| Presentation | 2019-12-19 Experimental Evaluation of Self-supervised Learning for Reading Activity Recognition Shuji Sakamoto, Yoshihiro Yamada, Masakazu Iwamura, Motoi Iwata, Koichi Kise, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | In recent years, reading activities have been analyzed by using eye and head movements. The average and variance value of electrooculogram (EOG), acceleration and angular velocity are often used as the features. However, statistical methods cannot express effective features, and the accuracy cannot be improved. On the other hand, a large amount of labeled data is required to obtain effective features using Deep Learning, but it is generally difficult to obtain such data. To solve these problems, we propose using Self-supervised Learning. High accuracy recognition is expected with a small amount of labeled data. In this paper, we get effective features by classifying the types of transformation applied to EOG, acceleration, and angular velocity. Applied on data from an experiment differentiating four types of reading activities, the proposed method achieves an average accuracy of 57.3%. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Self-supervised Learning / CNN / Reading Activity / JINS MEME |
| Paper # | HIP2019-71 |
| Date of Issue | 2019-12-12 (HIP) |
| Conference Information | |
| Committee | HIP |
|---|---|
| Conference Date | 2019/12/19(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | RIEC, Tohoku University |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Miyuki Kamachi(Kogakuin Univ.) |
| Vice Chair | Shuichi Sakamoto(Tohoku Univ.) / Yuji Wada(Ritsumeikan Univ.) |
| Secretary | Shuichi Sakamoto(NICT) / Yuji Wada(NTT) |
| Assistant | Atsushi Wada(NICT) / Hidetoshi Kanaya(Ritsumeikan Univ.) / Yuki Yamada(Kyushu Univ.) |
| Paper Information | |
| Registration To | Technical Committee on Human Information Processing |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Experimental Evaluation of Self-supervised Learning for Reading Activity Recognition |
| Sub Title (in English) | |
| Keyword(1) | Self-supervised Learning |
| Keyword(2) | CNN |
| Keyword(3) | Reading Activity |
| Keyword(4) | JINS MEME |
| 1st Author's Name | Shuji Sakamoto |
| 1st Author's Affiliation | Osaka Prefecture University(Osaka Prefecture Univ.) |
| 2nd Author's Name | Yoshihiro Yamada |
| 2nd Author's Affiliation | Osaka Prefecture University(Osaka Prefecture Univ.) |
| 3rd Author's Name | Masakazu Iwamura |
| 3rd Author's Affiliation | Osaka Prefecture University(Osaka Prefecture Univ.) |
| 4th Author's Name | Motoi Iwata |
| 4th Author's Affiliation | Osaka Prefecture University(Osaka Prefecture Univ.) |
| 5th Author's Name | Koichi Kise |
| 5th Author's Affiliation | Osaka Prefecture University(Osaka Prefecture Univ.) |
| Date | 2019-12-19 |
| Paper # | HIP2019-71 |
| Volume (vol) | vol.119 |
| Number (no) | HIP-348 |
| Page | pp.pp.35-40(HIP), |
| #Pages | 6 |
| Date of Issue | 2019-12-12 (HIP) |