with numerous modulation types. Experimental results confirm that the MTL-CNN method can work well by using the generated dataset. The MTL network designed in this paper improves the accuracy of RFFI by 1xs% relative to the single-task learning (STL) network. The keras code is released at https://github.comLiuK1288/1hw-000.

Human activity recognition (HAR) is one of the most promising technologies in the smart home, especially radio frequency (RF-based) method, which has the advantages of low cost, few privacy concerns and wide coverage. In recent years, deep learning (DL) has been introduced into HAR and these DL-based HAR methods usually have outstanding performance. However, as the recognition scenarios and target change, the model performance drops sharply. To solve this problem, we propose a generalized method for cross-person activity recognition (CPAR), which is called snapshot ensemble learning based an attention with bidirectional long short-term memory (SE-ABLSTM). Specifically, by defining the cosine annealing learning rate, the models with diversity are saved and integrated in the same training process. In addition, we provide a dataset for CPAR and simulation results show that our method improves generalization performance by 5% compared to the original method. The source code and dataset for all the experiments can be available at https://github.com/NJUPT-Sivan/Cross-person-HAR.

The fast development of intelligent wireless communications enables many devices to access various networks. It often leads to the security risks of malicious access of illegal devices. To ensure a secure and reliable wireless access, it is necessary to identify illegal devices and prevent their attacks accurately. To improve the performance of specific emitter identification (SEI), this paper proposes a multi-scale convolution neural network (MSCNN) based on convolution layers of three branches with different convolution kernel sizes. MSCNN extracts radio frequency fingerprints (RFF) in three receptive fields through different convolution kernels. We verify the identification accuracy using the RF signals conforming to long term evolution (LTE) standard. The experimental results show that our proposed MSCNN-based SEI method can improve the absolute accuracy by 15% and the relative accuracy by 22% in perfect communication environment. In addition, we verify the robustness of proposed MSCNN by comparing identification performance in imperfect environment. Simulation results show that the proposed MSCNN can extract more hidden features through convolution kernels of different sizes, and thus achieves better SEI performance than existing methods.

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.

As exploitation of low and medium airspace for air traffic management (ATM) is gaining more attention, aerial vehicles’ security issues pose a major challenge to the air–ground-integrated vehicle networks (AGIVNs). Traditional surveillance technology lacks the capacity to support the intensive ATM of the future. Therefore, an advanced automatic-dependent surveillance-broadcast (ADS-B) technique is applied to track and monitor aerial vehicles in a more effective manner. In this article, we propose a grouping-based conflict detection algorithm based on the preprocessed ADS-B data set, and analyze the experimental results and visualize the detected conflicts. Then, in order to further improve flight safety and conflict detection, the trajectories of the aerial vehicles are predicted based on machine learning-based algorithms. The results are fed into the conflict detection algorithm to execute conflict prediction. It was shown that the trajectory prediction model using long short-term memory (LSTM) can achieve better prediction performance, especially when predicting the long-term trajectory of aerial vehicles. The conflict detection results based on the trajectory prediction methods show that the proposed scheme can make it possible to detect whether there would be conflicts within seconds.

Due to the computing capability and memory limitations, it is difficult to apply the traditional deep learning (DL) models to the edge devices (EDs) for realizing lightweight automatic modulation classification (AMC). Recently, many works attempt to use different ways to realize lightweight AMC methods for EDs. However, the lightweight seems to be a contradiction with the classification performance in these lightweight networks. In this article, we propose an efficient lightweight decentralized-learning-based AMC (DecentAMC) method using spatiotemporal hybrid deep neural network based on multichannels and multifunction blocks (MCMBNN). Specifically, the lightweight network is designed from the perspectives of comprehensive consideration of lightweight and classification performance, which is composed of three parts to extract different features for realizing high classification performance and they are phase estimator and transformer (PET) block, spatial feature extraction block and temporal feature extraction & Softmax block. In addition, we use a multichannel input to extract complementary features of different channels for a better classification performance. The proposed DecentAMC method is an efficient training method, which is achieved by the cooperation in which multiple EDs update and upload the model weight to a central device (CD) for model aggregation to avoid the data privacy disclosure and reduce the computing power and storage pressure of CD. Experimental results show that the proposed MCMBNN can obtain an improved classification accuracy while reducing model complexity with the contributions of three blocks. Moreover, the proposed DecentAMC method can be deployed on EDs efficiently. Thus, the method has the advantages of avoiding data leakage on EDs and relieving the computing pressure of CD with relatively lower communication overhead. The simulation code and datasets are shared on GitHub.

Malware traffic classification (MTC) is a key technology for anomaly and intrusion detection in secure Industrial Internet of Things (IIoT). Traditional MTC methods based on port, payload, and statistic depend on the manual-designed features, which have low accuracy. Recently, deep-learning methods have attracted a significant attention due to their high accuracy in terms of classification. However, in practical application scenarios, deep-learning methods require a large amount of labeled samples for training, while the available labeled samples for training are very rare. Furthermore, the preparation of a large amount of labeled samples requires a lot of labor costs. To solve these problems, this article proposes three methods based on semisupervised learning (SSL), transfer learning (TL), and domain adaptive (DA), respectively. Our proposed methods use a large amount of unlabeled data collected in the Internet traffic, which can greatly improve the classification accuracy with few labeled samples. Then, we use the DA method to solve the mismatch problem between the source domain and the target domain in the TL process. The proposed method is not only applicable to the shallow network but also to the deep neural network structure, and can achieve better classification results. Experimental results show that our proposed methods can satisfy the requirement of MTC in the case of few labeled samples in IIoT. The source code for all the experiments is available at GitHub.The code of this article can be downloaded from GitHub link:https://github.com/yzjh/Keras-MTC-DA-Ladder.

Deep learning (DL) has been widely proposed for botnet attack detection in Internet of Things (IoT) networks. However, the traditional centralized DL (CDL) method cannot be used to detect the previously unknown (zero-day) botnet attack without breaching the data privacy rights of the users. In this article, we propose the federated DL (FDL) method for zero-day botnet attack detection to avoid data privacy leakage in IoT-edge devices. In this method, an optimal deep neural network (DNN) architecture is employed for network traffic classification. A model parameter server remotely coordinates the independent training of the DNN models in multiple IoT-edge devices, while the federated averaging (FedAvg) algorithm is used to aggregate local model updates. A global DNN model is produced after a number of communication rounds between the model parameter server and the IoT-edge devices. The zero-day botnet attack scenarios in IoT-edge devices is simulated with the Bot-IoT and N-BaIoT data sets. Experiment results show that the FDL model: 1) detects zero-day botnet attacks with high classification performance; 2) guarantees data privacy and security; 3) has low communication overhead; 4) requires low-memory space for the storage of training data; and 5) has low network latency. Therefore, the FDL method outperformed CDL, localized DL, and distributed DL methods in this application scenario.

The purpose of a network intrusion detection (NID) is to detect intrusions in the network, which plays a critical role in ensuring the security of the Internet of Things (IoT). Recently, deep learning (DL) has achieved a great success in the field of intrusion detection. However, the limited computing capabilities and storage of IoT devices hinder the actual deployment of DL-based high-complexity models. In this article, we propose a novel NID method for IoT based on the lightweight deep neural network (LNN). In the data preprocessing stage, to avoid high-dimensional raw traffic features leading to high model complexity, we use the principal component analysis (PCA) algorithm to achieve feature dimensionality reduction. Besides, our classifier uses the expansion and compression structure, the inverse residual structure, and the channel shuffle operation to achieve effective feature extraction with low computational cost. For the multiclassification task, we adopt the NID loss that acts as a better loss function to replace the standard cross-entropy loss for dealing with the problem of uneven distribution of samples. The results of experiments on two real-world NID data sets demonstrate that our method has excellent classification performance with low model complexity and small model size, and it is suitable for classifying the IoT traffic of normal and attack scenarios.

As a typical Internet of Things application, network traffic prediction (NTP) plays a decisive role in congestion control, resource allocation, and anomaly detection. The trend of network traffic is different at different scales, so multiscale is an important characteristic of network traffic. In addition, the network traffic is nonlinear on each scale and dependent between scales. The existing NTP methods cannot comprehensively consider these characteristics, which limits their performance. In view of the characteristics of network traffic, such as multiscale, nonlinearity, and scale dependence, this article proposes a new multiscale NTP method based on a deep echo-state network (ESN). First, a multiscale parallel layered structure based on deep ESN is designed to fully consider the influence of each scale on the prediction result and then reduce the prediction error. Second, a feature extraction algorithm is proposed to improve the nonlinear approximation ability by extracting more abundant dynamic features with multiple reservoirs. Third, an NTP model based on scale dependence is proposed to reduce the influence from partial scale missing and then improve the prediction accuracy. Finally, simulation results demonstrate that compared with the state-of-the-art NTP methods, the proposed method significantly improves the prediction performance of network traffic with a slight increase in running time.

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.

Energy-efficiency (EE) is a critical metric within wireless optimization. Power control over fading channels is considered as a promising EE-improving technique, but requires optimization of a series of fractional functional optimization problems which are hard to handle by existing optimization techniques. In this paper, we propose a novel EE power control method with unsupervised learning. Firstly, the original fractional problems are decomposed into sub-problems by Dinkelbach and quadratic transformations. Then, these sub-problems are reformulated into unconstrained forms through Lagrange dual formulation. Furthermore, unsupervised primal-dual learning method is applied to handle these unconstrained problems with strong duality. Finally, The unsupervised primal-dual learning is implemented by the deep neural network (DNN) with low computational complexity. Simulation results verify the effectiveness of the proposed approach on a number of typical wireless optimizing scenarios. It is shown that compared to conventional algorithms our method achieves better performance in cognitive radio networks, interference networks, and OFDM networks.

Reconfigurable intelligent surfaces (RIS) are currently drawing a lot of attention in the research community as a key technology for future wireless networks. In addition to boosting the signal-to-noise ratio, they can also be used to transmit data in the same way spatial modulation (SM) transmits data by mapping it to the activated antenna indices in MIMO systems. The problem of this transmission technique which we refer to as RIS-SM is that spatial correlation between elements of the RIS array strongly degrades bit error rate performance. In this paper, we analyze this degradation and introduce two techniques to compensate for spatial correlation. The first employs tile-specific phase shifts in the RIS elements and the second employs dynamic phase shifts that are specific to the RIS patterns activated by the information bits to be transmitted. The analysis and the simulation results show that the proposed techniques provide substantial performance improvements and make RIS-SM transmission reliable even in the presence of very strong spatial correlation.

Intelligent reflecting surface (IRS)-aided millimeter-wave (mmWave) multiple-input single-output (MISO) is considered one of the promising techniques in next-generation wireless communication. However, existing beamforming methods for IRS-aided mm Wave MISO systems require high computational power, so it cannot be widely used. In this paper, we combine an unsupervised learning-based fast beamforming method with IRS-aided MISO systems, to significantly reduce the computational complexity of this system. Specifically, a new beamforming design method is proposed by adopting the feature fusion means in unsupervised learning. By designing a specific loss function, the beamforming can be obtained to make the spectrum more efficient, and the complexity is lower than that of the existing algorithms. Simulation results show that the proposed beamforming method can effectively reduce the computational complexity while obtaining relatively good performance results.

