Development of skill evaluation and skill acquisition support system by using control engineering approaches
Project/Area Number |
16K12760
|
Research Category |
Grant-in-Aid for Challenging Exploratory Research
|
Allocation Type | Multi-year Fund |
Research Field |
Science education
|
Research Institution | Hiroshima University |
Principal Investigator |
Kawada Kazuo 広島大学, 教育学研究科, 准教授 (10300633)
|
Research Collaborator |
Tamai Teruyuki
Yamamoto Toru
Ito Masahiro
Okamoto Katsuya
Shoda Yoshiaki
Hiyama Tsukasa
|
Project Period (FY) |
2016-04-01 – 2019-03-31
|
Project Status |
Completed (Fiscal Year 2018)
|
Budget Amount *help |
¥3,250,000 (Direct Cost: ¥2,500,000、Indirect Cost: ¥750,000)
Fiscal Year 2018: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2017: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2016: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
|
Keywords | 技能評価モデル / 技能獲得支援 / 制御工学的アプローチ / 製図読図能力 / パーツ分類能力 / 掃き掃除能力 / 遺伝的アルゴリズム / 一時遅れ+むだ時間 / 技能評価 / 技能 / 評価 / 一次遅れ+むだ時間 / 学習者モデル / 触角フィードバック / 「一次遅れ+むだ時間」モデル |
Outline of Final Research Achievements |
This research aimed to evaluate MONODUKURI's skill using control engineering approaches and to develop a system for support the acquisition of skill. By using a real-coded genetic algorithm in making the skill evaluation model, it was possible to estimate the skill evaluation model parameters from actual skill data and make individual skill evaluation model. Then, as the skill evaluation model, using the "first-order system + delay time" model and the "exponential function" model (changing the number of trials of the learning curve model used in psychology evaluation to the learning time) were used, and it was made possible to evaluate individual characteristics with three parameters. Using these evaluation, we also developed a support system for the acquiring skill.
|
Academic Significance and Societal Importance of the Research Achievements |
技能を評価した研究は多数あるが,制御工学で用いられる「一次遅れ+むだ時間」モデルのTKLパラメータ,および教育や心理学等で用いられる「指数関数」モデルのパラメータを遺伝的アルゴリズムで少ないデータから個々の技能の評価を行い,技能獲得を支援する事例はなく,新奇な概念である。技能獲得を目指した支援システムを構築する上で,本研究の手法が様々な分野(教育,工学等)で活用されることが期待できる。また,ものづくり技術・技能の伝承にも応用でき,飛躍的進展と大いなる成果が期待される。
|
Report
(4 results)
Research Products
(12 results)