| 研究課題/領域番号 |
19K12167
|
|---|
| 研究機関 | 東京農工大学 |
|---|
研究代表者 |
Venture Gentiane 東京農工大学, 工学(系)研究科(研究院), 卓越教授 (30538278)
|
|---|
| 研究期間 (年度) |
2019-04-01 – 2022-03-31
|
| キーワード | Machine learning / Human behavior analysis / online teaching |
|---|
| 研究実績の概要 |
Three main tasks were achieved:
1. All the collected data last year are then processed to be analyzed in machine learning algorithms. This resulted in an offline behavior analysis software of students’ behaviors, enabling us to choose the relevant features for the next step.
2. The relevant features found in 1. were used to develop a real-time algorithm to identify the changes in students’ behavior. Again, this is based on an implementation of machine learning algorithm in real-time for classification. We tested several machine learning architecture to find the most relevant one.
3. A mimicking algorithm that allows the robot to reproduce the lecturer behaviors offline to generate easily robot's movement.
|
| 現在までの達成度 (区分) |
現在までの達成度 (区分)
2: おおむね順調に進展している
理由
The research was little impacted by the pandemic as this year it was mainly a task of programming and data analysis.
|
| 今後の研究の推進方策 |
We will now work further on the robotics development for a robot lecturer focusing on important behaviors of the lecturer. The behavior
of the robot will not be pre-programmed but will adaptively change depending on the students’ behavior measurement using the system developed in C. The whole system will then be tested with different teaching styles and different audiences in Japan. Evaluations will be conducted, and statistical analysis of the results between human lecturer and robot lecturer will be compared to assess the validity of the teaching robot.
|
