A Convolutional and Transformer Based Deep Neural Network for Automatic Modulation Classification

Automatic modulation classification(AMC)aims at identifying the modulation of the received signals,which is a significant approach to identifying the target in military and civil applications.In this paper,a novel data-driven framework named convolutional and transformer-based deep neural network(CTDNN)is proposed to improve the classification performance.CTDNN can be divided into four modules,i.e.,convolutional neural network(CNN)backbone,transition module,transformer module,and final classifier.In the CNN backbone,a wide and deep convolution structure is designed,which consists of 1×15 convolution kernels and intensive cross-layer connections instead of traditional 1×3 kernels and sequential connections.In the transition module,a 1×1 convolution layer is utilized to compress the channels of the previous multi-scale CNN features.In the transformer module,three self-attention layers are designed for extracting global features and generating the classification vector.In the classifier,the final decision is made based on the maximum a posterior probability.Extensive simulations are conducted,and the result shows that our proposed CTDNN can achieve superior classification performance than traditional deep models.

面向6G的智能机器通信与网络

随着智慧城市、智能制造等产业的快速发展,机器类通信得到学术界和产业界的广泛关注。机器类通信网络的功能集成化、智能化程度越来越高,对网络的时延、可靠性、连接设备数、峰值速率、安全性和可扩展性等指标提出了更严苛的要求。总结分析了4G、5G至未来6G时代的机器类通信网络需求的变化以及相应网络架构与关键技术的演化,在此基础上提出了面向6G机器类通信网络的感传算一体化智能机器通信网络架构。

Joint Radar and Communication: A Survey

Joint radar and communication(JRC)technology has become important for civil and military applications for decades.This paper introduces the concepts,characteristics and advantages of JRC technology,presenting the typical applications that have benefited from JRC technology currently and in the future.This paper explores the state-of-the-art of JRC in the levels of coexistence,cooperation,co-design and collaboration.Compared to previous surveys,this paper reviews the entire trends that drive the development of radar sensing and wireless communication using JRC.Specifically,we explore an open research issue on radar and communication operating with mutual benefits based on collaboration,which represents the fourth stage of JRC evolution.This paper provides useful perspectives for future researches of JRC technology.

Load-Aware Offloading Strategy in Two-Tier Heterogeneous Network

Although small cell offloading technology can alleviate the congestion in macrocell, aggressively offloading data traffic from macrocell to small cell can also degrade the performance of small cell due to the heavy load. Because of collision and backoff, the degradation is significant especially in network with contention-based channel access, and finally decreases throughput of the whole network. To find an optimal fraction of traffic to be offloaded in heterogeneous network, we combine Markov chain with the Poisson point process model to analyze contention-based throughput in irregularly deployment networks. Then we derive the close-form solution of the throughput and find that it is a function of the transmit power and density of base stations.Based on this, we propose the load-aware offloading strategies via power control and base station density adjustment. The numerical results verify our analysis and show a great performance gain compared with non-load-aware offloading.

Multi-Agent Reinforcement Learning for Resource Allocation in Io T Networks with Edge Computing

To support popular Internet of Things(IoT)applications such as virtual reality and mobile games,edge computing provides a front-end distributed computing archetype of centralized cloud computing with low latency and distributed data processing.However,it is challenging for multiple users to offload their computation tasks because they are competing for spectrum and computation as well as Radio Access Technologies(RAT)resources.In this paper,we investigate computation offloading mechanism of multiple selfish users with resource allocation in IoT edge computing networks by formulating it as a stochastic game.Each user is a learning agent observing its local network environment to learn optimal decisions on either local computing or edge computing with a goal of minimizing long term system cost by choosing its transmit power level,RAT and sub-channel without knowing any information of the other users.Since users’decisions are coupling at the gateway,we define the reward function of each user by considering the aggregated effect of other users.Therefore,a multi-agent reinforcement learning framework is developed to solve the game with the proposed Independent Learners based Multi-Agent Q-learning(IL-based MA-Q)algorithm.Simulations demonstrate that the proposed IL-based MA-Q algorithm is feasible to solve the formulated problem and is more energy efficient without extra cost on channel estimation at the centralized gateway.Finally,compared with the other three benchmark algorithms,it has better system cost performance and achieves distributed computation offloading.