Adaptive modulation and coding (AMC) technique plays an important role in vehicle-to-vehicle (V2V) systems. It enables smart vehicles to keep a good quality of communication for a better driving experience. However, the existing AMC methods for V2V system did not consider multiple scenarios and the amount of calculation is relatively large. In this paper, we propose a simple convolutional neural networks (CNN)-based AMC method which can extract features of channel and noise estimation from receiver, the transmitter will adjust in the light of modulation strategy to ensure the quality of V2V communication. Simulation results reveal that our proposed method performs better in terms of packet error rate (PER), throughput, classification accuracy with a lower prediction time.

The problem of unknown modulation signal recognition has been received intensely attentions in next-generational intelligent wireless communications. The deep learning (DL) has been widely used in unknown modulation signal recognition due to its excellent performance in solving classification problems and the DL-based automatic modulation classification (AMC) had been proposed. However, DL-based AMC method usually has high space complexity and computational complexity, which limits DL-based AMC to miniaturized devices with limited storage and computing capability. Therefore, a lightweight residual neural network (LResNet) for AMC is proposed in this paper. The simulation results show that the model parameters of LResNet is about 4.8% of the traditional CNN network, and about 14.9% of the ResNet and the classification performance of LResNet improves more than 3% compared with the traditional CNN network and decreases less than 1.5% compared to the ResNet.

In this paper, we propose Federated Deep Learning (FDL) for intrusion detection in heterogeneous networks. Local Deep Neural Network (DNN) models are used to learn the hierarchical representations of the private network traffic data in multiple edge nodes. A dedicated central server receives the parameters of the local DNN models from the edge nodes, and it aggregates them to produce an FDL model using the Fed+ fusion algorithm. Simulation results show that the FDL model achieved an accuracy of 99.27 ± 0.79%, a precision of 97.03 ± 4.22%, a recall of 98.06 ± 1.72%, an F1 score of 97.50 ± 2.55%, and a False Positive Rate (FPR) of 2.40 ± 2.47%. The classification performance and the generalisation ability of the FDL model are better than those of the local DNN models. The Fed+ algorithm outperformed two state-of-the-art fusion algorithms, namely federated averaging (FedAvg) and Coordinate Median (CM). Therefore, the DNN-Fed+ model is preferable for intrusion detection in heterogeneous wireless networks.

In massive multiple input multiple output (MIMO) systems, the base station (BS) requires channel state information (CSI) to better utilize the available spatial diversity and multiplexing gains. However, in frequency division duplex (FDD) systems, user equipment (UE) needs to keep on feeding downlink CSI back to the BS, thereby consuming precious bandwidth resources. In this paper, we propose a deep learning (DL) based downlink CSI limited feedback scheme, called FullyConv, which is composed of all convolutional layers to compress and decompress the downlink CSI. FullyConv will improve reconstruction accuracy and robustness as well as reduce the time and space complexity, thus enhancing the system feasibility. Experimental results demonstrate that the FullyConv has a gain of nearly 5 dB compared to baseline. The performance of the FullyConv degrades slightly in the noisy uplink channel, which shows the robustness of FullyConv. Meanwhile, the complexity of the model composed of time complexity and space complexity is significantly reduced.

This paper proposes a decentralized automatic modulation classification (DecentAMC) method using light network and model aggregation. Specifically, the lightweight network is designed by separable convolution neural network (S-CNN), in which the separable convolution layer is utilized to replace the standard convolution layer and most of the fully connected layers are cut off, the model aggregation is realized by a central device (CD) for edge device (ED) model weights aggregation and multiple EDs for ED model training. Simulation results show that the model complexity of S-CNN is decreased by about 94% while the average CCP is degraded by less than 1% when compared with CNN and that the proposed AMC method improves the training efficiency when compared with the centralized AMC (CentAMC) using S-CNN.

Accurate channel state information (CSI) is necessary for frequency-division duplexing (FDD) massive multi-input multi-output (MIMO) systems. Existing deep learning-based CSI feedback methods, e.g., CSI sensing and recovery neural network (CsiNet), designed based on an autoencoder architecture, achieves higher feedback accuracy and reconstruction speed. However, this network needs to be retrained due to different communication scenarios and channel conditions, which is costly in practical deployment. To solve this problem, this paper proposes a deep learning-based modular adaptive multiple-rate (MAMR) compression CSI feedback framework. Extra padding modules are added at the base station to pad compressed CSI into different compression rates into the same dimensions, thereby realizing a general autoencoder performing variable-rate compression. Simulation results are given to confirm the effectiveness of the proposed method in terms of normalized mean square error.

Automatic modulation classification (AMC) is an essential and meaningful technology in the development of cognitive radio. It can judge the modulation mode according to the signal acquired by the receiver. In recent years, the deep learning (DL) method has been used to take the place of modulation signal recognition based on decision theory and pattern recognition, which has achieved very effective results. The development of the neural network classification model focuses on architectural engineering. Discovering state-of-the-art neural network architectures requires substantial prior knowledge and effort of human experts. Neural architecture search (NAS) can be viewed as a subdomain of automatic machine learning (AutoML), which uses a neural network to automatically adjust the structures and parameters to obtain a network that researchers need by following search strategies that maximize performance. In this paper, we propose a differentiable architecture search (DARTS) based AMC method. In addition, we also consider six other methods, including convolutional neural network (CNN), simple recurrent unit (SRU), a convolutional-recurrent neural network (CRFN-CSS), Residual Networks (ResNet), Inception Modules (Inception) and MobileNet. Simulation results show that the proposed method can achieve the optimal classification accuracy at low parameters and floating-point operations (FLOPs) without manual architecture engineering.

In this paper, we focus on the sum-rate optimization in a multi-user millimeter-wave (mmWave) system with distributed intelligent reflecting surfaces (D-IRSs), where a base station (BS) communicates with users via multiple IRSs. The BS transmit beamforming, IRS switch vector, and phase shifts of the IRS are jointly optimized to maximize the sum-rate under minimum user rate, unit-modulus, and transmit power constraints. To solve the resulting non-convex optimization problem, we develop an efficient alternating optimization (AO) algorithm. Specifically, the non-convex problem is converted into three subproblems, which are solved alternatively. The solution to transmit beamforming at the BS and the phase shifts at the IRS are derived by using the successive convex approximation (SCA)-based algorithm, and a greedy algorithm is proposed to design the IRS switch vector. The complexity of the proposed AO algorithm is analyzed theoretically. Numerical results show that the D-IRSs-aided scheme can significantly improve the sum-rate and energy efficiency performance.

Acquisition of downlink channel state information (CSI) is an important procedure performed at the base station (BS) for high quality wireless communication in frequency division duplexing (FDD) communication system. Generally, the downlink CSI is fed back to the BS through the user equipment (UE). Compared with traditional methods, neural network (NN) can effectively compress the downlink CSI, thus greatly reducing the feedback overhead. However, the generalization of the NN is poor, hence it is necessary to train a NN from scratch whenever there is a change in the wireless channel environment. Nevertheless, training a NN this way requires huge data and time cost in 5G massive MIMO systems. In this paper, deep transfer learning (DTL) is proposed to solve the problem of high training cost of the downlink CSI feedback NN. In a new wireless environment, our proposed technique utilises relatively small number of samples to fine-tune a pre-trained model, in order to obtain a new model with low training cost. The performance of this model is shown to be comparable with that of the NN trained with large samples. Experiment results demonstrate the effectiveness and superiority of the proposed method.

With the ubiquitous network applications and the continuous development of network attack technology, all social circles have paid close attention to the cyberspace security. Intrusion detection systems (IDS) plays a very important role in ensuring computer and communication systems security. Recently, deep learning has achieved a great success in the field of intrusion detection. However, the high computational complexity poses a major hurdle for the practical deployment of DL-based models. In this paper, we propose a novel approach based on a lightweight deep neural network (LNN) for IDS. We design a lightweight unit that can fully extract data features while reducing the computational burden by expanding and compressing feature maps. In addition, we use inverse residual structure and channel shuffle operation to achieve more effective training. Experiment results show that our proposed model for intrusion detection not only reduces the computational cost by 61.99% and the model size by 58.84%, but also achieves satisfactory accuracy and detection rate.

Blockchain (BC) and artificial intelligence (AI) are often utilized separately in energy trading systems (ETSs). However, these technologies can complement each other and reinforce their capabilities when integrated. This article provides a comprehensive review of consensus algorithms (CAs) of BC and deep reinforcement learning (DRL) in ETS. While the distributed consensus underpins the immutability of transaction records of prosumers, the deluge of data generated paves the way to use AI algorithms for forecasting and address other data analytic-related issues. Hence, the motivation to combine BC with AI to realize secure and intelligent ETS. This study explores the principles, potentials, models, active research efforts and unresolved challenges in the CA and DRL. The review shows that despite the current interest in each of these technologies, little effort has been made at jointly exploiting them in ETS due to some open issues. Therefore, new insights are actively required to harness the full potentials of CA and DRL in ETS. We propose a framework and offer some perspectives on effective BC-AI integration in ETS.

Deep learning (DL) is an efficient method for botnet attack detection. However, the volume of network traffic data and memory space required is usually large. It is, therefore, almost impossible to implement the DL method in memory-constrained Internet-of-Things (IoT) devices. In this article, we reduce the feature dimensionality of large-scale IoT network traffic data using the encoding phase of long short-term memory autoencoder (LAE). In order to classify network traffic samples correctly, we analyze the long-term inter-related changes in the low-dimensional feature set produced by LAE using deep bidirectional long short-term memory (BLSTM). Extensive experiments are performed with the BoT-IoT data set to validate the effectiveness of the proposed hybrid DL method. Results show that LAE significantly reduced the memory space required for large-scale network traffic data storage by 91.89%, and it outperformed state-of-the-art feature dimensionality reduction methods by 18.92-27.03%. Despite the significant reduction in feature size, the deep BLSTM model demonstrates robustness against model underfitting and overfitting. It also achieves good generalisation ability in binary and multiclass classification scenarios.

