IEICE Technical Committee Submission System
Conference Paper's Information
Online Proceedings
[Sign in]
Tech. Rep. Archives
 Go Top Page Go Previous   [Japanese] / [English] 

Paper Abstract and Keywords
Presentation 2019-11-26 14:10
[Invited Lecture] Channel Estimation via Convolutional Neural Network for Massive MIMO with Pilot Contamination
Hiroki Hirose, Tomoaki Ohtsuki (Keio Univ.)
Abstract (in Japanese) (See Japanese page) 
(in English) In massive multiple-input multiple-output (MIMO) based on time division duplex (TDD), a base station (BS) needs accurate estimation of channel state information (CSI) for a user terminal (UT). UTs transmit pilot signals to the BS to estimate the channels between them. Since the propagation environment changes over time, the channel state also changes accordingly. Due to the time-variant channel, the length of the pilot signal is limited and thus the number of orthogonal pilot signals is finite. Therefore, same pilot signals are reused in neighboring cells. For this reason, channel estimation accuracy deteriorates due to the interference from the neighboring cells, which is called pilot contamination. With the minimum mean square error (MMSE) channel estimation, the influence of pilot contamination can be reduced if the covariance matrix of channels for all users is known. However, this matrix is unknown to the BS a priori, and has to be estimated. In this report, we propose a channel estimation method that reduces the influence of pilot contamination by learning a desired channel corresponding to a contaminated signal with a convolutional neural network. We evaluate both the case where timing synchronization mismatches have occurred between the BS and the UTs in another cell, and the case where it is perfectly synchronized. Our computer simulation results show that the proposed method improves the normalized mean square error (NMSE) of the channel compared with the covariance estimation method.
Keyword (in Japanese) (See Japanese page) 
(in English) Massive MIMO / pilot contamination / channel estimation / convolutional neural network / / / /  
Reference Info. IEICE Tech. Rep.
Paper #  
Date of Issue  
ISSN Print edition: ISSN 0913-5685  Online edition: ISSN 2432-6380
Download PDF

Conference Information
Committee RISING  
Conference Date 2019-11-26 - 2019-11-27 
Place (in Japanese) (See Japanese page) 
Place (in English) Fukutake Learning Theater, Hongo Campus, Univ. Tokyo 
Topics (in Japanese) (See Japanese page) 
Topics (in English) Researches on Super-Intelligent Networking, etc. 
Paper Information
Registration To RISING 
Conference Code 2019-11-RISING 
Language Japanese 
Title (in Japanese) (See Japanese page) 
Sub Title (in Japanese) (See Japanese page) 
Title (in English) Channel Estimation via Convolutional Neural Network for Massive MIMO with Pilot Contamination 
Sub Title (in English)  
Keyword(1) Massive MIMO  
Keyword(2) pilot contamination  
Keyword(3) channel estimation  
Keyword(4) convolutional neural network  
1st Author's Name Hiroki Hirose  
1st Author's Affiliation Keio University (Keio Univ.)
2nd Author's Name Tomoaki Ohtsuki  
2nd Author's Affiliation Keio University (Keio Univ.)
3rd Author's Name  
3rd Author's Affiliation ()
4th Author's Name  
4th Author's Affiliation ()
5th Author's Name  
5th Author's Affiliation ()
6th Author's Name  
6th Author's Affiliation ()
7th Author's Name  
7th Author's Affiliation ()
8th Author's Name  
8th Author's Affiliation ()
9th Author's Name  
9th Author's Affiliation ()
10th Author's Name  
10th Author's Affiliation ()
11th Author's Name  
11th Author's Affiliation ()
12th Author's Name  
12th Author's Affiliation ()
13th Author's Name  
13th Author's Affiliation ()
14th Author's Name  
14th Author's Affiliation ()
15th Author's Name  
15th Author's Affiliation ()
16th Author's Name  
16th Author's Affiliation ()
17th Author's Name  
17th Author's Affiliation ()
18th Author's Name  
18th Author's Affiliation ()
19th Author's Name  
19th Author's Affiliation ()
20th Author's Name  
20th Author's Affiliation ()
Date Time 2019-11-26 14:10:00 
Presentation Time 50 
Registration for RISING 
Paper #  
Volume (vol)  
Number (no)  
Date of Issue  

[Return to Top Page]

[Return to IEICE Web Page]

The Institute of Electronics, Information and Communication Engineers (IEICE), Japan