Coexistence Analysis between 5G System and Fixed- Satellite Service in 3400-3600 MHz

The 3400-3600 MHz band is one of the most important candidate frequency bands for the rollout of 5 G system. However, the coexistence between 5 G system and fixed-satellite service(FSS) in this frequency band is one of the most challenging problems for both academic researchers and industry engineers. In this paper, the saturation interference from 5 G base stations to the existing FSS above 3600 MHz is analyzed and the coexistence solution is achieved, which can reduce the interference and guarantee the coexistence between 5 G system and FSS. Furthermore, the Monte Carlo simulation, laboratory test and field test are carried out to verify the coexistence solution.Results show that an isolation distance of 1-2 km is required to avoid the saturation interference in terms of the adjacent bands scenario.To further reduce the isolation distance to 50 m, additional isolation of 35 dB will be necessary, which can be fulfilled by installing a filter at the input port of LNB from a real implementation perspective.

Spectrum Allocation and Performance Analysis for Backhauling of UAV Assisted Cellular Network

To reinforce the coverage and QoS(quality of service) of on-ground cellular communication system, unmanned aerial vehicles which are carrying small cells are deployed in some emergency and disaster areas. Although ASCs(aerial small cells) can provide a higher probability of LoS(line-of-sight) transmission, the wireless backhaul link will bring extra interference to the whole system if not well designed. Therefore, in this paper, we study the backhaul scheme for UAV-assist cellular network. We first analyze the interference environments of UAV-assist cellular network considering the IBOG(In-Band to On-Ground), OBOG(Out-of-Band to On-Ground) and IBTU(In-Band to Tethered-UAV) backhauling mode, and give the descriptions of the performance metrics for each mode. Then, the considered problem is formulated as an optimization of achievable rate. We derive the optimal solutions for the involved three backhauling modes for ASCs respectively, and closed-form optimal value for each mode is acquired with proof. We also give a pseudo-code form of our proposed optimal access/backhaul spectrum allocation algorithm. The simulation results indicate that the proposed scheme can deliver a significant gain, while IBTU performs best among proposed backhauling modes.

A Novel Automatic Modulation Classification Method Based on Dictionary Learning

Automatic Modulation Classification(AMC) is an important technology used to recognize the modulation type.A dictionary set was trained via signals with known modulation schemes in cooperative scenarios.Then we classify the modulation scheme of the signals received in the non-cooperative environment according to its sparse representation.Furthermore,we proposed a novel approach called Fast Block Coordinate descent Dictionary Learning(FBCDL).Moreover,the convergence of FBCDL was proved and we find that our proposed method achieves lower complexity.Experimental results indicate that our proposed FBCDL achieves better classification accuracy than traditional methods.

Space-Time Correlation Based Fast Regional Spectrum Sensing in Cognitive Radio

In this paper,a space-time correlation based fast regional spectrum sensing(RSS)scheme is proposed to reduce the time and energy consumption of traditional spatial spectrum sensing. The target region is divided into small meshes,and all meshes are clustered into highly related groups using the spatial correlation among them. In each group,some representative meshes are selected as detecting meshes(DMs)using a multi-center mesh(MCM)clustering algorithm,while other meshes(EMs)are estimated according to their correlations with DMs and the Markov modeled dependence on history by MAP principle. Thus,detecting fewer meshes saves the sensing consumption. Since two independent estimation processes may provide contradictory results,minimum entropy principle is adopted to merge the results. Tested with data acquired by radio environment mapping measurement conducted in the downtown Beijing,our scheme is capable to reduce the consumption of traditional sensing method with acceptable sensing performance.

