| Project/Area Number |
19K20420
|
|---|
| Research Category |
Grant-in-Aid for Early-Career Scientists
|
| Allocation Type | Multi-year Fund |
|---|
| Review Section |
Basic Section 62030:Learning support system-related
|
|---|
| Research Institution | University of Fukui |
|---|
Principal Investigator |
|
|---|
| Project Period (FY) |
2019-04-01 – 2023-03-31
|
| Project Status |
Completed (Fiscal Year 2022)
|
| Budget Amount *help |
¥4,160,000 (Direct Cost: ¥3,200,000、Indirect Cost: ¥960,000)
Fiscal Year 2021: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Fiscal Year 2020: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Fiscal Year 2019: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
|
|---|
| Keywords | 行動認識 / 学習支援 / 深層学習 / アンサンブル学習 / 学習効率 / m-Learning / 転移学習 / 確信度推定 / 学習支援システム / コンテキストアウェアネス / m-learning |
|---|
| Outline of Research at the Start |
本研究では，mobile-learningだからこそ実現できる最新の学習支援システムを実現する．特に常日頃から持ち運ばれるデバイスであると言う強みを活かし，次の3機能の実現を目指す．(1)学習者の学習状況と周囲の状況を同時に観測し記録する．(2)学習効率や学習着手率が向上する復習タイミングの推定を実現する．(3)個人差を考慮し，学習者に個人適応する推定を実現する．
|
| Outline of Final Research Achievements |
In this study, we have developed an intelligent self-directed learning support platform that is fully adaptive to the unique needs of each individual. Our research has yielded two key results.
Firstly, we have successfully developed cutting-edge technology that accurately recognizes user activities. By specializing deep learning models to human activity recognition field, we have achieved unprecedented levels of accuracy, paving the way for more advanced and effective intelligent systems.
Secondly, we have uncovered a groundbreaking insight regarding the optimal timing of learning based on user actions. Our research has conclusively demonstrated that learning is more efficient when performed in an environment that allows the user to concentrate and move at the same time, such as on a treadmill, as opposed to stationary environments.
|
| Academic Significance and Societal Importance of the Research Achievements |
本研究で開発した，行動認識技術と，学習支援に向けた新たな知見は様々な面で今後の応用が期待できる．まず，行動認識技術は学習支援のみならず，Society5.0の実現に向けたフィジカル空間の認識手法としての利活用が見込める．例えば，行動のログを自動で記録したり，ユーザの行動に応じて様々な情報提供を行うインタラクティブシステムの開発への応用が見込める．また，学習効果に対する知見は，今後革新的な学習支援システムを実現する際のエビデンスとして活用可能である．暗記学習を行う際にトレッドミルやエクササイズバイクを活用することで，容易に学習効果を高める効果が期待できる．
|
