Federated learning(FL)activates distributed on-device computation techniques to model a better algorithm performance with the interaction of local model updates and global model distributions in aggregation averaging ...Federated learning(FL)activates distributed on-device computation techniques to model a better algorithm performance with the interaction of local model updates and global model distributions in aggregation averaging processes.However,in large-scale heterogeneous Internet of Things(IoT)cellular networks,massive multi-dimensional model update iterations and resource-constrained computation are challenging aspects to be tackled significantly.This paper introduces the system model of converging softwaredefined networking(SDN)and network functions virtualization(NFV)to enable device/resource abstractions and provide NFV-enabled edge FL(eFL)aggregation servers for advancing automation and controllability.Multi-agent deep Q-networks(MADQNs)target to enforce a self-learning softwarization,optimize resource allocation policies,and advocate computation offloading decisions.With gathered network conditions and resource states,the proposed agent aims to explore various actions for estimating expected longterm rewards in a particular state observation.In exploration phase,optimal actions for joint resource allocation and offloading decisions in different possible states are obtained by maximum Q-value selections.Action-based virtual network functions(VNF)forwarding graph(VNFFG)is orchestrated to map VNFs towards eFL aggregation server with sufficient communication and computation resources in NFV infrastructure(NFVI).The proposed scheme indicates deficient allocation actions,modifies the VNF backup instances,and reallocates the virtual resource for exploitation phase.Deep neural network(DNN)is used as a value function approximator,and epsilongreedy algorithm balances exploration and exploitation.The scheme primarily considers the criticalities of FL model services and congestion states to optimize long-term policy.Simulation results presented the outperformance of the proposed scheme over reference schemes in terms of Quality of Service(QoS)performance metrics,including packet drop ratio,packet drop counts,packet delivery ratio,delay,and throughput.展开更多
Hand gestures have been used as a significant mode of communication since the advent of human civilization.By facilitating human-computer interaction(HCI),hand gesture recognition(HGRoc)technology is crucial for seaml...Hand gestures have been used as a significant mode of communication since the advent of human civilization.By facilitating human-computer interaction(HCI),hand gesture recognition(HGRoc)technology is crucial for seamless and error-free HCI.HGRoc technology is pivotal in healthcare and communication for the deaf community.Despite significant advancements in computer vision-based gesture recognition for language understanding,two considerable challenges persist in this field:(a)limited and common gestures are considered,(b)processing multiple channels of information across a network takes huge computational time during discriminative feature extraction.Therefore,a novel hand vision-based convolutional neural network(CNN)model named(HVCNNM)offers several benefits,notably enhanced accuracy,robustness to variations,real-time performance,reduced channels,and scalability.Additionally,these models can be optimized for real-time performance,learn from large amounts of data,and are scalable to handle complex recognition tasks for efficient human-computer interaction.The proposed model was evaluated on two challenging datasets,namely the Massey University Dataset(MUD)and the American Sign Language(ASL)Alphabet Dataset(ASLAD).On the MUD and ASLAD datasets,HVCNNM achieved a score of 99.23% and 99.00%,respectively.These results demonstrate the effectiveness of CNN as a promising HGRoc approach.The findings suggest that the proposed model have potential roles in applications such as sign language recognition,human-computer interaction,and robotics.展开更多
Formany years,researchers have explored power allocation(PA)algorithms driven bymodels in wireless networks where multiple-user communications with interference are present.Nowadays,data-driven machine learning method...Formany years,researchers have explored power allocation(PA)algorithms driven bymodels in wireless networks where multiple-user communications with interference are present.Nowadays,data-driven machine learning methods have become quite popular in analyzing wireless communication systems,which among them deep reinforcement learning(DRL)has a significant role in solving optimization issues under certain constraints.To this purpose,in this paper,we investigate the PA problem in a k-user multiple access channels(MAC),where k transmitters(e.g.,mobile users)aim to send an independent message to a common receiver(e.g.,base station)through wireless channels.To this end,we first train the deep Q network(DQN)with a deep Q learning(DQL)algorithm over the simulation environment,utilizing offline learning.Then,the DQN will be used with the real data in the online training method for the PA issue by maximizing the sumrate subjected to the source power.Finally,the simulation results indicate that our proposedDQNmethod provides better performance in terms of the sumrate compared with the available DQL training approaches such as fractional programming(FP)and weighted minimum mean squared error(WMMSE).Additionally,by considering different user densities,we show that our proposed DQN outperforms benchmark algorithms,thereby,a good generalization ability is verified over wireless multi-user communication systems.展开更多
Most formation approaches of autonomous underwater vehicles(AUVs)focus on the control techniques,ignoring the influence of underwater channel.This paper is concerned with a communication-aware formation issue for AUVs...Most formation approaches of autonomous underwater vehicles(AUVs)focus on the control techniques,ignoring the influence of underwater channel.This paper is concerned with a communication-aware formation issue for AUVs,subject to model uncertainty and fading channel.An integral reinforcement learning(IRL)based estimator is designed to calculate the probabilistic channel parameters,wherein the multivariate probabilistic collocation method with orthogonal fractional factorial design(M-PCM-OFFD)is employed to evaluate the uncertain channel measurements.With the estimated signal-to-noise ratio(SNR),we employ the IRL and M-PCM-OFFD to develop a saturated formation controller for AUVs,dealing with uncertain dynamics and current parameters.For the proposed formation approach,an integrated optimization solution is presented to make a balance between formation stability and communication efficiency.Main innovations lie in three aspects:1)Construct an integrated communication and control optimization framework;2)Design an IRL-based channel prediction estimator;3)Develop an IRL-based formation controller with M-PCM-OFFD.Finally,simulation results show that the formation approach can avoid local optimum estimation,improve the channel efficiency,and relax the dependence of AUV model parameters.展开更多
