Federated learning (FL) and reconfigurable intelligent surfaces (RIS) are pivotal technologies for future Internet of Things (IoT) networks, enhancing user privacy and system efficiency. However, realizing their full potential necessitates a cohesive and synergistic integration, challenging the traditional view of them as disparate components. This paper tackles the complex problem of maximizing energy efficiency (EE)—a critical yet under-explored metric insuch tightly coupled FL-RIS systems. We address this gap by formulating ajoint optimization problem that intrinsically links the FL process with physical layer resource allocation. Our framework maximizes the system’s global EE by concurrently designing the base station’s active beamforming and the RIS’s passive phase shifts,with an FL aggregation mechanism that is explicitly channel-aware and adaptive to the RIS-optimized wireless environment. This co-design ensures RIS actively facilitates FL by establishing robust communication, while FL intelligently leverages these improved channels for efficient and accelerated learning, all under practical FL performance constraints. Simulation results demonstrate that our proposed framework significantly enhances system energy efficiency compared to several benchmark schemes and exhibits robust convergence properties.

Deep learning based semantic communication (DeepSC) system has emerged as a promising paradigm for efficient wireless transmission. However, existing image DeepSC methods, frequently encounter challenges in balancing rate-distortion performance and computational complexity, and often exhibit inferior performance compared to traditional schemes, especially on high-resolution datasets. To address these limitations, we propose a novel image DeepSC system, using quadtree partition-based joint semantic-channel coding, named Quad-DeepSC, which maintains low complexity while achieving state-of-the-art transmission performance. Based on maturing learned image compression technologies, we establish a unified DeepSC system design and training pipeline. The proposed Quad-DeepSC integrates quadtree partition-based entropy estimation and feature coding modules with lightweight feature extraction and reconstruction networks to form an end-to-end architecture. During training, all components except the feature coding modules are jointly optimized as a compact learned image codec, Quad-LIC, for source compression tasks. The pretrained Quad-LIC is then embedded into Quad-DeepSC and fine-tuned end-to-end over wireless channels. Extensive experimental results demonstrate that Quad-DeepSC is the first DeepSC system to surpass conventional communication systems, which employ VTM for source coding and adopt the optimal MCS index under 3GPP standards for channel coding and digital modulation, in performance across datasets of varying resolutions. Notably, both Quad-DeepSC and Quad-LIC exhibit minimal latency, rendering them well-suited for deployment in real-time wireless communication systems.

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

Underwater communication is essential for environmental monitoring, marine biology research, and underwater exploration. Traditional underwater communication faces limitations like low bandwidth, high latency, and susceptibility to noise, while semantic communication (SC) offers a promising solution by focusing on the exchange of semantics rather than symbols or bits. However, SC encounters challenges in underwater environments, including semantic information mismatch and difficulties in accurately identifying and transmitting critical information that aligns with the diverse requirements of underwater applications. To address these challenges, we propose a novel SC framework based on Large Language Models (LLMs). Our framework leverages visual LLMs to perform semantic compression and prioritization of underwater image data according to the query from users. By identifying and encoding key semantic elements within the images, the system selectively transmits high-priority information while applying higher compression rates to less critical regions. On the receiver side, an LLM-based recovery mechanism, along with Global Vision ControlNet and Key Region ControlNet networks, aids in reconstructing the images, thereby enhancing communication efficiency and robustness. Our framework reduces the overall data size to 0.8% of the original. Experimental results demonstrate that our method significantly outperforms existing approaches, ensuring high-quality, semantically accurate image reconstruction.

Semantic communication (SemCom) has recently emerged as a promising paradigm for enhancing the efficiency and intelligence of wireless networks. Nevertheless, device het erogeneity, resource constraints, and the vulnerability of deep neural networks in open environments pose significant challenges to its practical deployment. In this paper, we propose a task oriented and lightweight SemCom system with secure aggregation for ensuring efficient and privacy-preserving interactions in distributed networks. First, we design a multi-task SemCom framework that unifies semantic feature extraction from sample based datasets. To accommodate resource-constrained devices, we further introduce a feature distillation mechanism that derives lightweight local models without sacrificing inference accuracy. To preserve the privacy of local datasets while leveraging the generalization capability of distributed devices, we develop a secure model aggregation algorithm based on multiparty homomorphic encryption. Simulation results and comparative experiments validate the effectiveness of our system, which fully utilizes the knowledge embedded in existing high-performance models. Our results demonstrate that the proposed local semantic models outperform the baseline models under limited datasets and reduced parameters. We also analyze the trade-off between computational complexity and security in the proposed aggregation scheme, highlighting its applicability to distributed SemCom scenarios.

Existing speech semantic communication systems mainly based on Joint Source-Channel Coding (JSCC) architectures have demonstrated impressive performance, but their effectiveness remains limited by model structures specifically designed for particular tasks and datasets. Recent advances indicate that generative large models pre-trained on massive datasets, can achieve outstanding performance and exhibit exceptional effectiveness across diverse downstream tasks with minimal fine-tuning. To exploit the rich semantic knowledge embedded in large models and enable adaptive transmission over lossy channels, we propose a Large Speech Model enabled Semantic Communication (LargeSC) system. Simultaneously achieving adaptive compression and robust transmission over lossy channels remains challenging, requiring trade-offs among compression efficiency, speech quality, and latency. In this work, we employ the Mimi as a speech codec, converting speech into discrete tokens compatible with existing network architectures. We propose an adaptive controller module that enables adaptive transmission and in-band Unequal Error Protection (UEP), dynamically adjusting to both speech content and packet loss probability under bandwidth constraints. Additionally, we employ Low-Rank Adaptation (LoRA) to fine-tune the Moshi foundation model for generative recovery of lost speech tokens. Simulation results show that the proposed system supports bandwidths ranging from 550 bps to 2.06 kbps, outperforms conventional baselines in speech quality under high packet loss rates and achieves an end-to-end latency of approximately 460 ms, thereby demonstrating its potential for real-time deployment.

Semantic communications are expected to improve the transmission efficiency in Internet of Things (IoT) networks. However, the distributed nature of networks and heterogeneity of devices challenge the secure utilization of semantic communication systems. In this paper, we develop a distributed semantic communication system that achieves the security and efficiency during update and usage phases. A blockchain-based trust scheme for update is designed to continuously train and synchronize the system in dynamic IoT environments. To improve the updating efficiency, we propose a flexible semantic coding method base on compressive semantic knowledge bases. It greatly reduces the amount of data shared among devices for system update, and realizes the flexible adjustment of the size of knowledge bases and the number of transmitted signal symbols in model training and inference stages. In the usage phase, a signature mechanism for lossy semantics is introduced to guarantee the integrity and authenticity of the transmitted semantics in lossy semantic communications. We further design a noise-aware differential privacy mechanism, which introduces optimized noise based on the different channel information available to heterogeneous devices. Experiments on transmission tasks show that the proposed system defends against cross-phase attacks of compromising semantics integrity and reduces the data to be shared in the update phase by about 36% to 90%, and in the usage phase by 60% compared with related works.

This paper proposes a novel diffusion-enabled pluggable encryption/decryption modules design against semantic eavesdropping, where the pluggable modules are optionally assembled into the semantic communication system for preventing eavesdropping. Inspired by the artificial noise (AN)-based security schemes in traditional wireless communication systems, in this paper, AN is introduced into semantic communication systems to prevent semantic eavesdropping. However, the introduction of AN also poses challenges for the legitimate receiver in extracting semantic information. Recently, denoising diffusion probabilistic models (DDPM) have demonstrated their powerful capabilities in generating multimedia content. Here, the paired pluggable modules are carefully designed using DDPM. Specifically, the pluggable encryption module generates AN and adds it to the output of the semantic transmitter, while the pluggable decryption module before semantic receiver uses DDPM to generate the detailed semantic information by removing both AN and the channel noise. In the scenario where the transmitter lacks eavesdropper’s knowledge, the artificial Gaussian noise (AGN) is used as AN. We first model a power allocation optimization problem to determine the power of AGN, in which the objective is to minimize the weighted sum of data reconstruction error of legal link, the mutual information of illegal link, and the channel input distortion. Then, a deep reinforcement learning framework using deep deterministic policy gradient is proposed to solve the optimization problem. In the scenario where the transmitter is aware of the eavesdropper’s knowledge, we propose an AN generation method based on adversarial residual networks (ARN). Unlike the previous scenario, the mutual information term in the objective function is replaced by the confidence of eavesdropper correctly retrieving private information. The adversarial residual network is then trained to minimize the modified objective function. Simulation results show that the diffusion-enabled pluggable encryption module prevents semantic eavesdropping with high covertness while the pluggable decryption module achieves the high-quality semantic communication.

As a promising 6G enabler beyond conventional bit-level transmission, semantic communication can considerably reduce required bandwidth resources, while its combination with multiple access requires further exploration. This paper proposes a knowledge distillation-driven and diffusion-enhanced (KDD) semantic non-orthogonal multiple access (NOMA), named KDD-SemNOMA, for multi-user uplink wireless image transmission. Specifically, to ensure robust feature transmission across diverse transmission conditions, we firstly develop a ConvNeXt-based deep joint source and channel coding architecture with enhanced adaptive feature module. This module incorporates signal-to-noise ratio and channel state information to dynamically adapt to additive white Gaussian noise and Rayleigh fading channels. Furthermore, to improve image restoration quality without inference overhead, we introduce a two-stage knowledge distillation strategy, i.e., a teacher model, trained on interference-free orthogonal transmission, guides a student model via feature affinity distillation and cross-head prediction distillation. Moreover, a diffusion model-based refinement stage leverages generative priors to transform initial SemNOMA outputs into high-fidelity images with enhanced perceptual quality. Extensive experiments on CIFAR-10 and FFHQ-256 datasets demonstrate superior performance over state-of-the-art methods, delivering satisfactory reconstruction performance even at extremely poor channel conditions. These results highlight the advantages in both pixel-level accuracy and perceptual metrics, effectively mitigating interference and enabling high-quality image recovery.

In this article, we propose a robust semantic communication system for speech transmission, named Ross-S2T, to execute the speech-to-text translation (S2TT) transmission efficiently. First, a deep semantic encoder is developed to directly convert speech in the source language to textual features associated with the target language, facilitating the end-to-end (E2E) semantic exchange to perform the S2TT task and reducing the amount of transmission data without performance degradation. To mitigate semantic impairments inherent in the corrupted speech, a novel generative adversarial network (GAN)-enabled deep semantic compensator is established to estimate the hidden semantic information within the speech and extract deep semantic features simultaneously, which enables robust semantic transmission for corrupted speech. Furthermore, a semantic probe-aided compensator is devised to enhance the semantic fidelity of recovered semantic features and improve the understandability of the target text. According to simulation results, the proposed Ross-S2T exhibits superior S2TT performance compared to conventional approaches and high robustness against semantic impairments.

In recent years, the Transformer architecture has achieved outstanding performance across a wide range of tasks and modalities. Token is the unified input and output representation in Transformer-based models, which has become a fundamental information unit. In this work, we consider the problem of token communication, studying how to transmit tokens efficiently and reliably. Point cloud, a prevailing three-dimensional format which exhibits a more complex spatial structure compared to image or video, is chosen to be the information source. We utilize the set abstraction method to obtain point tokens. Subsequently, to get a more informative and transmission-friendly representation based on tokens, we propose a joint semantic-channel and modulation (JSCCM) scheme for the token encoder, mapping point tokens to standard digital constellation points (modulated tokens). Specifically, the JSCCM consists of two parallel Point Transformer-based encoders and a differential modulator which combines the Gumel-softmax and soft quantization methods. Besides, the rate allocator and channel adapter are developed, facilitating adaptive generation of high-quality modulated tokens conditioned on both semantic information and channel conditions. Extensive simulations demonstrate that the proposed method outperforms both joint semantic-channel coding and traditional separate coding, achieving over 1dB gain in reconstruction and more than 6× compression ratio in modulated symbols.

The rapid development of generative artificial intelligence (AI) has introduced significant opportunities for enhancing the efficiency and accuracy of image transmission within semantic communication systems. Despite these advancements, existing methodologies often neglect the difference in importance of different regions of the image, potentially compromising the reconstruction quality of visually critical content. To address this issue, we introduce an innovative generative semantic communication system that refines semantic granularity by segmenting images into key and non-key regions. Key regions, which contain essential visual information, are processed using an image oriented semantic encoder, while non-key regions are efficiently compressed through an image-to-text modeling approach. Additionally, to mitigate the substantial storage and computational demands posed by large AI models, the proposed system employs a lightweight deployment strategy incorporating model quantization and low-rank adaptation fine-tuning techniques, significantly boosting resource utilization without sacrificing performance. Simulation results demonstrate that the proposed system outperforms traditional methods in terms of both semantic fidelity and visual quality, thereby affirming its effectiveness for image transmission tasks.