INTEGRATED TERRESTRIAL-SATELLITE NETWORKS：PART ONE

The rapid growing data traffic brings more and more pressure to the wireless networks,which is predicted to increase by over 10,000 times in the next 20 years.However,currently,there is still large number of population without coverage of mobile service.In addition

A Cyber–Physical Routing Protocol Exploiting Trajectory Dynamics for Mission-Oriented Flying Ad Hoc Networks

As a special type of mobile ad hoc network(MANET),the flying ad hoc network(FANET)has the potential to enable a variety of emerging applications in both civilian wireless communications(e.g.,5G and 6G)and the defense industry.The routing protocol plays a pivotal role in FANET.However,when designing the routing protocol for FANET,it is conventionally assumed that the aerial nodes move randomly.This is clearly inappropriate for a mission-oriented FANET(MO-FANET),in which the aerial nodes typically move toward a given destination from given departure point(s),possibly along a roughly deterministic flight path while maintaining a well-established formation,in order to carry out certain missions.In this paper,a novel cyber–physical routing protocol exploiting the particular mobility pattern of an MO-FANET is proposed based on cross-disciplinary integration,which makes full use of the missiondetermined trajectory dynamics to construct the time sequence of rejoining and separating,as well as the adjacency matrix for each node,as prior information.Compared with the existing representative routing protocols used in FANETs,our protocol achieves a higher packet-delivery ratio(PDR)at the cost of even lower overhead and lower average end-to-end latency,while maintaining a reasonably moderate and stable network jitter,as demonstrated by extensive ns-3-based simulations assuming realistic configurations in an MO-FANET.

INTEGRATED TERRESTRIAL-SATELLITE NETWORKS:PART Two

The rapid growing data traffic brings more and more pressure to the wireless networks,which is predicted to increase by over 10,000 times in the next 20 years.However,currently,there is still large number of population without coverage of mobile service.In addition to the issue of coverage,future wireless networks also need to guarantee the service continuity for emerging services such as Machine-to-Machine and Internet of Things.

Optimal Deployment Density for Maximum Coverage of Drone Small Cells

With the proliferation of small and mini drones, Drone Small Cells(DSCs) can cooperative multiple drones to provide communication service for ground users as emergency means or supplementary ones of traditional terrestrial cellular networks. In this paper, we study the fundamental problem of optimizing the deployment density of DSCs to achieve the maximum coverage performance. Most related works do not consider cumulative inter-cell interference when studying the coverage performance of DSCs. First, we derive an approximate and closed-form expression of the cumulative inter-cell interference which comes from both probabilistic Line-of-Sight(Lo S) and Non-Line-of-Sight(NLo S) links. Then, we analyze the coverage performance of DSCs and derive the transcendental function of optimal deployment density to obtain the maximum coverage. Last, we propose an algorithm to get the optimal deployment density with low complexity. We conduct both field experiments and Matlab simulations to verify the correctness of theoretical analysis. In addition, we show the impact of some factors on the relation between the deployment density and coverage performance through extensive numerical simulations.

Cluster-based RSU deployment strategy for vehicular ad hoc networks with integration of communication,sensing and computing

The integration of communications,sensing and computing(I-CSC)has significant applications in vehicular ad hoc networks(VANETs).A roadside unit(RSU)plays an important role in I-CSC by performing functions such as information transmission and edge computing in vehicular communication.Due to the constraints of limited resources,RSU cannot achieve full coverage and deploying RSUs at key cluster heads of hierarchical structures of road networks is an effective management method.However,direct extracting the hierarchical structures for the resource allocation in VANETs is an open issue.In this paper,we proposed a network-based renormalization method based on information flow and geographical location to hierarchically deploy the RSU on the road networks.The renormalization method is compared with two deployment schemes:genetic algorithm(GA)and memetic framework-based optimal RSU deployment(MFRD),to verify the improvement of communication performance.Our results show that the renormalization method is superior to other schemes in terms of RSU coverage and information reception rate.

