Presentation | 2023-02-28 Detection of trial reading actions using smartwatches Chisaki Takahashi, Hiroaki Morino, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | It would be useful in many situations if a person's behavior can be detected by sensors to estimate what the person is interested in. For example, if we can obtain information on places in which persons were particularly interested in some items, it can be useful in designing the placement of items to attract their attention. In this paper, we propose a method to detect trial reading actions of a book. More specifically, the methods detects the actions of "picking up the book from the shelf", "trial reading", and "putting it back on the shelf" from a twist of the person’s list using the time sequence of angular rate sensor data that will be obtained by a smartwatch. We assume that the time length of trial reading actions corresponds to the level of his/her interest in the book. Six participants were asked to perform the trial reading actions in the experiment, and the proposed method achieved a recall rate of detection over 80% and F value over 0.65. In this experiment, we found that the method wrongly estimated in some cases the time at which the action changed from picking up the book to starting trial reading. Similarly, in other cases, it misestimated an action of putting the book back on the shelf to a trial reading action. As our future work, we plan to improve detection accuracy by using an algorithm that does not start detecting trial reading actions during it detects that the person’s arm is raising or lowering judging from an acceleration sensor values. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Smartwatch / Level of Interest / Motion Recognition / Angular rate sensor |
Paper # | SeMI2022-109 |
Date of Issue | 2023-02-21 (SeMI) |
Conference Information | |
Committee | SeMI / IPSJ-UBI / IPSJ-MBL |
---|---|
Conference Date | 2023/2/28(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | Koji Yamamoto(Kyoto Univ.) / Jin Nakazawa(Keio University) / Hirozumi Yamaguchi(Osaka University) |
Vice Chair | Kazuya Monden(Hitachi) / Yasunori Owada(NICT) / Shunsuke Saruwatari(Osaka Univ.) |
Secretary | Kazuya Monden(NTT DOCOMO) / Yasunori Owada(Tokyo Univ. of Agri. and Tech.) / Shunsuke Saruwatari(Osaka Univ.) |
Assistant | Yuki Matsuda(NAIST) / Akihito Taya(Aoyama Gakuin Univ.) / Takeshi Hirai(Osaka Univ.) |
Paper Information | |
Registration To | Technical Committee on Sensor Network and Mobile Intelligence / Special Interest Group on Ubiquitous Computing System / Special Interest Group on Mobile Computing and Smart Society System |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Detection of trial reading actions using smartwatches |
Sub Title (in English) | |
Keyword(1) | Smartwatch |
Keyword(2) | Level of Interest |
Keyword(3) | Motion Recognition |
Keyword(4) | Angular rate sensor |
1st Author's Name | Chisaki Takahashi |
1st Author's Affiliation | Shibaura Institute of Technology(SIT) |
2nd Author's Name | Hiroaki Morino |
2nd Author's Affiliation | Shibaura Institute of Technology(SIT) |
Date | 2023-02-28 |
Paper # | SeMI2022-109 |
Volume (vol) | vol.122 |
Number (no) | SeMI-390 |
Page | pp.pp.13-18(SeMI), |
#Pages | 6 |
Date of Issue | 2023-02-21 (SeMI) |