Scene recognition is a popular open problem in the computer vision field.Among lots of methods proposed in recent years,Convolutional Neural Network(CNN)based approaches achieve the best performance in scene recogniti...Scene recognition is a popular open problem in the computer vision field.Among lots of methods proposed in recent years,Convolutional Neural Network(CNN)based approaches achieve the best performance in scene recognition.We propose in this paper an advanced feature fusion algorithm using Multiple Convolutional Neural Network(Multi-CNN)for scene recognition.Unlike existing works that usually use individual convolutional neural network,a fusion of multiple different convolutional neural networks is applied for scene recognition.Firstly,we split training images in two directions and apply to three deep CNN model,and then extract features from the last full-connected(FC)layer and probabilistic layer on each model.Finally,feature vectors are fused with different fusion strategies in groups forwarded into SoftMax classifier.Our proposed algorithm is evaluated on three scene datasets for scene recognition.The experimental results demonstrate the effectiveness of proposed algorithm compared with other state-of-art approaches.展开更多
Wireless devicetodevice （D2D） communications sharing the spectrum of cellular networks is important for improving spec trum efficiency. Furthermore, introducing multicast and multi hop communications to D2D networks...Wireless devicetodevice （D2D） communications sharing the spectrum of cellular networks is important for improving spec trum efficiency. Furthermore, introducing multicast and multi hop communications to D2D networks can expand D2D ser vice functions. In this paper, we propose an anglebased inter ferenceaware routing algorithm for D2D multicast communica tions. This algorithm reuses the uplink cellular spectrum. Our proposed algorithm aims to reduce the outage probability and minimize the average hop count over all multicast destina tions （i.e., multicast receivers）, while limiting interference to cellular users to a tolerable level. In particular, our algorithm integrates two design principles for hopbyhop route selec tion. First, we minimize the distance ratio of the candidateto destination link to the candidatetobasestation link, such that the selected route advances closer to a subset of multi cast receivers. Second, we design the anglethreshold based merging strategy to divide multicast receivers into subsets with geographically close destinations. By applying the two principles for selection of each hop and further deriving an adaptive powerallocation strategy, the message can be more effieiently delivered to destinations with fewer branches when constructing the multicast tree. This means fewer duplicated data transmissions. Analyses and simulations are presented to show the impact of system parameters on the routing perfor mances. Simulation results also demonstrate the superiority of our algorithm over baseline schemes in terms of outage proba bility and average hop count.展开更多
In this paper, we consider a novel two-dimensional(2D) geometry-based stochastic model(GBSM) for multiple-input multiple-output(MIMO) vehicle-to-vehicle(V2V) wideband fading channels. The proposed model employs the co...In this paper, we consider a novel two-dimensional(2D) geometry-based stochastic model(GBSM) for multiple-input multiple-output(MIMO) vehicle-to-vehicle(V2V) wideband fading channels. The proposed model employs the combination of a two-ring model and a multiple confocal ellipses model, where the signal is sum of the line-of-sight(Lo S) component, single-bounced(SB) rays, and double-bounced(DB) rays. Based on the reference model, we derive some expressions of channel statistical properties, including space-time correlation function(STCF), Doppler spectral power density(DPSD), envelope level crossing rate(LCR) and average fade duration(AFD). In addition, corresponding deterministic and stochastic simulation models are developed based on the reference model. Moreover, we compare the statistical properties of the reference model and the two simulation models in different scenarios and investigate the impact of different vehicular traffic densities(VTDs) on the channel statistical properties of the proposed model. Finally, the great agreement between simulation models and the reference model demonstrates not only the utility of simulation models, but also the correctness of theoretical derivations and simulations.展开更多