In this paper, we propose a robust semantic communication system for speech transmission, named Ross-S2T, by delivering the essential semantic information. Specifically, we consider the speech-to-text translation (S2TT) as the transmission goal. First, a new deep semantic encoder is developed to convert speech in the source language to textual features associated with the target language, facilitating the end-to-end semantic exchange to perform the S2TT task and reducing the transmission data without performance degradation. To mitigate semantic impairments inherent in the corrupted speech, a novel generative adversarial network (GAN)-enabled deep semantic compensator is established to estimate the lost semantic information within the speech and extract deep semantic features simultaneously, which enables robust semantic transmission for corrupted speech. Furthermore, a semantic probe-aided compensator is devised to enhance the semantic fidelity of recovered semantic features and improve the understandability of the target text. According to simulation results, the proposed Ross-S2T exhibits superior S2TT performance compared to conventional approaches and high robustness against semantic impairments.

Deep learning enabled semantic communications are attracting extensive attention. However, most works normally ignore the data acquisition process and suffer from robustness issues under dynamic channel environment. In this paper, we propose an adaptive joint sampling-semantic-channel coding (Adaptive-JSSCC) framework. Specifically, we propose a semantic-aware sampling and reconstruction method to optimize the number of samples dynamically for each region of the images. According to semantic significance, we optimize sampling matrices for each region of the most individually and obtain a semantic sampling ratio distribution map shared with the receiver. Through the guidance of the map, high-quality reconstruction is achieved. Meanwhile, attention-based channel adaptive module (ACAM) is designed to overcome the neural network model mismatch between the training and testing channel environment during samplingreconstruction and encoding-decoding. To this end, signal-to-noise ratio (SNR) is employed as an extra parameter input to integrate and reorganize intermediate characteristics. Simulation results show that the proposed Adaptive-JSSCC effectively reduces the amount of data acquisition without degrading the reconstruction performance in comparison to the state-of-the-art, and it is highly adaptable and adjustable to dynamic channel environments.

Semantic communications have demonstrated exceptional performance across various tasks, yet they are susceptible to semantic impairments due to the inherent vulnerability of deep neural networks. This paper focuses on semantic impairments in images, particularly those stemming from adversarial perturbations. We introduce a novel metric for quantifying the level of semantic impairment and create a semantic impairment dataset. Furthermore, we propose a deep learning enabled semantic communication system for robust image transmission, termed as DeepSC-RI. The proposed system harnesses a multi-scale semantic extractor with a dual-branch design tailored for extracting semantics with varying granularity, thereby boosting the robustness of the system. The fine-grained branch incorporates a semantic importance evaluation module to identify and prioritize crucial semantics through self-attention score manipulations, while the coarse-grained branch adopts a hierarchical approach for progressively capturing the robust semantics. These two streams of semantics are seamlessly integrated via an advanced cross-attention-based semantic fusion module. Experimental results highlight the superior performance of DeepSC-RI under diverse channel conditions, across various levels of semantic impairment intensity, and in multiple tasks.

Digital and analog semantic communications (SemCom) face inherent limitations such as data security concerns in analog SemCom, as well as leveling-off and cliff-edge effects in digital SemCom. In order to overcome these challenges, we propose a novel SemCom framework and a corresponding system called HDA-DeepSC, which leverages a hybrid digital-analog approach for multimedia transmission. This is achieved through the introduction of analog-digital allocation and fusion modules. To strike a balance between data rate and distortion, we design new loss functions that take into account long-distance dependencies in the semantic distortion constraint, essential information recovery in the channel distortion constraint, and optimal bit stream generation in the rate constraint. Additionally, we propose denoising diffusion-based signal detection techniques, which involve carefully designed variance schedules and sampling algorithms to refine transmitted signals. Through extensive numerical experiments, we will demonstrate that HDA-DeepSC exhibits robustness to channel variations and is capable of supporting various communication scenarios. Our proposed framework outperforms existing benchmarks in terms of peak signal-to-noise ratio and multi-scale structural similarity, showcasing its superiority in semantic communication quality.

Semantic communications have the potential to improve transmission efficiency and support intelligent tasks. However, the commonly used global sampling-based pattern ignores the fact that the data processing ability of edge transmitters is strictly limited and only a small part of information is available for a single sample in some scenarios. This paper proposes a novel partial sampling-based semantic communication (PSSC) framework where an edge transmitter is guided by feedback from the receiver to locate and collect only part of content relevant to the target task. Taking the vision-based task as an example, the transmitter selectively samples a small patch of a large-size image until the intelligent task is successfully executed at the receiver. The selection of sampling location is modeled as a partially observable Markov decision process problem and an intelligent approach based on reinforcement learning is proposed to solve the problem. In addition, a recurrent neural network-based receiver is designed to fuse information received over multiple transmission rounds. Besides, we prove that the feedback does not increase the semantic channel capacity. Simulation results demonstrate that the proposed framework can locate the informative areas accurately and achieve competitive performance compared to the existing global sampling-based methods.

Although the semantic communication with joint semantic-channel coding design has shown promising performance in transmitting data of different modalities over physical layer channels, the synchronization and packet-level forward error correction (FEC) of multimodal semantics have not been well studied. Synchronizing multimodal features in both the semantic and time domains is challenging due to the independent design of semantic encoders. In this paper, we take the facial video and speech transmission as an example and propose a Synchronous Multi-modal Semantic Communication System with Packet-Level Coding (SyncSC). To achieve semantic and time synchronization, 3D Morphable Mode (3DMM) coefficients and text are transmitted as semantics. We propose a semantic codec that achieves similar reconstruction quality with lower bandwidth. The visual-guided speech synthesis is designed to synchronize video, text and speech. We propose a packet-Level FEC method for video semantics, called PacSC, that maintains visual quality even at high packet loss rates. For text packets, a text packet loss concealment module, called TextPC, based on Bidirectional Encoder Representations from Transformers (BERT) is proposed, which improves the performance of traditional FEC methods. Simulation results show that SyncSC reduces transmission overhead while ensuring high-quality synchronous transmission of video and speech over the packet loss network.

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

Semantic communications have gained significant attention as a promising approach to address the transmission bottleneck, especially with the continuous development of 6G techniques. Distinct from the well investigated physical channel impairments, this paper focuses on semantic impairments in images, particularly those arising from adversarial perturbations. Specifically, we propose a novel metric for quantifying the intensity of semantic impairment and develop a semantic impairment dataset. Furthermore, we introduce a deep learning enabled semantic communication system, termed as DeepSC-RI, to enhance the robustness of image transmission, which incorporates a multi-scale semantic extractor with a dual-branch architecture for extracting semantics with varying granularity, thereby improving the robustness of the system. The fine-grained branch incorporates a semantic importance evaluation module to identify and prioritize crucial semantics, while the coarse-grained branch adopts a hierarchical approach for capturing the robust semantics. These two streams of semantics are seamlessly integrated via an advanced cross-attention-based semantic fusion module. Experimental results demonstrate the superior performance of DeepSC-RI under various levels of semantic impairment intensity.

Although semantic communication has shown great performance in various types of data transmission, the problem of semantic synchronization between multimodal data has not been well studied. Semantic synchronization is a challenging issue that requires the transmitted information to be synchronized in both semantic and time domains. In this article, we propose a synchronous semantic communication system for video and speech transmission, which the real-time facial transmission is adopted as the use case. Particularly, to achieve time domain synchronization, we design an efficient semantic transmitter to send multimodal data packets. 3D Morphable Mode (3DMM) coefficients and text are employed as semantic information, achieving semantic interactivity and lower bandwidth. To address synchronization in semantic domain, we firstly employ the visual voice clone at the receiver. Visual-guided speech synthesis module is designed to align text and facial semantics. Thus, the generated speech is synchronized with video frames in both semantic and time domains. The simulation results show that our proposed system achieves high-quality synchronous transmission of video and speech with reducing transmission overhead.

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

The metaverse is expected to provide immersive entertainment, education, and business applications. However, virtual reality (VR) transmission over wireless networks is data- and computation-intensive, making it critical to introduce novel solutions that meet stringent quality-of-service requirements. With recent advances in edge intelligence and deep learning, we have developed a novel multi-view synthesizing framework that can efficiently provide computation, storage, and communication resources for wireless content delivery in the metaverse. We propose a three-dimensional (3D)-aware generative model that uses collections of single-view images. These single-view images are transmitted to a group of users with overlapping fields of view, which avoids massive content transmission compared to transmitting tiles or whole 3D models. We then present a federated learning approach to guarantee an efficient learning process. The training performance can be improved by characterizing the vertical and horizontal data samples with a large latent feature space, while low-latency communication can be achieved with a reduced number of transmitted parameters during federated learning. We also propose a federated transfer learning framework to enable fast domain adaptation to different target domains. Simulation results have demonstrated the effectiveness of our proposed federated multi-view synthesizing framework for VR content delivery.

Artificial intelligence (AI) and machine learning (ML) have shown tremendous potential in reshaping the landscape of wireless communications and are, therefore, widely expected to be an indispensable part of the next-generation wireless network. This article presents an overview of how AI/ML and wireless communications interact synergistically to improve system performance and provides useful tips and tricks on realizing such performance gains when training AI/ML models. In particular, we discuss in detail the use of AI/ML to revolutionize key physical layer and lower medium access control (MAC) layer functionalities in traditional wireless communication systems. In addition, we provide a comprehensive overview of the AI/ML-enabled semantic communication systems, including key techniques from data generation to transmission. We also investigate the role of AI/ML as an optimization tool to facilitate the design of efficient resource allocation algorithms in wireless communication networks at both bit and semantic levels. Finally, we analyze major challenges and roadblocks in applying AI/ML in practical wireless system design and share our thoughts and insights on potential solutions.

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

Task-oriented semantic communications have achieved significant performance gains. However, the employed deep neural networks in semantic communications have to be updated when the task is changed or multiple models need to be stored for performing different tasks. To address this issue, we develop a unified deep learning-enabled semantic communication system (U-DeepSC), where a unified end-to-end framework can serve many different tasks with multiple modalities of data. As the number of required features varies from task to task, we propose a vector-wise dynamic scheme that can adjust the number of transmitted symbols for different tasks. Moreover, our dynamic scheme can also adaptively adjust the number of transmitted features under different channel conditions to optimize the transmission efficiency. Particularly, we devise a lightweight feature selection module (FSM) to evaluate the importance of feature vectors, which can hierarchically drop redundant feature vectors and significantly accelerate the inference. To reduce the transmission overhead, we then design a unified codebook for feature representation to serve multiple tasks, where only the indices of these task-specific features in the codebook are transmitted. According to the simulation results, the proposed U-DeepSC achieves comparable performance to the task-oriented semantic communication system designed for a specific task but with significant reduction in both transmission overhead and model size.

In cellular networks, resource allocation is usually performed in a centralized way, which brings huge computation complexity to the base station (BS) and high transmission overhead. This paper introduces a distributed resource allocation method that aims to maximize energy efficiency (EE) while ensuring quality of service (QoS) for users. Specifically, to address the challenge of fast-varying wireless channel conditions, we propose a robust meta federated reinforcement learning (MFRL) framework that enables local users to optimize transmit power and assign channels using locally trained neural network models. This approach offloads the computational burden from the cloud server to the local users, reducing transmission overhead associated with local channel state information. The BS performs the meta-learning procedure to initialize a general global model, enabling rapid adaptation to different environments and improved EE performance. The federated learning technique, based on decentralized reinforcement learning, promotes collaboration and mutual benefits among users. Analysis and numerical results demonstrate that the proposedMFRLframework accelerates the reinforcement learning process, decreases transmission overhead, and offloads computation, while outperforming the conventional decentralized reinforcement learning algorithm in terms of convergence speed and EE performance across various scenarios.

The limited capabilities of user equipment restrict the local implementation of computation-intensive applications. Edge computing, especially the edge intelligence system, enables local users to offload the computation tasks to the edge servers to reduce the computational energy consumption of user equipment and accelerate fast task execution. However, the limited bandwidth of upstream channels may increase the task transmission latency and affect the computation offloading performance. To overcome the challenge arising from scarce wireless communication resources, we propose a semantic-aware multi-modal task offloading system that facilitates the extraction and offloading of semantic task information to edge servers. To cope with the different tasks with multi-modal data, a unified quality of experience (QoE) criterion is designed. Furthermore, a proximal policy optimization-based multi-agent reinforcement learning algorithm (MAPPO) is proposed to coordinate the resource management for wireless communications and computation in a distributed and low computational complexity manner. Simulation results verify that the proposed MAPPO algorithm outperforms other reinforcement learning algorithms and fixed schemes in terms of task execution speed and the overall system QoE.

