2022 Fiscal Year Final Research Report
Sensing and Actuation for Accelerating Knowledge I/O by Humans
| Project/Area Number |
20H04213
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (B)
|
| Allocation Type | Single-year Grants |
|---|
| Section | 一般 |
|---|
| Review Section |
Basic Section 61010:Perceptual information processing-related
|
|---|
| Research Institution | Osaka Metropolitan University (2022)
Osaka Prefecture University (2020-2021) |
|---|
Principal Investigator |
Kise Koichi 大阪公立大学, 大学院情報学研究科, 教授 (80224939)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
石丸 翔也 大阪公立大学, 研究推進機構, 客員研究員 (10788730)
岩田 基 大阪公立大学, 大学院情報学研究科, 准教授 (70316008)
|
|---|
| Project Period (FY) |
2020-04-01 – 2023-03-31
|
| Keywords | 知能増強 / Learning Augmentation / Eye tracking / EOG / Accelometer / self-supervised learning / contrastive learning / vocabulometer |
|---|
| Outline of Final Research Achievements |
In this study, we focused on Learning Augmentation as a field of human-centered AI, and developed a system and evaluated experiments to realize it. The results of this study are (1) a proposal for a new vocabulary learning method called Vocabulometer, (2) a proposal for a nudge strategy to facilitate learning using Wordometer, which we have already developed, (3) a proposal for a method to facilitate learning by estimating the learner's confidence using eye trackers and arm movements (4) a deep learning method called Self-Supervised Learning that can accurately estimate reading behavior recognition and confidence even when labeled data is scarce.
|
| Free Research Field |
知能増強、ヒューマンセンシング
|
| Academic Significance and Societal Importance of the Research Achievements |
本研究では、人間の学習をＡＩが助けるという枠組にのっとって、より人間が使いやすく，学習が容易であり，かつ離脱しにくいシステムを目指して研究を行ってきた．研究成果の学術的意義については，以下が挙げられる．(1) In-the-wildの環境で動作するツール群を構築し，有効性を検証した．(2)時系列データに対するself-supervised learningとその関連手法を提案した．一方で社会的意義としては，以下が挙げられる．(1) 作成した学習システムが，実際に学習者のパフォーマンスを改善することを示した．(2) 学習のモチベーションの維持，向上に有効となるナッジ戦略を4種類提案した．
|