Nonorthogonal multiple access (NOMA) significantly improves the connectivity opportunities and enhances the spectrum efficiency (SE) in the fifth generation and beyond (B5G) wireless communications. Meanwhile, emerging B5G services demand for higher SE in the NOMA-based wireless communications. However, traditional ground-to-ground (G2G) communications are hard to satisfy these demands, especially for the cellular uplinks. To solve these challenges, this article proposes a multiple unmanned-aerial-vehicles (UAVs)-aided uplink NOMA method. In detail, multiple hovering UAVs relay data for a half of ground users (GUs) and share the spectrums with the other GUs that communicate with the base station (BS) directly. Furthermore, this article proposes a K-means clustering-based UAV deployment scheme and location-based user pairing (UP) scheme to optimize the transceiver association for the multiple UAVs-aided NOMA uplinks. Finally, a sum power minimization-based resource allocation problem is formulated with the lowest Quality-of-Service (QoS) constraints. We solve it with the message-passing algorithm and evaluate the superior performances of the proposed scheduling and paring schemes on SE and energy efficiency (EE). Extensive simulations are conducted to compare the performances of the proposed schemes with those of the single UAV-aided NOMA uplinks, G2G-based NOMA uplinks, and the proposed multiple UAVs-aided uplinks with a facility location framework-based UAV deployment. Simulation results demonstrate that the proposed multiple UAVs deployment and UP-based NOMA scheme significantly improves the EE and the SE of the cellular uplinks at the cost of only a little relaying power consumption of UAVs.

Specific emitter identification (SEI) is a promising technology to discriminate the individual emitter and enhance the security of various wireless communication systems. SEI is generally based on radio frequency fingerprinting (RFF) originated from the imperfection of emitter's hardware, which is difficult to forge. SEI is generally modeled as a classification task and deep learning (DL), which exhibits powerful classification capability, has been introduced into SEI for better identification performance. In the recent years, a novel DL model, named as complex-valued neural network (CVNN), has been applied into SEI methods for directly processing complex baseband signal and improving identification performance, but it also brings high model complexity and large model size, which is not conducive to the deployment of SEI, especially in Internet-of-things (IoT) scenarios. Thus, we propose an efficient SEI method based on CVNN and network compression, and the former is for performance improvement, while the latter is to reduce model complexity and size with ensuring satisfactory identification performance. Simulation results demonstrated that our proposed CVNN-based SEI method is superior to the existing DL-based methods in both identification performance and convergence speed, and the identification accuracy of CVNN can reach up to nearly 100% at high signal-to-noise ratios (SNRs). In addition, SlimCVNN just has 10% ~ 30% model sizes of the basic CVNN, and its computing complexity has different degrees of decline at different SNRs; there is almost no performance gap between SlimCVNN and CVNN. These results demonstrated the feasibility and potential of CVNN and model compression.

This paper proposes an unmanned aerial vehicle (UAV)-aided full-duplex non-orthogonal multiple access (FD-NOMA) method to improve spectrum efficiency. Here, UAV is utilized to partially relay uplink data and achieve channel differentiation. Successive interference cancellation algorithm is used to eliminate the interference from different directions in FD-NOMA systems. Firstly, a joint optimization problem is formulated for the uplink and downlink resource allocation of transceivers and UAV relay. The receiver determination is performed using an access-priority method. Based on the results of the receiver determination, the initial power of ground users (GUs), UAV, and base station is calculated. According to the minimum sum of the uplink transmission power, the Hungarian algorithm is utilized to pair the users. Secondly, the subchannels are assigned to the paired GUs and the UAV by a message-passing algorithm. Finally, the transmission power of the GUs and the UAV is jointly fine-tuned using the proposed access control methods. Simulation results confirm that the proposed method achieves higher performance than state-of-the-art orthogonal frequency division multiple-access method in terms of spectrum efficiency, energy efficiency, and access ratio of the ground users.

Accurate downlink channel state information (CSI) is required to be fed back to the base station (BS) in frequency division duplexing (FDD) massive multiple-input multiple-output (MIMO) systems in order to achieve maximum antenna diversity and multiplexing. However, downlink CSI feedback overhead scales with the number of transceiver antennas, a major hurdle for practical deployment of FDD massive MIMO systems. To solve this problem, we propose a compressive sampled CSI feedback method based on deep learning (SampleDL). In SampleDL, the massive MIMO channel matrix is sampled uniformly in time/frequency dimension before being fed into neural networks (NNs), which will reduce the computational resource/time at user equipment (UE) as well as enhance the CSI recovery accuracy at the BS. Both theoretical analysis and normalized mean square errors (NMSE) results confirm the advantages of the proposed method in terms of time complexity and recovery accuracy. Besides, a suitable CSI feedback period is explored by link level simulations, which aims to further reduce the overhead of CSI feedback without degrading the communication quality.

Automatic modulation classification (AMC) is a critical algorithm for the identification of modulation types so as to enable more accurate demodulation in the non-cooperative scenarios. Deep learning (DL)-based AMC is believed as one of the most promising methods with great classification accuracy. However, the conventional CNN-based methods are lack of generality capabilities under time-varying signal-to-noise ratio (SNR) conditions, because these methods are merely trained on specific datasets and can only work under the corresponding condition. In this paper, a novel multi-task learning (MTL)-based generalized AMC method is proposed, and a more realistic scenario is considered, including white non-Gaussian noise and synchronization error. Its generalization capability stems from knowledge-sharing-based MTL in varying noise scenarios. In detail, multiple CNN models with the same structure are trained for multiple SNR conditions, but they share their knowledge (e.g. model weight) with each other. Thus, MTL can extract the general features from datasets in different noise scenarios. Simulation results show that our proposed architecture can achieve higher robustness and generalization than the conventional ones.

In this paper, a reconfigurable intelligent surface (RIS)-aided millimeter wave (mmWave) non-orthogonal multiple access (NOMA) system is analyzed. In particular, we consider an RIS-aided mmWave-NOMA downlink system with a hybrid beamforming structure. To maximize the achievable sum-rate under a minimum rate constraint for the users and a maximum transmit power constraint, a joint RIS phase shifts, hybrid beamforming, and power allocation problem is formulated. To solve this non-convex optimization problem, we develop an alternating optimization (AO) algorithm. Specifically, first, the non-convex problem is transformed into three subproblems, i.e., power allocation, joint phase shifts and analog beamforming optimization, and digital beamforming design. Then, we solve the power allocation problem by keeping fixed the phase shifts of the RIS and the hybrid beamforming. Finally, given the power allocation matrix, an alternating manifold optimization (AMO)-based method and a successive convex approximation (SCA)-based method are utilized to design the phase shifts, analog beamforming, and transmit beamforming, respectively. Numerical results reveal that the proposed AO algorithm outperforms existing schemes in terms of sum-rate. Moreover, compared to a conventional mmWave-NOMA system without RIS, the proposed RIS-aided mmWave-NOMA system is capable of improving the achievable sum-rate.

In a time division duplex (TDD) based massive multiple-input multiple-output (MIMO) system, a base station (BS) needs accurate estimation of channel state information (CSI) for a user terminal (UT). Due to the time-varying nature of the channel, the length of pilot signals is limited and the number of the orthogonal pilot signals is finite. Hence, the same pilot signals are required to be reused in neighboring cells and thus its channel estimation performance is deteriorated by pilot contamination from the neighboring cells. With the minimum mean square error (MMSE) channel estimation, the influence of pilot contamination can be reduced by the fully known covariance matrix of channels for all the UTs using the same pilot signal. However, this matrix is unknown to the BS a priori, and has to be estimated. In this paper, we propose two methods of deep learning aided channel estimation to reduce the influence of pilot contamination. One method uses a neural network consisting of fully connected layers, while the other method uses a convolutional neural network (CNN). The neural network, particularly the CNN, plays a role in extracting features of the spatial information from the contaminated signals. In terms of the speed of training, the former method is better than the latter one. We evaluate the proposed methods under two scenarios, i.e., perfect timing synchronization and imperfect one. Simulation results confirm that the proposed methods are better than the LS and the covariance estimation method via normalized mean square error (NMSE) of the channel.

So far, most separation approaches of vital signs such as heartbeat and respiration, are implemented based on linear mixtures. However, some literatures have reported that non-linear mixtures actually occur in the associated applications, e.g., heart rate (HR) estimation with Doppler radar, where the simple linear demixing architecture may limit the effect of source separation. In addition, the human motions during HR measurement further complicate the mixing processes. The issue motivates us to exploit a more suitable separation approach to deal with contact-free HR estimation, considering non-linear mixtures including motions. A semi-supervised deep clustering (DC) is proposed to separate the three mixed sources of heartbeat, respiration, and motions, by segmenting the spectrogram of Doppler signal. First, through training a deep recurrent neural network (RNN) with long short-term memory (LSTM) via heartbeat/respiration-only data, the embeddings to each frame-sample from spectrogram can be acquired, which enables feature optimization in a lower dimensional space. Then, in the test phase, K-means clusters the embeddings associated with each source, to infer the masks used for spectrogram segmentation. The proposed deep clustering has three main strengths: It (i) gets rid of the restriction of mixture class, relying on data mining; (ii) can handle three-source mixtures by training two sorts of source-independent samples; (iii) only requires the mixtures from single-channel. The HR measurement experiments on subjects' sitting still and typing, validate the improvements of accuracy and robustness by our proposal, over some prevailing approaches in signal decomposition or separation.

Cellular network performance is often evaluated by key performance indicator (KPI) and key quality indicator (KQI). The association between KQI and KPI is the most critical step to optimize the performance of cellular networks. Traditional association methods between KPI and KQI are based on the end-to-end evaluation. However, these methods require professional engineers to evaluate cellular network performance, and the man-manned evaluation is often inaccurate and labor-consuming, which cannot find out the main caused factor of deterioration networks. In order to solve the problem, we propose a machine learning-based quantitative association rule mining (QARM) method called SWP to associate KPI with KQI. Specifically, we mainly discretize continuous attributes into boolean values and then the association rules of these boolean values are mined by QARM algorithms, such as the Apriori algorithm. Finally, we select the warning intervals and the warning points obtained by SWP method as an optimal output solution. Experiments are conducted over the actual data from telecom operators and the results confirm the feasibility and accuracy of the proposed method.

Signa1 modulation recognition (SMR) is an essential and challenging topic in orthogonal frequency-division multiplexing (OFDM) systems, and also it is the fundamental technique for signal detection and recovery. However, traditional feature extraction based SMR methods cannot effectively acquire the characteristics of the OFDM signals. Hence, the modulated OFD-M signal cannot be reliably identified. In this paper, we propose a deep learning (DL) based SMR method for recognizing OFDM signals, which is combined with a convolutional neural network (CNN) trained on in-phase and quadrature (IQ) samples. In the network model, the batch normalization (BN) layer and dropout layer are used to speed up model training and prevent overfitting, respectively. Three convolution layers with different convolution kernels perform well than traditional feature extraction methods in obtaining intrinsic properties of OFDM signals. The same number of multiple modulated signals are mixed and sent to the trained model for identification. Experiments are conducted to show that the method we proposed performs better than the traditional methods, mainly reflected in a higher probability of correct classification (PCC) and better consistency.

