Towards reading trackers in the wild: Detecting reading activities by EOG glasses and deep neural networks

Shoya Ishimaru, Kensuke Hoshika, Koichi Kise, Andreas Dengel, Kai Steven Kunze

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

Reading in real life occurs in a variety of settings. One may read while commuting to work, waiting in a queue or lying on the sofa relaxing. However, most of current activity recognition work focuses on reading in fully controlled experiments. This paper proposes reading detection algorithms that consider such natural readings. The key idea is to record a large amount of data including natural reading habits in real life (more than 980 hours from 7 participants) with commercial electrooculography (EOG) glasses and to use them for deep learning. Our proposed approaches classified controlled reading vs. not reading with 92.2% accuracy on a user-dependent training. However, the classification accuracy decreases to 73.8% on natural reading vs. not reading. The results indicate that there is a strong gap between controlled reading and natural reading, highlighting the need for more robust reading detection algorithms. Copyright held by the owner/author(s).

Original languageEnglish
Title of host publicationUbiComp/ISWC 2017 - Adjunct Proceedings of the 2017 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2017 ACM International Symposium on Wearable Computers
PublisherAssociation for Computing Machinery, Inc
Pages704-711
Number of pages8
ISBN (Electronic)9781450351904
DOIs
Publication statusPublished - 2017 Sep 11
Event2017 ACM International Joint Conference on Pervasive and Ubiquitous Computing and ACM International Symposium on Wearable Computers, UbiComp/ISWC 2017 - Maui, United States
Duration: 2017 Sep 112017 Sep 15

Other

Other2017 ACM International Joint Conference on Pervasive and Ubiquitous Computing and ACM International Symposium on Wearable Computers, UbiComp/ISWC 2017
CountryUnited States
CityMaui
Period17/9/1117/9/15

Fingerprint

Electrooculography
Glass
Experiments
Deep neural networks

Keywords

  • Convolutional neural network
  • Electrooculography
  • Eye movement
  • Quantified self
  • Reading
  • Recurrent neural network

ASJC Scopus subject areas

  • Software
  • Hardware and Architecture
  • Computer Networks and Communications

Cite this

Ishimaru, S., Hoshika, K., Kise, K., Dengel, A., & Kunze, K. S. (2017). Towards reading trackers in the wild: Detecting reading activities by EOG glasses and deep neural networks. In UbiComp/ISWC 2017 - Adjunct Proceedings of the 2017 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2017 ACM International Symposium on Wearable Computers (pp. 704-711). Association for Computing Machinery, Inc. https://doi.org/10.1145/3123024.3129271

Towards reading trackers in the wild : Detecting reading activities by EOG glasses and deep neural networks. / Ishimaru, Shoya; Hoshika, Kensuke; Kise, Koichi; Dengel, Andreas; Kunze, Kai Steven.

