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 2021-09-03 13:35
Convolutional Radio Modulation Recognition Networks with Attention Models in Wireless Systems
Haohui Jia, Na Chen, Minoru Okada (NAIST)
Abstract (in Japanese) (See Japanese page) 
(in English) In modern wireless systems, deep learning (DL) shows promising performance for wireless signal processing. DL model driven communication system is able to recognize the class of modulation signals as a DL training process, such as convolutional neural network (CNN), without any expert knowledge of underlying channel models. However, the performance of radio recognition based on CNN architecture is sensitive, unreliable and slow training convergence due to the noise interference. In this paper, we introduce a learned attention model into the radio domain for modulation recognition by employing the transformer networks and CNN-based pretreatment to extract the premier feature as input of transformer networks. This attention model allows the network to focus on the characteristics of the radio signal itself without expert knowledge of the signal structure for classification. Using this architecture, we develop a highly reliable modulation recognition under the low signal to noise ratio (SNR) over the wireless communication system.
Keyword (in Japanese) (See Japanese page) 
(in English) Wireless Communication / Deep Learning / Convolutional Neural Network / Self-attention / Transformer / / /  
Reference Info. ITE Tech. Rep., vol. 45, no. 24, BCT2021-35, pp. 1-4, Sept. 2021.
Paper # BCT2021-35 
Date of Issue 2021-08-27 (BCT) 
ISSN Print edition: ISSN 1342-6893  Online edition: ISSN 2424-1970
Download PDF

Conference Information
Committee BCT IEEE-BT  
Conference Date 2021-09-03 - 2021-09-03 
Place (in Japanese) (See Japanese page) 
Place (in English) Online 
Topics (in Japanese) (See Japanese page) 
Topics (in English) Mobile systems, etc 
Paper Information
Registration To BCT 
Conference Code 2021-09-BCT-BT 
Language English 
Title (in Japanese) (See Japanese page) 
Sub Title (in Japanese) (See Japanese page) 
Title (in English) Convolutional Radio Modulation Recognition Networks with Attention Models in Wireless Systems 
Sub Title (in English)  
Keyword(1) Wireless Communication  
Keyword(2) Deep Learning  
Keyword(3) Convolutional Neural Network  
Keyword(4) Self-attention  
Keyword(5) Transformer  
1st Author's Name Haohui Jia  
1st Author's Affiliation Nara Institute of Science and Technology (NAIST)
2nd Author's Name Na Chen  
2nd Author's Affiliation Nara Institute of Science and Technology (NAIST)
3rd Author's Name Minoru Okada  
3rd Author's Affiliation Nara Institute of Science and Technology (NAIST)
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 2021-09-03 13:35:00 
Presentation Time 20 
Registration for BCT 
Paper # ITE-BCT2021-35 
Volume (vol) ITE-45 
Number (no) no.24 
Page pp.1-4 
#Pages ITE-4 
Date of Issue ITE-BCT-2021-08-27 

[Return to Top Page]

[Return to ITE Web Page]

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