Accurate flight delay prediction contains great reference value for airline business and passenger travel. Recent studies have been concentrated on applying machine learning methods to predict the probability of flight delay. Most of the previous prediction methods are built for a single air route or airport. This paper explores a broader spectrum of factors that may potentially affect the flight delay and proposes a gradient boosting decision tree (GBDT) based models for generalized flight delay prediction. To build a dataset for the proposed model, automatic dependent surveillance-broadcast (ADS-B) messages are received, pre-processed, and integrated with other information such as weather condition of airport, flight schedule, and airport information. Since the delay prediction results can be given with higher resolution, the designed prediction tasks contain four different classification tasks. Experimental results show that the proposed GBDT-based model can obtain higher prediction accuracy (87.72% for the binary classification) when handling our limited dataset.

In this paper, we propose a convolutional neural network (CNN) aided automatic modulation recognition (AMR) method for a multiple antenna system. We also present two specific combination strategies, such as the relative majority voting method and arithmetic mean method to improve the classification performance in comparison with the state of the art. Our results are given to verify that the proposed method dominant exploits features and classify the modulation types with higher accuracy in comparison with the AMR employing high order cumulants (HOC) and artificial neural networks (ANN).

Comprehensive evaluation methods of wireless user perception for cellular cells in the same scenario involve multi-indicators. Traditional methods use the weighted sum of all indicators as the evaluation result. However, many unimportant indicators occupy a part of the overall weight, which leads to an unconvincing evaluation result. To achieve a convincing and accurate result, we propose a lightweight comprehensive evaluation method. Firstly, most important indicators are chosen via the random forest algorithm. Secondly, those indicators are weighted via the entropy method. Finally, we compute the score of all cells with the weights. Experiment results are given to show that the cells with higher scores perform better in all indicators, which is coincide with the actual situation. Hence, our proposed method is not only lightweight but also obtain a more accurate result.

The traditional radar techniques are not suitable for the precise positioning of the aircraft with the rapid development of air traffic. Automatic dependent surveillance-broadcast (ADSB) is one of the most important technologies in the field of air traffic control. Unfortunately, the ADS-B technique is prone to cyber threats due to its open architecture. In order to validate the ADS-B signal and to enhance positioning accuracy of en-route aircraft, an approach unite the technology of ADS-B and multilateration (MLAT) is presented, where a dynamic flight model of aircraft is utilized. We use MLAT to overcome the problems caused by the drawbacks of ADS-B. Moreover, we propose a hybrid time-difference-of-arrival/angle-of-arrival (TDOA/AOA) positioning technology using Extened Kalman Filters (EKF) for ADS-B/MLAT positioning system. The experimental results show that the hybrid technology can improve the position accuracy and enhance the robustness of the surveillance systems.

This article aims to improve spectrum efficiency (SE) for the unmanned aerial vehicle (UAV)-relayed cellular uplinks, through distinguishing both line-of-sight (LoS) and non-LoS (NLoS) links. Meanwhile, aiming to accommodate the air-to-ground (A2G) cooperative nonorthogonal multiple access (NOMA)-based cellular users (CUs) with a high energy efficiency (EE), a joint resource allocation (RA) problem is further considered for the UAV and the CUs. To solve the problem, first, an access-priority-based receiver determination (RD) method is derived. According to the RD result, the heuristic user association (UA) strategies are given. Then, based on the UA result, transmission powers of the CUs and the UAV are initialized based on their quality-of-service (QoS) demands. Furthermore, the subchannels are assigned to the associated CUs and the UAV with the reweighted message-passing algorithm. Finally, the transmission power of the CUs and the UAV is jointly fine-tuned with the proposed access control schemes. Compared with the traditional orthogonal frequency-division multiple access (OFDMA) scheme and the traditional ground-to-ground (G2G) NOMA scheme, simulation results confirm that the UAV-aided NOMA with the proposed joint RA scheme yields better performances in terms of the SE, the EE, and the access ratio of the CUs.

Support vector machine (SVM) is a powerful machine learning (ML) technology and the distinctive generalization ability makes it one of the most popular approximation tools in the field of Internet-of-Things (IoT)-based marine data processing. However, SVM has been criticized for trial and error of parameters, especially, kernel function. How to determine a suitable kernel for SVM in a specific problem has been rather tricky. To give a systematic research of the field, we concentrate on the self-adaptive selection of kernel functions in the framework of SVM for IoT-based marine data prediction. Specifically, we adopt the optimal kernel for obtaining competitive SVM and devises a kernel selection criteria of such high-efficiency models. Experiments are conducted via IoT-based real-world marine data sets of different characteristics. The results demonstrate that our proposed self-adaptive SVM model can autonomously provide a suitable kernel for given marine environmental factor prediction, and outperform the alternative with the linear combination of multiple kernels. Besides, the superior performance is verified from the perspective of statistic analysis.

Network traffic prediction is a great challenge due to complex statistical properties, generally covering the long-range correlations and self-similarity. To address this issue, this article applies an integrated neural computing model to predict network traffic, namely, enhanced echo-state restricted Boltzmann machine (eERBM). In structure, this model possesses the following functional components of feature learning, information compensation, input superposition, and supervised nonlinear approximation. It is motivated by the introduction of information theory in modeling the hybrid architecture of the echo state network and the restricted Boltzmann machine. This is the first attempt that eERBM is applied in network traffic prediction tasks of different origin and characteristics, considering TCP/IP packet and variable-bit-rate video. By performing a theoretical analysis, we show that eERBM achieves superior nonlinear approximation and robustness in comparison to the baseline methods, and effectively preserves the self-similarity of network traffic traces.

As an important branch of the Internet of Vehicles (IoV), vehicle positioning has drawn extensive attention. Traditional positioning systems based on a global positioning system incur long delays, and may fail due to obstructions. In this article, we propose an auxiliary positioning architecture, whose core is to estimate the direction of arrival (DOA) of signals from landmarks, such as wireless access points, utilizing a sensor array in the vehicle. Due to space limitations, the array may be placed in an arbitrary geometry and may suffer from unknown mutual coupling. Most algorithms are only effective for sensor arrays with special geometries, e.g., a uniform linear array or rectangular array. To tackle this problem, an improved multiple signal classification algorithm is derived, which is superior to the state-of-the-art iterative method from the perspective of computational complexity. Detailed analysis concerning identifiability, computational complexity, and Cramér-Rao bounds are given. The simulation results verify the improvement of the proposed DOA estimation algorithm. The proposed architecture can obtain robust self-localization with existing vehicular ad hoc networks, and it can collaborate with other positioning systems to provide a safe driving environment.

Unmanned aerial vehicles (UAVs) are playing an important role in wireless networks, due to their cost effectiveness and flexible deployment. Particularly, integrating UAVs into existing cellular networks has great potential to provide high-rate and ultra-reliable communications. In this paper, we investigate the uplink transmission in a cellular network from a UAV using non-orthogonal multiple access (NOMA) and from ground users to base stations (BSs). Specifically, we aim to maximize the sum rate of uplink from UAV to BSs in a specific band as well as from the UAV's co-channel users to their associated BSs via optimizing the precoding vectors at the multi-antenna UAV. To mitigate the interference, we apply successive interference cancellation (SIC) not only to the UAV-connected BSs, but also to the BSs associated with ground users in the same band. The precoding optimization problem with constraints on the SIC decoding and the transmission rate requirements is formulated, which is non-convex. Thus, we introduce auxiliary variables and apply approximations based on the first-order Taylor expansion to convert it into a second-order cone programming. Accordingly, an iterative algorithm is designed to obtain the solution to the problem with low complexity. Numerical results are presented to demonstrate the effectiveness of our proposed scheme.

In this paper, the error performance and spectrum efficiency (SE) of uplink massive multiuser spatial modulation (SM) MIMO systems with zero-forcing detection for perfect and imperfect channel state information (CSI) are investigated over composite Rayleigh fading channels. We firstly derive the error probabilities of transmit antenna index detection and transmitted symbol detection of each user. Using these results, the bit error rate (BER) performance of the system under perfect CSI is analyzed. Furthermore, a closed-form average BER of the system is derived. We generalize the analytical results of perfect CSI to those of imperfect CSI for practicality, and derive a closed-form BER for the system with imperfect CSI. Based on this, two asymptotic BER expressions are developed to characterize the error performance of the system for large-scale receive antennas and high SNR. By means of the asymptotic expressions, the diversity order of the system is attained. Besides, we derive a lower bound on the achievable SE of the system with imperfect CSI. With this lower bound, an approximate expression of the achievable SE is obtained in closed form. Simulation results indicate that our theoretical analysis is valid, and agrees with simulation results well.

Hybrid analog-digital precoding is challenging for broadband millimeter-wave (mmWave) massive MIMO systems, since the analog precoder is frequency-flat but the mmWave channels are frequency-selective. In this paper, we propose a principal component analysis (PCA)-based broadband hybrid precoder/combiner design, where both the fully-connected array and partially-connected subarray (including the fixed and adaptive subarrays) are investigated. Specifically, we first design the hybrid precoder/combiner for fully-connected array and fixed subarray based on PCA, whereby a low-dimensional frequency-flat precoder/combiner is acquired based on the optimal high-dimensional frequency-selective precoder/combiner. Meanwhile, the near-optimality of our proposed PCA approach is theoretically proven. Moreover, for the adaptive subarray, a low-complexity shared agglomerative hierarchical clustering algorithm is proposed to group the antennas for the further improvement of spectral efficiency (SE) performance. Besides, we theoretically prove that the proposed antenna grouping algorithm is only determined by the slow time-varying channel parameters in the large antenna limit. Simulation results demonstrate the superiority of the proposed solution over state-of-the-art schemes in SE, energy efficiency (EE), bit-error-rate performance, and the robustness to time-varying channels. Our work reveals that the EE advantage of adaptive subarray over fully-connected array is obvious for both active and passive antennas, but the EE advantage of fixed subarray only holds for passive antennas.

Non-Orthogonal Multiple Access (NOMA) has been a hot research topic in recent years, because it is widely advocated that this technique represents a promising technology for 5G cellular networks and beyond. The NOMA literature today is heavily based on the so-called Power-Domain NOMA (PD-NOMA), which requires a strong power imbalance between the signals assigned to different users. Also, the focus in the literature has been on the derivation of achievable rates, which represent an information theoretic measure. In contrast, the signal-to-noise ratio (SNR) degradation that is caused by multiuser interference at practical bit error rate (BER) values has not attracted much attention. In some recent papers, the present authors revived an early NOMA concept, which had been rather overlooked in the recent NOMA literature. This concept, which we refer to as NOMA-2000, consists of superposing the signals of two user groups with different signal waveforms rather than the signals of two users. In our earlier papers, performance of NOMA-2000 was investigated in various conditions, but no comparisons were provided with PD-NOMA. The purpose of this paper is to compare the BER performances of the two schemes using several values of the power splitting factor between users. The results confirm that PD-NOMA suffers a strong SNR degradation and that NOMA-2000 provides substantially better performance in general.

