Improving the mathematical input efficiency for mathematical e-assessment systems using an intelligent predictive algorithm
Project/Area Number |
26330413
|
Research Category |
Grant-in-Aid for Scientific Research (C)
|
Allocation Type | Multi-year Fund |
Section | 一般 |
Research Field |
Learning support system
|
Research Institution | Mukogawa Women's University |
Principal Investigator |
Fukui Tetsuo 武庫川女子大学, 生活環境学部, 教授 (70218890)
|
Co-Investigator(Renkei-kenkyūsha) |
NAKAMURA Katsunori 武庫川女子大学, 生活環境学部, 講師 (10413329)
ONO Kentarou 武庫川女子大学, 短期大学部・幼児教育学科, 教授 (50268538)
|
Research Collaborator |
SHIRAI Shizuka
FURUKAWA Akira
SUGINO Ryuuzaburou
|
Project Period (FY) |
2014-04-01 – 2017-03-31
|
Project Status |
Completed (Fiscal Year 2016)
|
Budget Amount *help |
¥4,680,000 (Direct Cost: ¥3,600,000、Indirect Cost: ¥1,080,000)
Fiscal Year 2016: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Fiscal Year 2015: ¥1,690,000 (Direct Cost: ¥1,300,000、Indirect Cost: ¥390,000)
Fiscal Year 2014: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
|
Keywords | 数式入力インタフェース / 知的学習支援システム / 数学eラーニング / 機械学習 / 理数系IT活用教育 / 知的インタフェース / 知的インターフェース / 自然言語処理 / 知的UI |
Outline of Final Research Achievements |
This study aimed to address shortcomings for improving the mathematical input efficiency for mathematical e-assessment systems. We have proposed a predictive algorithm in terms of a perceptron machine learning and developed an intelligent mathematical input user interface (UI), named MathTOUCH, by implementing such the algorithm. We examined the prediction accuracy using a dataset of general 4,000 mathematical formulae from five volumes of a mathematics textbook. The results showed that the accuracy of top ten ranking with our proposed algorithms achieved 85.2%. Finally, we conducted two experiments, i.e. a performance survey and an eight-week learning experiment, to evaluate the efficacy of MathTOUCH implementing STACK e-assessment system. As a result, we have shown that MathTOUCH enabled participants to enter mathematical expressions approximately 1.2 to 1.6 times faster than the standard interfaces and had a high level of user satisfaction in regards to mathematics input usability.
|
Report
(4 results)
Research Products
(27 results)