Maritime communications with sea surface reflections and sea wave occlusions are susceptible to jamming attacks due to the wide geographical area and intensive wireless communication services.Unmanned Aerial Vehicles(...Maritime communications with sea surface reflections and sea wave occlusions are susceptible to jamming attacks due to the wide geographical area and intensive wireless communication services.Unmanned Aerial Vehicles(UAVs)help relay messages to improve communication performance,but the relay policy that depends on the rapidly changing maritime environments is difficult to optimize.In this paper,a reinforcement learning-based UAV relay policy for maritime communications is proposed to resist jamming attacks.Based on previous transmission performance,the relay location,the received power of the transmitted signal and the received jamming power,this scheme optimizes the UAV trajectory and relay power to save the energy consumption and decrease the Bit-Error-Rate(BER)of the maritime signals.A deep reinforcement learning-based scheme is also proposed,which designs a deep neural network with dueling architecture to further improve the communication performance and computational complexity.The performance bounds regarding the signal to interference plus noise ratio,energy consumption and the communication utility are provided based on the Nash equilibrium of the game against jamming,and the computational complexity of the proposed schemes is analyzed.Simulation results show that the proposed schemes improve the energy efficiency and decrease the BER compared with the benchmark.展开更多
Covert communications can hide the existence of a transmission from the transmitter to receiver.This paper considers an intelligent reflecting surface(IRS)assisted unmanned aerial vehicle(UAV)covert communication syst...Covert communications can hide the existence of a transmission from the transmitter to receiver.This paper considers an intelligent reflecting surface(IRS)assisted unmanned aerial vehicle(UAV)covert communication system.It was inspired by the high-dimensional data processing and decisionmaking capabilities of the deep reinforcement learning(DRL)algorithm.In order to improve the covert communication performance,an UAV 3D trajectory and IRS phase optimization algorithm based on double deep Q network(TAP-DDQN)is proposed.The simulations show that TAP-DDQN can significantly improve the covert performance of the IRS-assisted UAV covert communication system,compared with benchmark solutions.展开更多
The Internet ofMedical Things(IoMT)is mainly concernedwith the efficient utilisation of wearable devices in the healthcare domain to manage various processes automatically,whereas machine learning approaches enable th...The Internet ofMedical Things(IoMT)is mainly concernedwith the efficient utilisation of wearable devices in the healthcare domain to manage various processes automatically,whereas machine learning approaches enable these smart systems to make informed decisions.Generally,broadcasting is used for the transmission of frames,whereas congestion,energy efficiency,and excessive load are among the common issues associated with existing approaches.In this paper,a machine learning-enabled shortest path identification scheme is presented to ensure reliable transmission of frames,especially with the minimum possible communication overheads in the IoMT network.For this purpose,the proposed scheme utilises a well-known technique,i.e.,Kruskal’s algorithm,to find an optimal path from source to destination wearable devices.Additionally,other evaluation metrics are used to find a reliable and shortest possible communication path between the two interested parties.Apart from that,every device is bound to hold a supplementary path,preferably a second optimised path,for situations where the current communication path is no longer available,either due to device failure or heavy traffic.Furthermore,the machine learning approach helps enable these devices to update their routing tables simultaneously,and an optimal path could be replaced if a better one is available.The proposed mechanism has been tested using a smart environment developed for the healthcare domain using IoMT networks.Simulation results show that the proposed machine learning-oriented approach performs better than existing approaches where the proposed scheme has achieved the minimum possible ratios,i.e.,17%and 23%,in terms of end to end delay and packet losses,respectively.Moreover,the proposed scheme has achieved an approximately 21%improvement in the average throughput compared to the existing schemes.展开更多
Recently,unmanned aerial vehicles(UAV)or drones are widely employed for several application areas such as surveillance,disaster management,etc.Since UAVs are limited to energy,efficient coordination between them becom...Recently,unmanned aerial vehicles(UAV)or drones are widely employed for several application areas such as surveillance,disaster management,etc.Since UAVs are limited to energy,efficient coordination between them becomes essential to optimally utilize the resources and effective communication among them and base station(BS).Therefore,clustering can be employed as an effective way of accomplishing smart communication systems among multiple UAVs.In this aspect,this paper presents a group teaching optimization algorithm with deep learning enabled smart communication system(GTOADL-SCS)technique for UAV networks.The proposed GTOADL-SCS model encompasses a two stage process namely clustering and classification.At the initial stage,the GTOADL-SCS model includes a GTOA based clustering scheme to elect cluster heads(CHs)and organize clusters.Besides,the GTOADL-SCS model develops a fitness function containing three input parameters as residual energy of UAVs,average neighoring distance,and UAV degree.For classification process,the GTOADLSCS model applies pre-trained densely connected network(DenseNet201)feature extractor with gated recurrent unit(GRU)classifier.For ensuring the enhanced performance of the GTOADL-SCS model,a widespread simulation analysis is performed and the comparative study reported the significant outcomes over the existing approaches with maximum packet delivery ratio(PDR)of 92.60%.展开更多
With the rapid advancements in edge computing and artificial intelligence,federated learning(FL)has gained momentum as a promising approach to collaborative data utilization across organizations and devices,while ensu...With the rapid advancements in edge computing and artificial intelligence,federated learning(FL)has gained momentum as a promising approach to collaborative data utilization across organizations and devices,while ensuring data privacy and information security.In order to further harness the energy efficiency of wireless networks,an integrated sensing,communication and computation(ISCC)framework has been proposed,which is anticipated to be a key enabler in the era of 6G networks.Although the advantages of pushing intelligence to edge devices are multi-fold,some challenges arise when incorporating FL into wireless networks under the umbrella of ISCC.This paper provides a comprehensive survey of FL,with special emphasis on the design and optimization of ISCC.We commence by introducing the background and fundamentals of FL and the ISCC framework.Subsequently,the aforementioned challenges are highlighted and the state of the art in potential solutions is reviewed.Finally,design guidelines are provided for the incorporation of FL and ISCC.Overall,this paper aims to contribute to the understanding of FL in the context of wireless networks,with a focus on the ISCC framework,and provide insights into addressing the challenges and optimizing the design for the integration of FL into future 6G networks.展开更多
