| Project/Area Number |
18K11396
|
|---|
| 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 | Tokyo Denki University (2022-2023)
Kyoto Institute of Technology (2018-2021) |
|---|
Principal Investigator |
Yamamoto Keiko 東京電機大学, システム デザイン 工学部, 准教授 (10585756)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
金谷 一朗 長崎大学, 情報データ科学部, 教授 (50314555)
|
|---|
| Project Period (FY) |
2018-04-01 – 2024-03-31
|
| Project Status |
Completed (Fiscal Year 2023)
|
| Budget Amount *help |
¥4,160,000 (Direct Cost: ¥3,200,000、Indirect Cost: ¥960,000)
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)
Fiscal Year 2018: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
|
|---|
| Keywords | IoT / 子ども / 創作活動 / 見護り / 発達支援 / お絵描き |
|---|
| Outline of Final Research Achievements |
Children develop both mentally and physically through a variety of play, but the degree of development differs from one child to another. In this project, we proposed a method of estimating children's developmental stages through machine learning by measuring in real time which toys children are playing with and how they are playing with them, using sensors and other devices installed in toys. We implemented a ball type and a pen-holder type devices, and confirmed that we could estimate about 70% of the developmental stages of children's play. Although there is still room for improvement in accuracy, we believe that the accuracy is sufficient for practical use because children's play has a high degree of freedom and it is important to make judgments based on multiple factors. However, it remains to be verified whether the same level of accuracy can be achieved in actual play by young children.
|
| Academic Significance and Societal Importance of the Research Achievements |
子どもは多様な遊びを行うことで心身ともに成長していくが，その発達の進度は個々で異なっており，保護者や保育者が適切に見護ることが必要である．しかし従来のカメラや身体装着型デバイスによるセンシングでは，見護りのために過度の制限を与えることとなり，子どもの活動意欲を奪ってしまう可能性がある．これに対し本研究課題では，子どもが遊ぶときに使用するおもちゃ自体にセンサと無線通信デバイスを仕込み，子どもがどのおもちゃでどのように遊んでいるかをリアルタイムに計測し，それらの計測データから機械学習によって子どもの発達度を推定する手法を提案し，個々の子どもの適切な見護りと支援へ適用できる可能性があることを示した．
|
