In the vision of the incoming 5G era,billions of people as well as trillions of ma chines are expected to be connected by the next generation mobile network.However,functions of massive communication devices have been...In the vision of the incoming 5G era,billions of people as well as trillions of ma chines are expected to be connected by the next generation mobile network.However,functions of massive communication devices have been substantially limited by insufficient power supply.As an efficient solution,dedicated RF sig nals are capable of carrying wellcontrolled energy towards the rechargeable devices in order to achieve ondemand energy transfer.Although RF signals are capable of simulta neously carrying both data and energy,diverse requirements of data and energy trans fers pose huge challenges in their effective integration.For example,the energy receiver and the data receiver have diverse sensitivity to the received power.The received power as low as-80 dBm is sufficient for recovering contaminated packets,thanks to thestate oftheart channel encoding/decoding techniques.However,only when the received pow er is higher than-20 dBm,the energy reception circuit can be effectively activated for converting a fraction of the energy carried by RF signals to the direct current(DC).展开更多
With the maturity of 5G technology and global commercialization,scholars in institutions and industrial circles began to research 6G technology.An important innovation of 6G technology is to integrate artificial intel...With the maturity of 5G technology and global commercialization,scholars in institutions and industrial circles began to research 6G technology.An important innovation of 6G technology is to integrate artificial intelligence(AI)technology and communication technology to build a highly endogenous intelligent communication network.This paper investigates the process of AI technology introduced into the field of communication and reviews the use cases of the simulation and application of AI algorithms being discussed in 3GPP meetings in industry circles.In this research report,we first investigate the progress of AI technology in 5G network architecture and then discuss the requirements of endogenous intelligent 6G networks,which leads to the possible network architecture.This work aims to provide enlightening guidance for subsequent research of intelligence-endogenous 6G network.展开更多
The IEEE/CIC International Conference on Communication in China（ICCC）has been globally recognized as one of the important annual international conference held by the IEEE Communication Society（Com Soc）and China In...The IEEE/CIC International Conference on Communication in China（ICCC）has been globally recognized as one of the important annual international conference held by the IEEE Communication Society（Com Soc）and China Institute of Communication（CIC）in China.IEEE/CIC ICCC 2016,展开更多
Fast and accurate MRI reconstruction is a key concern in modern clinical practice.Recently,numerous Deep-Learning methods have been proposed for MRI reconstruction,however,they usually fail to reconstruct sharp detail...Fast and accurate MRI reconstruction is a key concern in modern clinical practice.Recently,numerous Deep-Learning methods have been proposed for MRI reconstruction,however,they usually fail to reconstruct sharp details from the subsampled k-space data.To solve this problem,we propose a lightweight and accurate Edge Attention MRI Reconstruction Network(EAMRI)to reconstruct images with edge guidance.Specifically,we design an efficient Edge Prediction Network to directly predict accurate edges from the blurred image.Meanwhile,we propose a novel Edge Attention Module(EAM)to guide the image reconstruction utilizing the extracted edge priors,as inspired by the popular self-attention mechanism.EAM first projects the input image and edges into Q_(image),K_(edge),and V_(image),respectively.Then EAM pairs the Q_(image)with K_(edge)along the channel dimension,such that 1)it can search globally for the high-frequency image features that are activated by the edge priors;2)the overall computation burdens are largely reduced compared with the traditional spatial-wise attention.With the help of EAM,the predicted edge priors can effectively guide the model to reconstruct high-quality MR images with accurate edges.Extensive experiments show that our proposed EAMRI outperforms other methods with fewer parameters and can recover more accurate edges.展开更多
Service-Oriented Architecture（SOA） is employed in a wide range of applications because it promises to expose computation-intensive tasks as services and combine them with new applications to accelerate their applica...Service-Oriented Architecture（SOA） is employed in a wide range of applications because it promises to expose computation-intensive tasks as services and combine them with new applications to accelerate their applications development process. For service-oriented multimedia applications, the performance of multicasting transmission services under multimedia traffic must be evaluated. Multiview Video（MVV） is a promising and emerging type of multimedia traffic that consists of multiple video streams, allows stream switching, and requires strict Quality-of-Service（Qo S）. In this study, we investigated multicast transmission of MVV in wireless cellular networks with Partial Frequency Reuse（PFR） and focused on two challenging problems：（1） multicast group formation and（2） subchannel and power allocation. Initially, we propose a novel Content-based Partial frequency reuse Diversity Grouping（CPDG） scheme to allocate users to multicast groups on the basis of Partial frequency reuse Diversity（PD） in wireless networks with PFR. After group formation, an optimization problem for subchannel and power allocation is formulated to minimize network power consumption under Qo S constraint. Thereafter,the optimization problem is divided into two subproblems and solved using simplex method and Karush-KuhnTucker（KKT） condition. Finally, to solve the optimization problem, a suboptimal scheme referred to as Partial frequency reuse Diversity Based Energy-efficient Multicasting（PDEM） is proposed by dynamically allocating wireless resources under Qo S constraint. The simulation results show that the proposed PDEM scheme can achieve close-to-optimal performance. Moreover, mathematical analysis of the effect of PD on network performance can provide guidelines for optimization of multimedia traffic in multicasting-enabled wireless cellular networks with PFR.展开更多
文摘In the vision of the incoming 5G era,billions of people as well as trillions of ma chines are expected to be connected by the next generation mobile network.However,functions of massive communication devices have been substantially limited by insufficient power supply.As an efficient solution,dedicated RF sig nals are capable of carrying wellcontrolled energy towards the rechargeable devices in order to achieve ondemand energy transfer.Although RF signals are capable of simulta neously carrying both data and energy,diverse requirements of data and energy trans fers pose huge challenges in their effective integration.For example,the energy receiver and the data receiver have diverse sensitivity to the received power.The received power as low as-80 dBm is sufficient for recovering contaminated packets,thanks to thestate oftheart channel encoding/decoding techniques.However,only when the received pow er is higher than-20 dBm,the energy reception circuit can be effectively activated for converting a fraction of the energy carried by RF signals to the direct current(DC).
