An integrated sensing and communication(ISAC)scheme for a millimeter wave(mmWave)multiple-input multiple-output orthogonal frequency division multiplexing(MIMO-OFDM)Vehicle-to-Infrastructure(V2I)system is presented,in...An integrated sensing and communication(ISAC)scheme for a millimeter wave(mmWave)multiple-input multiple-output orthogonal frequency division multiplexing(MIMO-OFDM)Vehicle-to-Infrastructure(V2I)system is presented,in which both the access point(AP)and the vehicle are equipped with large antenna arrays and employ hybrid analog and digital beamforming structures to compensate the path loss,meanwhile compromise between hardware complexity and system performance.Based on the sparse scattering nature of the mmWave channel,the received signal at the AP is organized to a four-order tensor by the introduced novel frame structure.A CANDECOMP/PARAFAC(CP)decomposition-based method is proposed for time-varying channel parameter extraction,including angles of departure/arrival(AoDs/AoAs),Doppler shift,time delay and path gain.Then leveraging the estimates of channel parameters,a nonlinear weighted least-square problem is proposed to recover the location accurately,heading and velocity of vehicles.Simulation results show that the proposed methods are effective and efficient in time-varying channel estimation and vehicle sensing in mmWave MIMOOFDM V2I systems.展开更多
Array of Things (AoT)通过单一位置上的多传感器对城市系统进行连续动态观测。AoT观测数据量大且持续增长,使得如何利用有限的计算资源进行AoT序列数据的压缩传输成为其应用的关键瓶颈之一。本文提出了一种基于张量分解的AoT序列数据...Array of Things (AoT)通过单一位置上的多传感器对城市系统进行连续动态观测。AoT观测数据量大且持续增长,使得如何利用有限的计算资源进行AoT序列数据的压缩传输成为其应用的关键瓶颈之一。本文提出了一种基于张量分解的AoT序列数据的有损压缩方法。面向其海量、高维且需在传感器端处理的需求,该方法首先将AoT序列数据组织成高维张量,利用算法复杂度较低的张量CANDECOMP/PARAFAC (CP)分解提取各维度上的特征主分量,而后利用张量重构实现特征保持的数据有损压缩。利用基于张量分解的有损压缩方法,针对美国芝加哥市区的24 h内感测的声光电磁数据进行了实验,讨论了不同压缩参数对压缩比、压缩误差、压缩精度、压缩时间、压缩过程运行内存占用和压缩结果内存占用之间的影响。实验结果表明该方法可实现AoT序列数据的有损压缩,其较小的内存占用能够支持传感器端数据压缩。并且与原始光场强度对比表明,压缩后的数据保持了原有时空分布特征。与传统矢量量化编码压缩方法相比,在相同压缩精度下,本文方法的压缩比约高27%~76%,压缩时间约节省46%~73%,压缩结果所占内存约节省17%~57%,因此本文方法具有更高的压缩比,更低的压缩时间和内存占用,可为Ao T这一类数据的大规模有损压缩提供借鉴意义。展开更多
Quantile regression is widely used in variable relationship research for statistical learning.Traditional quantile regression model is based on vector-valued covariates and can be efficiently estimated via traditional...Quantile regression is widely used in variable relationship research for statistical learning.Traditional quantile regression model is based on vector-valued covariates and can be efficiently estimated via traditional estimation methods.However,many modern applications involve tensor data with the intrinsic tensor structure.Traditional quantile regression can not deal with tensor regression issues well.To this end,we consider a tensor quantile regression with tensor-valued covariates and develop a novel variational Bayesian estimation approach to make estimation and prediction based on the asymmetric Laplace model and the CANDECOMP/PARAFAC decomposition of tensor coefficients.To incorporate the sparsity of tensor coefficients,we consider the multiway shrinkage priors for marginal factor vectors of tensor coefficients.The key idea of the proposed method is to efficiently combine the prior structural information of tensor and utilize the matricization of tensor decomposition to simplify the complexity of tensor coefficient estimation.The coordinate ascent algorithm is employed to optimize variational lower bound.Simulation studies and a real example show the numerical performances of the proposed method.展开更多