Device-to-device(D2D)communications underlying cellular networks enabled by unmanned aerial vehicles(UAV)have been regarded as promising techniques for next-generation communications.To mitigate the strong interferenc...Device-to-device(D2D)communications underlying cellular networks enabled by unmanned aerial vehicles(UAV)have been regarded as promising techniques for next-generation communications.To mitigate the strong interference caused by the line-of-sight(LoS)airto-ground channels,we deploy a reconfigurable intelligent surface(RIS)to rebuild the wireless channels.A joint optimization problem of the transmit power of UAV,the transmit power of D2D users and the RIS phase configuration are investigated to maximize the achievable rate of D2D users while satisfying the quality of service(QoS)requirement of cellular users.Due to the high channel dynamics and the coupling among cellular users,the RIS,and the D2D users,it is challenging to find a proper solution.Thus,a RIS softmax deep double deterministic(RIS-SD3)policy gradient method is proposed,which can smooth the optimization space as well as reduce the number of local optimizations.Specifically,the SD3 algorithm maximizes the reward of the agent by training the agent to maximize the value function after the softmax operator is introduced.Simulation results show that the proposed RIS-SD3 algorithm can significantly improve the rate of the D2D users while controlling the interference to the cellular user.Moreover,the proposed RIS-SD3 algorithm has better robustness than the twin delayed deep deterministic(TD3)policy gradient algorithm in a dynamic environment.展开更多
The course “Taishan Cultural Communication with the World” has been online and offline teaching and learning for two terms based on the theoretical ideas: Blended Learning and Outcome-Based Education. This paper use...The course “Taishan Cultural Communication with the World” has been online and offline teaching and learning for two terms based on the theoretical ideas: Blended Learning and Outcome-Based Education. This paper uses the data from one semester to state how to carry out the program and the good results. At the same time disadvantages are also the points that should be taken into consideration. From the teaching and learning practice, students have benefited from the online videos, complementary materials and discussions;they need to be guided as well, especially the guidance offline to make up. Furthermore, the balance of time online and offline is a great challenge.展开更多
Guest Editorial Currently,the rapid development of storage technologies combined with some potential factors such as mobile networks,Internet of Things(IoT),cloud computing and the emergence of new technologies pose s...Guest Editorial Currently,the rapid development of storage technologies combined with some potential factors such as mobile networks,Internet of Things(IoT),cloud computing and the emergence of new technologies pose some problems for big data processing and blockchain security in the communication domain.Moreover,the complexity of network security and data processing has increased dramatically,making it more difficult and challenging to solve various problems in the communication domain.Therefore,Machine Learning(ML)algorithms have been proposed to process big data and enhance blockchain security and further enable intelligent analysis in the communication domain.展开更多
Compressed Sensing(CS)is a Machine Learning(ML)method,which can be regarded as a single-layer unsupervised learning method.It mainly emphasizes the sparsity of the model.In this paper,we study an ML-based CS Channel E...Compressed Sensing(CS)is a Machine Learning(ML)method,which can be regarded as a single-layer unsupervised learning method.It mainly emphasizes the sparsity of the model.In this paper,we study an ML-based CS Channel Estimation(CE)method for wireless communications,which plays an important role in Industrial Internet of Things(IIoT)applications.For the sparse correlation between channels in Multiple Input Multiple Output Filter Bank MultiCarrier with Offset Quadrature Amplitude Modulation(MIMO-FBMC/OQAM)systems,a Distributed Compressed Sensing(DCS)-based CE approach is studied.A distributed sparse adaptive weak selection threshold method is proposed for CE.Firstly,the correlation between MIMO channels is utilized to represent a joint sparse model,and CE is transformed into a joint sparse signal reconstruction problem.Then,the number of correlation atoms for inner product operation is optimized by weak selection threshold,and sparse signal reconstruction is realized by sparse adaptation.The experiment results show that the proposed DCS-based method not only estimates the multipath channel components accurately but also achieves higher CE performance than classical Orthogonal Matching Pursuit(OMP)method and other traditional DCS methods in the time-frequency dual selective channels.展开更多
The connected autonomous vehicle is considered an effective way to improve transport safety and efficiency.To overcome the limited sensing and computing capabilities of individual vehicles,we design a digital twin ass...The connected autonomous vehicle is considered an effective way to improve transport safety and efficiency.To overcome the limited sensing and computing capabilities of individual vehicles,we design a digital twin assisted decision-making framework for Internet of Vehicles,by leveraging the integration of communication,sensing and computing.In this framework,the digital twin entities residing on edge can effectively communicate and cooperate with each other to plan sub-targets for their respective vehicles,while the vehicles only need to achieve the sub-targets by generating a sequence of atomic actions.Furthermore,we propose a hierarchical multiagent reinforcement learning approach to implement the framework,which can be trained in an end-to-end way.In the proposed approach,the communication interval of digital twin entities could adapt to timevarying environment.Extensive experiments on driving decision-making have been performed in traffic junction scenarios of different difficulties.The experimental results show that the proposed approach can largely improve collaboration efficiency while reducing communication overhead.展开更多
To meet the high-performance requirements of fifth-generation(5G)and sixth-generation(6G)wireless networks,in particular,ultra-reliable and low-latency communication(URLLC)is considered to be one of the most important...To meet the high-performance requirements of fifth-generation(5G)and sixth-generation(6G)wireless networks,in particular,ultra-reliable and low-latency communication(URLLC)is considered to be one of the most important communication scenarios in a wireless network.In this paper,we consider the effects of the Rician fading channel on the performance of cooperative device-to-device(D2D)communication with URLLC.For better performance,we maximize and examine the system’s minimal rate of D2D communication.Due to the interference in D2D communication,the problem of maximizing the minimum rate becomes non-convex and difficult to solve.To solve this problem,a learning-to-optimize-based algorithm is proposed to find the optimal power allocation.The conventional branch and bound(BB)algorithm are used to learn the optimal pruning policy with supervised learning.Ensemble learning is used to train the multiple classifiers.To address the imbalanced problem,we used the supervised undersampling technique.Comparisons are made with the conventional BB algorithm and the heuristic algorithm.The outcome of the simulation demonstrates a notable performance improvement in power consumption.The proposed algorithm has significantly low computational complexity and runs faster as compared to the conventional BB algorithm and a heuristic algorithm.展开更多
