| Item type |
Symposium(1) |
| 公開日 |
2023-12-20 |
| タイトル |
|
|
タイトル |
Feature Selection of EEG and Heart Rate Variability Indexes for Estimation of Cognitive Function in the Elderly |
| タイトル |
|
|
言語 |
en |
|
タイトル |
Feature Selection of EEG and Heart Rate Variability Indexes for Estimation of Cognitive Function in the Elderly |
| 言語 |
|
|
言語 |
eng |
| 資源タイプ |
|
|
資源タイプ識別子 |
http://purl.org/coar/resource_type/c_5794 |
|
資源タイプ |
conference paper |
| 著者所属 |
|
|
|
Shibaura Institute of Technology |
| 著者所属 |
|
|
|
Shibaura Institute of Technology |
| 著者所属 |
|
|
|
Shibaura Institute of Technology |
| 著者所属(英) |
|
|
|
en |
|
|
Shibaura Institute of Technology |
| 著者所属(英) |
|
|
|
en |
|
|
Shibaura Institute of Technology |
| 著者所属(英) |
|
|
|
en |
|
|
Shibaura Institute of Technology |
| 著者名 |
Kentarou, Kanai
Yuri, Nakagawa
Midori, Sugaya
|
| 著者名(英) |
Kentarou, Kanai
Yuri, Nakagawa
Midori, Sugaya
|
| 論文抄録 |
|
|
内容記述タイプ |
Other |
|
内容記述 |
In recent years, the number of dementia patients has been increasing, and the number of residents in nursing homes has been rising, increasing the burden on nursing care workers. However, the current situation is that the cognitive level of elderly patients is not sufficiently assessed, and thus, caregivers are not able to respond to the patients accordingly. In this study, we aimed to estimate cognitive function by a machine learning model using simple electroencephalograph (EEG) and heart rate monitor data as a simple and objective method of estimating cognitive function, and to evaluate cognitive level using this model. However, there are many features that can be calculated from electroencephalography and heart rate monitors, and it is not clear which features should be machine-learned. Therefore, in this paper, we used feature selection to identify important features for building a model for estimating cognitive function in the elderly. The results showed that the importance of the HRV index was higher when the mutual information content was used, and the importance of the EEG index was higher when the random forest variable importance was used. |
| 論文抄録(英) |
|
|
内容記述タイプ |
Other |
|
内容記述 |
In recent years, the number of dementia patients has been increasing, and the number of residents in nursing homes has been rising, increasing the burden on nursing care workers. However, the current situation is that the cognitive level of elderly patients is not sufficiently assessed, and thus, caregivers are not able to respond to the patients accordingly. In this study, we aimed to estimate cognitive function by a machine learning model using simple electroencephalograph (EEG) and heart rate monitor data as a simple and objective method of estimating cognitive function, and to evaluate cognitive level using this model. However, there are many features that can be calculated from electroencephalography and heart rate monitors, and it is not clear which features should be machine-learned. Therefore, in this paper, we used feature selection to identify important features for building a model for estimating cognitive function in the elderly. The results showed that the importance of the HRV index was higher when the mutual information content was used, and the importance of the EEG index was higher when the random forest variable importance was used. |
| 書誌情報 |
Proceedings of Asia Pacific Conference on Robot IoT System Development and Platform
巻 2023,
p. 9-13,
発行日 2023-12-20
|
| 出版者 |
|
|
言語 |
ja |
|
出版者 |
情報処理学会 |
IPSJ-APRIS2023002.pdf (1.5 MB)