Reconfigurable intelligent surface(RIS)is an emerging meta-surface that can provide additional communications links through reflecting the signals,and has been recognized as a strong candidate of 6G mobile communicati...Reconfigurable intelligent surface(RIS)is an emerging meta-surface that can provide additional communications links through reflecting the signals,and has been recognized as a strong candidate of 6G mobile communications systems.Meanwhile,it has been recently admitted that implementing artificial intelligence(AI)into RIS communications will extensively benefit the reconfiguration capacity and enhance the robustness to complicated transmission environments.Besides the conventional model-driven approaches,AI can also deal with the existing signal processing problems in a data-driven manner via digging the inherent characteristic from the real data.Hence,AI is particularly suitable for the signal processing problems over RIS networks under unideal scenarios like modeling mismatching,insufficient resource,hardware impairment,as well as dynamical transmissions.As one of the earliest survey papers,we will introduce the merging of AI and RIS,called AIRIS,over various signal processing topics,including environmental sensing,channel acquisition,beamforming design,and resource scheduling,etc.We will also discuss the challenges of AIRIS and present some interesting future directions.展开更多
In new radio （NR） access technology, the radio access network （RAN） architecture is split into two kinds of entities, i.e., the centralized unit （CU） and the distributed unit （DU）, to enhance the network flexi...In new radio （NR） access technology, the radio access network （RAN） architecture is split into two kinds of entities, i.e., the centralized unit （CU） and the distributed unit （DU）, to enhance the network flexibility. In this split architecture, one CU is able to control several DUs, which enables the function of base-band central control and remote service for users. In this paper, the general aspects of CU-DU split architecture are introduced, including the split method, interface functions （control plane functions and user plane functions）, mobility scenarios and other CU-DU related issues. The simulations show the performance of Options 2 and 3 for CU-DU split.展开更多
Quality of Experience(QoE)is used to monitor the user experience of telecommunication services,which has been studied for a long time.In universal terrestrial radio access network(UTRAN),evolved UTRAN(E-UTRA)and Long ...Quality of Experience(QoE)is used to monitor the user experience of telecommunication services,which has been studied for a long time.In universal terrestrial radio access network(UTRAN),evolved UTRAN(E-UTRA)and Long Term Evolution(LTE),QoE has also been specified for the improvement of user experience.The 5G New Radio(NR)technology is designed for providing various types of new services,and therefore operators have strong demand to continuously upgrade the 5G network to provide sufficient and good QoE for corresponding services.With new emerging 5G services,5G QoE management collection aims at specifying the mechanism to collect the experience parameters for the multimedia telephony service for IP multimedia subsystem(IMS),multimedia broadcast and multicast service(MBMS),virtual reality(VR),etc.Taking LTE QoE as a baseline,generic NR QoE management mechanisms for activation,deactivation,configuration,and reporting of QoE measurement are introduced in this paper.Additionally,some enhanced QoE features in NR are discussed,such as radio access network(RAN)overload handling,RAN-visible QoE,perslice QoE measurement,radio-related measurement,and QoE continuity for mobility.This paper also introduces solutions to NR QoE,which concludes the progress of NR QoE in the 3rd Generation Partnership Project(3GPP).展开更多
Self-organizing network(SON)and minimization of driver tests(MDT)are functions designed for Long Term Evolution(LTE)system.SON is designed for network deployment by automatic configuration.MDT is designed for network ...Self-organizing network(SON)and minimization of driver tests(MDT)are functions designed for Long Term Evolution(LTE)system.SON is designed for network deployment by automatic configuration.MDT is designed for network performance evaluation by automatic signalling procedure.However,these functions do not support new features in new radio(NR)access technology,e.g.,multiple radio access technology(RAT)-dual connectivity(MR-DC),central unit-distribute unit(CU-DU)split architecture,beam,etc.Therefore,how to support these features is a challenge for the industry.This paper provides analysis for these problems and provides the summary of SON/MDT functions progress in3 GPP.The analysis includes sub functions such as inter/intra system mobility robustness enhancement,inter/intra system mobility load balance,measurement qualities and mechanism of MDT,energy saving mechanism and procedure,RACH procedure optimization,PCI selection optimization,coverage and capacity optimization,and quality of service(QoS)monitoring mechanism.In addition,this paper also provides an initial thought on artificial intelligence(AI)algorithms applied to SON/MDT functions in NR,so called Smart Grid.展开更多