In this paper, we propose a novel scheme to guarantee the security of UAV-relayed networks with caching via jointly optimizing the UAV trajectory and time scheduling. For the two users that have cached the required file for the other, the UAV broadcasts the files together to these two users and the eavesdropping can be disrupted. For the user without caching, we maximize its secrecy rate by jointly optimizing the trajectory and scheduling, with the secrecy rate of the caching users satisfied. The corresponding optimization problem is difficult to solve due to its non-convexity, and we propose an iterative algorithm via successive convex optimization to solve it approximatively. Simulation results are provided to show the effectiveness and efficiency of our proposed scheme.

In this paper, we present a three-dimensional (3D) wideband geometry-based channel model for multiple-input and multiple-output (MIMO) vehicle-to-vehicle (V2V) Ricean fading channels, where the received signal is constructed as a sum of line-of-sight (LoS) and non-LoS (NLoS) propagation rays. We first introduce multiple confocal semi-ellipsoid models to depict roadside environments, which is able to efficiently model scatterers with identical delays on the same semi-ellipsoid. Therefore, the V2V channel characteristics for different propagation delays can be investigated. Moreover, the proposed models can easily be reduced to various simplified channel models by properly adjusting model parameters. Using this channel model, the channel characteristics, i.e., the spatial correlation functions (CFs) and Doppler power spectral densities (PSDs), are investigated. The numerical results are very close to the previous results and measurements, thereby demonstrating the accuracy of the proposed channel model.

In some recent papers, the present authors revived an early non-orthogonal multiple access (NOMA) concept, which uses two sets of orthogonal signal waveforms and iterative interference cancellation. The beauty of this concept, which was introduced back in the year 2000, is that it fully avoids the power imbalance requirements of power-domain NOMA on which the current NOMA literature is heavily based. Using different type of receivers, these papers reported channel overload factors up to 25% on additive white Gaussian noise (AWGN) channels. In this paper, we investigate uplink performance on Rayleigh fading channels and we introduce a dynamic user grouping strategy, which leads to a substantial increase of the channel overload capability. Using this strategy, we show that the channel overload factor can be increased up to 100% at the expense of a virtually zero degradation of the signal-to-noise ratio (SNR).

Given vast expansion of video/data in many Internet of things (IoT) based intelligent surveillance systems, transferring data consumes many internet resources. Real-time intelligent analysis of multichannel digital video streams also poses substantial challenges to traditional central-based computing when applying ubiquitous IoT. In this paper, we put forth a couple-like computing method using cooperative computing between a central server and edge terminal for timely detection of potential risks at construction sites. Specifically, we assemble NVIDIA Jetson TX2 on each surveillance terminal and compute video at 3 frames per second for coarse detection. If the target is identified, the video is then transmitted to the central server for precise detection. The main contributions of this paper are twofold: reducing network traffic and reducing the computational burden for the central server. Our experiment is conducted using IoTbased intelligent surveillance systems at a real construction site to confirm the feasibility of the proposed method.

In this paper, user selection and transceiver design are proposed to guarantee the secure transmission in a multiple-input multiple-output interference network with an eavesdropper. First, user selection is performed to select the most suitable user to transmit confidential information according to the topology and path loss in each time slot. Then, based on user selection, the transceivers are jointly designed to maximize the secrecy rate of the selected user while guaranteeing a minimum transmission rate for other users. Due to the non-convexity of the problem, an alternate iteration algorithm is proposed to obtain the optimal solution with the help of successive approximations. Finally, simulation results are presented to show the effectiveness and efficiency of the proposed schemes.

Spatial Modulation (SM) was first introduced to reduce the number of radio frequency (RF) chains in a multiple-input multiple-output (MIMO) transmitter and thereby reduce cost and power consumption. Although it is very appealing in theory, this concept actually has two main problems, which are not sufficiently highlighted in the existing literature: The first is that the antenna switching involved destroys the spectral shaping of the transmitted signal, and the second is the limited spectral efficiency due to the presence of silent antennas. In order to remedy the second problem, Enhanced Spatial Modulation (ESM) was introduced. As for the problem of antenna switching, it actually disappears when SM is implemented in the frequency-domain, because the switching operation in Frequency-Domain SM (FD-SM) occurs at baseband. But the number of RF chains needed becomes equal to the number of transmit antennas. In this paper, we investigate Frequency-Domain ESM (FD-ESM), which avoids both the spectral efficiency limitations and the antenna switching of the original SM. Exploiting the property that switching occurs at baseband and no savings in terms of the number of RF chains can be achieved in frequency-domain implementation, we design FD-ESM schemes which provide spectacular gains with respect to conventional Multi-Stream SM (MSM) and also significant gains compared to spatial multiplexing.

When natural disasters strike, the coverage for Internet of Things (IoT) may be severely destroyed, due to the damaged communications infrastructure. Unmanned aerial vehicles (UAVs) can be exploited as flying base stations to provide emergency coverage for IoT, due to its mobility and flexibility. In this paper, we propose multiantenna transceiver design and multihop device-to-device (D2D) communication to guarantee the reliable transmission and extend the UAV coverage for IoT in disasters. First, multihop D2D links are established to extend the coverage of UAV emergency networks due to the constrained transmit power of the UAV. In particular, a shortest-path-routing algorithm is proposed to establish the D2D links rapidly with minimum nodes. The closed-form solutions for the number of hops and the outage probability are derived for the uplink and downlink. Second, the transceiver designs for the UAV uplink and downlink are studied to optimize the performance of UAV transmission. Due to the nonconvexity of the problem, they are first transformed into convex ones and then, low-complexity algorithms are proposed to solve them efficiently. Simulation results show the performance improvement in the throughput and outage probability by the proposed schemes for UAV wireless coverage of IoT in disasters.

The Internet of Things (IoT) has attracted significant attentions in the fifth generation mobile networks and the smart cities. However, considering the large numbers of connectivity demands, it is vital to improve the spectrum efficiency (SE) of the IoT with an affordable power consumption. To improve the SE, the nonorthogonal multiple access (NOMA) technology is newly proposed through accommodating multiple users in the same spectrums. As a result, in this paper, an energy efficient resource allocation (RA) problem is introduced for the NOMA-based heterogeneous IoT. At first, we assume the successive interference cancellation (SIC) is imperfect for practical implementations. Then, based on the analyzing method for cognitive radio networks, we present a stepwise RA scheme for the mobile users and the IoT users with the mutual interference management. Third, we propose a deep recurrent neural network-based algorithm to solve the problem optimally and rapidly. Moreover, a priorities and rate demands-based user scheduling method is supplemented, to coordinate the access of the heterogeneous users with the limited radio resource. At last, the simulation results verify that the deep learning-based scheme is able to provide optimal RA results for the NOMA heterogeneous IoT with fast convergence and low computational complexity. Compared with the conventional orthogonal frequency division multiple access system, the NOMA system with imperfect SIC yields better performance on the SE and the scale of connectivity, at the cost of high power consumption and low energy efficiency.

The Internet of Things (IoT) has significant importance in the beyond fifth generation (B5G) communication systems. However, the IoT is vulnerable to disasters because the network is mains powered and the devices are delicate. In this paper, an unmanned aerial vehicle (UAV) is utilized to assist with emergency communications in a heterogeneous IoT (Het-IoT) and a distributed nonorthogonal multiple access (NOMA) scheme is proposed without the requirement of successive interference cancelation (SIC). In order to accommodate the communications of the surviving users and IoT devices efficiently, a multiobjective resource allocation (MORA) scheme is proposed for the UAV-assisted Het-IoT. At first, the original MORA problem is formulated and decoupled with the user power initialization. Then, based on a reweighted message-passing algorithm (ReMPA), the subchannels are assigned to the devices and the users in a stepwise manner. Finally, the transmitting power of the users and the devices is jointly fine-tuned using an iterative access control scheme. The simulation results confirm that the distributed SIC-free NOMA (DSF-NOMA) based on the MORA scheme provides satisfactory communication performances for the users and the devices with a tradeoff between the two subsystems. Compared with the traditional orthogonal frequency division multiple access (OFDMA) scheme and the MORA scheme with random subchannel assignment, the proposed DSF-NOMA-based MORA scheme yields better performances in terms of the sum rate of the users and the access ratio of the devices.

In this paper, we propose a relay cooperation scheme for backscatter communication systems for performance enhancement, in which one user backscatters incident signals from a power beacon (PB) to a relay and a receiver simultaneously, and then the relay decodes the received signals and forwards the decoded signals to the receiver. We consider two cases that the relay is with/without an embedded energy source. In particular, if the relay does not have an energy source, an energy harvesting phase is required, during which the relay harvests energy from the PB while the user backscatters information to the receiver. We first formulate system throughput maximization problems for both cases by finding the optimal time allocation schemes, from which some useful insights are provided. Then, with a given amount of information required to be delivered, the transmission time minimization problems for both cases are also formulated, and the optimal solutions are derived in closed-form. Numerical results reveal the proposed scheme can significantly enhance the system throughput and transmission time.

Deep neural networks (DNNs) have widely used in various Internet-of-Things (IoT) applications. Pursuing superior performance is always a hot spot in the field of DNN modeling. Recently, feature reuse provides an effective means of achieving favorable nonlinear approximation performance in deep learning. Existing implementations utilizes a multilayer perception (MLP) to act as a functional unit for feature reuse. However, determining connection weight and bias of MLP is a rather intractable problem, since the conventional back-propagation learning approach encounters the limitations of slow convergence and local optimum. To address this issue, this paper develops a novel DNN considering a well-behaved alternative called reservoir computing, i.e., reservoir in network (ResInNet). In this structure, the built-in reservoir has two notable functions. First, it behaves as a bridge between any two restricted Boltzmann machines in the feature learning part of ResInNet, performing a feature abstraction once again. Such reservoir-based feature translation provides excellent starting points for the following nonlinear regression. Second, it serves as a nonlinear approximation, trained by a simple linear regression using the most representative (learned) features. Experimental results over various benchmark datasets show that ResInNet can achieve the superior nonlinear approximation performance in comparison to the baseline models, and produce the excellent dynamic characteristics and memory capacity. Meanwhile, the merits of our approach is further demonstrated in the network traffic prediction related to real-world IoT application.

Heterogeneous network (HetNet) with energy harvesting is a promising technique to provide perpetual power supplies and ubiquitous coverage as well as high data rate for next-generation wireless communications. In this article, we consider a robust power allocation and power splitting (PS) problem for downlink simultaneous wireless information and power transfer (SWIPT)-enabled HetNets. The robust energy-efficiency (EE) maximization problem of femtocell users (FUs) is formulated under the outage-probability interference power constraint of macrocell user (MU), the maximum allowable transmission power of FU, and the EE-based outage constraint of each FU. The originally fractional optimization problem with the probabilistic constraint is NP-hard and difficult to solve. Without knowing the distribution of uncertain parameters, a min–max probability machine approach isfirstintroduced to convert the semi-infinite optimization problem into a deterministic one which is transformed into a deterministic convex one by using the Dinkelbach method and the quadratic transformation approach. An iterative power allocation and PS scheme is obtained based on convex optimization methods. Finally, the effectiveness of the proposed algorithm is demonstrated by simulation results from the perspective of EE and robustness.

