kumoh national institute of technology
Networked Systems Lab.

NSL Seminar

NSL > Education> NSL Seminar
Deep Learning for Massive MIMO CSI Feedback
By : Rizki Rivai Ginanjar
Date : 2018-09-28
Views : 91

Abstract—In frequency division duplex mode, the downlink chan-
nel state information (CSI) should be sent to the base station through
feedback links so that the potential gains of a massive multiple-
input multiple-output can be exhibited. However, such a transmission
is hindered by excessive feedback overhead. In this letter, we use
deep learning technology to develop CsiNet, a novel CSI sensing and
recovery mechanism that learns to effectively use channel structure
from training samples. CsiNet learns a transformation from CSI
to a near-optimal number of representations (or codewords) and
an inverse transformation from codewords to CSI. We perform
experiments to demonstrate that CsiNet can recover CSI with
significantly improved reconstruction quality compared with existing
compressive sensing (CS)-based methods. Even at excessively low
compression regions where CS-based methods cannot work, CsiNet
retains effective beamforming gain.
Only registered members can view this page.
(Total:679 articles / page:1/68 )
No. Subject By Date Views
 From AI to ML: Category, Industrial Apps., and Tr.. 2019-04-29 46
679  An IoT Unified Access Platform for Heterogeneity Sensi.. ÿ 2019-05-17 3
678  Node Discovery Scheme of DDS for Combat Management Sys.. 2019-05-17 3
677  Task Offloading in UAV-Aided Edge Computing Bit Alloca.. So-Hyang 2019-05-15 2
676  SEER-MCache: A Prefetchable Memory Object Caching Syst.. ڼȭ 2019-05-15 6
675  Reliability Analysis of Distributed Cyber-physical Ene.. Asatilla 2019-05-03 4
674  Performance Enhancement of High-Availability Seamless .. 2019-05-03 13
673  Self-Deployment of Mobile Sensors to Achieve Target Co.. Nwadiugwu Williams P 2019-04-19 5
672  Fog Computing for 5G Tactile Industrial Internet of Th.. Muhammad Rusyadi 2019-04-19 23
671  Performance Analysis of CSMA/CA and PCA for Time Criti.. 2019-04-12 30
670  A Hybrid Computing Solution and Resource Scheduling St.. Esmot Ara Tuli 2019-04-11 9