In the new radio(NR)access technology,non-terrestrial networks(NTN)are intro-duced to meet the requirement of anywhere and anytime connections from the world market.With the introduction of NTN,the NR system is able t...In the new radio(NR)access technology,non-terrestrial networks(NTN)are intro-duced to meet the requirement of anywhere and anytime connections from the world market.With the introduction of NTN,the NR system is able to offer the wide-area coverage and en-sure the service availability for users.In this paper,the general aspects of NTN are intro-duced,including the NTN architecture overview,the impact of NTN on next-generation radio access network(NG-RAN)interface functions,mobility scenarios and other NTN related is-sues.The current progress in 3GPP Release 17 is also provided.展开更多
Einstein equation of gravity has on one side the momentum energy density tensor and on the other, Einstein tensor which is derived from Ricci curvature tensor. A better theory of gravity will have both sides geometric...Einstein equation of gravity has on one side the momentum energy density tensor and on the other, Einstein tensor which is derived from Ricci curvature tensor. A better theory of gravity will have both sides geometric. One way to achieve this goal is to develop a new measure of time that will be independent of the choice of coordinates. One natural nominee for such time is the upper limit of measurable time form an event back to the big bang singularity. This limit should exist despite the singularity, otherwise the cosmos age would be unbounded. By this, the author constructs a scalar field of time. Time, however, is measured by material clocks. What is the maximal time that can be measured by a small microscopic clock when our curve starts at near the “big bang” event and ends at an event within the nucleus of an atom? Will our tiny clock move along geodesic curves or will it move in a non geodesic curve within matter? It is almost paradoxical that a test particle in General Relativity will always move along geodesic curves but the motion of matter within the particle may not be geodesic at all. For example, the ground of the Earth does not move at geodesic velocity. Where there is no matter, we choose a curve from near “big bang” to an event such that the time measured is maximal. Without assuming force fields, the gravitational field which causes that two or more such curves intersect at events, would cause discontinuity of the gradient of the upper limit of measurable time scalar field. The discontinuity can be avoided only if we give up on measurement along geodesic curves where there is matter. In other words, our tiny test particle clock will experience force when it travels within matter or near matter.展开更多
As a critical candidate technology for 5G-advanced and 6G,reconfigurable intelligent surfaces(RIS)have received extensive atten-tion from academia and industry.RIS has the promising features of passiveness,reconfigura...As a critical candidate technology for 5G-advanced and 6G,reconfigurable intelligent surfaces(RIS)have received extensive atten-tion from academia and industry.RIS has the promising features of passiveness,reconfigurable ability,and low cost.RIS channel estimation faces the challenges of high matrix dimension,passive estimation,and spatial-wideband effect.In this article,we analyze the impact of the spatial-wideband effect on the RIS channel to account for the propagation delay across RIS elements and estimate sparse channel parameters such as angle and gain through a super-resolution compressive sensing(CS)algorithm.The simulation results explore the influence of the spatial-wideband effect on the RIS channel and verify the effectiveness of the proposed algorithm.展开更多
A novel non-geometrical stochastic model(NGSM)for non-wide sense station ary uncorrelated scattering(non-WSSUS)vehicle-to-vehicle(V2V)channels is proposed.This model is based on a conventional NGSM and employs a more ...A novel non-geometrical stochastic model(NGSM)for non-wide sense station ary uncorrelated scattering(non-WSSUS)vehicle-to-vehicle(V2V)channels is proposed.This model is based on a conventional NGSM and employs a more accurate method to reproduce the realistic characteristics of V2V channels,which successfully extends the existing NGSM to include the line-of-sight(LoS)component.Moreover,the statistical properties of the proposed model in different scenarios,including Doppler power spectral density(PSD),power delay profile(PDP),and the tap correlation coefficient matrix are simulated and compared with those of the existing NGSM.Furthermore,the simulation results dem onstrate not only the utility of the proposed model,but also the correctness of our theoreti cal derivations.展开更多
