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 2022-02-27 14:15
A time-series learning model for estimating the microsaccade segments from fixation eye movement data
Tomoaki Morimoto, Kousuke Nakagaki, Masahito Sakaguchi, Ryoma Kobata, Hisashi Yoshida, Takeshi Kohama (Kindai Univ.)
Abstract (in Japanese) (See Japanese page) 
(in English) In this study, we constructed a time-series learning model with the structure of Bi-LSTM for fixation eye movement data to establish a highly accurate estimation method of the section consisting of the start and endpoints of microsaccades (MS). We evaluated the accuracy of MS prediction by training the original signal of the fixation eye movement, its higher-order derivative signal, and their sum-of-squares signal of each. As a result, the average MS detection rate was about 98.8$pm 2.3$%, and the recall rate and precision for the predicted MS section were about 89.2$pm 7.2$% and 84.8$pm 7.2$%, respectively. In order to examine the interaction of the features, we trained the system using only the features with high contribution derived by Permutation Importance. The result indicates that the higher-order differential signal and its sum-of-squares signal may interact with each other in the MS detection accuracy.
Keyword (in Japanese) (See Japanese page) 
(in English) Eye movements / Fixation eye movement / Microsaccades / Neural networks / Time series learning / / /  
Reference Info. ITE Tech. Rep., vol. 46, no. 7, HI2022-4, pp. 33-38, Feb. 2022.
Paper # HI2022-4 
Date of Issue 2022-02-20 (HI) 
ISSN Print edition: ISSN 1342-6893  Online edition: ISSN 2424-1970
Download PDF

Conference Information
Committee HI IEICE-HIP ASJ-H VRPSY  
Conference Date 2022-02-27 - 2022-02-28 
Place (in Japanese) (See Japanese page) 
Place (in English) on line 
Topics (in Japanese) (See Japanese page) 
Topics (in English)  
Paper Information
Registration To HI 
Conference Code 2022-02-HI-HIP-H-VRPSY 
Language Japanese 
Title (in Japanese) (See Japanese page) 
Sub Title (in Japanese) (See Japanese page) 
Title (in English) A time-series learning model for estimating the microsaccade segments from fixation eye movement data 
Sub Title (in English)  
Keyword(1) Eye movements  
Keyword(2) Fixation eye movement  
Keyword(3) Microsaccades  
Keyword(4) Neural networks  
Keyword(5) Time series learning  
Keyword(6)  
Keyword(7)  
Keyword(8)  
1st Author's Name Tomoaki Morimoto  
1st Author's Affiliation Kindai University (Kindai Univ.)
2nd Author's Name Kousuke Nakagaki  
2nd Author's Affiliation Kindai University (Kindai Univ.)
3rd Author's Name Masahito Sakaguchi  
3rd Author's Affiliation Kindai University (Kindai Univ.)
4th Author's Name Ryoma Kobata  
4th Author's Affiliation Kindai University (Kindai Univ.)
5th Author's Name Hisashi Yoshida  
5th Author's Affiliation Kindai University (Kindai Univ.)
6th Author's Name Takeshi Kohama  
6th Author's Affiliation Kindai University (Kindai Univ.)
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
Date Time 2022-02-27 14:15:00 
Presentation Time 25 
Registration for HI 
Paper # ITE-HI2022-4 
Volume (vol) ITE-46 
Number (no) no.7 
Page pp.33-38 
#Pages ITE-6 
Date of Issue ITE-HI-2022-02-20 


[Return to Top Page]

[Return to ITE Web Page]


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