文摘With the maturity of 5G technology and global commercialization,scholars in institutions and industrial circles began to research 6G technology.An important innovation of 6G technology is to integrate artificial intelligence(AI)technology and communication technology to build a highly endogenous intelligent communication network.This paper investigates the process of AI technology introduced into the field of communication and reviews the use cases of the simulation and application of AI algorithms being discussed in 3GPP meetings in industry circles.In this research report,we first investigate the progress of AI technology in 5G network architecture and then discuss the requirements of endogenous intelligent 6G networks,which leads to the possible network architecture.This work aims to provide enlightening guidance for subsequent research of intelligence-endogenous 6G network.
文摘The IEEE/CIC International Conference on Communication in China（ICCC）has been globally recognized as one of the important annual international conference held by the IEEE Communication Society（Com Soc）and China Institute of Communication（CIC）in China.IEEE/CIC ICCC 2016,
基金This work is supported in part by the National Key R&D Program of China under Grant 2021YFE0203700 and 2021YFA1003004in part by the Natural Science Foundation of Shanghai under Grand 23ZR1422200+1 种基金in part by the Shanghai Sailing Program under Grant 23YF1412800in part by the NSFC/RGC N CUHK 415/19,Grant ITF MHP/038/20,Grant CRF 8730063,Grant RGC 14300219,14302920,14301121,and CUHK Direct Grant for Research.
文摘Fast and accurate MRI reconstruction is a key concern in modern clinical practice.Recently,numerous Deep-Learning methods have been proposed for MRI reconstruction,however,they usually fail to reconstruct sharp details from the subsampled k-space data.To solve this problem,we propose a lightweight and accurate Edge Attention MRI Reconstruction Network(EAMRI)to reconstruct images with edge guidance.Specifically,we design an efficient Edge Prediction Network to directly predict accurate edges from the blurred image.Meanwhile,we propose a novel Edge Attention Module(EAM)to guide the image reconstruction utilizing the extracted edge priors,as inspired by the popular self-attention mechanism.EAM first projects the input image and edges into Q_(image),K_(edge),and V_(image),respectively.Then EAM pairs the Q_(image)with K_(edge)along the channel dimension,such that 1)it can search globally for the high-frequency image features that are activated by the edge priors;2)the overall computation burdens are largely reduced compared with the traditional spatial-wise attention.With the help of EAM,the predicted edge priors can effectively guide the model to reconstruct high-quality MR images with accurate edges.Extensive experiments show that our proposed EAMRI outperforms other methods with fewer parameters and can recover more accurate edges.
基金supported by the EU FP7 Project CLIMBER(PIRSES-GA-2012-318939)the program of China Scholarship Council(No.201506070027)National Key Technology Research and Development Program of China(No.2015BAH08F01)
文摘Service-Oriented Architecture（SOA） is employed in a wide range of applications because it promises to expose computation-intensive tasks as services and combine them with new applications to accelerate their applications development process. For service-oriented multimedia applications, the performance of multicasting transmission services under multimedia traffic must be evaluated. Multiview Video（MVV） is a promising and emerging type of multimedia traffic that consists of multiple video streams, allows stream switching, and requires strict Quality-of-Service（Qo S）. In this study, we investigated multicast transmission of MVV in wireless cellular networks with Partial Frequency Reuse（PFR） and focused on two challenging problems：（1） multicast group formation and（2） subchannel and power allocation. Initially, we propose a novel Content-based Partial frequency reuse Diversity Grouping（CPDG） scheme to allocate users to multicast groups on the basis of Partial frequency reuse Diversity（PD） in wireless networks with PFR. After group formation, an optimization problem for subchannel and power allocation is formulated to minimize network power consumption under Qo S constraint. Thereafter,the optimization problem is divided into two subproblems and solved using simplex method and Karush-KuhnTucker（KKT） condition. Finally, to solve the optimization problem, a suboptimal scheme referred to as Partial frequency reuse Diversity Based Energy-efficient Multicasting（PDEM） is proposed by dynamically allocating wireless resources under Qo S constraint. The simulation results show that the proposed PDEM scheme can achieve close-to-optimal performance. Moreover, mathematical analysis of the effect of PD on network performance can provide guidelines for optimization of multimedia traffic in multicasting-enabled wireless cellular networks with PFR.