The impacts of rain on millimeter wave(mmW)terrestrial links,which are inevitably affected by ground-objects-induced multipath propagation,are presented based on the signal time series data measured at 35 GHz.We analy...The impacts of rain on millimeter wave(mmW)terrestrial links,which are inevitably affected by ground-objects-induced multipath propagation,are presented based on the signal time series data measured at 35 GHz.We analyze the coupled influence mechanism of rain-induced and ground-objects-induced multipath propagation on mmW terrestrial links.It can be deduced that the rain-induced impacts on millimeter wave terrestrial links cannot be neglected.The results given in this paper are significant for developing 5G millimeter wave terrestrial mobile communication links.展开更多
文摘Scene recognition is a popular open problem in the computer vision field.Among lots of methods proposed in recent years,Convolutional Neural Network(CNN)based approaches achieve the best performance in scene recognition.We propose in this paper an advanced feature fusion algorithm using Multiple Convolutional Neural Network(Multi-CNN)for scene recognition.Unlike existing works that usually use individual convolutional neural network,a fusion of multiple different convolutional neural networks is applied for scene recognition.Firstly,we split training images in two directions and apply to three deep CNN model,and then extract features from the last full-connected(FC)layer and probabilistic layer on each model.Finally,feature vectors are fused with different fusion strategies in groups forwarded into SoftMax classifier.Our proposed algorithm is evaluated on three scene datasets for scene recognition.The experimental results demonstrate the effectiveness of proposed algorithm compared with other state-of-art approaches.
基金Acknowledgment： This work was partly supported by the National Natural Science Foundation of China（60672150） and Science and Technology Planning Project of Shenzhen, China （szkj0706）.
基金supported by National Natural Science Foundation of China under Grant No.61102078ZTE Industry-Academic-Research Cooperation Fundsthe Fundamental Research Funds for the Central Universities
文摘Wireless devicetodevice （D2D） communications sharing the spectrum of cellular networks is important for improving spec trum efficiency. Furthermore, introducing multicast and multi hop communications to D2D networks can expand D2D ser vice functions. In this paper, we propose an anglebased inter ferenceaware routing algorithm for D2D multicast communica tions. This algorithm reuses the uplink cellular spectrum. Our proposed algorithm aims to reduce the outage probability and minimize the average hop count over all multicast destina tions （i.e., multicast receivers）, while limiting interference to cellular users to a tolerable level. In particular, our algorithm integrates two design principles for hopbyhop route selec tion. First, we minimize the distance ratio of the candidateto destination link to the candidatetobasestation link, such that the selected route advances closer to a subset of multi cast receivers. Second, we design the anglethreshold based merging strategy to divide multicast receivers into subsets with geographically close destinations. By applying the two principles for selection of each hop and further deriving an adaptive powerallocation strategy, the message can be more effieiently delivered to destinations with fewer branches when constructing the multicast tree. This means fewer duplicated data transmissions. Analyses and simulations are presented to show the impact of system parameters on the routing perfor mances. Simulation results also demonstrate the superiority of our algorithm over baseline schemes in terms of outage proba bility and average hop count.
基金supported in part by the project from the ZTEthe National Natural Science Foundation of China under Grant 61622101 and Grant 61571020National Science and Technology Major Project under Grant 2018ZX03001031
文摘In this paper, we consider a novel two-dimensional(2D) geometry-based stochastic model(GBSM) for multiple-input multiple-output(MIMO) vehicle-to-vehicle(V2V) wideband fading channels. The proposed model employs the combination of a two-ring model and a multiple confocal ellipses model, where the signal is sum of the line-of-sight(Lo S) component, single-bounced(SB) rays, and double-bounced(DB) rays. Based on the reference model, we derive some expressions of channel statistical properties, including space-time correlation function(STCF), Doppler spectral power density(DPSD), envelope level crossing rate(LCR) and average fade duration(AFD). In addition, corresponding deterministic and stochastic simulation models are developed based on the reference model. Moreover, we compare the statistical properties of the reference model and the two simulation models in different scenarios and investigate the impact of different vehicular traffic densities(VTDs) on the channel statistical properties of the proposed model. Finally, the great agreement between simulation models and the reference model demonstrates not only the utility of simulation models, but also the correctness of theoretical derivations and simulations.