For a 5G wireless communication system,a convolutional deep neural network(CNN)is employed to synthesize a robust channel state estimator(CSE).The proposed CSE extracts channel information from transmit-and-receive pa...For a 5G wireless communication system,a convolutional deep neural network(CNN)is employed to synthesize a robust channel state estimator(CSE).The proposed CSE extracts channel information from transmit-and-receive pairs through offline training to estimate the channel state information.Also,it utilizes pilots to offer more helpful information about the communication channel.The proposedCNN-CSE performance is compared with previously published results for Bidirectional/long short-term memory(BiLSTM/LSTM)NNs-based CSEs.The CNN-CSE achieves outstanding performance using sufficient pilots only and loses its functionality at limited pilots compared with BiLSTM and LSTM-based estimators.Using three different loss function-based classification layers and the Adam optimization algorithm,a comparative study was conducted to assess the performance of the presented DNNs-based CSEs.The BiLSTM-CSE outperforms LSTM,CNN,conventional least squares(LS),and minimum mean square error(MMSE)CSEs.In addition,the computational and learning time complexities for DNN-CSEs are provided.These estimators are promising for 5G and future communication systems because they can analyze large amounts of data,discover statistical dependencies,learn correlations between features,and generalize the gotten knowledge.展开更多
As an important mechanism in multi-agent interaction,communication can make agents form complex team relationships rather than constitute a simple set of multiple independent agents.However,the existing communication ...As an important mechanism in multi-agent interaction,communication can make agents form complex team relationships rather than constitute a simple set of multiple independent agents.However,the existing communication schemes can bring much timing redundancy and irrelevant messages,which seriously affects their practical application.To solve this problem,this paper proposes a targeted multiagent communication algorithm based on state control(SCTC).The SCTC uses a gating mechanism based on state control to reduce the timing redundancy of communication between agents and determines the interaction relationship between agents and the importance weight of a communication message through a series connection of hard-and self-attention mechanisms,realizing targeted communication message processing.In addition,by minimizing the difference between the fusion message generated from a real communication message of each agent and a fusion message generated from the buffered message,the correctness of the final action choice of the agent is ensured.Our evaluation using a challenging set of Star Craft II benchmarks indicates that the SCTC can significantly improve the learning performance and reduce the communication overhead between agents,thus ensuring better cooperation between agents.展开更多
Satellite communications has been regarded as an indispensable technology for future mobile networks to provide extremely high data rates,ultra-reliability,and ubiquitous coverage.However,the high dynamics caused by t...Satellite communications has been regarded as an indispensable technology for future mobile networks to provide extremely high data rates,ultra-reliability,and ubiquitous coverage.However,the high dynamics caused by the fast movement of low-earth-orbit(LEO)satellites bring huge challenges in designing and optimizing satellite communication systems.Especially,admission control,deciding which users with diversified service requirements are allowed to access the network with limited resources,is of paramount importance to improve network resource utilization and meet the service quality requirements of users.In this paper,we propose a dynamic channel reservation strategy based on the Actor-Critic algorithm(AC-DCRS)to perform intelligent admission control in satellite networks.By carefully designing the longterm reward function and dynamically adjusting the reserved channel threshold,AC-DCRS reaches a long-run optimal access policy for both new calls and handover calls with different service priorities.Numerical results show that our proposed AC-DCRS outperforms traditional channel reservation strategies in terms of overall access failure probability,the average call success rate,and channel utilization under various dynamic traffic conditions.展开更多
BACKGROUND Liver transplantation(LT)is a life-saving intervention for patients with end-stage liver disease.However,the equitable allocation of scarce donor organs remains a formidable challenge.Prognostic tools are p...BACKGROUND Liver transplantation(LT)is a life-saving intervention for patients with end-stage liver disease.However,the equitable allocation of scarce donor organs remains a formidable challenge.Prognostic tools are pivotal in identifying the most suitable transplant candidates.Traditionally,scoring systems like the model for end-stage liver disease have been instrumental in this process.Nevertheless,the landscape of prognostication is undergoing a transformation with the integration of machine learning(ML)and artificial intelligence models.AIM To assess the utility of ML models in prognostication for LT,comparing their performance and reliability to established traditional scoring systems.METHODS Following the Preferred Reporting Items for Systematic Reviews and Meta-Analysis guidelines,we conducted a thorough and standardized literature search using the PubMed/MEDLINE database.Our search imposed no restrictions on publication year,age,or gender.Exclusion criteria encompassed non-English studies,review articles,case reports,conference papers,studies with missing data,or those exhibiting evident methodological flaws.RESULTS Our search yielded a total of 64 articles,with 23 meeting the inclusion criteria.Among the selected studies,60.8%originated from the United States and China combined.Only one pediatric study met the criteria.Notably,91%of the studies were published within the past five years.ML models consistently demonstrated satisfactory to excellent area under the receiver operating characteristic curve values(ranging from 0.6 to 1)across all studies,surpassing the performance of traditional scoring systems.Random forest exhibited superior predictive capabilities for 90-d mortality following LT,sepsis,and acute kidney injury(AKI).In contrast,gradient boosting excelled in predicting the risk of graft-versus-host disease,pneumonia,and AKI.CONCLUSION This study underscores the potential of ML models in guiding decisions related to allograft allocation and LT,marking a significant evolution in the field of prognostication.展开更多
基金This work was funded by BK21 FOUR(Fostering Outstanding Universities for Research)(No.5199990914048)this research was supported by Basic Science Research Program through the National Research Foundation of Korea(NRF)funded by the Ministry of Education(NRF-2020R1I1A3066543)In addition,this work was supported by the Soonchunhyang University Research Fund.
