| Presentation | 2021-01-28 Electroencephalogram classification to motor imagery, execution, and observation of right index finger flexion using convolutional neural network Yugo Kuramura, Junya Takemoto, Tomohiko Igasaki, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | We attempted to classify the EEG when the participants performed five tasks related to the right index finger flexion: kinesthetic motor imagery, visual motor imagery, no motor imagery, motor execution, and motor observation. We employed a convolutional neural network (CNN) as a classifier and compared the classification accuracy of the "batch CNN," which classifies five tasks with a single CNN, and the "segmented CNN," which combined ten CNNs that classify two tasks each. We also compared the classification accuracy when using EEGs of all nineteen sites as input data to the CNNs and using EEGs of four sites closely related to motor execution and motor observation of the index finger. As a result, for the batch CNN, we found that the classification accuracies using EEGs of nineteen and four sites were 48.2±5.9% and 46.6±6.9%, respectively. On the other hand, 52.8±9.7% and 47.5±9.4% of classification accuracies were found for the segmented CNN using EEGs of nineteen and four sites, respectively. These results suggest the effectiveness of segmented CNN using EEGs of nineteen sites as input data for classifying motor imagery, execution, and observation. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | convolutional neural network / motor imagery / motor execution / motor observation / electroencephalogram |
| Paper # | MICT2020-24,MBE2020-29 |
| Date of Issue | 2021-01-21 (MICT, MBE) |
| Conference Information | |
| Committee | MBE / MICT |
|---|---|
| Conference Date | 2021/1/28(1days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Online |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Takashi Watanabe(Tohoku Univ.) / Eisuke Hanada(Saga Univ.) |
| Vice Chair | Ryuhei Okuno(Setsunan Univ.) / Hirokazu Tanaka(Hiroshima City Univ.) / Daisuke Anzai(Nagoya Inst. of Tech.) |
| Secretary | Ryuhei Okuno(Akita-noken) / Hirokazu Tanaka(Kobe Univ.) / Daisuke Anzai(Yokohama National Univ.) |
| Assistant | Akihiro Karashima(Tohoku Inst. of Tech.) / Jun Akazawa(Meiji Univ. of Integrative Medicine) / Keita Saku(Kyushu Univ.) / Kai Ishida(KISTEC) / Kento Takabayashi(Okayama Pref. Univ.) |
| Paper Information | |
| Registration To | Technical Committee on ME and Bio Cybernetics / Technical Committee on Healthcare and Medical Information Communication Technology |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Electroencephalogram classification to motor imagery, execution, and observation of right index finger flexion using convolutional neural network |
| Sub Title (in English) | |
| Keyword(1) | convolutional neural network |
| Keyword(2) | motor imagery |
| Keyword(3) | motor execution |
| Keyword(4) | motor observation |
| Keyword(5) | electroencephalogram |
| 1st Author's Name | Yugo Kuramura |
| 1st Author's Affiliation | Kumamoto University(Kumamoto Univ.) |
| 2nd Author's Name | Junya Takemoto |
| 2nd Author's Affiliation | Kumamoto University(Kumamoto Univ.) |
| 3rd Author's Name | Tomohiko Igasaki |
| 3rd Author's Affiliation | Kumamoto University(Kumamoto Univ.) |
| Date | 2021-01-28 |
| Paper # | MICT2020-24,MBE2020-29 |
| Volume (vol) | vol.120 |
| Number (no) | MICT-348,MBE-349 |
| Page | pp.pp.17-21(MICT), pp.17-21(MBE), |
| #Pages | 5 |
| Date of Issue | 2021-01-21 (MICT, MBE) |