通信感知一体化的信息理论极限

无线感知已成为通信产业界广泛公认的、下一代无线网络中的原生能力.通信感知一体化将通信和感知功能集成在同一个无线系统中,能够提高资源利用率,减少基础设施开销,并增强通信和感知各自的性能.通信与感知间的性能折衷是通感一体化的关键基础理论问题之一.本文首先指出通感性能极限和可达性能边界是研究通感性能折衷的重要手段,然后从容量–失真理论、基于均方误差的通感性能边界理论、基于感知等效速率的通感性能边界理论,以及面向目标检测的通感性能边界理论4个方面出发,对相关的当前研究进展进行了详细总结与分析.文中指出通感性能折衷可进一步划分为确定–随机折衷和子空间折衷,并详细讨论了现有研究工作中与之相关的结论.在此基础上,讨论了基于实际的5G NR协议与帧结构的通感性能边界理论.最后,本文对通感一体化的信息理论极限中仍需关注和进一步研究的开放问题进行了总结.

3.6 W compact all-fiber Pr3+-doped green laser at 521 nm

Green semiconductor lasers are still undeveloped,so high-power green lasers have heavily relied on nonlinear frequency conversion of near-infrared lasers,precluding compact and low-cost green laser systems.Here,we report the first Watt-level all-fiber CW Pr3t-doped laser operating directly in the green spectral region,addressing the aforementioned difficulties.The compact all-fiber laser consists of a double-clad Pr3t-doped fluoride fiber,two homemade fiber dichroic mirrors at visible wavelengths,and a 443-nm fiber-pigtailed pump source.Benefitting from>10 MW∕cm2 high damage intensity of our designed fiber dielectric mirror,the green laser can stably deliver 3.62-W of continuous-wave power at∼521 nm with a slope efficiency of 20.9%.To the best of our knowledge,this is the largest output power directly from green fiber lasers,which is one order higher than previously reported.Moreover,these green all-fiber laser designs are optimized by using experiments and numerical simulations.Numerical results are in excellent agreement with our experimental results and show that the optimal gain fiber length,output mirror reflectivity,and doping level should be considered to obtain higher power and efficiency.This work may pave a path toward compact high-power green all-fiber lasers for applications in biomedicine,laser display,underwater detection,and spectroscopy.

ComR:a combined OWL reasoner for ontology classification

Ontology classification,the problem of computing the subsumption hierarchies for classes (atomic concepts),is a core reasoning service provided by Web Ontology Language (OWL)reasoners.Although general-purpose OWL 2 reasoners employ sophisticated optimizations for classification,they are still not efficient owing to the high complexity of tableau algorithms for expressive ontologies. Profile-specific OWL 2 EL reasoners are efficient;however, they become incomplete even if the ontology contains only a small number of axioms that are outside the OWL 2 EL fragment.In this paper,we present a technique that combines an OWL 2 EL reasoner with an OWL 2 reasoner for ontology classification of expressive SROIQ.To optimize the workload,we propose a task decomposition strategy for identifying the minimal non-EL subontology that contains only necessary axioms to ensure completeness.During the ontology classification,the bulk of the workload is delegated to an efficient OWL 2 EL reasoner and only the minimal non- EL subontology is handled by a less efficient OWL 2 reasoner.The proposed approach is implemented in a prototype ComR and experimental results show that our approach offers a substantial speedup in ontology classification.For the wellknown ontology NCI,the classification time is reduced by 96.9%(resp.83.7%)compared against the standard reasoner Pellet (resp.the modular reasoner MORe).

Cognitive information metrics for cognitive wireless networks

Considering the dynamic changes and uncertainty features of the radio environment in cognitive wireless networks(CWNs),the environment cognition ability is critical for the performance evaluation of CWNs design and optimization.However,there are no effective metrics to evaluate the ability and gain of information cognition in CWNs from an information theory perspective.Therefore,the novel cognitive information concept is proposed and defined as a metric to evaluate the uncertainty of both the internal and external environments of one system that can be removed by other systems or nodes using cognitive radio techniques.As an intelligent wireless communication system that is aware of its surrounding radio,network,and user multi-domains environment,the more cognitive information it achieves,the higher level cognitive capability it is.In this paper,we define and analyze the mathematical features of cognitive information.Results reveal that the increase of cognitive information can improve the spectrum efficiency and reduce the interference probability simultaneously in CWNs.Thus cognitive information can be regarded as a metric for CWNs optimization.Finally,we apply the theory of cognitive information in the parameters optimization in energy detection and cooperative spectrum sensing.