文摘Federated learning(FL)activates distributed on-device computation techniques to model a better algorithm performance with the interaction of local model updates and global model distributions in aggregation averaging processes.However,in large-scale heterogeneous Internet of Things(IoT)cellular networks,massive multi-dimensional model update iterations and resource-constrained computation are challenging aspects to be tackled significantly.This paper introduces the system model of converging softwaredefined networking(SDN)and network functions virtualization(NFV)to enable device/resource abstractions and provide NFV-enabled edge FL(eFL)aggregation servers for advancing automation and controllability.Multi-agent deep Q-networks(MADQNs)target to enforce a self-learning softwarization,optimize resource allocation policies,and advocate computation offloading decisions.With gathered network conditions and resource states,the proposed agent aims to explore various actions for estimating expected longterm rewards in a particular state observation.In exploration phase,optimal actions for joint resource allocation and offloading decisions in different possible states are obtained by maximum Q-value selections.Action-based virtual network functions(VNF)forwarding graph(VNFFG)is orchestrated to map VNFs towards eFL aggregation server with sufficient communication and computation resources in NFV infrastructure(NFVI).The proposed scheme indicates deficient allocation actions,modifies the VNF backup instances,and reallocates the virtual resource for exploitation phase.Deep neural network(DNN)is used as a value function approximator,and epsilongreedy algorithm balances exploration and exploitation.The scheme primarily considers the criticalities of FL model services and congestion states to optimize long-term policy.Simulation results presented the outperformance of the proposed scheme over reference schemes in terms of Quality of Service(QoS)performance metrics,including packet drop ratio,packet drop counts,packet delivery ratio,delay,and throughput.
基金funded by Researchers Supporting Project Number(RSPD2024 R947),King Saud University,Riyadh,Saudi Arabia.
文摘Hand gestures have been used as a significant mode of communication since the advent of human civilization.By facilitating human-computer interaction(HCI),hand gesture recognition(HGRoc)technology is crucial for seamless and error-free HCI.HGRoc technology is pivotal in healthcare and communication for the deaf community.Despite significant advancements in computer vision-based gesture recognition for language understanding,two considerable challenges persist in this field:(a)limited and common gestures are considered,(b)processing multiple channels of information across a network takes huge computational time during discriminative feature extraction.Therefore,a novel hand vision-based convolutional neural network(CNN)model named(HVCNNM)offers several benefits,notably enhanced accuracy,robustness to variations,real-time performance,reduced channels,and scalability.Additionally,these models can be optimized for real-time performance,learn from large amounts of data,and are scalable to handle complex recognition tasks for efficient human-computer interaction.The proposed model was evaluated on two challenging datasets,namely the Massey University Dataset(MUD)and the American Sign Language(ASL)Alphabet Dataset(ASLAD).On the MUD and ASLAD datasets,HVCNNM achieved a score of 99.23% and 99.00%,respectively.These results demonstrate the effectiveness of CNN as a promising HGRoc approach.The findings suggest that the proposed model have potential roles in applications such as sign language recognition,human-computer interaction,and robotics.
文摘Formany years,researchers have explored power allocation(PA)algorithms driven bymodels in wireless networks where multiple-user communications with interference are present.Nowadays,data-driven machine learning methods have become quite popular in analyzing wireless communication systems,which among them deep reinforcement learning(DRL)has a significant role in solving optimization issues under certain constraints.To this purpose,in this paper,we investigate the PA problem in a k-user multiple access channels(MAC),where k transmitters(e.g.,mobile users)aim to send an independent message to a common receiver(e.g.,base station)through wireless channels.To this end,we first train the deep Q network(DQN)with a deep Q learning(DQL)algorithm over the simulation environment,utilizing offline learning.Then,the DQN will be used with the real data in the online training method for the PA issue by maximizing the sumrate subjected to the source power.Finally,the simulation results indicate that our proposedDQNmethod provides better performance in terms of the sumrate compared with the available DQL training approaches such as fractional programming(FP)and weighted minimum mean squared error(WMMSE).Additionally,by considering different user densities,we show that our proposed DQN outperforms benchmark algorithms,thereby,a good generalization ability is verified over wireless multi-user communication systems.
基金supported in part by the National Natural Science Foundation of China(62222314,61973263,61873345,62033011)the Youth Talent Program of Hebei(BJ2020031)+2 种基金the Distinguished Young Foundation of Hebei Province(F2022203001)the Central Guidance Local Foundation of Hebei Province(226Z3201G)the Three-Three-Three Foundation of Hebei Province(C20221019)。
文摘Most formation approaches of autonomous underwater vehicles(AUVs)focus on the control techniques,ignoring the influence of underwater channel.This paper is concerned with a communication-aware formation issue for AUVs,subject to model uncertainty and fading channel.An integral reinforcement learning(IRL)based estimator is designed to calculate the probabilistic channel parameters,wherein the multivariate probabilistic collocation method with orthogonal fractional factorial design(M-PCM-OFFD)is employed to evaluate the uncertain channel measurements.With the estimated signal-to-noise ratio(SNR),we employ the IRL and M-PCM-OFFD to develop a saturated formation controller for AUVs,dealing with uncertain dynamics and current parameters.For the proposed formation approach,an integrated optimization solution is presented to make a balance between formation stability and communication efficiency.Main innovations lie in three aspects:1)Construct an integrated communication and control optimization framework;2)Design an IRL-based channel prediction estimator;3)Develop an IRL-based formation controller with M-PCM-OFFD.Finally,simulation results show that the formation approach can avoid local optimum estimation,improve the channel efficiency,and relax the dependence of AUV model parameters.