CANDECOMP/PARAFAC(CP) tensor factorization is an efficient technique for incomplete tensor-data processing through capturing the multilinear latent factors. Based on the incorporate a sparsity-inducing prior over mult...CANDECOMP/PARAFAC(CP) tensor factorization is an efficient technique for incomplete tensor-data processing through capturing the multilinear latent factors. Based on the incorporate a sparsity-inducing prior over multiple latent factors and appropriate hyper-priors over all hyper-parameters, a Bayesian-based hierarchical probabilistic CP factorization model could be formed. By this way, the rank of the incomplete tensor can be determined automatically. In this paper, we explored the tensor completion method in processing incomplete multidimensional electroencephalogram(EEG) and magnetic resonance imaging(MRI) clinical data. The empirical results indicated that the Bayesian CP tensor factorization of incomplete data method can effectively recover EEG signal with missing data and denoised the noisy MRI data.展开更多
Nonnegative tensor decomposition has become increasingly important for multiway data analysis in recent years. The alternating proximal gradient(APG) is a popular optimization method for nonnegative tensor decompositi...Nonnegative tensor decomposition has become increasingly important for multiway data analysis in recent years. The alternating proximal gradient(APG) is a popular optimization method for nonnegative tensor decomposition in the block coordinate descent framework. In this study, we propose an inexact version of the APG algorithm for nonnegative CANDECOMP/PARAFAC decomposition, wherein each factor matrix is updated by only finite inner iterations. We also propose a parameter warm-start method that can avoid the frequent parameter resetting of conventional APG methods and improve convergence performance.By experimental tests, we find that when the number of inner iterations is limited to around 10 to 20, the convergence speed is accelerated significantly without losing its low relative error. We evaluate our method on both synthetic and real-world tensors.The results demonstrate that the proposed inexact APG algorithm exhibits outstanding performance on both convergence speed and computational precision compared with existing popular algorithms.展开更多
文摘An integrated sensing and communication(ISAC)scheme for a millimeter wave(mmWave)multiple-input multiple-output orthogonal frequency division multiplexing(MIMO-OFDM)Vehicle-to-Infrastructure(V2I)system is presented,in which both the access point(AP)and the vehicle are equipped with large antenna arrays and employ hybrid analog and digital beamforming structures to compensate the path loss,meanwhile compromise between hardware complexity and system performance.Based on the sparse scattering nature of the mmWave channel,the received signal at the AP is organized to a four-order tensor by the introduced novel frame structure.A CANDECOMP/PARAFAC(CP)decomposition-based method is proposed for time-varying channel parameter extraction,including angles of departure/arrival(AoDs/AoAs),Doppler shift,time delay and path gain.Then leveraging the estimates of channel parameters,a nonlinear weighted least-square problem is proposed to recover the location accurately,heading and velocity of vehicles.Simulation results show that the proposed methods are effective and efficient in time-varying channel estimation and vehicle sensing in mmWave MIMOOFDM V2I systems.