Unmanned aerial vehicle (UAV) can be utilized as a relay to connect nodes with long distance, which can achieve significant throughput gain owing to its mobility and line-of-sight (LoS) channel with ground nodes. However, such LoS channels make UAV transmission easy to eavesdrop. In this paper, we propose a novel scheme to guarantee the security of UAV-relayed wireless networks with caching via jointly optimizing the UAV trajectory and time scheduling. For every two users that have cached the required file for the other, the UAV broadcasts the files together to these two users, and the eavesdropping can be disrupted. For the users without caching, we maximize their minimum average secrecy rate by jointly optimizing the trajectory and scheduling, with the secrecy rate of the caching users satisfied. The corresponding optimization problem is difficult to solve due to its non-convexity, and we propose an iterative algorithm via successive convex optimization to solve it approximately. Furthermore, we also consider a benchmark scheme in which we maximize the minimum average secrecy rate among all users by jointly optimizing the UAV trajectory and time scheduling when no user has the caching ability. Simulation results are provided to show the effectiveness and efficiency of our proposed scheme.

Non-Orthogonal Multiple Access (NOMA) has been a hot research topic over the past few years, particularly because it is widely recognized that this technique represents a promising technology for massive Machine-Type Communications (mMTC) in future 5G cellular networks. The NOMA literature today is heavily focused on the so-called Power-Domain NOMA, which requires a strong power imbalance at the receiver between user signals. In some recent papers ([1] and [2]), the present authors revived a NOMA concept introduced back in the year 2000 and completely overlooked in the recent NOMA literature. This NOMA concept, which uses two sets of orthogonal signal waveforms and iterative interference cancellation at the receiver, fully avoids the power imbalance requirements of power-domain NOMA and makes it possible to grant the same data rates and performance levels to different users. In this paper, we first shed further light on the limitations of today's power-domain NOMA and we give insight on the potential of superposing the signals of two user groups with different characteristics instead of superposing two user signals. Next, we propose a new variant of the NOMA technique proposed in [1] and [2], which avoids the use of a complex interference canceler. This scheme achieves a 25% channel overloading factor at a negligible degradation of the signal-to-noise ratio (SNR) using a very simple maximumlikelihood (ML) receiver.

In this paper, an energy efficient resource allocation (RA) problem is introduced for a NOMA based heterogeneous IoT. Particularly, the successive interference cancelation (SIC) is assumed imperfect for implementations. Accordingly, a stepwise scheme is presented with the mutual interference management. Specifically, a deep learning based algorithm is proposed to solve the problem optimally and rapidly. The simulation results verify that the proposed RA scheme provides the optimal results for the NOMA based heterogeneous IoT with fast convergence and low computational complexity. Compared with the OFDMA scheme, the NOMA based scheme yields better performance on the spectrum efficiency (SE) and the scale of connectivity, at the cost of high power consumption and low energy efficiency (EE).

The requirement of the increasing capacity of the communication networks promotes the massive multiple input multiple output (MIMO), which has attracted a lot of attention among academic and industry communities. Due to the inherent sparsity features of channel structure in uplink massive MIMO systems, conventional methods often bring about high computational complexity and also fail to make full use of the structural information. In order to solve this problem, this paper proposes a novel deep learning (DL) based super-resolution direction of arrivals (DOA) estimation method. Specifically, it is realized with the aids of the well-designed deep neural network (DNN). Then we employ the DNN to carry out offline learning and online deployment procedures. This learning mechanism can learn the features of the wireless channel and the spacial structures efficiently. Finally, simulation results are provided to show that the proposed DL based scheme can achieve better performance in terms of the DOA estimation compared with conventional methods.

In this paper, we consider a relay assisted backscatter communication (RaBackCom) system, where a user backscatters incident signals from a carrier emitter (CE) to a relay and a receiver simultaneously, and then the relay forwards the user's information to the receiver for throughput improvement. We consider two cases that the relay is with/without an embedded energy source. Specifically, if the relay does not have an energy source, it first harvests energy from the signals from the CE and then uses its harvested energy for information forwarding. For both cases, we formulate time allocation problems on the user's information backscattering, the user's information forwarding, or the relay's energy harvesting to maximize the system throughput, and then derive closed-form solutions. Simulation results demonstrate the advantages of the proposed relay cooperation scheme with the optimal time allocation in terms of system throughput.

Non-orthogonal multiple access (NOMA) is recognized today as a most promising technology for future 5G cellular networks and a large number of papers have been published on the subject over the past few years. Interestingly, none of these authors seems to be aware that the foundation of NOMA actually dates back to the year 2000, when a series of papers introduced and investigated multiple access schemes using two sets of orthogonal signal waveforms and iterative interference cancellation at the receiver. The purpose of this paper is to shed light on that early literature and to describe a practical scheme based on that concept, which is particularly attractive for machine-type communications (MTC) in future 5G cellular networks. Using this approach, NOMA appears as a convenient extension of orthogonal multiple access rather than a strictly competing technology, and most important of all, the power imbalance between the transmitted user signals that is required to make the receiver work in other NOMA schemes is not required here.

Compared with the conventional degrees of freedom, the orbital angular momentum (OAM), which describes the helical phase structure of electromagnetic wave, provides a new degree of freedom. As a new multiple access scheme, mode division multiple access (MDMA) is constructed in millimetre wave frequency band utilising the orthogonality and high dimensionality in this study. Various traditional resources such as frequency, time and code pattern have been shared. Therefore, addresses of signals from different terminal users can be distinguished by OAM mode to realise multi‐address connection. In this study, the theoretical analysis of the number of terminals in MDMA scheme is carried out. According to the analysis results, infinite terminals can be connected together in the ideal case. Moreover, the simulation results show that compared with the conventional multi‐input multi‐output millimetre wave communication systems, the performance indicators of MDMA millimetre wave communication systems are improved remarkably.

The ‐norm penalised (LP) normalised least mean square algorithm converges faster than the LP normalised least mean fourth algorithm does, but the latter can achieve better steady‐state performance, particularly in regions with low signal‐to‐noise ratios (SNRs). To simultaneously take advantage of both merits, a sparse hybrid adaptive filtering algorithm is proposed in various SNR environments. Specifically, the authors construct a cost function that uses the statistical error term and sparse penalty term. The first term is designed by a hybrid error function of the second‐ and fourth‐order statistical errors, respectively, and the second term is obtained using a sparse constraint function. The hybrid error term can be easily balanced by a proportional parameter . Moreover, they devise a non‐uniform step size in the proposed algorithm to further balance the convergence speed and estimation error. Simulation results are provided to validate the proposed algorithm in various SNR environments.

In this paper, we consider a cognitive wireless powered communication network for Internet of Things applications, which consists of a primary communication pair and a secondary communication system. We propose a novel hybrid harvest-then-transmit (HTT) and backscatter communication (BackCom) mode for the information transmission of the secondary communication system. When the primary channel is busy, cognitive users (CUs) backscatter the incident signal from the primary transmitter to the information receiver in the ambient backscatter (AB) mode or harvest energy for the future information transmission. When the primary channel is idle, CUs backscatter the incident signal from the power beacon in the bistatic scatter (BS) mode or work in the HTT mode to transmit information. We further investigate the optimal time allocation between the AB mode and energy harvesting and that between the BS mode and the HTT mode for the sake of maximizing the throughput of the secondary communication system, and derive the numerical solutions. To be specific, we derive the closed-form optimal solution for a single CU case, and moreover, obtain the optimal combination of the working modes. Numerical results demonstrate the advantage of our proposed hybrid HTT and BackCom mode over the benchmark mode in terms of system throughput.

Unmanned aerial vehicles (UAVs) can help small-cell base stations (SBSs) offload traffic via wireless backhaul to improve coverage and increase rate. However, the capacity of backhaul is limited. In this paper, UAV assisted secure transmission for scalable videos in hyper-dense networks via caching is studied. In the proposed scheme, UAVs can act as SBSs to provide videos to mobile users in some small cells. To reduce the pressure of wireless backhaul, UAVs and SBSs are both equipped with caches to store videos at off-peak time. To facilitate UAVs, a single antenna is equipped at each UAV and thus, only the precoding matrices of SBSs should be cooperatively designed to manage interference by exploiting the principle of interference alignment. On the other hand, the SBSs replaced by UAVs will be idle. Thus, in order to guarantee secure transmission, the idle SBSs can be further exploited to generate jamming signal to disrupt eavesdropping. The jamming signal is zero-forced at the legitimate users through the precoding of the idle SBSs, without affecting the legitimate transmission. The feasibility conditions of the proposed scheme are derived, and the secrecy performance is analyzed. Finally, simulation results are presented to verify the effectiveness of the proposed scheme.

Device‐to‐Device communication underlaying cellular network can increase the spectrum efficiency due to direct proximity communication and frequency reuse. However, such performance improvement is influenced by the power interference caused by spectrum sharing and social characteristics in each social community jointly. In this investigation, we present a dynamic game theory with complete information based D2D resource allocation scheme for D2D communication underlaying cellular network. In this resource allocation method, we quantify both the rate influence from the power interference caused by the D2D transmitter to cellular users and rate enhancement brought by the social relationships between mobile users. Then, the utility function maximization game is formulated to optimize the overall transmission rate performance of the network, which synthetically measures the final influence from both power interference and sociality enhancement. Simultaneously, we discuss the Nash Equilibrium of the proposed utility function maximization game from a theoretical point of view and further put forward a utility priority searching algorithm based resource allocation scheme. Simulation results show that our proposed scheme attains better performance compared with the other two advanced proposals.

The robust adaptive beamforming (RAB) problem for noncircular signals with the desired signal's steering vector (SV) mismatch is considered. As we know, noncircular signals are widely used in the satellite communication and radio communication. Some existing approaches for estimating the extended SV of the desired signal are based on the second-order cone programming (SOCP), which results in a high computational cost. In this paper, we propose a novel robust widely linear (WL) beamforming algorithm by using a low-complexity shrinkage-based approach. The augmented interference-plus-noise covariance matrix (IPNCM) is reconstructed first by using the SVs corresponding to the interference region. Then, a modified oracle approximating shrinkage (OAS) method is applied to estimate the desired signal's extended SV. Only the prior knowledge of the antenna array geometry and the angular sector in which the desired signal is located are utilized in the proposed method. Numerical simulations show that the proposed algorithm outperforms the existing robust WL beamforming methods.

Channel feedback is essential for frequency division duplex (FDD) massive multiple-input multiple-output (MIMO) systems to realize precoding and power allocation. Traditional codebooks for channel feedback, where the required number of feedback bits is proportional to the number of base station (BS) antennas, can not scale up with massive MIMO due to the large number of BS antennas. To solve this problem, in this paper, we propose an angle-of-departure (AoD) adaptive subspace codebook to reduce the codebook size and feedback overhead. Specifically, by leveraging the concept of angle coherence time, which implies that the path AoDs vary much slower than path gains, we propose an AoD-adaptive subspace codebook to quantize the channel vector in a more accurate way. We also provide performance analysis of the proposed AoD-adaptive subspace codebook, where we prove that the required number of feedback bits only scales linearly with the number of resolvable AoDs, which is much smaller than the number of BS antennas. This quantitative result is also verified by simulations.