The spiking neural network (SNN) is distinguished by its ultra-low power consumption, making it attractive for resource-limited edge intelligence. This paper investigates an energy-efficient (EE) distributed SNN, where multiple edge nodes, each containing a subset of spiking neurons, collaborate to gather and process information through wireless channels. To leverage the benefits of the joint design of neuromorphic computing and wireless communications, we develop quantitative system models and formulate the problem of minimizing the energy consumption of edge devices under constraints of limited bandwidth and spike loss probability. Particularly, a simplified homogeneous SNN is first explored, where the system is proved to have stationary states with a constant firing rate and an alternating optimization based algorithm is proposed for jointly allocating the computation and communication resources. The algorithms are further extended to heterogeneous SNNs by exploiting the statistics of spikes. Extensive simulation results on neuromorphic datasets demonstrate that the developed algorithms can significantly reduce the power consumption of edge systems while ensuring inference accuracy. Moreover, SNNs achieve comparable performance with state-of-the-art recurrent neural networks (RNNs) but are much more bandwidth-efficient and energy-saving.

Recently, semantic communication (SC) has been regarded as one of the most potential paradigms of 6G. Current SC frameworks require the physical layer channel state information (CSI) in order to handle the severe signal distortion induced by channel fading. Since practical CSI cannot be obtained accurately and the overhead of channel estimation cannot be neglected, we therefore propose a generative adversarial network (GAN) based SC framework (Ti-GSC) that doesn’t require CSI. In Ti-GSC, there are two main modules, i.e., an autoencoder-based encoder-decoder module (AEDM) and a GAN-based non-CSI signal distortion suppression (SDS) module (GSDSM), where SDS only relies on learning the syntactic distribution and the semantics of the transmitted data, so no prior information such as CSI is needed by GSDSM. In order to measure signal distortion, a novel loss function is proposed where two terms, i.e., a syntactic distortion loss term and a semantic distortion loss term, are newly added, and a differentiable semantic measurement method is designed based on the intermediate layers of the AEDM decoder. To achieve better training results of Ti-GSC, two training schemes, i.e., the joint optimization based training (JOT) and the alternating optimization based training (AOT) are designed for the proposed Ti-GSC. Experimental results show that JOT is more efficient for Ti-GSC, and Ti-GSC outperforms conventional communication frameworks in terms of bilingual evaluation understudy (BLEU) score in both Rician and Rayleigh fading channels. Moreover, without CSI, the BLEU score achieved by Ti-GSC is about 40% and 62% higher than that achieved by existing SC frameworks in Rician and Rayleigh fading, respectively. Besides, each term of the presented loss function has a great impact on the BLEU performance of Ti-GSC, where in Rician fading syntactic learning has the greatest impact, and in Rayleigh fading, the adversarial learning becomes important.

Semantic communication is increasingly viewed as a promising solution to improve the transmission efficiency. However, semantic communications are susceptible not only to physical channel impairments, but also to semantic impairments, which degrade semantic understanding at the receiver and disrupt the associated downstream tasks. Hence, we focus our attention on the robustness of semantic communications against semantic impairments. Specifically, we first categorize textual semantic impairments into three categories based on their sources. Then, we propose a robust deep learning enabled semantic communication system (R-DeepSC) by introducing a semantic corrector for robust semantic encoding so as to facilitate semantic transmission. Moreover, we develop a non-autoregressive version of R-DeepSC, namely NA-RDeepSC, which offers improved inference speed by relying on a non-autoregressive architecture and an adaptive generator embedded into the semantic decoder. NA-RDeepSC performs semantic decoding in parallel, hence reducing the decoding complexity fromO(n) toO(1) with a comparable performance to that of R-DeepSC. Our experimental results demonstrate the superior robustness of the proposed R-DeepSC and NA-RDeepSC architectures in eliminating semantic impairments, hence highlighting the significance of this work in advancing the development of robust semantic communications.

Semantic communications have shown great potential in reducing the transmitted data amount through the powerful capability to extract and transmit essential semantic information. Although existing works have achieved certain transmission efficiency, challenges such as efficiently interpretable semantic extraction, and dynamically adaptive channel coding have not been fully explored. In this paper, we tackle these challenges by proposing a task-oriented scene graph-based semantic communication system with adaptive channel coding, named GRACE, to perform image retrieval task. To enhance the interpretability of semantic communications and reduce semantic redundancy, we introduce a scene graph semantic encoder. This encoder fully exploits informative scene graph semantics, effectively extracting scene graphs and performing further semantic coding. Additionally, to handle variable channel conditions in real-world scenarios, we develop a semantic-aware adaptive channel coding to adapt to channel conditions and reduce the communication resources. At the receiver, the image retrieval task is accomplished based on the recovered scene graph semantics. The experimental results demonstrate the superiority of the proposed system compared to other communication systems in terms of task-execution performance, robustness against channel variations, transmission efficiency, and computational complexity.

Semantic communications have been utilized to execute numerous intelligent tasks by transmitting task-related semantic information instead of bits. In this article, we propose a semantic-aware speech-to-text transmission system for the single-user multiple-input multiple-output (MIMO) and multi-user MIMO communication scenarios, named SAC-ST. Particularly, a semantic communication system to serve the speech-to-text task at the receiver is first designed, which compresses the semantic information and generates the low-dimensional semantic features by leveraging the transformer module. In addition, a novel semantic-aware network is proposed to facilitate transmission with high semantic fidelity by identifying the critical semantic information and guaranteeing its accurate recovery. Furthermore, we extend the SAC-ST with a neural network-enabled channel estimation network to mitigate the dependence on accurate channel state information and validate the feasibility of SAC-ST in practical communication environments. Simulation results will show that the proposed SAC-ST outperforms the communication framework without the semantic-aware network for speech-to-text transmission over the MIMO channels in terms of the speech-to-text metrics, especially in the low signal-to-noise regime. Moreover, the SAC-ST with the developed channel estimation network is comparable to the SAC-ST with perfect channel state information.

By transmitting task-related information only, semantic communications yield significant performance gains over conventional communications. However, the lack of mature semantic theory about semantic information quantification and performance evaluation makes it challenging to perform resource allocation for semantic communications, especially when multiple tasks coexist in the network. To cope with this challenge, we propose a quality-of-experience (QoE) based semantic-aware resource allocation method for multi-task networks in this paper. First, semantic entropy is defined to quantify the semantic information for different tasks, and the relationship between semantic entropy and Shannon entropy is analyzed. Then, we develop a novel QoE model to formulate the semantic-aware resource allocation in terms of semantic compression, channel assignment, and transmit power. The compatibility of the formulated problem with conventional communications is further demonstrated. To solve this problem, we decouple it into two subproblems and solved them by a developed deep Q-network (DQN) based method and a proposed low-complexity matching algorithm, respectively. Finally, simulation results validate the effectiveness and superiority of the proposed method, as well as its compatibility with conventional communications.

Semantic communications have been regarded as a promising solution for the next generation communication systems to alleviate the spectral resource shortage and the network congestion. Existing image semantic communication systems extract and transmit global semantics, which can cope with the downstream data reconstruction or intelligent tasks. However, the semantics involved in these methods are still severely redundant and uninterpretable. In this work, we propose a novel task-oriented semantic communication framework based on scene graph, named DeepSC-SG. Specifically, we first devise a scene graph based semantic encoder, which extracts the explainable scene graph semantics from the input images and encodes the semantics into informative graph embeddings. Then we design a joint source-channel (JSC) codec to combat physical channel impairment. After receiving the semantics, a semantic decoder is devised to achieve the downstream image retrieval task by computing scene graph similarities. Simulation results demonstrate that the proposed DeepSC-SG is fairly robust to the channel variations compared to the traditional communication systems, which has great potential in realizing downstream intelligent tasks like image retrieval with significantly reduced size of transmitted data.

The limited computation capacity of user equipments restricts the local implementation of computation-intense applications. Edge computing, especially the edge intelligence system enables local users to offload the computation tasks to the edge servers for reducing the computational energy consumption of user equipments and fast task execution. However, the limited bandwidth of upstream channels may increase the task transmission latency and affect the computation offloading performance. To overcome the challenge of the limited resource of wireless communications, we adopt a semantic-aware task offloading system, where the semantic information of tasks is extracted and offloaded to the edge servers. Furthermore, a proximal policy optimization based multi-agent reinforcement learning algorithm (MAPPO) is proposed to coordinate the resource of wireless communications and the computation, so that the resource management can be performed distributedly and the computational complexity of the online algorithm can be reduced.

While semantic communications succeed in effectively transmitting due to the strong capability to extract the essential semantic information, it is still far from intelligent communications. In this paper, we introduce an essential component, memory, into semantic communications to mimic human communications. Particularly, we propose a deep learning (DL) based semantic communication system with memory, named Mem-DeepSC, by considering the scenario question answer as the task at the receiver. We exploit universal Transformer based transceiver to extract the semantic information and introduce the memory module to enhance the semantic decoding capability at the receiver. Moreover, we derive the semantic channel capacity and propose a consecutive dynamic transmission method to minimize the transmission latency. Numerical results show that Mem-DeepSC is superior to benchmarks in terms of answer accuracy and the number of transmitted symbols.

Scene graph generation (SGG) is designed to represent images by objects and their relationships. Existing works mainly attempt to strengthen object pair representations for SGG. However, most methods ignore the significant semantic information implied in union regions, which refers to the surrounding area of object pairs. In this paper, we propose a new union message based architecture, named as USGG, to profoundly exploit the relational semantics of unions to facilitate SGG. Concretely, we employ sufficient feature extraction to enhance the features of objects and unions. Next, we devise the Union Embedding Network to model the relational representations through two symmetric encoder-decoder branches. Moreover, the Union Fusion Network is designed to integrate the refined semantics by two-stage feature fusion. Extensive experiments are conducted on Visual Genome dataset, which demonstrates that the proposed approach achieves competitive performance against state-of-the-art methods on Recall, mean Recall and Zero Shot Recall metrics.

Semantic communications execute intelligent tasks at the receiver by only transmitting necessary information. In this paper, we introduce TOS-ST, a task-oriented semantic communication system for speech transmission, which efficiently serves the semantic tasks at the receiver, including speech-to-text translation and speech-to-speech translation. Particularly, TOS-ST condenses the input speech in the source language and extracts the task-related semantics features prior to transmission. At the receiver, these features are recovered and utilized by the neural network-based semantic preserver and machine translation module to generate the uncorrupted text in the target language. To perform the speech-to-speech translation task, the translated text passes through a sophisticated neural network to obtain speech in the target language. According to the simulation results, the TOS-ST outperforms conventional speech transmission systems and exhibits higher robustness against channel impairment.

It is our pleasure to share with you this Special Issue, which brings together a diverse set of articles dealing with various aspects of semantic and goal-oriented communications, providing a snapshot of research activities in this highly active research area. Wireless communications and networking research has traditionally focused on improving the capacity and throughput of the underlying wireless network. However, recent explosion in data-driven machine learning applications and their reliance on huge datasets collected by edge devices have raised legitimate concerns that the increasing data traffic might soon overwhelm the capacity of current networks despite ongoing efforts to increase their capacity and efficiency. Also, most of the edge intelligence applications impose stringent delay constraints, which cannot be met by naive forwarding of data samples for processing at the receiver end. This made it obvious to researchers in both academia and industry that it is essential to analyze the “value” or “relevance” of collected data, and filter and prioritize the delivery of data based on its value/relevance as well as the wireless channel and network conditions. In this context, data value will be closely connected to the underlying signals and processes that generate the data, e.g., text, image, video, or sensor data, and what the receiver intends to do with the received data. This subjectivity of data value makes semantic and goal-oriented communication a rather elusive research topic, which has led to both an increasingly rich and active area of investigation, but also a controversial one, mainly due to the lack of clear and widely agreed-upon definitions of some of the core concepts and formulations. Despite these disagreements, there is almost unanimous consensus on the importance and potential impact of this line of investigation for the design of future communication systems and networks.