基金This work was supported in part by the Funds of the National Natural Science Foundation of China under Grant(U21A20444,61971366)in part by the Fundamental Research Funds for the central universities No.20720210073.
文摘Maritime communications with sea surface reflections and sea wave occlusions are susceptible to jamming attacks due to the wide geographical area and intensive wireless communication services.Unmanned Aerial Vehicles(UAVs)help relay messages to improve communication performance,but the relay policy that depends on the rapidly changing maritime environments is difficult to optimize.In this paper,a reinforcement learning-based UAV relay policy for maritime communications is proposed to resist jamming attacks.Based on previous transmission performance,the relay location,the received power of the transmitted signal and the received jamming power,this scheme optimizes the UAV trajectory and relay power to save the energy consumption and decrease the Bit-Error-Rate(BER)of the maritime signals.A deep reinforcement learning-based scheme is also proposed,which designs a deep neural network with dueling architecture to further improve the communication performance and computational complexity.The performance bounds regarding the signal to interference plus noise ratio,energy consumption and the communication utility are provided based on the Nash equilibrium of the game against jamming,and the computational complexity of the proposed schemes is analyzed.Simulation results show that the proposed schemes improve the energy efficiency and decrease the BER compared with the benchmark.
文摘Covert communications can hide the existence of a transmission from the transmitter to receiver.This paper considers an intelligent reflecting surface(IRS)assisted unmanned aerial vehicle(UAV)covert communication system.It was inspired by the high-dimensional data processing and decisionmaking capabilities of the deep reinforcement learning(DRL)algorithm.In order to improve the covert communication performance,an UAV 3D trajectory and IRS phase optimization algorithm based on double deep Q network(TAP-DDQN)is proposed.The simulations show that TAP-DDQN can significantly improve the covert performance of the IRS-assisted UAV covert communication system,compared with benchmark solutions.
文摘The Internet ofMedical Things(IoMT)is mainly concernedwith the efficient utilisation of wearable devices in the healthcare domain to manage various processes automatically,whereas machine learning approaches enable these smart systems to make informed decisions.Generally,broadcasting is used for the transmission of frames,whereas congestion,energy efficiency,and excessive load are among the common issues associated with existing approaches.In this paper,a machine learning-enabled shortest path identification scheme is presented to ensure reliable transmission of frames,especially with the minimum possible communication overheads in the IoMT network.For this purpose,the proposed scheme utilises a well-known technique,i.e.,Kruskal’s algorithm,to find an optimal path from source to destination wearable devices.Additionally,other evaluation metrics are used to find a reliable and shortest possible communication path between the two interested parties.Apart from that,every device is bound to hold a supplementary path,preferably a second optimised path,for situations where the current communication path is no longer available,either due to device failure or heavy traffic.Furthermore,the machine learning approach helps enable these devices to update their routing tables simultaneously,and an optimal path could be replaced if a better one is available.The proposed mechanism has been tested using a smart environment developed for the healthcare domain using IoMT networks.Simulation results show that the proposed machine learning-oriented approach performs better than existing approaches where the proposed scheme has achieved the minimum possible ratios,i.e.,17%and 23%,in terms of end to end delay and packet losses,respectively.Moreover,the proposed scheme has achieved an approximately 21%improvement in the average throughput compared to the existing schemes.
基金The authors extend their appreciation to the Deanship of Scientific Research at King Khalid University for funding this work under Grant Number(RGP 2/158/43)Princess Nourah bint Abdulrahman University Researchers Supporting Project Number(PNURSP2022R238)Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia.The authors would like to thank the Deanship of Scientific Research at Umm Al-Qura University for supporting this work by Grant Code:22UQU4340237DSR13.
文摘Recently,unmanned aerial vehicles(UAV)or drones are widely employed for several application areas such as surveillance,disaster management,etc.Since UAVs are limited to energy,efficient coordination between them becomes essential to optimally utilize the resources and effective communication among them and base station(BS).Therefore,clustering can be employed as an effective way of accomplishing smart communication systems among multiple UAVs.In this aspect,this paper presents a group teaching optimization algorithm with deep learning enabled smart communication system(GTOADL-SCS)technique for UAV networks.The proposed GTOADL-SCS model encompasses a two stage process namely clustering and classification.At the initial stage,the GTOADL-SCS model includes a GTOA based clustering scheme to elect cluster heads(CHs)and organize clusters.Besides,the GTOADL-SCS model develops a fitness function containing three input parameters as residual energy of UAVs,average neighoring distance,and UAV degree.For classification process,the GTOADLSCS model applies pre-trained densely connected network(DenseNet201)feature extractor with gated recurrent unit(GRU)classifier.For ensuring the enhanced performance of the GTOADL-SCS model,a widespread simulation analysis is performed and the comparative study reported the significant outcomes over the existing approaches with maximum packet delivery ratio(PDR)of 92.60%.
