2022 Fiscal Year Final Research Report
Bayesian estimation using external force/stress information for accurate EEG artifact removal
Project/Area Number |
20K11913
|
Research Category |
Grant-in-Aid for Scientific Research (C)
|
Allocation Type | Multi-year Fund |
Section | 一般 |
Review Section |
Basic Section 61020:Human interface and interaction-related
|
Research Institution | National Institute of Information and Communications Technology |
Principal Investigator |
Umehara Hiroaki 国立研究開発法人情報通信研究機構, 脳情報通信融合研究センター脳情報工学研究室, 研究マネージャー (60358942)
|
Project Period (FY) |
2020-04-01 – 2023-03-31
|
Keywords | 脳波計測 / 時系列解析 / ベイズ推定 / ハイパーパラメータ推定 |
Outline of Final Research Achievements |
In order to establish an EEG measurement technique involving physical movement in real-world environments using spring-type dry electrodes that are easy and comfortable to wear, we have developed an estimation method that reduces artifacts caused by the movement of the electrodes by simultaneously measuring the EEG and the accelerations applied to the electrodes. The advantage of this method is that hyperparameters, which are artificially and unavoidably introduced into the estimation model to improve estimation accuracy, can also be estimated by maximum likelihood within the framework of Bayesian estimation. In an EEG measurement experiment during an auditory oddball task while walking, it was shown that the motion artifact can be reduced while retaining the EEG component that appears in the task.
|
Free Research Field |
ベイズ推定
|
Academic Significance and Societal Importance of the Research Achievements |
効果的なリハビリや英語学習等につなげる等の生活の質の向上につながる脳波計測技術が確立され始めている.それに応じて,実験室ではなく生活する環境下でも脳波計測ができるよう,装着が容易で束縛の少ない脳波計も開発されている.しかし,簡単に快適に装着できるようにするため電極等が柔軟構造になっているため,計測時は依然として身体固定を課している.本研究では,身体運動が伴うような状況下で発生してしまう大きなノイズを低減させて,脳波計測の精度を上げる確率モデルを組み確実に推定するという学術的意義の高い手法を確立させ,生活環境下における脳波計測の実現に近づけ,生活の質を高めることに資するという社会的意義を有する.
|