Communication systems to date primarily aim at reliably communicating bit sequences. Such an approach provides efficient engineering designs that are agnostic to the meanings of the messages or to the goal that the message exchange aims to achieve. Next generation systems, however, can be potentially enriched by folding message semantics and goals of communication into their design. Further, these systems can be made cognizant of the context in which communication exchange takes place, thereby providing avenues for novel design insights. This tutorial summarizes the efforts to date, starting from its early adaptations, semantic-aware and task-oriented communications, covering the foundations, algorithms and potential implementations. The focus is on approaches that utilize information theory to provide the foundations, as well as the significant role of learning in semantics and task-aware communications.

While semantic communication succeeds in efficiently transmitting due to the strong capability to extract the essential semantic information, it is still far from the intelligent or human-like communications. In this paper, we introduce an essential component, memory, into semantic communications to mimic human communications. Particularly, we investigate a deep learning (DL) based semantic communication system with memory, named Mem-DeepSC, by considering the scenario question answer task. We exploit the universal Transformer based transceiver to extract the semantic information and introduce the memory module to process the context information. Moreover, we derive the relationship between the length of semantic signal and the channel noise to validate the possibility of dynamic transmission. Specially, we propose two dynamic transmission methods to enhance the transmission reliability as well as to reduce the communication overheads by masking some unessential elements, which are recognized through training the model with mutual information. Numerical results show that the proposed Mem-DeepSC is superior to benchmarks in terms of answer accuracy and transmission efficiency, i.e., number of transmitted symbols.

Reconfigurable intelligent surface (RIS) enables the configuration of the propagation environment. Channel estimation is an essential task in realizing the RIS-aided communication system. A RIS-aided multi-user multiple-input multiple-output (MIMO) orthogonal frequency division multiplexing (OFDM) communication system involves cascaded channels with high dimensions and sophisticated statistics. Thus, implementing the optimal minimum mean square error (MMSE) with the integration computation is infeasible in practice. To accurately estimate channels with high accuracy in a RIS-aided multi-user MIMO-OFDM system, we model the channel state information (CSI) estimation as an image super-resolution (SR) problem to recover and denoise the channel matrix. Particularly, a convolutional neural network based on a super-resolution convolutional neural network (SRCNN) and denoising convolutional neural network (DnCNN), named SRDnNet, is then proposed. By taking estimated channels at pilot positions as a low-resolution image, the enhanced SRCNN can fully exploit the features of inputs to learn a suitable interpolation method and generate the coarse estimation of the channel matrix. The denoising model DnCNN with an element-wise subtraction structure can exploit features of the additive noise and recover channel coefficients from the coarse channel matrix. The simulation results demonstrate the effectiveness and excellent performance of the proposed SRDnNet.

Although semantic communications have exhibited satisfactory performance on a large number of tasks, the impact of semantic noise and the robustness of the systems have not been well investigated. Semantic noise refers to the misleading between the intended semantic symbols and received ones, thus causes the failure of tasks. In this paper, we first propose a framework for the robust end-to-end semantic communication systems to combat the semantic noise. In particular, we analyze sample-dependent and sample-independent semantic noise. To combat the semantic noise, the adversarial training with weight perturbation is developed to incorporate the samples with semantic noise in the training dataset. Then, we propose to mask a portion of the input, where the semantic noise appears frequently, and design the masked vector quantized-variational autoencoder (VQ-VAE) with the noise-related masking strategy. We use a discrete codebook shared by the transmitter and the receiver for encoded feature representation. To further improve the system robustness, we develop a feature importance module (FIM) to suppress the noise-related and task-unrelated features. Thus, the transmitter simply needs to transmit the indices of these important task-related features in the codebook. Simulation results show that the proposed method can be applied in many downstream tasks and significantly improve the robustness against semantic noise with remarkable reduction on the transmission overhead.

In this paper, we develop a deep learning based semantic communication system for speech transmission, named DeepSC-ST. We take the speech recognition and speech synthesis as the transmission tasks of the communication system, respectively. First, the speech recognition-related semantic features are extracted for transmission by a joint semantic-channel encoder and the text is recovered at the receiver based on the received semantic features, which significantly reduces the required amount of data transmission without performance degradation. Then, we perform speech synthesis at the receiver, which dedicates to re-generate the speech signals by feeding the recognized text and the speaker information into a neural network module. To enable the DeepSC-ST adaptive to dynamic channel environments, we identify a robust model to cope with different channel conditions. According to the simulation results, the proposed DeepSC-ST significantly outperforms conventional communication systems and existing DL-enabled communication systems, especially in the low signal-to-noise ratio (SNR) regime. A software demonstration is further developed as a proof-of-concept of the DeepSC-ST.

With the advent of the 6G era, the concept of semantic communication has attracted increasing attention. Compared with conventional communication systems, semantic communication systems are not only affected by physical noise existing in the wireless communication environment, e.g., additional white Gaussian noise, but also by semantic noise due to the source and the nature of deep learning-based systems. In this paper, we elaborate on the mechanism of semantic noise. In particular, we categorize semantic noise into two categories: literal semantic noise and adversarial semantic noise. The former is caused by written errors or expression ambiguity, while the latter is caused by perturbations or attacks added to the embedding layer via the semantic channel. To prevent semantic noise from influencing semantic communication systems, we present a robust deep learning enabled semantic communication system (R-DeepSC) that leverages a calibrated self-attention mechanism and adversarial training to tackle semantic noise. Compared with baseline models that only consider physical noise for text transmission, the proposed R-DeepSC achieves remarkable performance in dealing with semantic noise under different signal-to-noise ratios.

Channel Estimation is one of the essential tasks to realize a reconfigurable intelligent surface (RIS)-aided orthogonal frequency division multiplexing (OFDM) communication system. Compared with conventional systems, the RIS introduces a cascaded channel with high dimension and sophisticated statistics. In this case, it is infeasible to derive the optimal minimum mean square error (MMSE) estimator. Additionally, the analytical channel estimators, e.g., the least square (LS) estimator and the linear minimum mean square error (LMMSE) estimator are computational costly and imprecise for practical RIS-aided systems. To address these challenge problems and accurately estimate the channel in an RIS-aided OFDM system, we model the channel estimation as a super-resolution (SR) and image restoration (IR) problem to recover the channel matrix from estimated channel at pilot positions. A convolutional neural network based on super-resolution convolutional neural network (SRCNN) and denoising convolutional neural network (DnCNN), named SRDnNet, is then proposed. The simulation results show that the performance of the proposed SRDnNet outperforms the state-of-the-art deep learning-based estimation methods and the LMMSE estimator.

With the aim of accomplishing intelligence tasks, semantic communications transmit task-related information only, yielding significant performance gains over conventional communications. To guarantee user requirements for different tasks, we study the semantic-aware resource allocation in a multi-cell multi-task network in this paper. Specifically, an approximate measure of semantic entropy is first developed to quantify the semantic information for different tasks, based on which a novel quality-of-experience (QoE) model is proposed. We formulate the QoE-aware resource allocation in terms of the number of transmitted semantic symbols, channel assignment, and power allocation. To solve this problem, we first decouple it into two independent subproblems. The first one is to optimize the number of transmitted semantic symbols with given channel assignment and power allocation, which is solved by the exhaustive search method. The second one is the channel assignment and power allocation subproblem, which is modeled as a many-to-one matching game and solved by the proposed low-complexity matching algorithm. Simulation results demonstrate the effectiveness and superiority of the proposed method on the overall QoE.

The task-oriented semantic communication sys-tems have achieved significant performance gain, however, the paradigm that employs a model for a specific task might be limited, since the system has to be updated once the task is changed or multiple models are stored for serving various tasks. To address this issue, we firstly propose a unified deep learning enabled semantic communication system (U-DeepSC), where a unified model is developed to serve various transmission tasks. To jointly serve these tasks in one model with fixed parameters, we employ domain adaptation in the training procedure to specify the task-specific features for each task. Thus, the system only needs to transmit the task-specific features, rather than all the features, to reduce the transmission overhead. Moreover, since each task is of different difficulty and requires different number of layers to achieve satisfactory performance, we develop the multi-exit architecture to provide early-exit results for relatively simple tasks. In the experiments, we employ a proposed U-DeepSC to serve five tasks with multi-modalities. Simulation re-sults demonstrate that our proposed U-DeepSC achieves compa-rable performance to the task-oriented semantic communication system designed for a specific task with significant transmission overhead reduction and much less number of model parameters.

AI-empowered Cognitive Radio (i.e., AI-enabled radios) is a paradigm shift to achieve the highest level of Self-Awareness in future wireless communications. This work proposes a joint automatic modulation conversion and classification (AMCC) framework, which allows an AI-enabled wireless node to predict signals' dynamics of different modulation schemes and explain how it can be transported (converted) with minimal effort and forwarded with higher spectral efficiency. To achieve this goal, we propose a Generalized Filtering framework integrated by Transport Planning to learn the way of converting low-order modulations to high-order modulations, which has also been validated by performing the automatic modulation classification. Simulation results demonstrate the effective performance of our novel framework on converting and classifying multiple modulation formats.

Digital immersion via virtual reality (VR) has promising applications in entertainment, education, and business. However, VR transmissions over wireless are data-intensive and computation-intensive. It is critical to investigate novel wireless network solutions that meet stringent quality-of-service requirements in VR. In this paper, we propose a novel VR transmission scheme to transmit single-view images only. Particularly, single-view images are broadcasted to users with the overlapped field of view, and the corresponding multi-view consistent content is generated by a neural network to avoid massive content transmission. We design a federated learning framework to guarantee an efficient learning process by characterizing vertical and horizontal data samples. Meanwhile, exchanging parts of models during the federated learning process can achieve low-latency communications. Simulation results validate the effectiveness of the proposed VR transmission scheme.

Although the semantic communications have exhibited satisfactory performance in a large number of tasks, the impact of semantic noise and the robustness of the systems have not been well investigated. Semantic noise is a particular kind of noise in semantic communication systems, which refers to the misleading between the intended semantic symbols and received ones. In this paper, we first propose a framework for the robust end-to-end semantic communication systems to combat the semantic noise. Particularly, we analyze the causes of semantic noise and propose a practical method to generate it. To remove the effect of semantic noise, adversarial training is proposed to incorporate the samples with semantic noise in the training dataset. Then, the masked autoencoder (MAE) is designed as the architecture of a robust semantic communication system, where a portion of the input is masked. To further improve the robustness of semantic communication systems, we firstly employ the vector quantization-variational autoencoder (VQ-VAE) to design a discrete codebook shared by the transmitter and the receiver for encoded feature representation. Thus, the transmitter simply needs to transmit the indices of these features in the codebook. Simulation results show that our proposed method significantly improves the robustness of semantic communication systems against semantic noise with significant reduction on the transmission overhead.

The fourth call for papers of the Series on Machine Learning in Communications and Networks has continued to receive a great number of high-quality papers covering various aspects of intelligent communications, from which we have included 16 original contributions in this issue. In the following, we provide a brief review of these papers according to their topics.

The third call for papers of the Series on Machine Learning in Communications and Networks has continued to receive a great number of high-quality papers covering various aspects of intelligent communications, from which we have included 26 original contributions in this issue. In the following, we provide a brief review of key contributions of papers in this issue according to their topics.

The fourth (and final) call for papers of the Series on Machine Learning in Communications and Networks has continued to receive a great number of high-quality papers covering various aspects of intelligent communications. In addition to those published in the August issue, we include in this issue 16 articles submitted to the call. In the following, we provide a brief review of these articles according to their topics.

While semantic communications have shown the potential in the case of single-modal single-users, its applications to the multi-user scenario remain limited. In this paper, we investigate deep learning (DL) based multi-user semantic communication systems for transmitting single-modal data and multimodal data, respectively. We adopt three intelligent tasks, including, image retrieval, machine translation, and visual question answering (VQA) as the transmission goal of semantic communication systems. We propose a Transformer based framework to unify the structure of transmitters for different tasks. For the single-modal multi-user system, we propose two Transformer based models, named, DeepSC-IR and DeepSC-MT, to perform image retrieval and machine translation, respectively. In this case, DeepSC-IR is trained to optimize the distance in embedding space between images and DeepSC-MT is trained to minimize the semantic errors by recovering the semantic meaning of sentences. For the multimodal multi-user system, we develop a Transformer enabled model, named, DeepSC-VQA, for the VQA task by extracting text-image information at the transmitters and fusing it at the receiver. In particular, a novel layer-wise Transformer is designed to help fuse multimodal data by adding connection between each of the encoder and decoder layers. Numerical results show that the proposed models are superior to traditional communications in terms of the robustness to channels, computational complexity, transmission delay, and the task-execution performance at various task-specific metrics.