文摘With the rapid advancements in edge computing and artificial intelligence,federated learning(FL)has gained momentum as a promising approach to collaborative data utilization across organizations and devices,while ensuring data privacy and information security.In order to further harness the energy efficiency of wireless networks,an integrated sensing,communication and computation(ISCC)framework has been proposed,which is anticipated to be a key enabler in the era of 6G networks.Although the advantages of pushing intelligence to edge devices are multi-fold,some challenges arise when incorporating FL into wireless networks under the umbrella of ISCC.This paper provides a comprehensive survey of FL,with special emphasis on the design and optimization of ISCC.We commence by introducing the background and fundamentals of FL and the ISCC framework.Subsequently,the aforementioned challenges are highlighted and the state of the art in potential solutions is reviewed.Finally,design guidelines are provided for the incorporation of FL and ISCC.Overall,this paper aims to contribute to the understanding of FL in the context of wireless networks,with a focus on the ISCC framework,and provide insights into addressing the challenges and optimizing the design for the integration of FL into future 6G networks.
基金supported by the National Natural Science Foundation of China under Grant Nos.62201462 and 62271412.
文摘Device-to-device(D2D)communications underlying cellular networks enabled by unmanned aerial vehicles(UAV)have been regarded as promising techniques for next-generation communications.To mitigate the strong interference caused by the line-of-sight(LoS)airto-ground channels,we deploy a reconfigurable intelligent surface(RIS)to rebuild the wireless channels.A joint optimization problem of the transmit power of UAV,the transmit power of D2D users and the RIS phase configuration are investigated to maximize the achievable rate of D2D users while satisfying the quality of service(QoS)requirement of cellular users.Due to the high channel dynamics and the coupling among cellular users,the RIS,and the D2D users,it is challenging to find a proper solution.Thus,a RIS softmax deep double deterministic(RIS-SD3)policy gradient method is proposed,which can smooth the optimization space as well as reduce the number of local optimizations.Specifically,the SD3 algorithm maximizes the reward of the agent by training the agent to maximize the value function after the softmax operator is introduced.Simulation results show that the proposed RIS-SD3 algorithm can significantly improve the rate of the D2D users while controlling the interference to the cellular user.Moreover,the proposed RIS-SD3 algorithm has better robustness than the twin delayed deep deterministic(TD3)policy gradient algorithm in a dynamic environment.
文摘The course “Taishan Cultural Communication with the World” has been online and offline teaching and learning for two terms based on the theoretical ideas: Blended Learning and Outcome-Based Education. This paper uses the data from one semester to state how to carry out the program and the good results. At the same time disadvantages are also the points that should be taken into consideration. From the teaching and learning practice, students have benefited from the online videos, complementary materials and discussions;they need to be guided as well, especially the guidance offline to make up. Furthermore, the balance of time online and offline is a great challenge.
文摘Guest Editorial Currently,the rapid development of storage technologies combined with some potential factors such as mobile networks,Internet of Things(IoT),cloud computing and the emergence of new technologies pose some problems for big data processing and blockchain security in the communication domain.Moreover,the complexity of network security and data processing has increased dramatically,making it more difficult and challenging to solve various problems in the communication domain.Therefore,Machine Learning(ML)algorithms have been proposed to process big data and enhance blockchain security and further enable intelligent analysis in the communication domain.
基金supported by National Natural Science Foundation of China under Grant Nos.61901409 and 61961013Jiangxi Provincial Natural Science Foundation under Grant No.20202BABL212001Open Project of State Key Laboratory of Marine Resources Utilization in South China Sea under Grant No.MRUKF2021034.
文摘Compressed Sensing(CS)is a Machine Learning(ML)method,which can be regarded as a single-layer unsupervised learning method.It mainly emphasizes the sparsity of the model.In this paper,we study an ML-based CS Channel Estimation(CE)method for wireless communications,which plays an important role in Industrial Internet of Things(IIoT)applications.For the sparse correlation between channels in Multiple Input Multiple Output Filter Bank MultiCarrier with Offset Quadrature Amplitude Modulation(MIMO-FBMC/OQAM)systems,a Distributed Compressed Sensing(DCS)-based CE approach is studied.A distributed sparse adaptive weak selection threshold method is proposed for CE.Firstly,the correlation between MIMO channels is utilized to represent a joint sparse model,and CE is transformed into a joint sparse signal reconstruction problem.Then,the number of correlation atoms for inner product operation is optimized by weak selection threshold,and sparse signal reconstruction is realized by sparse adaptation.The experiment results show that the proposed DCS-based method not only estimates the multipath channel components accurately but also achieves higher CE performance than classical Orthogonal Matching Pursuit(OMP)method and other traditional DCS methods in the time-frequency dual selective channels.
基金supported in part by the Natural Science Foundation of China under Grant 62001054,Grant 62272053 and Grant 61901191in part by the Natural Science Foundation of Shandong Province of China under Grant ZR2020LZH005in part by the Fundamental Research Funds for the Central Universities。
文摘The connected autonomous vehicle is considered an effective way to improve transport safety and efficiency.To overcome the limited sensing and computing capabilities of individual vehicles,we design a digital twin assisted decision-making framework for Internet of Vehicles,by leveraging the integration of communication,sensing and computing.In this framework,the digital twin entities residing on edge can effectively communicate and cooperate with each other to plan sub-targets for their respective vehicles,while the vehicles only need to achieve the sub-targets by generating a sequence of atomic actions.Furthermore,we propose a hierarchical multiagent reinforcement learning approach to implement the framework,which can be trained in an end-to-end way.In the proposed approach,the communication interval of digital twin entities could adapt to timevarying environment.Extensive experiments on driving decision-making have been performed in traffic junction scenarios of different difficulties.The experimental results show that the proposed approach can largely improve collaboration efficiency while reducing communication overhead.
基金supported in part by the National Natural Science Foundation of China under Grant 61771410in part by the Sichuan Science and Technology Program 2023NSFSC1373in part by Postgraduate Innovation Fund Project of SWUST 23zx7101.