文摘Array of Things (AoT)通过单一位置上的多传感器对城市系统进行连续动态观测。AoT观测数据量大且持续增长,使得如何利用有限的计算资源进行AoT序列数据的压缩传输成为其应用的关键瓶颈之一。本文提出了一种基于张量分解的AoT序列数据的有损压缩方法。面向其海量、高维且需在传感器端处理的需求,该方法首先将AoT序列数据组织成高维张量,利用算法复杂度较低的张量CANDECOMP/PARAFAC (CP)分解提取各维度上的特征主分量,而后利用张量重构实现特征保持的数据有损压缩。利用基于张量分解的有损压缩方法,针对美国芝加哥市区的24 h内感测的声光电磁数据进行了实验,讨论了不同压缩参数对压缩比、压缩误差、压缩精度、压缩时间、压缩过程运行内存占用和压缩结果内存占用之间的影响。实验结果表明该方法可实现AoT序列数据的有损压缩,其较小的内存占用能够支持传感器端数据压缩。并且与原始光场强度对比表明,压缩后的数据保持了原有时空分布特征。与传统矢量量化编码压缩方法相比,在相同压缩精度下,本文方法的压缩比约高27%~76%,压缩时间约节省46%~73%,压缩结果所占内存约节省17%~57%,因此本文方法具有更高的压缩比,更低的压缩时间和内存占用,可为Ao T这一类数据的大规模有损压缩提供借鉴意义。
基金Supported by National Key R&D Program of China(Grant No.102022YFA1003701)National Natural Science Foundation of China(Grant No.12271472,12231017,12001479)Natural Science Foundation of Yunnan Province(Grant No.202101AU070073,202201AT070101)。
文摘Quantile regression is widely used in variable relationship research for statistical learning.Traditional quantile regression model is based on vector-valued covariates and can be efficiently estimated via traditional estimation methods.However,many modern applications involve tensor data with the intrinsic tensor structure.Traditional quantile regression can not deal with tensor regression issues well.To this end,we consider a tensor quantile regression with tensor-valued covariates and develop a novel variational Bayesian estimation approach to make estimation and prediction based on the asymmetric Laplace model and the CANDECOMP/PARAFAC decomposition of tensor coefficients.To incorporate the sparsity of tensor coefficients,we consider the multiway shrinkage priors for marginal factor vectors of tensor coefficients.The key idea of the proposed method is to efficiently combine the prior structural information of tensor and utilize the matricization of tensor decomposition to simplify the complexity of tensor coefficient estimation.The coordinate ascent algorithm is employed to optimize variational lower bound.Simulation studies and a real example show the numerical performances of the proposed method.
基金supported by the JSPS KAKENHI,Japan(Grant Nos.17K00326 and 18K04178)the National Natural Science Foundation of China(Grant Nos.61773129,61633010)the JST CREST,Japan(Grant No.JPMJCR1784)。
文摘CANDECOMP/PARAFAC(CP) tensor factorization is an efficient technique for incomplete tensor-data processing through capturing the multilinear latent factors. Based on the incorporate a sparsity-inducing prior over multiple latent factors and appropriate hyper-priors over all hyper-parameters, a Bayesian-based hierarchical probabilistic CP factorization model could be formed. By this way, the rank of the incomplete tensor can be determined automatically. In this paper, we explored the tensor completion method in processing incomplete multidimensional electroencephalogram(EEG) and magnetic resonance imaging(MRI) clinical data. The empirical results indicated that the Bayesian CP tensor factorization of incomplete data method can effectively recover EEG signal with missing data and denoised the noisy MRI data.
基金This work was supported by the National Natural Science Foundation of China(Grant No.91748105)the National Foundation in China(Grant Nos.JCKY2019110B009 and 2020-JCJQ-JJ-252)+1 种基金the Fundamental Research Funds for the Central Universities(Grant Nos.DUT20LAB303 and DUT20LAB308)in Dalian University of Technology in Chinathe scholarship from China Scholarship Council(Grant No.201600090043)。
文摘Nonnegative tensor decomposition has become increasingly important for multiway data analysis in recent years. The alternating proximal gradient(APG) is a popular optimization method for nonnegative tensor decomposition in the block coordinate descent framework. In this study, we propose an inexact version of the APG algorithm for nonnegative CANDECOMP/PARAFAC decomposition, wherein each factor matrix is updated by only finite inner iterations. We also propose a parameter warm-start method that can avoid the frequent parameter resetting of conventional APG methods and improve convergence performance.By experimental tests, we find that when the number of inner iterations is limited to around 10 to 20, the convergence speed is accelerated significantly without losing its low relative error. We evaluate our method on both synthetic and real-world tensors.The results demonstrate that the proposed inexact APG algorithm exhibits outstanding performance on both convergence speed and computational precision compared with existing popular algorithms.