Reconfigurable intelligent surface (RIS) technology is promising to enhance wireless communications services by providing smart radio environment. In this paper, we investigate the RIS aided cellular networks with device-to-device (D2D) users, and maximize the sum of the transmission rate of the D2D communications and the cellular networks from a new perspective. In addition to solving the typical resource allocation problems for D2D communications, this paper further optimize the wireless environment by adjusting the position and phase shift of the RIS. To solve this non-convex problem, we propose a novel decentralized double deep Q-network (D3QN) framework for the resource allocation at users and a centralized DDQN for RIS optimization at the base station (BS), which are verified to achieve the near-optimal performance with lower complexity and enhanced robustness. Simulation results illustrate that the proposed framework can achieve higher transmission rates compared to benchmarks, meanwhile meeting the quality of service (QoS) requirements at the BS and D2D users.

The vigorous developments of the Internet of Things make it possible to extend its computing and storage capabilities to computing tasks in the aerial system with the collaboration of cloud and edge, especially for artificial intelligence (AI) tasks based on deep learning (DL). Collecting a large amount of image/video data, unmanned aerial vehicles (UAVs) can only hand over intelligent analysis tasks to the back-end mobile edge computing (MEC) server due to their limited storage and computing capabilities. How to efficiently transmit the most correlated information for the AI model is a challenging topic. Inspired by task-oriented communication in recent years, we propose a new aerial image transmission paradigm for the scene classification task. A lightweight model is developed on the front-end UAV for semantic block transmission with the perception of images and channel states. To achieve the tradeoff between transmission latency and classification accuracy, deep reinforcement learning (DRL) is applied to explore the semantic blocks which have the greatest contribution to the back-end classifier under various channel states. Experimental results show that the proposed method can significantly improve classification accuracy by more than 4% under the same conditions, compared to other semantic saliency learning methods.

The traditional communications transmit all the source date represented by bits, regardless of the content of source and the semantic information required by the receiver. However, in some applications, the receiver only needs part of the source data that represents critical semantic information, which prompts to transmit the application-related information, especially when bandwidth resources are limited. In this paper, we consider a semantic communication system for speech recognition by designing the transceiver as an end-to-end (E2E) system. Particularly, a deep learning (DL)-enabled semantic communication system, named DeepSC-SR, is developed to learn and extract text-related semantic features at the transmitter, which motivates the system to transmit much less than the source speech data without performance degradation. Moreover, in order to facilitate the proposed DeepSC-SR for dynamic channel environments, we investigate a robust model to cope with various channel environments without requiring retraining. The simulation results demonstrate that our proposed DeepSC-SR outperforms the traditional communication systems in terms of the speech recognition metrics, such as character-error-rate and word-error-rate, and is more robust to channel variations, especially in the low signal-to-noise (SNR) regime.

As an enabling technology to address spectrum shortage, spectrum sensing has been investigated a lot. However, the uncertainties in the detection environment, including noise uncertainty and carrier frequency (CF) mismatch, still remain as the main challenges of spectrum sensing, which greatly degrades the sensing performance of typical sensing methods, such as energy detection and cyclostationary detection. To this end, this paper proposes two robust spectrum sensing schemes by leveraging the difference between the phase difference (PD) distribution of noise-perturbed signal and that of Gaussian noise. Specifically, the compact approximation of the PD distribution is first derived to enable the extraction of the features of PD distributions, which are robust to noise uncertainty and CF mismatch. Based on these features, two sensing schemes based on the deep neural network (DNN), referred to as DNN-based PD distribution detection (PDD) and blind PDD (BPDD), are proposed to detect spectrum holes in cases with known CF and unknown CF, respectively. Simulation results show that our proposed schemes are more robust to CF mismatch and noise uncertainty in comparison with the existing sensing schemes. Furthermore, when the CF of the sensed signal is unknown, the proposed BPDD significantly outperforms existing blind sensing schemes.

We consider a semantic communication system for speech signals, named DeepSC-S. Motivated by the breakthroughs in deep learning (DL), we make an effort to recover the transmitted speech signals in the semantic communication systems, which minimizes the error at the semantic level rather than the bit level or symbol level as in the traditional communication systems. Particularly, based on an attention mechanism employing squeeze-and-excitation (SE) networks, we design the transceiver as an end-to-end (E2E) system, which learns and extracts the essential speech information. Furthermore, in order to facilitate the proposed DeepSC-S to work well on dynamic practical communication scenarios, we find a model yielding good performance when coping with various channel environments without retraining process. The simulation results demonstrate that our proposed DeepSC-S is more robust to channel variations and outperforms the traditional communication systems, especially in the low signal-to-noise (SNR) regime.

Grant-free non-orthogonal multiple access (NOMA) is considered as one of the supporting technology for massive connectivity for future networks. In the grant-free NOMA systems with a massive number of users, user activity detection is of great importance. Existing multi-user detection (MUD) techniques rely on complicated update steps which may cause latency in signal detection. In this paper, we propose a generative neural network-based MUD (GenMUD) framework to utilize low-complexity neural networks, which are trained to reconstruct signals in a small fixed number of steps. By exploiting the uncorrelated user behaviours, we design a network architecture to achieve higher recovery accuracy with a low computational cost. Experimental results show significant performance gains in detection accuracy compared to conventional solutions under different channel conditions and user sparsity levels. We also provide a sparsity estimator through extensive experiments. Simulation results of the sparsity estimator showed high estimation accuracy, strong robustness to channel variations and neglectable impact on support detection accuracy.

In the era of the new generation of communication systems, data traffic is expected to continuously strain the capacity of future communication networks. Along with the remarkable growth in data traffic, new applications, such as wearable devices, autonomous systems, and the Internet of Things (IoT), continue to emerge and generate even more data traffic with vastly different requirements. This growth in the application domain brings forward an inevitable need for more intelligent processing, operation, and optimization of future communication networks.

The Second Call for Papers of the Series on Machine Learning in Communications and Networks has continued to receive a great number of high-quality papers covering various aspects of intelligent communication systems. In addition to 23 original contributions in response to the first call for papers, we include in this issue 5 articles submitted to the second call for papers. In the following, we provide a brief review of key contributions of papers in this issue according to their topics.

Semantic communications could improve the transmission efficiency significantly by exploring the semantic information. In this paper, we make an effort to recover the transmitted speech signals in the semantic communication systems, which minimizes the error at the semantic level rather than the bit or symbol level. Particularly, we design a deep learning (DL)-enabled semantic communication system for speech signals, named DeepSC-S. In order to improve the recovery accuracy of speech signals, especially for the essential information, DeepSC-S is developed based on an attention mechanism by utilizing a squeeze-and-excitation (SE) network. The motivation behind the attention mechanism is to identify the essential speech information by providing higher weights to them when training the neural network. Moreover, in order to facilitate the proposed DeepSC-S for dynamic channel environments, we find a general model to cope with various channel conditions without retraining. Furthermore, we investigate DeepSC-S in telephone systems as well as multimedia transmission systems to verify the model adaptation in practice. The simulation results demonstrate that our proposed DeepSC-S outperforms the traditional communications in both cases in terms of the speech signals metrics, such as signal-to-distortion ration and perceptual evaluation of speech distortion. Besides, DeepSC-S is more robust to channel variations, especially in the low signal-to-noise (SNR) regime.

The rapid development of deep learning (DL) and widespread applications of Internet-of-Things (IoT) have made the devices smarter than before, and enabled them to perform more intelligent tasks. However, it is challenging for any IoT device to train and run DL models independently due to its limited computing capability. In this paper, we consider an IoT network where the cloud/edge platform performs the DL based semantic communication (DeepSC) model training and updating while IoT devices perform data collection and transmission based on the trained model. To make it affordable for IoT devices, we propose a lite distributed semantic communication system based on DL, named L-DeepSC, for text transmission with low complexity, where the data transmission from the IoT devices to the cloud/edge works at the semantic level to improve transmission efficiency. Particularly, by pruning the model redundancy and lowering the weight resolution, the L-DeepSC becomes affordable for IoT devices and the bandwidth required for model weight transmission between IoT devices and the cloud/edge is reduced significantly. Through analyzing the effects of fading channels in forward-propagation and back-propagation during the training of L-DeepSC, we develop a channel state information (CSI) aided training processing to decrease the effects of fading channels on transmission. Meanwhile, we tailor the semantic constellation to make it implementable on capacity-limited IoT devices. Simulation demonstrates that the proposed L-DeepSC achieves competitive performance compared with traditional methods, especially in the low signal-to-noise (SNR) region. In particular, while it can reach as large as $40\times $ compression ratio without performance degradation.

Long range (LoRa) demonstrates high potential in supporting massive Internet-of-Things (IoT) applications. In this paper, we study the resource allocation in energy harvesting (EH)-enabled LoRa networks with imperfect spreading factor (SF) orthogonality. We maximize the user fairness in terms of the minimum time-averaged throughput while jointly optimizing the SF assignment, the EH time duration, and the transmit power of all LoRa users. First, we provide a general expression of the packet collision time between LoRa users which depends on the SFs and EH duration requirements of each user. Then, we develop two SF allocation schemes that either assure fairness or not for the LoRa users. Within this, we optimize the EH time and the power allocation for single and multiple uplink transmission attempts. For the single uplink transmission attempt, the optimal power allocation is obtained using bisection method. For the multiple uplink transmission attempts, the suboptimal power allocation is derived using concave-convex procedure (CCCP). Our results unearth new findings. Firstly, we demonstrate that the unfair SF allocation algorithm outperforms the others in terms of the minimum data rate. Additionally, we observe that co-SF interference is the main limitation in the throughput performance, and not really energy scarcity.

This paper considers a two-user downlink transmission in intelligent reflecting surface (IRS) aided network over fading channels. Particularly, non-orthogonal multiple access (NOMA) and two orthogonal multiple access (OMA) schemes, namely, time division multiple access (TDMA) and frequency division multiple access (FDMA), are studied. The objective is to maximize the system average sum rate for the delay-tolerant transmission. We propose two adjustment schemes, namely, dynamic phase adjustment and one-time phase adjustment. The power budget, minimum average data rate, and discrete unit modulus reflection coefficient are considered as constrains. To solve the problem, two phase shifters adjustment algorithms with low complexity are proposed to obtain near optimal solutions. With given phase shifters and satisfaction of time-sharing condition, the optimal resource allocations are obtained using the Lagrangian dual decomposition. The numerical results reveal that: i) the average sum rate of proposed NOMA network aided by IRS outperforms the conventional NOMA network over fading channels; ii) with continuous IRS adjustment in the fading block, the proposed TDMA scheme performs better than the FDMA scheme; iii) increasing the minimum average user rate requirement has less impact on the proposed IRS-NOMA system than on the IRS-OMA system.

Due to the blooming of Internet of Things (IoT), heterogeneous IoT mobile devices emerge to connect the network infrastructure. Traditional mobile access system faces several challenges arising from these IoT devices: 1) centralized controllers are distant from the end devices, 2) inefficient access control of heterogeneous IoT devices, and 3) insufficient authentication and monitoring for IoT devices. In order to tackle the challenges from IoT devices on mobile access control and scalable access monitoring, we present LEDGE, an agile and secured software-defined edge computing system for resilient access management of mobile IoT. In a nutshell, our LEDGE is a synergy of an efficient location authentication method to secure communication between each IoT mobile device and access point (AP) pair, an optimal AP assignment scheme to satisfy IoT flow requests, a Personal AP protocol for scalable access, and a deep learning model for anomaly detection. We prototype our system, and realistic testbed experiments demonstrate that LEDGE could achieve promising results in mobile IoT.

Non-orthogonal multiple access (NOMA) exploits the potential of the power domain to enhance the connectivity for the Internet of Things (IoT). Due to time-varying communication channels, dynamic user clustering is a promising method to increase the throughput of NOMA-IoT networks. This article develops an intelligent resource allocation scheme for uplink NOMA-IoT communications. To maximise the average performance of sum rates, this work designs an efficient optimization approach based on two reinforcement learning algorithms, namely deep reinforcement learning (DRL) and SARSA-learning. For light traffic, SARSA-learning is used to explore the safest resource allocation policy with low cost. For heavy traffic, DRL is used to handle traffic-introduced huge variables. With the aid of the considered approach, this work addresses two main problems of fair resource allocation in NOMA techniques: 1) allocating users dynamically and 2) balancing resource blocks and network traffic. We analytically demonstrate that the rate of convergence is inversely proportional to network sizes. Numerical results show that: 1) Compared with the optimal benchmark scheme, the proposed DRL and SARSA-learning algorithms have lower complexity with acceptable accuracy and 2) NOMA-enabled IoT networks outperform the conventional orthogonal multiple access based IoT networks in terms of system throughput.