基金This work was supported in part by National Key Research and Development Program of China under Grant 2017YFB1010002in part by National Natural Science Foundation of China under Grant 61871455,61831013.
文摘Reconfigurable intelligent surface(RIS)is an emerging meta-surface that can provide additional communications links through reflecting the signals,and has been recognized as a strong candidate of 6G mobile communications systems.Meanwhile,it has been recently admitted that implementing artificial intelligence(AI)into RIS communications will extensively benefit the reconfiguration capacity and enhance the robustness to complicated transmission environments.Besides the conventional model-driven approaches,AI can also deal with the existing signal processing problems in a data-driven manner via digging the inherent characteristic from the real data.Hence,AI is particularly suitable for the signal processing problems over RIS networks under unideal scenarios like modeling mismatching,insufficient resource,hardware impairment,as well as dynamical transmissions.As one of the earliest survey papers,we will introduce the merging of AI and RIS,called AIRIS,over various signal processing topics,including environmental sensing,channel acquisition,beamforming design,and resource scheduling,etc.We will also discuss the challenges of AIRIS and present some interesting future directions.
文摘In new radio （NR） access technology, the radio access network （RAN） architecture is split into two kinds of entities, i.e., the centralized unit （CU） and the distributed unit （DU）, to enhance the network flexibility. In this split architecture, one CU is able to control several DUs, which enables the function of base-band central control and remote service for users. In this paper, the general aspects of CU-DU split architecture are introduced, including the split method, interface functions （control plane functions and user plane functions）, mobility scenarios and other CU-DU related issues. The simulations show the performance of Options 2 and 3 for CU-DU split.
文摘Quality of Experience(QoE)is used to monitor the user experience of telecommunication services,which has been studied for a long time.In universal terrestrial radio access network(UTRAN),evolved UTRAN(E-UTRA)and Long Term Evolution(LTE),QoE has also been specified for the improvement of user experience.The 5G New Radio(NR)technology is designed for providing various types of new services,and therefore operators have strong demand to continuously upgrade the 5G network to provide sufficient and good QoE for corresponding services.With new emerging 5G services,5G QoE management collection aims at specifying the mechanism to collect the experience parameters for the multimedia telephony service for IP multimedia subsystem(IMS),multimedia broadcast and multicast service(MBMS),virtual reality(VR),etc.Taking LTE QoE as a baseline,generic NR QoE management mechanisms for activation,deactivation,configuration,and reporting of QoE measurement are introduced in this paper.Additionally,some enhanced QoE features in NR are discussed,such as radio access network(RAN)overload handling,RAN-visible QoE,perslice QoE measurement,radio-related measurement,and QoE continuity for mobility.This paper also introduces solutions to NR QoE,which concludes the progress of NR QoE in the 3rd Generation Partnership Project(3GPP).
文摘Self-organizing network(SON)and minimization of driver tests(MDT)are functions designed for Long Term Evolution(LTE)system.SON is designed for network deployment by automatic configuration.MDT is designed for network performance evaluation by automatic signalling procedure.However,these functions do not support new features in new radio(NR)access technology,e.g.,multiple radio access technology(RAT)-dual connectivity(MR-DC),central unit-distribute unit(CU-DU)split architecture,beam,etc.Therefore,how to support these features is a challenge for the industry.This paper provides analysis for these problems and provides the summary of SON/MDT functions progress in3 GPP.The analysis includes sub functions such as inter/intra system mobility robustness enhancement,inter/intra system mobility load balance,measurement qualities and mechanism of MDT,energy saving mechanism and procedure,RACH procedure optimization,PCI selection optimization,coverage and capacity optimization,and quality of service(QoS)monitoring mechanism.In addition,this paper also provides an initial thought on artificial intelligence(AI)algorithms applied to SON/MDT functions in NR,so called Smart Grid.