This paper studies the relay selection schemes in mobile communication system over Nakagami-m channel. To make efficient use of licensed spectrum, both single relay selection (SRS) scheme and multirelays selection (MRS) scheme over the Nakagami-m channel are proposed. Also, the intercept probability (IP) and outage probability (OP) of the proposed SRS and MRS for the communication links depending on realistic spectrum sensing are derived. Furthermore, this paper assesses the manifestation of conventional direct transmission scheme to compare with the proposed SRS and MRS ones based on the Nakagami-m channel, and the security-reliability trade-off (SRT) performance of the proposed schemes and the conventional schemes is well investigated. Additionally, the SRT of the proposed SRS and MRS schemes is demonstrated better than that of direct transmission scheme over the Nakagami-m channel, which can protect the communication transmissions against eavesdropping attacks. Additionally, simulation results show that our proposed relay selection schemes achieve better SRT performance than that of conventional direct transmission over the Nakagami-m channel.

Signal detection is one of the fundamental problems in three-dimensional multiple-input multiple-output (3D-MIMO) wireless communication systems. This paper addresses a signal detection problem in 3D-MIMO system, in which spatial modulation (SM) transmission scheme is considered due to its advantages of low complexity and high-energy efficiency. SM based signal transmission typically results in the block-sparse structure in received signals. Hence, structured compressed sensing (SCS) based signal detection is proposed to exploit the inherent block sparsity information in the received signal for the uplink (UL). Moreover, normalization preprocessing is considered before iteration process with the purpose of preventing the noise from being overamplified by the column vector with inadequately large elements. Simulation results are provided to show the stable and reliable performance of the proposed algorithm under both Gaussian and non-Gaussian noise, in comparison with methods such as compressed sensing based detectors, minimum mean square error (MMSE), and zero forcing (ZF).

Sparse adaptive filtering algorithms are utilized to exploit potential sparse structure information as well as to mitigate noises in many unknown sparse systems. Sparse recursive least square (RLS) algorithms have been attracted intensely attentions due to their low-complexity and easy- implementation. Basically, these algorithms are constructed by standard RLS algorithm and sparse penalty functions (e.g., l_1-norm). However, existing sparse RLS algorithms do not exploit the sparsity efficiently. In this paper, an improved adaptive filtering algorithm is proposed by incorporating a novel correntropy induced metric (CIM) constraint into RLS, which is termed as RLS- CIM algorithm. Specifically, we adopt a well-known Gaussian kernel in CIM and further devise a novel variable kernel width to control the sparse penalty in different transient-error scenarios. Numerical simulation results are given to corroborate the proposed algorithm via mean square deviation (MSD).

Broadband frequency-selective fading channels usually exhibit the inherent sparse structure distribution in spread time-domain. By exploiting the sparsity, adaptive sparse channel estimation (ASCE) algorithms, e.g., least mean square with reweighted L1-norm constraint (LMS-RL1) algorithm, can bring a considerable performance gain under the assumption of additive white Gaussian noise (AWGN). In the scenarios of real wireless communication systems, however, channel estimation performance is often deteriorated by the unexpected non-Gaussian mixture noises which usually include AWGN and impulsive noises. To design stable communication systems, we propose sign LMS-RL1 (SLMS-RL1) channel estimation algorithm to remove the non-Gaussian noises and to exploit channel sparsity simultaneously. In addition, the regularization parameter (REPA) selection for SLMS-RL1 algorithm is proposed via Monte Carlo method. Simulation results are provided to corroborate our studies.

In this paper, by exploiting the special features of temporal correlations of dynamic sparse channels that path delays change slowly over time but path gains evolve faster, we propose the structured matching pursuit (SMP) algorithm to realize the reconstruction of dynamic sparse channels. Specifically, the SMP algorithm divides the path delays of dynamic sparse channels into two different parts to be considered separately, i.e., the common channel taps and the dynamic channel taps. Based on this separation, the proposed SMP algorithm simultaneously detects the common channel taps of dynamic sparse channels in all time slots at first, and then tracks the dynamic channel taps in each single time slot individually. Theoretical analysis of the proposed SMP algorithm provides a guarantee that the common channel taps can be successfully detected with a high probability, and the reconstruction distortion of dynamic sparse channels is linearly upper bounded by the noise power. Simulation results demonstrate that the proposed SMP algorithm has excellent reconstruction performance with competitive computational complexity compared with conventional reconstruction algorithms.

Large‐scale multiple‐input multiple‐output (MIMO) system is considered one of promising technologies to realise next‐generation wireless communication system (5G). So far, channel estimation problem is a big obstacle to develop large‐scale MIMO system design due to high computational complexity and curse of dimensionality, which are caused by the long delay spread as well as a large number of antennas. Hence, devising any low‐complexity channel estimation method could promote the successful development of the large‐scale MIMO system. Due to the fact that, large‐scale MIMO channels often exhibit sparse or/and cluster‐sparse structure, in this study, the authors propose an effective low‐complexity large‐scale MIMO channel estimation method by using affine combination of sparse adaptive filtering filters. First, problem formulation and standard affine combination of adaptive least mean square (LMS) filters are introduced. Then they propose an effective affine combination method with two sparse LMS filters and design an approximate optimum affine combiner according to stochastic gradient search method. Later, to verify the proposed algorithm for large‐scale MIMO channel estimation, both theoretical analysis and numerical simulations are provided to confirm effectiveness of the proposed algorithm which can achieve better estimation performance than the traditional methods.

Abstract Standard least mean square/fourth (LMS/F) is a classical adaptive algorithm that combined the advantages of both least mean square (LMS) and least mean fourth (LMF). The advantage of LMS is fast convergence speed while its shortcoming is suboptimal solution in low signal‐to‐noise ratio (SNR) environment. On the contrary, the advantage of LMF algorithm is robust in low SNR while its drawback is slow convergence speed in high SNR case. Many finite impulse response systems are modeled as sparse rather than traditionally dense. To take advantage of system sparsity, different sparse LMS algorithms withlp‐LMS andl0‐LMS have been proposed to improve adaptive identification performance. However, sparse LMS algorithms have the same drawback as standard LMS. Different from LMS filter, standard LMS/F filter can achieve better performance. Hence, the aim of this paper is to introduce sparse penalties to the LMS/F algorithm so that it can further improve identification performance. We propose two sparse LMS/F algorithms using two sparse constraints to improve adaptive identification performance. Two experiments are performed to show the effectiveness of the proposed algorithms by computer simulation. In the first experiment, the number of nonzero coefficients is changing, and the proposed algorithms can achieve better mean square deviation performance than sparse LMS algorithms. In the second experiment, the number of nonzero coefficient is fixed, and mean square deviation performance of sparse LMS/F algorithms is still better than that of sparse LMS algorithms. Copyright © 2013 John Wiley & Sons, Ltd.

To realize high-speed communication, broadband transmission has become an indispensable technique in the next-generation wireless communication systems. Broadband channel is often characterized by the sparse multipath channel model, and significant taps are widely separated in time, and thereby, a large delay spread exists. Accurate channel state information is required for coherent detection. Traditionally, accurate channel estimation can be achieved by sampling the received signal with large delay spread by analog-to-digital converter ADC at Nyquist rate and then estimate all of channel taps. However, as the transmission bandwidth increases, the demands of the Nyquist sampling rate already exceed the capabilities of current ADC. In addition, the high-speed ADC is very expensive for ordinary wireless communication. In this paper, we present a novel receiver, which utilizes a sub-Nyquist ADC that samples at much lower rate than the Nyquist one. On the basis of the sampling scheme, we propose a compressive channel estimation method using Dantzig selector algorithm. By comparing with the traditional least square channel estimation, our proposed method not only achieves robust channel estimation but also reduces the cost because low-speed ADC is much cheaper than high-speed one. Computer simulations confirm the effectiveness of our proposed method. Copyright © 2013 John Wiley & Sons, Ltd.

Abstract This paper studies normalized least mean square‐based adaptive sparse filtering algorithms for estimating multiple‐input multiple‐output (MIMO) channels. Although the MIMO channel is often modeled as sparse, traditional normalized least mean square‐based filtering algorithm never takes the advantage of the inherent sparse structure information and thus causes some performance loss. Unlike the traditional method, the proposed two adaptive sparse channel estimation methods exploit the sparse structure information of MIMO channels. To validate the effectiveness of proposed MIMO channel estimates, theoretical analysis and simulation results are provided. We derive steady‐state mean‐square deviations of the proposed MIMO channel estimates and theoretically show that it is better than the traditional one. Moreover, their performance advantages are confirmed by computer simulations. Copyright © 2014 John Wiley & Sons, Ltd.

Compared with standard cyclic prefix OFDM (CP-OFDM), time domain synchronous OFDM (TDS-OFDM) can achieve a higher spectrum efficiency by using the known training sequence instead of CP as the guard interval. However, TDS-OFDM suffers from reduced energy efficiency and performance loss due to the existing mutual inferences. In this paper, based on the newly emerging theory of structured compressive sensing (SCS), we propose a reliable and energy-efficient TDS-OFDM transmission scheme with reduced guard interval power (which is impossible for CP-OFDM) by designing a channel estimation scheme with high accuracy. The wireless channel properties including channel sparsity and inter-channel correlation, which are usually not considered in conventional OFDM schemes, have been exploited. We further exploit the worst-case system design principle to extract multiple interference-free regions of small size to simultaneously reconstruct multiple channels of large size without iterative interference cancellation. In this way, the guard interval power in TDS-OFDM can be reduced to achieve a 20% higher energy efficiency than standard CP-OFDM, and the system reliability can be also improved in fast fading channels.

Accurate channel estimation is essential for broadband wireless communications. Adaptive sparse channel estimation schemes based on normalized least mean square (NLMS) have been proposed to exploit channel sparsity for improved performance. However, their performance bound as derived in this paper indicates that the invariable step size (ISS) usually used for iteration in these schemes would lead to performance loss or/and slow convergence speed as well as high computational cost. To solve this problem, based on the observation that a large step size is preferred for fast convergence while a small step size is preferred for accurate estimation, we then propose to replace the ISS by the variable step size (VSS) to improve the performance of sparse channel estimation. The key idea is that the VSS can be adaptive to the estimation error in each iteration, i.e., a large step size is used in the case of large estimation error to accelerate the convergence speed, while a small step size is used when the estimation error is small to improve the steady-state estimation accuracy. Finally, simulation results verify that better mean square error (MSE) and bit error rate (BER) performance could be achieved by the proposed scheme.