A novel framework of intelligent reflecting surface (IRS)-aided multiple-input single-output (MISO) non-orthogonal multiple access (NOMA) network is proposed, where a base station (BS) serves multiple clusters with unfixed number of users in each cluster. The goal is to maximize the sum rate of all users by jointly optimizing the passive beamforming vector at the IRS, decoding order and power allocation coefficient vector, subject to the rate requirements of users. In order to tackle the formulated problem, a three-step approach is proposed. More particularly, a long short-term memory (LSTM) based algorithm is first adopted for predicting the mobility of users. Secondly, a K-means based Gaussian mixture model (K-GMM) algorithm is proposed for user clustering. Thirdly, a deep Q-network (DQN) based algorithm is invoked for jointly determining the phase shift matrix and power allocation policy. Simulation results are provided for demonstrating that the proposed algorithm outperforms the benchmarks, while the performance of IRS-NOMA system is better than IRS-OMA system.

This paper considers a two-user downlink intelligent reflecting surface (IRS) assisted network over fading channels. Particularly, non-orthogonal multiple access (NOMA) and two orthogonal multiple access (OMA) schemes, namely, time division multiple access (TDMA) and frequency division multiple access (FDMA), are studied. Our goal is maximizing the system average sum rate for delay-tolerant transmission. The power budget, minimum average user rate and discrete unit modulus reflection coefficient constraints are considered as constraints. To solve the problem, phase shifters adjustment algorithms with low complexity are proposed to obtain high quality solutions. With given phase shifters, the optimal power allocation is obtained using the Lagrangian dual decomposition. Numerical results demonstrate the performance gain by introducing IRS into the system as well as the utility of the proposed algorithms.

Reconfigurable intelligent surface (RIS) technology is a promising method to enhance the device-to-device (D2D) communications. To maximize the sum rate of the cellular and D2D networks, a joint optimization of the position and the phase shift of RIS in D2D communications is considered in this paper. To solve the non-convex sum rate maximum problem, we propose a novel convolutional neural network (CNN) based deep Q-network (DQN) that jointly optimizes the RIS position and its phase shift with lower complexity. Numerical results illustrate that the proposed algorithm can achieve higher sum rate compared to the benchmark algorithms, meanwhile meeting the quality of service (QoS) requirements at D2D receivers and the base station (BS).

Recently, deep learned enabled end-to-end (E2E) communication systems have been developed to merge all physical layer blocks in the traditional communication systems, which makes joint transceiver optimization possible. Powered by deep learning, natural language processing (NLP) has achieved great success in analyzing and understanding large amounts of language texts. Inspired by research results in both areas, we aim to provide a new view on communication systems from the semantic level. Particularly, we propose a deep learning based semantic communication system, named DeepSC, for text transmission. Based on the Transformer, the DeepSC aims at maximizing the system capacity and minimizing the semantic errors by recovering the meaning of sentences, rather than bit- or symbol-errors in traditional communications. Compared with the traditional communication system without considering semantic information exchange, the proposed DeepSC is more robust to channel variation and can achieve better performance, especially in the low signal-to-noise ratio (SNR) regime, as demonstrated by the extensive simulation results.

By activating blocked users and altering successive interference cancellation (SIC) sequences, reconfigurable intelligent surfaces (RISs) become promising for enhancing non-orthogonal multiple access (NOMA) systems. This work investigates the downlink performance of RIS-aided NOMA networks via stochastic geometry. We first introduce the unique path loss model for RIS reflecting channels. Then, we evaluate the angle distributions based on a Poisson cluster process (PCP) framework, which theoretically demonstrates that the angles of incidence and reflection are uniformly distributed. Lastly, we derive closed-form expressions for coverage probabilities of the paired NOMA users. Our results show that 1) RIS-aided NOMA networks perform better than the traditional NOMA networks; and 2) the SIC order in NOMA systems can be altered since RISs are able to change the channel gains of NOMA users.

The downlink communications are vulnerable to intelligent unmanned aerial vehicle (UAV) jamming attack. In this paper, we propose a novel anti-intelligent UAV jamming strategy, in which the ground users can learn the optimal trajectory to elude such jamming. The problem is formulated as a stackelberg dynamic game, where the UAV jammer acts as a leader and the ground users act as followers. First, as the UAV jammer is only aware of the incomplete channel state information (CSI) of the ground users, for the first attempt, we model such leader sub-game as a partially observable Markov decision process (POMDP). Then, we obtain the optimal jamming trajectory via the developed deep recurrent Q-networks (DRQN) in the three-dimension space. Next, for the followers sub-game, we use the Markov decision process (MDP) to model it. Then we obtain the optimal communication trajectory via the developed deep Q-networks (DQN) in the two-dimension space. We prove the existence of the stackelberg equilibrium and derive the closed-form expression for the stackelberg equilibrium in a special case. Moreover, some insightful remarks are obtained and the time complexity of the proposed defense strategy is analyzed. The simulations show that the proposed defense strategy outperforms the benchmark strategies.

LoRa has been recognized as one of the most promising low-power wide-area (LPWA) techniques. Since LoRa devices are usually powered by batteries, energy efficiency (EE) is an essential consideration. In this paper, we investigate the energy efficient resource allocation in LoRa networks to maximize the system EE (SEE) and the minimal EE (MEE) of LoRa users, respectively. Specifically, our objective is to maximize the corresponding EE by jointly exploiting user scheduling, spreading factor (SF) assignment, and transmit power allocations. To solve them efficiently, we first propose a suboptimal algorithm, including the low-complexity user scheduling scheme based on matching theory and the heuristic SF assignment approach for LoRa users scheduled on the same channel. Then, to deal with the power allocation, an optimal algorithm is proposed to maximize the SEE. To maximize the MEE of LoRa users assigned to the same channel, an iterative power allocation algorithm based on the generalized fractional programming and sequential convex programming is proposed. Numerical results show that the proposed user scheduling algorithm achieves near-optimal EE performance, and the proposed power allocation algorithms outperform the benchmarks.

This article investigates the downlink communications of intelligent reflecting surface (IRS) assisted non-orthogonal multiple access (NOMA) systems. To maximize the system throughput, we formulate a joint optimization problem over the channel assignment, decoding order of NOMA users, power allocation, and reflection coefficients. The formulated problem is proved to be NP-hard. To tackle this problem, a three-step novel resource allocation algorithm is proposed. Firstly, the channel assignment problem is solved by a many-to-one matching algorithm. Secondly, by considering the IRS reflection coefficients design, a low-complexity decoding order optimization algorithm is proposed. Thirdly, given a channel assignment and decoding order, a joint optimization algorithm is proposed for solving the joint power allocation and reflection coefficient design problem. Numerical results illustrate that: i) with the aid of IRS, the proposed IRS-NOMA system outperforms the conventional NOMA system without the IRS in terms of system throughput; ii) the proposed IRS-NOMA system achieves higher system throughput than the IRS assisted orthogonal multiple access (IRS-OMA) systems; iii) simulation results show that the performance gains of the IRS-NOMA and the IRS-OMA systems can be enhanced via carefully choosing the location of the IRS.

This article investigates a wireless caching framework based on tweets and their location data collected from Twitter. The tweet texts are associated with the location information of the corresponding base stations (BSs) for improving the caching efficiency at BSs. Extracted latent topics and predicted content probability are applied to reduce caching redundancy at BSs. A machine learning approach, namely latent Dirichlet allocation (LDA), is invoked to extract location-aware latent topics for better caching performances. In an effort to predict content probability for caching, a novel skip-gram based long short-term memory (LSTM) model is proposed to cluster words with similar semantics for content probability prediction. Moreover, practical data collected from Twitter is tackled to verify the performance of the proposed framework. Extensive practical tests demonstrate that: 1) Our proposed framework is capable of perceiving caching peaks while the conventional counting method fails; 2) The proposed machine learning approaches are capable of generating accurate topics extraction and content probability prediction results; 3) Our proposed framework maintains superiority over conventional caching approaches and possesses considerable application potential due to its ability of associating with indigenous public preferences.

This paper studies the non-orthogonal multiple access (NOMA)-based spatial modulation (SM) systems with multiple subchannels. A mixed multicast and unicast transmission is considered in each channel, in which a common content is multicasted in the transmit antenna (TA) domain to all the users, and the unicast contents are transmitted as amplitude- phase modulated (APM) symbols in the classical signal domain using NOMA via the active antenna. First, we obtain the achievable unicast rate for each user and an upper bound for the achievable multicast rate in the TA domain. Then, the subchannel assignment and power allocation schemes are designed to maximize the system sum rate. Specifically, the subchannel assignment is formulated as a many-to-one matching with peer effect, and we propose a suboptimal but efficient algorithm incorporating the swap operation to solve it. We then optimize the power allocation subproblem by employing the successive convex approximation approach, which iteratively approximates the original nonconvex problem to a convex one. Finally, numerical results are presented to demonstrate the effectiveness of the proposed schemes.

In this paper, we investigate the uplink transmissions in low-power wide-area networks (LPWAN) where the users are self-powered by the energy harvested from the ambient environment. Demonstrating their potential in supporting diverse Internet-of-Things (IoT) applications, we focus on long range (LoRa) networks where the LoRa users are using the harvested energy to transmit data to a gateway via different spreading codes. Precisely, we study the throughput fairness optimization problem for LoRa users by jointly optimizing the spreading factor (SF) assignment, energy harvesting (EH) time duration, and the transmit power of LoRa users. First, through examination of the various permutations of collisions among users, we derive a general expression of the packet collision time between LoRa users, which depends on the SFs and EH duration requirements. Then, after reviewing prior SF allocation work, we develop two types of algorithms that either assure fair SF assignment indeed purposefully `unfair' allocation schemes for the LoRa users. Our results unearth three new findings. Firstly, we demonstrate that, to maximize the minimum rate, the unfair SF allocation algorithm outperforms the other approaches. Secondly, considering the derived expression of packet collision between simultaneous users, we are now able to improve the performance of the minimum rate of LoRa users and show that it is protected from inter-SF interference which occurs between users with different SFs. That is, imperfect SF orthogonality has no impact on minimum rate performance. Finally, we have observed that co-SF interference is the main limitation in the throughput performance, and not the energy scarcity.

The downlink communications are vulnerable to intelligent unmanned aerial vehicle (UAV) jamming attack which can learn the optimal attack strategy in complex communication environments. In this paper, we propose an anti-intelligent UAV jamming strategy, in which the mobile users can learn the optimal defense strategy to prevent jamming. Specifically, the UAV jammer acts as a leader and the users act as followers. The problem is formulated as a stackelberg dynamic game, which includes the leader sub-game and the followers sub-game. As the UAV jammer is only aware of the incomplete channel state information (CSI) of the users, we model the leader sub-game as a partially observable Markov decision process (POMDP). The optimal jamming trajectory is obtained via deep recurrent Q-networks (DRQN) in the three-dimension space. For the followers sub-game, we use the Markov decision process (MDP) to model it. Then the optimal communication trajectory can be learned via deep Q-networks (DQN) in the two-dimension space. We prove the existence of the stackelberg equilibrium. The simulations show that the proposed strategy outperforms the benchmark strategies.

In this paper, we consider resource allocation for edge computing in internet of things (IoT) networks. Specifically, each end device is considered as an agent, which makes its decisions on whether offloading the computation tasks to the edge devices or not. To minimize the long-term weighted sum cost which includes the power consumption and the task execution latency, we consider the channel conditions between the end devices and the gateway, the computation task queue as well as the remaining computation resource of the end devices as the network states. The problem of making a series of decisions at the end devices is modelled as a Markov decision process and solved by the reinforcement learning approach. Therefore, we propose a near optimal task offloading algorithm based on ϵ-greedy Q-learning. Simulations validate the feasibility of our proposed algorithm, which achieves a better trade-off between the power consumption and the task execution latency compared to these of edge computing and local computing modes.

