2022 Fiscal Year Final Research Report
Establishment of Situation-Adaptive Learning Technology Using Shallow Neural Networks and Its Application to Personal Assistance Systems.
| Project/Area Number |
18H03304
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (B)
|
| Allocation Type | Single-year Grants |
|---|
| Section | 一般 |
|---|
| Review Section |
Basic Section 61040:Soft computing-related
|
|---|
| Research Institution | University of Tsukuba |
|---|
Principal Investigator |
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
井澤 淳 筑波大学, システム情報系, 准教授 (20582349)
川崎 真弘 筑波大学, システム情報系, 准教授 (40513370)
堀江 和正 筑波大学, 計算科学研究センター, 助教 (60817112)
|
|---|
| Project Period (FY) |
2018-04-01 – 2023-03-31
|
| Keywords | 浅層学習 / 脳情報処理 / うつバイオマーカー |
|---|
| Outline of Final Research Achievements |
Shallow neural networks are more transparent and require less training data than deep neural networks. Using this advantage, we have developed a method for analyzing brain waves, human movement and behavior, which vary greatly from person to person. Combining this method with experimental techniques, we have applied it to the early detection of depression, the diagnosis of developmental disorders and physical rehabilitation, and have obtained useful results in each case. In particular, the discovery of EEG activity reflecting daily fluctuations in depressive mood, which had previously been completely unknown, is a very significant achievement.
|
| Free Research Field |
脳型情報処理，認知脳科学
|
| Academic Significance and Societal Importance of the Research Achievements |
得られた成果はすべて有意義なものであるが，特にうつ気分を反映する脳波活動の発見は，学術的にも社会的にも大きな意義がある．まず，未知の脳メカニズムの存在を示唆する脳科学における新しい知見であるとともに，脳波解析の手法としても新しくかつ有効である．深層学習では発見できなかった点も重要である．また，これによって安価な脳波計で1分間計測するだけでうつ度が推定可能となり，うつ病の早期発見や治療効果の確認などの応用上も非常に有益である．
|
