Smarter eyewear-using commercial EOG glasses for activity recognition

Shoya Ishimaru, Yuji Uema, Kai Steven Kunze, Koichi Kise, Katsuma Tanaka, Masahiko Inami

研究成果: Conference contribution

24 引用 (Scopus)

抄録

Smart eyewear computing is a relatively new subcategory in ubiquitous computing research, which has enormous potential. In this paper we present a first evaluation of soon commercially available Electrooculography (EOG) glasses (J!NS MEME) for the use in activity recognition. We discuss the potential of EOG glasses and other smart eye-wear. Afterwards, we show a first signal level assessment of MEME, and present a classification task using the glasses. We are able to distinguish of 4 activities for 2 users ( typing, reading, eating and talking) using the sensor data (EOG and acceleration) from the glasses with an accuracy of 70 % for 6 sec. windows and up to 100 % for a 1 minute majority decision. The classification is done user-independent. The results encourage us to further explore the EOG glasses as platform for more complex, real-life activity recognition systems.

元の言語English
ホスト出版物のタイトルUbiComp 2014 - Adjunct Proceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing
出版者Association for Computing Machinery, Inc
ページ239-242
ページ数4
ISBN(印刷物)9781450330473
DOI
出版物ステータスPublished - 2014
外部発表Yes
イベント2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing, UbiComp 2014 - Seattle, United States
継続期間: 2014 9 132014 9 17

Other

Other2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing, UbiComp 2014
United States
Seattle
期間14/9/1314/9/17

Fingerprint

Electrooculography
Glass
Ubiquitous computing
Wear of materials
Sensors

ASJC Scopus subject areas

  • Software

これを引用

Ishimaru, S., Uema, Y., Kunze, K. S., Kise, K., Tanaka, K., & Inami, M. (2014). Smarter eyewear-using commercial EOG glasses for activity recognition. : UbiComp 2014 - Adjunct Proceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing (pp. 239-242). Association for Computing Machinery, Inc. https://doi.org/10.1145/2638728.2638795

Smarter eyewear-using commercial EOG glasses for activity recognition. / Ishimaru, Shoya; Uema, Yuji; Kunze, Kai Steven; Kise, Koichi; Tanaka, Katsuma; Inami, Masahiko.

UbiComp 2014 - Adjunct Proceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing. Association for Computing Machinery, Inc, 2014. p. 239-242.

研究成果: Conference contribution

Ishimaru, S, Uema, Y, Kunze, KS, Kise, K, Tanaka, K & Inami, M 2014, Smarter eyewear-using commercial EOG glasses for activity recognition. : UbiComp 2014 - Adjunct Proceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing. Association for Computing Machinery, Inc, pp. 239-242, 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing, UbiComp 2014, Seattle, United States, 14/9/13. https://doi.org/10.1145/2638728.2638795
Ishimaru S, Uema Y, Kunze KS, Kise K, Tanaka K, Inami M. Smarter eyewear-using commercial EOG glasses for activity recognition. : UbiComp 2014 - Adjunct Proceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing. Association for Computing Machinery, Inc. 2014. p. 239-242 https://doi.org/10.1145/2638728.2638795
Ishimaru, Shoya ; Uema, Yuji ; Kunze, Kai Steven ; Kise, Koichi ; Tanaka, Katsuma ; Inami, Masahiko. / Smarter eyewear-using commercial EOG glasses for activity recognition. UbiComp 2014 - Adjunct Proceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing. Association for Computing Machinery, Inc, 2014. pp. 239-242
@inproceedings{ca6ea6b748b3403ba5ea342622e409e1,
title = "Smarter eyewear-using commercial EOG glasses for activity recognition",
abstract = "Smart eyewear computing is a relatively new subcategory in ubiquitous computing research, which has enormous potential. In this paper we present a first evaluation of soon commercially available Electrooculography (EOG) glasses (J!NS MEME) for the use in activity recognition. We discuss the potential of EOG glasses and other smart eye-wear. Afterwards, we show a first signal level assessment of MEME, and present a classification task using the glasses. We are able to distinguish of 4 activities for 2 users ( typing, reading, eating and talking) using the sensor data (EOG and acceleration) from the glasses with an accuracy of 70 {\%} for 6 sec. windows and up to 100 {\%} for a 1 minute majority decision. The classification is done user-independent. The results encourage us to further explore the EOG glasses as platform for more complex, real-life activity recognition systems.",
keywords = "Activity recognition, Electrooculography, Eye movement analysis, Smart glasses",
author = "Shoya Ishimaru and Yuji Uema and Kunze, {Kai Steven} and Koichi Kise and Katsuma Tanaka and Masahiko Inami",
year = "2014",
doi = "10.1145/2638728.2638795",
language = "English",
isbn = "9781450330473",
pages = "239--242",
booktitle = "UbiComp 2014 - Adjunct Proceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing",
publisher = "Association for Computing Machinery, Inc",

}

TY - GEN

T1 - Smarter eyewear-using commercial EOG glasses for activity recognition

AU - Ishimaru, Shoya

AU - Uema, Yuji

AU - Kunze, Kai Steven

AU - Kise, Koichi

AU - Tanaka, Katsuma

AU - Inami, Masahiko

PY - 2014

Y1 - 2014

N2 - Smart eyewear computing is a relatively new subcategory in ubiquitous computing research, which has enormous potential. In this paper we present a first evaluation of soon commercially available Electrooculography (EOG) glasses (J!NS MEME) for the use in activity recognition. We discuss the potential of EOG glasses and other smart eye-wear. Afterwards, we show a first signal level assessment of MEME, and present a classification task using the glasses. We are able to distinguish of 4 activities for 2 users ( typing, reading, eating and talking) using the sensor data (EOG and acceleration) from the glasses with an accuracy of 70 % for 6 sec. windows and up to 100 % for a 1 minute majority decision. The classification is done user-independent. The results encourage us to further explore the EOG glasses as platform for more complex, real-life activity recognition systems.

AB - Smart eyewear computing is a relatively new subcategory in ubiquitous computing research, which has enormous potential. In this paper we present a first evaluation of soon commercially available Electrooculography (EOG) glasses (J!NS MEME) for the use in activity recognition. We discuss the potential of EOG glasses and other smart eye-wear. Afterwards, we show a first signal level assessment of MEME, and present a classification task using the glasses. We are able to distinguish of 4 activities for 2 users ( typing, reading, eating and talking) using the sensor data (EOG and acceleration) from the glasses with an accuracy of 70 % for 6 sec. windows and up to 100 % for a 1 minute majority decision. The classification is done user-independent. The results encourage us to further explore the EOG glasses as platform for more complex, real-life activity recognition systems.

KW - Activity recognition

KW - Electrooculography

KW - Eye movement analysis

KW - Smart glasses

UR - http://www.scopus.com/inward/record.url?scp=84908672175&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84908672175&partnerID=8YFLogxK

U2 - 10.1145/2638728.2638795

DO - 10.1145/2638728.2638795

M3 - Conference contribution

AN - SCOPUS:84908672175

SN - 9781450330473

SP - 239

EP - 242

BT - UbiComp 2014 - Adjunct Proceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing

PB - Association for Computing Machinery, Inc

ER -