In non-orthogonal multiple access (NOMA) systems, the outage is considered to happen when a user cannot correctly decode the messages for the users with higher decoding order and hence the successive interference cancellation (SIC) is failed in traditional definition. However, in this case, the user may still correctly decode its message by treating the uncancelled signal as interference and the outage is avoided. By considering this behavior, a more accurate alternative outage probability can be defined. In this paper, we investigate user scheduling and power allocation for a downlink NOMA system with imperfect SIC by employing the alternative outage probability as then performance metric. The coupling of user scheduling and power allocation makes the problem complicated. Therefore, we propose a two-phase algorithm, in which the user scheduling is first optimized through a matching theory based algorithm, and then power allocation is performed with the aid of the concave-convex procedure (CCCP) method. Simulation results show that the proposed low- complexity algorithm can achieve near-optimal performance and the algorithm based on the alternative outage probability outperforms the traditional one when the decoding is significantly affected by imperfect SIC.

Random matrix theory (RMT) has been used to derive the asymptotic capacity of multiple-input-multiple-output (MIMO) channels by approximating the asymptotic eigenvalue distributions (AEDs) of the associated channel matrices. A novel methodology is introduced which enables the computation of the asymptotic capacity for a generalised system in which two relays cooperate to facilitate communication between two remote devices. It is computationally demanding to calculate this capacity using RMT when nodes are equipped with large-scale antenna arrays, and impossible in the case where asymmetry exists between channels within the system. This is because deriving the capacity across the combined channels from the relays to the receiver involves polynomials in large and non-commutative random matrix variables. This paper uses free probability theory (FPT) as an efficient alternative tool for analysis in these circumstances. The method described can be applied with no additional complexity for arbitrarily large antenna arrays. The minimum SNR required to achieve a given asymptotic capacity is computed and the simulation results verify the accuracy of the FPT approach.

Unmanned aerial vehicles (UAVs) have been considered in wireless communication systems to provide high-quality services for their low cost and high maneuverability. This paper addresses a UAV-aided mobile edge computing system, where a number of ground users are served by a moving UAV equipped with computing resources. Each user has computing tasks to complete, which can be separated into two parts: one portion is offloaded to the UAV and the remaining part is implemented locally. The UAV moves around above the ground users and provides computing service in an orthogonal multiple access manner over time. For each time period, we aim to minimize the sum of the maximum delay among all the users in each time slot by jointly optimizing the UAV trajectory, the ratio of offloading tasks, and the user scheduling variables, subject to the discrete binary constraints, the energy consumption constraints, and the UAV trajectory constraints. This problem has highly nonconvex objective function and constraints. Therefore, we equivalently convert it into a better tractable form based on introducing the auxiliary variables, and then propose a novel penalty dual decomposition-based algorithm to handle the resulting problem. Furthermore, we develop a simplified l0-norm algorithm with much reduced complexity. Besides, we also extend our algorithm to minimize the average delay. Simulation results illustrate that the proposed algorithms significantly outperform the benchmarks.

In this paper, the efficient resource allocation for the uplink transmission of wireless powered Internet of Things (IoT) networks is investigated. We adopt LoRa technology as an example in the IoT network, but this paper is still suitable for other communication technologies. Allocating limited resources, like spectrum and energy resources, among a massive number of users faces critical challenges. We consider grouping wireless powered IoT users into available channels first and then investigate power allocation for users grouped in the same channel to improve the network throughput. Specifically, the user grouping problem is formulated as a many to one matching game. It is achieved by considering IoT users and channels as selfish players which belong to two disjoint sets. Both selfish players focus on maximizing their own utilities. Then we propose an efficient channel allocation algorithm (ECAA) with low complexity for user grouping. Additionally, a Markov decision process is used to model unpredictable energy arrival and channel conditions uncertainty at each user, and a power allocation algorithm is proposed to maximize the accumulative network throughput over a finite-horizon of time slots. By doing so, we can distribute the channel access and dynamic power allocation local to IoT users. Numerical results demonstrate that our proposed ECAA algorithm achieves near-optimal performance and is superior to random channel assignment, but has much lower computational complexity. Moreover, simulations show that the distributed power allocation policy for each user is obtained with better performance than a centralized offline scheme.

In the channel training phase, the attacker launches a pilot contamination attack by sending a synchronized and identical pilot signal with the legitimate transmitter. Such an attack can contaminate the channel estimation and alter the legitimate beamformer design. In this letter, first, we propose a pilot contamination attack detection scheme for wireless communications. By considering the prior uncertainty of the attack, we find that the decision-maker will conservatively decide the state of the attack, which is a subjective choice. In this case, we derive the subjective detection probability, the subjective false alarm probability, and the threshold. We analyze the tradeoff problem between ergodic wiretap channel rate and subjective detection probability. Next, based on the worst case that the attacker adopts the optimal power allocation to launch the optimal attack, we discuss the defense strategy of the optimal attack. Simulations show that the proposed scheme has a better performance than the benchmark method.

In this paper, we investigate joint trajectory design and resource allocation algorithms to maximize the minimum average rate among ground users for unmanned aerial vehicle (UAV) communication systems, where both the orthogonal multiple access (OMA) and non-orthogonal multiple access (NOMA) modes are considered. We first formulate the problems for UAV communications with the OMA and NOMA modes, respectively, which contain binary variables and highly coupled nonconvex objective functions and constraints. In order to handle the challenging problems, we transform the original problems into more tractable forms and then develop novel algorithms based on penalty dual-decomposition technique to solve them. Simulation results show that the proposed algorithms outperform the benchmarks.

In this article, we investigate the application of NOMA in mobile unmanned aerial vehicle (UAV) communication networks and propose the algorithm to jointly optimize the UAV trajectory and power allocation. Specifically, we formulate the optimization problem to maximize the minimum average rate among ground users for NOMA based UAV communication systems, which contains complicated and discrete binary constraints, as well as the highly coupled nonconvex objective function. Then, we transform the challenging original problem into a more tractable form with some equality constraints. Finally, we develop a double-loop algorithm to solve it with the aid of penalty dual-decomposition (PDD) technique. From the simulation results, the proposed algorithm outperforms the benchmarks.

In this paper, we investigate energy efficiency for uplink LoRa, which is one of the most promising and widely deployed low-power wide-area (LPWA) networks. In the considered networks, we explore user scheduling, spreading factor (SF) assignment, and power allocation jointly. A nonconvex optimization problem for maximizing the system energy efficiency is formulated, with targeted SNR requirement and power range as constraints for each LoRa user. To solve this problem, we first propose a low-complexity suboptimal algorithm, which includes energy-efficient user scheduling and heuristic SF assignment for scheduled users based on matching theory. Then a novel power allocation based on Charnes-Cooper transformation is proposed to transform the fractional objective into the convex form to maximize the system energy efficiency. Simulation results show that the proposed algorithms achieve near-optimal performance in terms of energy efficiency.

Location-based information dissemination has become increasingly popular in the recent years. Extensive research work has been done on the matching of interested parties to event information via publish/subscribe systems. However, the rich content types of such location-specific data, especially when the data are presented in multimedia form, requires efficient methods with low cost to transfer the content to the subscribers. In this paper, the potential of utilising human centric device-to-device (D2D) communications to disseminate location-based event content is investigated. The human centric D2D data dissemination process is formulated as a task assignment problem, which can be modelled as a Integer Quadratically Constrained Quadratic Programming (IQCQP) problem. Since the IQCQP problem is in general NP-hard, a sub- optimal polynomial framework named EventMe is proposed, which is able to compute a solution with guaranteed lower bounds on data distribution capacity in terms of throughput. Through extensive evaluation using several real world datasets, it has shown that EventMe is able to improve the network throughput by 100%-500% compared to baseline methods. A prototype is developed and shows that it is practical to implement EventMe on mobile devices by generating minimal control data overhead.

In this paper, a unified framework of non-orthogonal multiple access (NOMA) networks is proposed, which can be applied to code-domain NOMA (CD-NOMA) and power-domain NOMA (PD-NOMA). Since the detection of NOMA users mainly depend on efficient successive interference cancellation (SIC) schemes, both imperfect SIC (ipSIC) and perfect SIC (pSIC) are taken into considered. To characterize the performance of this unified framework, the exact and asymptotic expressions of outage probabilities as well as delay-limited throughput for CD/PD-NOMA with ipSIC/pSIC are derived. Based on the asymptotic analysis, the diversity orders of CD/PD-NOMA are provided. It is confirmed that due to the impact of residual interference (RI), the outage probability of the n-th user with ipSIC for CD/PD-NOMA converges to an error floor in the high signal-to-noise ratio (SNR) region. Numerical simulations demonstrate that the outage behavior of CD-NOMA is superior to that of PD-NOMA.

Mobile peer to peer (P2P) networks offer a huge potential for distributed mobile P2P crowd services (MPCS), which enable data and computational tasks to be offloaded and executed directly between mobile devices. Similar to centralised mobile crowd services, such as mobile crowdsensing, incentivisation mechanisms are core to encouraging mobile users to participate in MPCS systems. However, due to the impact of task execution failures and unreliable behaviours of mobile users (particularly task requesters), it is a daunting task to design and implement an incentivisation mechanism to cater for the needs of MPCS systems. In this paper, we propose a fault-tolerant incentivisation mechanism (FTIM) for MPCS systems. With conditional payment strategies, FTIM is proven to accommodate the requirements of two important application scenarios by achieving mechanism properties such as incentive compatibility, economic efficiency, individual rationality, and weak budget balance. Moreover, to tackle the practical challenges in implementing FTIM in the real world, we design a MPCSTo-ken smart contract to facilitate its service auction, task execution and payment settlement process. We implement the MPCSToken contract on Ethereum blockchain. Both real-world experiment and simulation results show that the system is cost effective for deployments and improves the overall mobile users' utility by exploring the opportunities offered by MPCS.

This paper proposes a unified framework of non-orthogonal multiple access (NOMA) networks. Stochastic geometry is employed to model the locations of spatially NOMA users. The proposed unified NOMA framework is capable of being applied to both code-domain NOMA (CD-NOMA) and power-domain NOMA (PD-NOMA). Since the detection of NOMA users mainly depend on efficient successive interference cancelation (SIC) schemes, both imperfect SIC (ipSIC) and perfect SIC (pSIC) are taken into account. To characterize the performance of the proposed unified NOMA framework, the exact and asymptotic expressions of outage probabilities as well as delay-limited throughput for CD/PD-NOMA with ipSIC/pSIC are derived. In order to obtain more insights, the diversity analysis of a pair of NOMA users (i.e., the nth user and mth user) is provided. Our analytical results reveal that: 1) the diversity orders of mth and nth user with pSIC for CD-NOMA are mK and nK, respectively; 2) due to the influence of residual interference, the nth user with ipSIC obtains a zero diversity order; and 3) the diversity order is determined by the user who has the poorer channel conditions out of the pair. Finally, Monte Carlo simulations are presented to verify the analytical results: 1) when the number of subcarriers becomes lager, the NOMA users are capable of achieving more steep slope in terms of outage probability and 2) the outage behavior of CD-NOMA is superior to that of PD-NOMA.

Estimating communication latency is a challenging task in the applications of industrial Internet of things (IIoT). Mobile convergecast, as a many-to-one communication pattern, has been recently explored in mobile sensor networks for IIoT, where sensor nodes are usually in mobile status, and report the sensed data regularly or randomly to one or more stationary sinks through the multihop routing path. As convergecast becomes increasingly relevant for industrial sensing and monitoring, a critical part of empowering information aggregation is to maintain consistent transmission. Path duration is one important component of end-to-end delay for communications along the path. In this paper, a probabilistic model for mobile convergecast has been proposed and evaluated to capture path duration times, by considering parameters including network models, sensor network scope, and mobility patterns of network elements. Through experiments, it has been verified that the proposed model can provide a feasible analysis of end-to-end delays in industrial networks implementing convergecast.

In this paper, we investigate the resource efficiency of uplink transmission for low-power wide-area (LPWA) networks. LoRa is adopted as an example network of focus, however the work can be easily generalized to other radios. We first formulate resource allocation in LPWA networks as a joint optimization problem of channel assignment and power allocation, with guaranteeing throughput fairness among LoRa users with limited spectrum resources, especially for the case with a large number of connected devices in LPWA networks. Specifically, we formulate channel assignment as a many-to-one matching game by treating LoRa users and channels as two sets of selfish players aiming to maximize their own utilities. We then propose a low-complexity matching channel assignment algorithm (MCAA) through distributing the channel access decision making local to LoRa users. For LoRa users assigned to the same channel, we further develop an optimal power allocation algorithm to maximize the achieved minimal transmission rate in LPWA networks. Moreover, simulation results demonstrate that the proposed MCAA can achieve near-optimal performance with much lower computational complexity.

