An analysis of program comprehension process from biometrics and activity history
| Project/Area Number |
16K00114
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Research Field |
Software
|
|---|
| Research Institution | Nara National College of Technology |
|---|
Principal Investigator |
Uwano Hidetake 奈良工業高等専門学校, 情報工学科, 准教授 (70550094)
|
|---|
| Project Period (FY) |
2016-04-01 – 2021-03-31
|
| Project Status |
Completed (Fiscal Year 2020)
|
| Budget Amount *help |
¥4,940,000 (Direct Cost: ¥3,800,000、Indirect Cost: ¥1,140,000)
Fiscal Year 2020: ¥520,000 (Direct Cost: ¥400,000、Indirect Cost: ¥120,000)
Fiscal Year 2019: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2018: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2017: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2016: ¥2,470,000 (Direct Cost: ¥1,900,000、Indirect Cost: ¥570,000)
|
|---|
| Keywords | プログラム理解 / 生体計測 / 脳波 / 脳活動 / 視線移動 / 機械学習 / ヒューマンファクター / 視線 |
|---|
| Outline of Final Research Achievements |
The author analyzed eye movements and brain activity during program comprehensions, such as source code reading and design document reading. In the experiment, participants were given a task to estimate the implementation strategy that realizes the specified requirement, a task to understand the program's operation based on the source code and the design document, and a task to judge the presence/absence of failures. During each task, the authors recorded brain waves and eye movements.
As the result of four experiments shows that the power spectrum of alpha and beta waves differs when a programmer succeeds in estimating implementation strategy, understood a program operation, and determines the program contains the failure or not. Also, the authors found that the success/failure of program comprehension can estimate with high accuracy by machine learning that uses time-series changes of alpha wave and eye movement toward source code as features.
|
| Academic Significance and Societal Importance of the Research Achievements |
非侵襲で，作業者の訓練を必要とせず，開発者の理解過程を計測できる脳活動計測と視線計測の組み合わせは，プログラミング作業を構成する知的活動をより詳細に理解することで，開発支援手法や支援ツール，教育法の開発に役立てることができる．また，機械学習によってリアルタイムな状態の推定が可能になれば，開発者の作業を妨害しないタイミングで適切な支援を行う手法の開発も可能になると考えられる．
|
Report
(6 results)
Research Products
(11 results)