文摘In the new radio(NR)access technology,non-terrestrial networks(NTN)are intro-duced to meet the requirement of anywhere and anytime connections from the world market.With the introduction of NTN,the NR system is able to offer the wide-area coverage and en-sure the service availability for users.In this paper,the general aspects of NTN are intro-duced,including the NTN architecture overview,the impact of NTN on next-generation radio access network(NG-RAN)interface functions,mobility scenarios and other NTN related is-sues.The current progress in 3GPP Release 17 is also provided.
文摘Einstein equation of gravity has on one side the momentum energy density tensor and on the other, Einstein tensor which is derived from Ricci curvature tensor. A better theory of gravity will have both sides geometric. One way to achieve this goal is to develop a new measure of time that will be independent of the choice of coordinates. One natural nominee for such time is the upper limit of measurable time form an event back to the big bang singularity. This limit should exist despite the singularity, otherwise the cosmos age would be unbounded. By this, the author constructs a scalar field of time. Time, however, is measured by material clocks. What is the maximal time that can be measured by a small microscopic clock when our curve starts at near the “big bang” event and ends at an event within the nucleus of an atom? Will our tiny clock move along geodesic curves or will it move in a non geodesic curve within matter? It is almost paradoxical that a test particle in General Relativity will always move along geodesic curves but the motion of matter within the particle may not be geodesic at all. For example, the ground of the Earth does not move at geodesic velocity. Where there is no matter, we choose a curve from near “big bang” to an event such that the time measured is maximal. Without assuming force fields, the gravitational field which causes that two or more such curves intersect at events, would cause discontinuity of the gradient of the upper limit of measurable time scalar field. The discontinuity can be avoided only if we give up on measurement along geodesic curves where there is matter. In other words, our tiny test particle clock will experience force when it travels within matter or near matter.
基金Acknowledgment： This work was partly supported by the National Natural Science Foundation of China （No. 60772163） and Science and Technology Planning Project of Shenzhen, China （No. szkj0706）.
文摘As a critical candidate technology for 5G-advanced and 6G,reconfigurable intelligent surfaces(RIS)have received extensive atten-tion from academia and industry.RIS has the promising features of passiveness,reconfigurable ability,and low cost.RIS channel estimation faces the challenges of high matrix dimension,passive estimation,and spatial-wideband effect.In this article,we analyze the impact of the spatial-wideband effect on the RIS channel to account for the propagation delay across RIS elements and estimate sparse channel parameters such as angle and gain through a super-resolution compressive sensing(CS)algorithm.The simulation results explore the influence of the spatial-wideband effect on the RIS channel and verify the effectiveness of the proposed algorithm.
基金supported by the Ministry National Key Research and Development Project under Grant No.2017YFE0121400the open research fund of Key Laboratory of Wireless Sensor Network&Communication under Grant No.2017003Shanghai Institute of Microsystem and Information Technology,and Chinese Academy of Sciences.
文摘A novel non-geometrical stochastic model(NGSM)for non-wide sense station ary uncorrelated scattering(non-WSSUS)vehicle-to-vehicle(V2V)channels is proposed.This model is based on a conventional NGSM and employs a more accurate method to reproduce the realistic characteristics of V2V channels,which successfully extends the existing NGSM to include the line-of-sight(LoS)component.Moreover,the statistical properties of the proposed model in different scenarios,including Doppler power spectral density(PSD),power delay profile(PDP),and the tap correlation coefficient matrix are simulated and compared with those of the existing NGSM.Furthermore,the simulation results dem onstrate not only the utility of the proposed model,but also the correctness of our theoreti cal derivations.
基金This work was supported in part by ZTE Corporation Program under Grant No.2017ZTE01-01-06.
文摘The impacts of rain on millimeter wave(mmW)terrestrial links,which are inevitably affected by ground-objects-induced multipath propagation,are presented based on the signal time series data measured at 35 GHz.We analyze the coupled influence mechanism of rain-induced and ground-objects-induced multipath propagation on mmW terrestrial links.It can be deduced that the rain-induced impacts on millimeter wave terrestrial links cannot be neglected.The results given in this paper are significant for developing 5G millimeter wave terrestrial mobile communication links.
