ITE Technical Group Submission System
Conference Paper's Information
Online Proceedings
[Sign in]
 Go Top Page Go Previous   [Japanese] / [English] 

Paper Abstract and Keywords
Presentation 2023-07-28 11:50
An Evaluation of Neural Network Parameters for Decoding (8,4) and (16,8) Polar Codes
Reona Kumaki, Hiroshi Tsutsui, Takeo Ohgane (Hokkaido Univ.)
Abstract (in Japanese) (See Japanese page) 
(in English) Polar codes are one type of error correction codes.
When operated with a sufficiently long code length, polar codes can achieve communication channel capacity approaching the Shannon limit, and they are adopted for control channels in 5G.
However, when considering small data communications used by IoT devices that do not require high capacity, the error correction capability with shorter code lengths is desired.
In this study, we discuss the variation in code length and the transition of the number of variables concerning the evaluation of neural network parameters required for decoding (8,4) and (16,8) polar codes, aiming to practicalize the decoding method of error correction codes using deep learning.
From the simulation results, it was observed that doubling the code length increases the required number of variables by approximately 10 times, highlighting the importance of accommodating the increase in code length while restraining the growth of network size.
Keyword (in Japanese) (See Japanese page) 
(in English) 5G / Polar codes / deep neural network / small-data communications / / / /  
Reference Info. ITE Tech. Rep., vol. 47, no. 21, BCT2023-61, pp. 49-52, July 2023.
Paper # BCT2023-61 
Date of Issue 2023-07-20 (BCT) 
ISSN Online edition: ISSN 2424-1970
Download PDF

Conference Information
Conference Date 2023-07-27 - 2023-07-28 
Place (in Japanese) (See Japanese page) 
Place (in English) Sapporo Business Innovation Center 
Topics (in Japanese) (See Japanese page) 
Topics (in English) Broadcast Operating, Transmission & Reception, Program creation, Broadcast master control , etc 
Paper Information
Registration To BCT 
Conference Code 2023-07-BCT-BT-HOKKAIDO 
Language Japanese 
Title (in Japanese) (See Japanese page) 
Sub Title (in Japanese) (See Japanese page) 
Title (in English) An Evaluation of Neural Network Parameters for Decoding (8,4) and (16,8) Polar Codes 
Sub Title (in English)  
Keyword(1) 5G  
Keyword(2) Polar codes  
Keyword(3) deep neural network  
Keyword(4) small-data communications  
1st Author's Name Reona Kumaki  
1st Author's Affiliation Hokkaido University (Hokkaido Univ.)
2nd Author's Name Hiroshi Tsutsui  
2nd Author's Affiliation Hokkaido University (Hokkaido Univ.)
3rd Author's Name Takeo Ohgane  
3rd Author's Affiliation Hokkaido University (Hokkaido Univ.)
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 ()
Speaker Author-1 
Date Time 2023-07-28 11:50:00 
Presentation Time 20 minutes 
Registration for BCT 
Paper # BCT2023-61 
Volume (vol) vol.47 
Number (no) no.21 
Page pp.49-52 
Date of Issue 2023-07-20 (BCT) 

[Return to Top Page]

[Return to ITE Web Page]

The Institute of Image Information and Television Engineers (ITE), Japan