UbiComp/ISWC 2017 - Adjunct Proceedings of the 2017 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2017 ACM International Symposium on Wearable Computers. Association for Computing Machinery, Inc, 2017. p. 704-711.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Ishimaru, S, Hoshika, K, Kise, K, Dengel, A & Kunze, KS 2017, Towards reading trackers in the wild: Detecting reading activities by EOG glasses and deep neural networks. in UbiComp/ISWC 2017 - Adjunct Proceedings of the 2017 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2017 ACM International Symposium on Wearable Computers. Association for Computing Machinery, Inc, pp. 704-711, 2017 ACM International Joint Conference on Pervasive and Ubiquitous Computing and ACM International Symposium on Wearable Computers, UbiComp/ISWC 2017, Maui, United States, 17/9/11. https://doi.org/10.1145/3123024.3129271
Ishimaru S, Hoshika K, Kise K, Dengel A, Kunze KS. Towards reading trackers in the wild: Detecting reading activities by EOG glasses and deep neural networks. In UbiComp/ISWC 2017 - Adjunct Proceedings of the 2017 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2017 ACM International Symposium on Wearable Computers. Association for Computing Machinery, Inc. 2017. p. 704-711 https://doi.org/10.1145/3123024.3129271
Ishimaru, Shoya ; Hoshika, Kensuke ; Kise, Koichi ; Dengel, Andreas ; Kunze, Kai Steven. / Towards reading trackers in the wild : Detecting reading activities by EOG glasses and deep neural networks. UbiComp/ISWC 2017 - Adjunct Proceedings of the 2017 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2017 ACM International Symposium on Wearable Computers. Association for Computing Machinery, Inc, 2017. pp. 704-711
@inproceedings{fd8a51d6922e4623862912a1e973ae8d,
title = "Towards reading trackers in the wild: Detecting reading activities by EOG glasses and deep neural networks",
abstract = "Reading in real life occurs in a variety of settings. One may read while commuting to work, waiting in a queue or lying on the sofa relaxing. However, most of current activity recognition work focuses on reading in fully controlled experiments. This paper proposes reading detection algorithms that consider such natural readings. The key idea is to record a large amount of data including natural reading habits in real life (more than 980 hours from 7 participants) with commercial electrooculography (EOG) glasses and to use them for deep learning. Our proposed approaches classified controlled reading vs. not reading with 92.2{\%} accuracy on a user-dependent training. However, the classification accuracy decreases to 73.8{\%} on natural reading vs. not reading. The results indicate that there is a strong gap between controlled reading and natural reading, highlighting the need for more robust reading detection algorithms. Copyright held by the owner/author(s).",
keywords = "Convolutional neural network, Electrooculography, Eye movement, Quantified self, Reading, Recurrent neural network",
author = "Shoya Ishimaru and Kensuke Hoshika and Koichi Kise and Andreas Dengel and Kunze, {Kai Steven}",
year = "2017",
month = "9",
day = "11",
doi = "10.1145/3123024.3129271",
language = "English",
pages = "704--711",
booktitle = "UbiComp/ISWC 2017 - Adjunct Proceedings of the 2017 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2017 ACM International Symposium on Wearable Computers",
publisher = "Association for Computing Machinery, Inc",

}

TY - GEN

T1 - Towards reading trackers in the wild

T2 - Detecting reading activities by EOG glasses and deep neural networks

AU - Ishimaru, Shoya

AU - Hoshika, Kensuke

AU - Kise, Koichi

AU - Dengel, Andreas

AU - Kunze, Kai Steven

PY - 2017/9/11

Y1 - 2017/9/11

N2 - Reading in real life occurs in a variety of settings. One may read while commuting to work, waiting in a queue or lying on the sofa relaxing. However, most of current activity recognition work focuses on reading in fully controlled experiments. This paper proposes reading detection algorithms that consider such natural readings. The key idea is to record a large amount of data including natural reading habits in real life (more than 980 hours from 7 participants) with commercial electrooculography (EOG) glasses and to use them for deep learning. Our proposed approaches classified controlled reading vs. not reading with 92.2% accuracy on a user-dependent training. However, the classification accuracy decreases to 73.8% on natural reading vs. not reading. The results indicate that there is a strong gap between controlled reading and natural reading, highlighting the need for more robust reading detection algorithms. Copyright held by the owner/author(s).

AB - Reading in real life occurs in a variety of settings. One may read while commuting to work, waiting in a queue or lying on the sofa relaxing. However, most of current activity recognition work focuses on reading in fully controlled experiments. This paper proposes reading detection algorithms that consider such natural readings. The key idea is to record a large amount of data including natural reading habits in real life (more than 980 hours from 7 participants) with commercial electrooculography (EOG) glasses and to use them for deep learning. Our proposed approaches classified controlled reading vs. not reading with 92.2% accuracy on a user-dependent training. However, the classification accuracy decreases to 73.8% on natural reading vs. not reading. The results indicate that there is a strong gap between controlled reading and natural reading, highlighting the need for more robust reading detection algorithms. Copyright held by the owner/author(s).

KW - Convolutional neural network

KW - Electrooculography

KW - Eye movement

KW - Quantified self

KW - Reading

KW - Recurrent neural network

UR - http://www.scopus.com/inward/record.url?scp=85030867676&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85030867676&partnerID=8YFLogxK

U2 - 10.1145/3123024.3129271

DO - 10.1145/3123024.3129271

M3 - Conference contribution

AN - SCOPUS:85030867676

SP - 704

EP - 711

BT - UbiComp/ISWC 2017 - Adjunct Proceedings of the 2017 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2017 ACM International Symposium on Wearable Computers

PB - Association for Computing Machinery, Inc

ER -