We investigate the uplink transmission performance of low-power wide-area networks (LPWANs) with regards to coexisting radio modules using LoRa as an example. In doing so we adopt a new topology to model the network where the node locations of the network of focus (LoRa) follow a Poisson cluster process (PCP) while other coexisting interfering radio modules follow a Poisson point process (PPP). To characterize the performance of the proposed model as well as obtain insights, both analytical and closed-form approximated expressions for coverage probability are derived. Based on this, area spectrum efficiency, and energy efficiency are further characterized. These results demonstrate the degree to which the performance, with regard to the aforementioned metrics, is capable of being enhanced through varying the density of the deployment of LoRa nodes around each LoRa receiver. Moreover, simulation results unveil that an optimal value of active LoRa nodes in each cluster exists that maximizes area spectrum efficiency.

Energy Neutral Operation (ENO) has created the ability to continuously operate wireless sensor networks in areas such as environmental monitoring, hazard detection and industrial IoT applications. Current ENO approaches utilise techniques such as sample rate control, adaptive duty cycling and data reduction methods to balance energy generation, storage and consumption. However, the state of the art approaches makes a strong and unrealistic assumption that battery capacity is fixed throughout the deployment time of an application. This results in scenarios where ENO systems over allocate sensing tasks, therefore as battery capacity degrades it causes the system to no longer be energy neutral and then fail unexpectedly. In this paper, we formulate the problem to maximise the quality-of-service in terms of duty cycle and the battery capacity to extend the deployment lifetime of a sensing application. In addition, we develop a lightweight algorithm to solve the formulated problem. Moreover, we evaluate the proposed method using real sensor energy consumption data captured from micro-climate sensors deployed in Queen Elizabeth Olympic Park, London. Results show that a 307% extension of deployment lifetime can be achieved when compared to a traditional ENO solution without a reduction in the duty cycle of the sensor.

The large number of personal wireless devices in the urban areas could be used to provide various opportunistic data services, such as WiFi sharing, content-based file sharing and opportunistic networking. In order to facilitate these services, it is essential to incentivise the device owners to become service providers. However, previous research failed to deliver any practical payment systems for opportunistic data services. Inspired by smart contracts functionalities of bitcoin, this paper proposes a payment system named OPPay for opportunistic data services, which implements a micropayment communication protocol for mobile devices to perform data transactions and make payments using bitcoin. The system is designed to make incremental payments and thus resilient to interrupted communications caused by human mobility in the mobile network. By implementing and evaluating the system for three different applications, we show that the system is able to work in heterogeneous hardware and software environments and can achieve fast transactions confirmation with small fee overhead and low faulty payment value.

In this paper, the potential benefits of applying non-orthogonal multiple access (NOMA) technique in K -tier hybrid heterogeneous networks (HetNets) is explored. A promising new transmission framework is proposed, in which NOMA is adopted in small cells and massive multiple-input multiple-output (MIMO) is employed in macro cells. For maximizing the biased average received power for mobile users, a NOMA and massive MIMO based user association scheme is developed. To evaluate the performance of the proposed framework, we first derive the analytical expressions for the coverage probability of NOMA enhanced small cells. We then examine the spectrum efficiency of the whole network by deriving exact analytical expressions for NOMA enhanced small cells and a tractable lower bound for massive MIMO enabled macro cells. Finally, we investigate the energy efficiency of the hybrid HetNets. Our results demonstrate that: 1) the coverage probability of NOMA enhanced small cells is affected to a large extent by the targeted transmit rates and power sharing coefficients of two NOMA users; 2) massive MIMO enabled macro cells are capable of significantly enhancing the spectrum efficiency by increasing the number of antennas; 3) the energy efficiency of the whole network can be greatly improved by densely deploying NOMA enhanced small cell base stations; and 4) the proposed NOMA enhanced HetNets transmission scheme has superior performance compared with the orthogonal multiple access-based HetNets.

Driven by the rapid escalation of the wireless capacity requirements imposed by advanced multimedia applications (e.g., ultrahigh-definition video, virtual reality, etc.), as well as the dramatically increasing demand for user access required for the Internet of Things (IoT), the fifth-generation (5G) networks face challenges in terms of supporting large-scale heterogeneous data traffic. Nonorthogonal multiple access (NOMA), which has been recently proposed for the third-generation partnership projects long-term evolution advanced (3GPP-LTE-A), constitutes a promising technology of addressing the aforementioned challenges in 5G networks by accommodating several users within the same orthogonal resource block. By doing so, significant bandwidth efficiency enhancement can be attained over conventional orthogonal multiple-access (OMA) techniques. This motivated numerous researchers to dedicate substantial research contributions to this field. In this context, we provide a comprehensive overview of the state of the art in power-domain multiplexing-aided NOMA, with a focus on the theoretical NOMA principles, multiple-antenna-aided NOMA design, on the interplay between NOMA and cooperative transmission, on the resource control of NOMA, on the coexistence of NOMA with other emerging potential 5G techniques and on the comparison with other NOMA variants. We highlight the main advantages of power-domain multiplexing NOMA compared to other existing NOMA techniques. We summarize the challenges of existing research contributions of NOMA and provide potential solutions. Finally, we offer some design guidelines for NOMA systems and identify promising research opportunities for the future.

In this paper, we consider cognitive radio networks in which energy constrained secondary users (SUs) can harvest energy from the randomly deployed power beacons. A new frame structure is proposed for the considered networks. In the considered network, a wireless power transfer model is proposed, and the closed-form expressions for the power outage probability are derived. In addition, in order to reduce the energy consumption at SUs, sub-Nyquist sampling are performed at SUs. Subsequently, compressive sensing and matrix completion techniques are invoked to recover the original signals at the fusion center by utilizing the sparsity property of spectral signals. Throughput optimizations of the secondary networks are formulated into two linear constrained problems, which aim to maximize the throughput of a single SU and the whole cooperative network, respectively. Three methods are provided to obtain the maximal throughput of secondary networks by optimizing the time slots allocation and the transmit power. Simulation results show that the maximum throughput can be improved by implementing compressive spectrum sensing in the proposed frame structure design.

This paper investigates the physical layer security of non-orthogonal multiple access (NOMA) in large-scale networks with invoking stochastic geometry. Both single-antenna and multiple-antenna aided transmission scenarios are considered, where the base station (BS) communicates with randomly distributed NOMA users. In the single-antenna scenario, we adopt a protected zone around the BS to establish an eavesdropper-exclusion area with the aid of careful channel ordering of the NOMA users. In the multiple-antenna scenario, artificial noise is generated at the BS for further improving the security of a beamforming-aided system. In order to characterize the secrecy performance, we derive new exact expressions of the security outage probability for both single-antenna and multiple-antenna aided scenarios. For the single-antenna scenario, we perform secrecy diversity order analysis of the selected user pair. The analytical results derived demonstrate that the secrecy diversity order is determined by the specific user having the worse channel condition among the selected user pair. For the multiple-antenna scenario, we derive the asymptotic secrecy outage probability, when the number of transmit antennas tends to infinity. Monte Carlo simulations are provided for verifying the analytical results derived and to show that: 1) the security performance of the NOMA networks can be improved by invoking the protected zone and by generating artificial noise at the BS and 2) the asymptotic secrecy outage probability is close to the exact secrecy outage probability.

In this paper, the application of non-orthogonal multiple access (NOMA) into K-tier heterogeneous networks (HetNets) is investigated. A new promising transmission framework is proposed, in which massive multiple-input multiple-output (MIMO) is employed in macro cells and NOMA is adopted in small cells. For maximizing the biased average received power at mobile users, a massive MIMO and NOMA based user association scheme is developed. In an effort to evaluate the performance of the proposed framework, analytical expressions for the spectrum efficiency of each tier are derived using stochastic geometry. Simulation results are presented to verify the accuracy of the proposed analytical derivations and confirm that NOMA is capable of enhancing the spectrum efficiency of the network compared to the orthogonal multiple access (OMA) based HetNets.

In this paper, the physical layer security of applying non-orthogonal multiple access (NOMA) in large-scale networks is investigated. In the considered scenario, both the NOMA users and eavesdroppers are spatially randomly deployed. A protected zone around the source node is adopted to enhance the security of a random network. In order to characterize the secrecy performance of the considered scenario, new exact and asymptotic expressions for the security outage probability are derived. These analytical results demonstrate that the secrecy diversity order is m, which is determined by the user with poor channel condition. Monte Carlo simulations are provided to verify the derived analytical results. Furthermore, it is also confirmed that the secure performance of the NOMA networks can be improved by either enlarging the scope of the protected zone or reducing the scope of the user zone.

Cognitive radio (CR) has emerged as one of the most promising candidate solutions to improve spectrum utilization for future wireless networks. A crucial requirement for future CR networks is the ability to sense wideband spectrum. Recently, compressive sensing (CS) has been proposed as a solution to replace high speed analog-to-digital converters. CS enables sub-Nyquist sampling for wideband spectrum sensing by exploiting the sparse nature of spectrum occupancy. In this paper, the CS based spectrum sensing model is firstly summarized. The measurement matrix designs and the hardware implementations of CS based wideband spectrum sensing algorithms are then explored. The implementations of CS with real-time signals over TV white space spectrum in CR is further established. This paper is concluded by providing outlooks and open research challenges on the practical implementation of CS in wideband spectrum sensing in cognitive radio.

To underpin the predicted growth of the Internet of Things (IoT), a highly scalable, reliable and available connectivity technology will be required. Whilst numerous technologies are available today, the industry trend suggests that cellular systems will play a central role in ensuring IoT connectivity globally. With spectrum generally a bottleneck for 3GPP technologies, TV white space (TVWS) approaches are a very promising means to handle the billions of connected devices in a highly flexible, reliable and scalable way. To this end, we propose a cognitive radio enabled TD-LET test-bed to realize the dynamic spectrum management over TVWS. In order to reduce the data acquisition and improve the detection performance, we propose a hybrid framework for the dynamic spectrum management of machine-to-machine networks. In the proposed framework, compressed sensing is implemented with the aim to reduce the sampling rates for wideband spectrum sensing. A noniterative reweighed compressive spectrum sensing algorithm is proposed with the weights being constructed by data from geolocation databases. Finally, the proposed hybrid framework is tested by means of simulated as well as real-world data.

In this paper, we present a novel hybrid framework combining compressive spectrum sensing with geo-location database to find spectrum holes in a decentralized cognitive radio. In the hybrid framework, a geo-location database algorithm is proposed to be stored locally at secondary users (SUs) to remove the extra transmission link to a centralized remote geo-location database. Specifically, by utilizing the output of the locally stored geo-location database algorithm, a data-assisted noniteratively reweighted least squares (DNRLS)-based compressive spectrum sensing algorithm is proposed to improve detection performance under sub-Nyquist sampling rates for wideband spectrum sensing, and to reduce the computational complexity of signal recovery. In addition, an efficient method for the calculation of maximum allowable equivalent isotropic radiated power in TV white space (TVWS) is also designed to further support SUs. The convergence and complexity of the proposed DNRLS algorithm are analyzed theoretically. Furthermore, the proposed framework is pioneered on real-time “from air” signals and data after having been validated by simulated signals and data in TVWS.

In this paper, we consider a cognitive radio network in which energy constrained secondary users (SUs) can harvest energy from the randomly deployed power beacons. A new frame structure with four time slots, namely, energy harvesting, spectrum sensing, energy harvesting and data transmission is proposed. In the energy harvesting slot, a new wireless power transfer (WPT) scheme in a bounded power transfer model is proposed to enable power SUs wirelessly. Closed-form expression for the power outage probability of the proposed WPT scheme is derived. In the spectrum sensing slot, we propose to utilize the compressive sensing technique which enables sub-Nyquist sampling to further reduce the energy consumption at SUs. Throughput of the secondary network with the proposed frame structure is formulated into a nonlinear constraint problem. Three optimization methods are provided to obtain the maximal throughput of secondary network by optimizing the time slots allocation and the transmit power of SUs.

TV White Spaces (TVWS) technology allows wireless devices to opportunistically use locally-available TV channels enabled by a geolocation database. The UK regulator Ofcom has initiated a pilot of TVWS technology in the UK. This paper concerns a large- scale series of trials under that pilot. The purposes are to test aspects of white space technology, including the white space device and geolocation database interactions, the validity of the channel availability/powers calculations by the database and associated interference effects on primary services, and the performances of the white space devices, among others. An additional key purpose is to perform research investigations such as on aggregation of TVWS resources with conventional resources and also aggregation solely within TVWS, secondary coexistence issues and means to mitigate such issues, and primary coexistence issues under challenging deployment geometries, among others. This paper provides an update on the trials, giving an overview of their objectives and characteristics, some aspects that have been covered, and some early results and observations.