文摘To meet the high-performance requirements of fifth-generation(5G)and sixth-generation(6G)wireless networks,in particular,ultra-reliable and low-latency communication(URLLC)is considered to be one of the most important communication scenarios in a wireless network.In this paper,we consider the effects of the Rician fading channel on the performance of cooperative device-to-device(D2D)communication with URLLC.For better performance,we maximize and examine the system’s minimal rate of D2D communication.Due to the interference in D2D communication,the problem of maximizing the minimum rate becomes non-convex and difficult to solve.To solve this problem,a learning-to-optimize-based algorithm is proposed to find the optimal power allocation.The conventional branch and bound(BB)algorithm are used to learn the optimal pruning policy with supervised learning.Ensemble learning is used to train the multiple classifiers.To address the imbalanced problem,we used the supervised undersampling technique.Comparisons are made with the conventional BB algorithm and the heuristic algorithm.The outcome of the simulation demonstrates a notable performance improvement in power consumption.The proposed algorithm has significantly low computational complexity and runs faster as compared to the conventional BB algorithm and a heuristic algorithm.
基金funded by Taif University Researchers Supporting Project No.(TURSP-2020/214),Taif University,Taif,Saudi Arabia。
文摘For a 5G wireless communication system,a convolutional deep neural network(CNN)is employed to synthesize a robust channel state estimator(CSE).The proposed CSE extracts channel information from transmit-and-receive pairs through offline training to estimate the channel state information.Also,it utilizes pilots to offer more helpful information about the communication channel.The proposedCNN-CSE performance is compared with previously published results for Bidirectional/long short-term memory(BiLSTM/LSTM)NNs-based CSEs.The CNN-CSE achieves outstanding performance using sufficient pilots only and loses its functionality at limited pilots compared with BiLSTM and LSTM-based estimators.Using three different loss function-based classification layers and the Adam optimization algorithm,a comparative study was conducted to assess the performance of the presented DNNs-based CSEs.The BiLSTM-CSE outperforms LSTM,CNN,conventional least squares(LS),and minimum mean square error(MMSE)CSEs.In addition,the computational and learning time complexities for DNN-CSEs are provided.These estimators are promising for 5G and future communication systems because they can analyze large amounts of data,discover statistical dependencies,learn correlations between features,and generalize the gotten knowledge.
文摘As an important mechanism in multi-agent interaction,communication can make agents form complex team relationships rather than constitute a simple set of multiple independent agents.However,the existing communication schemes can bring much timing redundancy and irrelevant messages,which seriously affects their practical application.To solve this problem,this paper proposes a targeted multiagent communication algorithm based on state control(SCTC).The SCTC uses a gating mechanism based on state control to reduce the timing redundancy of communication between agents and determines the interaction relationship between agents and the importance weight of a communication message through a series connection of hard-and self-attention mechanisms,realizing targeted communication message processing.In addition,by minimizing the difference between the fusion message generated from a real communication message of each agent and a fusion message generated from the buffered message,the correctness of the final action choice of the agent is ensured.Our evaluation using a challenging set of Star Craft II benchmarks indicates that the SCTC can significantly improve the learning performance and reduce the communication overhead between agents,thus ensuring better cooperation between agents.
基金supported by the ZTE Industry⁃University⁃Institute Cooperation Funds.
文摘Satellite communications has been regarded as an indispensable technology for future mobile networks to provide extremely high data rates,ultra-reliability,and ubiquitous coverage.However,the high dynamics caused by the fast movement of low-earth-orbit(LEO)satellites bring huge challenges in designing and optimizing satellite communication systems.Especially,admission control,deciding which users with diversified service requirements are allowed to access the network with limited resources,is of paramount importance to improve network resource utilization and meet the service quality requirements of users.In this paper,we propose a dynamic channel reservation strategy based on the Actor-Critic algorithm(AC-DCRS)to perform intelligent admission control in satellite networks.By carefully designing the longterm reward function and dynamically adjusting the reserved channel threshold,AC-DCRS reaches a long-run optimal access policy for both new calls and handover calls with different service priorities.Numerical results show that our proposed AC-DCRS outperforms traditional channel reservation strategies in terms of overall access failure probability,the average call success rate,and channel utilization under various dynamic traffic conditions.
文摘BACKGROUND Liver transplantation(LT)is a life-saving intervention for patients with end-stage liver disease.However,the equitable allocation of scarce donor organs remains a formidable challenge.Prognostic tools are pivotal in identifying the most suitable transplant candidates.Traditionally,scoring systems like the model for end-stage liver disease have been instrumental in this process.Nevertheless,the landscape of prognostication is undergoing a transformation with the integration of machine learning(ML)and artificial intelligence models.AIM To assess the utility of ML models in prognostication for LT,comparing their performance and reliability to established traditional scoring systems.METHODS Following the Preferred Reporting Items for Systematic Reviews and Meta-Analysis guidelines,we conducted a thorough and standardized literature search using the PubMed/MEDLINE database.Our search imposed no restrictions on publication year,age,or gender.Exclusion criteria encompassed non-English studies,review articles,case reports,conference papers,studies with missing data,or those exhibiting evident methodological flaws.RESULTS Our search yielded a total of 64 articles,with 23 meeting the inclusion criteria.Among the selected studies,60.8%originated from the United States and China combined.Only one pediatric study met the criteria.Notably,91%of the studies were published within the past five years.ML models consistently demonstrated satisfactory to excellent area under the receiver operating characteristic curve values(ranging from 0.6 to 1)across all studies,surpassing the performance of traditional scoring systems.Random forest exhibited superior predictive capabilities for 90-d mortality following LT,sepsis,and acute kidney injury(AKI).In contrast,gradient boosting excelled in predicting the risk of graft-versus-host disease,pneumonia,and AKI.CONCLUSION This study underscores the potential of ML models in guiding decisions related to allograft allocation and LT,marking a significant evolution in the field of prognostication.