In this paper, we present a sparse channel estimation method for orthogonal frequency division multiplexing (OFDM) based two-way relay networks (TWRN). Conventional channel estimation methods, such as least squares (LS), have been proposed to obtain channel state information (CSI) at the cost of the training resource, which reduce spectrum efficiency. However, physical measurements have verified that the wireless channels tend to exhibit sparse structures in high-dimensional spaces, e.g., delay spread, Doppler spread and space spread. With the development of compressive sensing (CS), a novel compressive channel estimation method which is called adaptive compressive matching pursuit (ACMP) algorithm is proposed by using the sparse constraint between the terminal nodes and the relay node in the TWRN. Simulation results confirm that ACMP channel estimation method provides significant improvement in mean square error (MSE) performance compared to the conventional channel estimation methods.

Sparse system identification problems often exist in many applications, such as echo interference cancellation, sparse channel estimation, and adaptive beamforming. One of popular adaptive sparse system identification (ASSI) methods is adopting only one sparse least mean square (LMS) filter. However, the adoption of only one sparse LMS filter cannot simultaneously achieve fast convergence speed and small steady-state mean state deviation (MSD). Unlike the conventional method, we propose an improved ASSI method using affine combination of two sparse LMS filters to simultaneously achieving fast convergence and low steady-state MSD. First, problem formulation and standard affine combination of LMS filters are introduced. Then an approximate optimum affine combiner is adopted for the proposed filter according to stochastic gradient search method. Later, to verify the proposed filter for ASSI, computer simulations are provided to confirm effectiveness of the proposed filter which can achieve better estimation performance than the conventional one and standard affine combination of LMS filters.

Channel estimation problem is one of the key technical issues for broadband multiple‐input–multiple‐output (MIMO) signal transmission. To estimate the MIMO channel, a standard least mean square (LMS) algorithm was often applied to adaptive channel estimation because of its low complexity and stability. The sparsity of the broadband MIMO channel can be exploited to further improve the estimation performance. This observation motivates us to consider adaptive sparse channel estimation (ASCE) methods using sparse LMS (ASCE‐LMS) algorithms. However, conventional ASCE methods have two main drawbacks: (i) sensitivity to random scaling of training signal and (ii) poor estimation performance in low signal‐to‐noise ratio (SNR) regime. The former drawback is tackled by proposing novel ASCE‐NLMS algorithms. ASCE‐NLMS mitigates interference of random scale of training signal and therefore it improves its algorithm stability. It is well‐known that stable sparse normalised least‐mean fourth (NLMF) algorithms can achieve better estimation performance than sparse NLMS algorithms. Therefore the authors propose an improved ASCE method using sparse NLMF algorithms (ASCE‐NLMF) to improve the estimation performance in low SNR regime. Simulation results show that the proposed ASCE methods are shown to achieve better performance than conventional methods, that is, ASCE‐LMS by computer simulations. Also, the stability of the proposed methods is confirmed by theoretical analysis.

Least mean square (LMS)-type adaptive sparse algorithms have been attracting much attention on sparse multipath channel estimation (SMPC) due to their two advantages: low computational complexity and reliability. By introducing ℓ1-norm sparse constraint function into LMS algorithm, both zero-attracting least mean square (ZA-LMS) and reweighted zero-attracting least mean square (RZA-LMS) have been proposed for SMPC. It is well known that the performance of the SMPC is decided by regularization parameter which balances channel estimation error and sparse penalty strength. However, optimal regularization parameter selection has not yet considered in the two proposed algorithms. Based on the compressive sensing theory, in this paper, we explain the mathematical relationship between Lasso and LMS-type adaptive sparse algorithms. Later, an approximate optimal regulation parameter selection method is proposed for ZA-LMS and RZA-LMS, respectively. Monte Carlo based computer simulations are presented to show the effectiveness of our propose method.

Accurate channel state information (CSI) is required for coherent detection in time-variant multiple-input multiple-output (MIMO) communication systems using orthogonal frequency division multiplexing (OFDM) modulation. One of low-complexity and stable adaptive channel estimation (ACE) approaches is the normalized least mean square (NLMS)-based ACE. However, it cannot exploit the inherent sparsity of MIMO channel which is characterized by a few dominant channel taps. In this paper, we propose two adaptive sparse channel estimation (ASCE) methods to take advantage of such sparse structure information for time-variant MIMO-OFDM systems. Unlike traditional NLMS-based method, two proposed methods are implemented by introducing sparse penalties to the cost function of NLMS algorithm. Computer simulations confirm obvious performance advantages of the proposed ASCEs over the traditional ACE.

Broadband signal transmission over frequency-selective fading channel often requires accurate channel state information at receiver. One of the most attracting adaptive channel estimation (ACE) methods is least mean square (LMS) algorithm. However, its performance is often degraded by random scaling of input training signal. To overcome this degradation, in this paper we consider the use of standard least mean square/fourth (LMS/F) algorithm. Since the broadband channel is often described by sparse channel model, such sparsity could be exploited as prior information. First, we propose an adaptive sparse channel estimation (ASCE) method with zero-attracting LMS/F (ZA-LMS/F) algorithm by introducing an ℓ1-norm sparse constraint into the cost function. Then, to exploit the sparsity more effectively, an improved ASCE with reweighted zero-attracting LMS/F (RZA-LMS/F) algorithm is proposed. For different channel sparsity, we propose a Monte Carlo method for a regularization parameter selection in RA-LMS/F and RZA-LMS/F to achieve better steady-state estimation performance. Simulation results show that the proposed ASCE methods achieve better estimation performance than the conventional one.

Channel estimation problem is one of the key technical issues in time-variant multiple-input multiple-output (MIMO) communication systems. To estimate the MIMO channel, least mean square (LMS) algorithm was applied to adaptive channel estimation (ACE). Since the MIMO channel is often described by sparse channel model#65292;such sparsity can be exploited to improve the estimation performance by adaptive sparse channel estimation (ASCE) methods using sparse LMS algorithms. However, conventional ASCE methods have two main drawbacks: 1) sensitive to random scale of training signal and 2) unstable in low signal-to-noise ratio (SNR) regime. To overcome the two harmful factors, in this paper, we propose a novel ASCE method using normalized LMS (NLMS) algorithm (ASCE-NLMS). In addition, we also proposed an improved ASCE method using normalized least mean fourth (NLMF) algorithm (ASCE-NLMF). Two proposed methods can exploit the channel sparsity effectively. Also, stability of the proposed methods is confirmed by mathematical derivation. Computer simulation results show that the proposed sparse channel estimation methods can achieve better estimation performance than conventional methods.

Channel state information (CSI) is required at receiver in orthogonal frequency division modulation (OFDM) communication systems due to the fact that frequency-selective fading channel leads to inter- symbol interference (ISI) over data transmission. Broadband channel model is often described by very few dominant channel taps and they can be probed by sparse channel estimation (SCE) methods, e.g., subspace pursuit (SP) algorithm, can take the advantage of sparse structure effectively in broadband channels as for prior information. However, these developed methods are vulnerable to both noise, interference and column coherence of training signal matrix. In other words, the primary objective of these conventional methods is to catch the dominant channel taps without a report of posterior channel uncertainty. To improve the estimation performance, we proposed a Bayesian sparse channel estimation (BSCE) method which not only exploits the channel sparsity but also mitigates the unexpected channel uncertainty. The proposed method can reveal potential ambiguity among multiple channel estimators that are ambiguous due to observation noise or correlation interference among columns in the training matrix. Computer simulations show that our technique can improve the estimation performance with comparable computational complexity when comparing with conventional SCE methods.

Accurate channel impulse response (CIR) is required for coherent detection and it also helps to improve the quality of service in next-generation wireless communication systems. Linear channel estimation methods, e.g., least square (LS), have been proposed to estimate the CIR. However, these methods never take advantage of the channel sparsity and they also cause performance loss. In this paper, we propose a sparse channel estimation method for multi-input multi-output orthogonal frequency-division multiplexing (MIMO-OFDM) amplify and forward two-way relay networks (AF-TWRN), to exploit the sparse structure information in the CIR for each user. Sparse channel estimation problem is formulated as compressed sensing (CS) using sparse decomposition theory and the estimation process is implemented by LASSO algorithm. Computer simulation results are given to confirm the superiority of the proposed method over the LS-based channel estimation.

Least mean square (LMS) based adaptive algorithms have been attracted much attention since their low computational complexity and robust recovery capability. To exploit the channel sparsity, LMS-based adaptive sparse channel estimation methods, e.g., zero-attracting LMS (ZA-LMS), reweighted zero-attracting LMS (RZA-LMS) and Lp- norm sparse LMS (LP-LMS), have also been proposed. To take full advantage of channel sparsity, in this paper, we propose several improved adaptive sparse channel estimation methods using Lp-norm normalized LMS (LP-NLMS) and L0-norm normalized LMS (L0-NLMS). Comparing with previous methods, effectiveness of the proposed methods is confirmed by computer simulations.

Accurate channel state information (CSI) is necessary for coherent detection in amplify and forward (AF) broadband cooperative communication systems. Based on the assumption of ordinary sparse channel, efficient sparse channel estimation methods have been investigated in our previous works. However, when the cooperative channel exhibits partial sparse structure rather than ordinary sparsity, our previous method cannot take advantage of the prior information. In this paper, we propose an improved channel estimation method with partial sparse constraint on cooperative channel. At first, we formulate channel estimation as a compressive sensing problem and utilize sparse decomposition theory. Secondly, the cooperative channel is reconstructed by LASSO with partial sparse constraint. Finally, numerical simulations are carried out to confirm the superiority of proposed methods over ordinary sparse channel estimation methods.

Coherent detection and demodulation at the receiver requires channel state information (CSI). We investigate channel estimation problem in sparse multipath non-orthogonal amplify-and- forward (NAF) cooperative networks. Traditional linear estimation methods can obtain lower bound at the cost of spectrum efficiency which is becoming more and more scarcity. In this paper, system model is described from sparse representation perspective. Based on the compressed sensing theory, we propose several compressed channel estimation methods to exploit sparsity of the cooperative channels. Simulation results confirm the superiority of proposed methods than LS-based linear estimation method.

Multiple-input multiple-output orthogonal frequency division multiplexing (MIMO-OFDM) is the promising technology for next generation communication systems due to high throughput. Due to the coherent receiving and demodulation at the receiver, accurate channel state information (CSI) is indispensable. Conventional rich assumption-based channel estimators have been proposed at the cost of enough training resource which leads to extra spectrum waste. However, physical measurements have verified that the wireless channels tend to exhibit sparse structure in high-dimensional space, e.g., delay spread, Doppler spread and space spread. Some sparse channel estimation methods for the MIMO-OFDM have been proposed. These estimation methods utilize either greedy algorithm or convex optimization. In this paper, we propose a novel sparse channel estimation method using sparse cognitive matching pursuit (SCMP) algorithm. Compared to other compressive algorithms in the state of art, the major innovation of the SCMP sparse channel estimation method (SCMP-SCE) is the ability of obtaining the accurate CSI without prior information of sparsity. Simulation results confirm that the proposed method has better estimation performance and lower estimation complexity.