A MIMO Channel Prediction Scheme Based on Multi-Task Learning

被引:2
作者
Li, Jing [1 ]
Sun, DeChun [1 ]
Liu, ZuJun [1 ]
机构
[1] Xidian Univ, Sch Commun Engn, Xian 710071, Peoples R China
基金
中国国家自然科学基金;
关键词
MIMO; Channel prediction; Kronecker model; Multi-task; Spatial correlation; MODEL;
D O I
10.1007/s11277-020-07658-8
中图分类号
TN [电子技术、通信技术];
学科分类号
0809 ;
摘要
This paper proposes a multi-input multi-output (MIMO) channel prediction scheme using multi-task learning algorithm. Based on the spatially correlated MIMO channel Channel State Information (CSI) observations, a multi-task least square support vector machine (MTLS-SVM) is trained, where the CSI prediction for each antenna pair can be modeled as one task and jointly learning between these tasks are implemented. Then the future CSI is predicted by this MTLS-SVM. By using the relatedness of the multiple tasks, the spatial correlations between different antenna pairs can fully be exploited and hence better channel prediction performance can be achieved compared with the single task prediction scheme.
引用
收藏
页码:1869 / 1880
页数:12
相关论文
共 13 条
[1]  
Adeogun R. O., 2017, P 24 INT C TEL ICT M, P1
[2]  
Adeogun RO, 2014, IEEE ICC, P4632, DOI 10.1109/ICC.2014.6884052
[3]  
Adeoti R., 2013, P 4 INT C AFR ASS AG, P1
[4]  
Bhuyan M, 2013, 2013 1ST INTERNATIONAL CONFERENCE ON EMERGING TRENDS AND APPLICATIONS IN COMPUTER SCIENCE (ICETACS), P104, DOI 10.1109/ICETACS.2013.6691404
[5]  
Hjorungnes A., 2016, IEEE SIGN PROC C EUR, P515
[7]  
Kashyap S, 2017, INT CONF ACOUST SPEE, P3554, DOI 10.1109/ICASSP.2017.7952818
[8]   A Stochastic MIMO radio channel model with experimental validation [J].
Kermoal, JP ;
Schumacher, L ;
Pedersen, KI ;
Mogensen, PE ;
Frederiksen, F .
IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS, 2002, 20 (06) :1211-1226
[9]   A Comparison of MIMO Techniques in Downlink Millimeter Wave Cellular Networks With Hybrid Beamforming [J].
Kulkarni, Mandar N. ;
Ghosh, Amitava ;
Andrews, Jeffrey G. .
IEEE TRANSACTIONS ON COMMUNICATIONS, 2016, 64 (05) :1952-1967
[10]   A Multi-Task Learning Framework for Emotion Recognition Using 2D Continuous Space [J].
Xia, Rui ;
Liu, Yang .
IEEE TRANSACTIONS ON AFFECTIVE COMPUTING, 2017, 8 (01) :3-14