This course introduces the core concept of data science and its applications in the domain of human behavior analysis. Human
behavior data is the data obtained from several sources of human body. Since the human behavior data is very complicated and
noisy, it is difficult to make use of the data by simple statistical analysis techniques. Therefore, this course applies data
science techniques to better understand the data through hands-on experience with data handling and analysis as well as data
interpretation in domain-oriented manner.
The classes will be conducted in hybrid style. As most classes are interactive, you are encouraged to attend face-to-face.
The classes will be conducted in hybrid style. As most classes are interactive, you are encouraged to attend face-to-face.
You are expected to obtain knowledge, understanding, and technical skills related to data science as well as able to apply
it to the analysis of human behavior data.
- The students can explain the core concept of data science pipeline.
- The students can analyze and interpret data related to human behavior.
- The students can explain and discuss about the effective use of data science in the domain of human behavior analysis.
| Class schedule | HW assignments (Including preparation and review of the class.) | Amount of Time Required | |
|---|---|---|---|
| 1． | Introduction to data science and human behavior | Review after class and do assignment | 190minutes |
| 2． | Data science pipeline and tools | Review after class and do assignment | 190minutes |
| 3． | Design and analysis of human experiment | Review after class and do assignment | 190minutes |
| 4． | Data visualization | Review after class and do assignment | 190minutes |
| 5． | Data preprocessing and cleaning | Review after class and do assignment | 190minutes |
| 6． | Explanatory data analysis | Review after class and do assignment | 190minutes |
| 7． | Mid-term presentation and discussion | Preparation for presentation | 160minutes |
| Review after class and do assignment | 60minutes | ||
| 8． | Feature engineering for human behavior data | Review after class and do assignment | 190minutes |
| 9． | Machine learning tools and techniques | Review after class and do assignment | 190minutes |
| 10． | Machine learning modeling and evaluation (1) | Review after class and do assignment | 190minutes |
| 11． | Machine learning modeling and evaluation (2) | Review after class and do assignment | 190minutes |
| 12． | Machine learning modeling and evaluation (3) | Review after class and do assignment | 190minutes |
| 13． | Model interpretation and applications | Review after class and do assignment | 190minutes |
| 14． | Final presentation and discussion | Preparation for presentation | 160minutes |
| Review after class and do assignment | 60minutes | ||
| Total. | - | - | 2720minutes |
| Assignments | Presentations | Total. | |
|---|---|---|---|
| 1. | 10% | 15% | 25% |
| 2. | 10% | 15% | 25% |
| 3. | 10% | 40% | 50% |
| Total. | 30% | 70% | - |
The assignment and presentation scores are given based on the quality of the contents of reports/presentations, the remarks
in the discussions, and the degree of interaction and participation in class activities.
Assignments will contribute 30% of your grade.
Presentations will contribute 70% of your grade.
Those who get at least 60% of the full score will pass this course.
Assignments will contribute 30% of your grade.
Presentations will contribute 70% of your grade.
Those who get at least 60% of the full score will pass this course.
| ways of feedback | specific contents about "Other" |
|---|---|
| The Others | The lecturer will give feedback in class. |
- By appointment.
Please contact me by e-mail: tipporn@shibaura-it.ac.jp
- Course that cultivates a basic problem-solving skills
- Course that cultivates an ability for utilizing knowledge
| Work experience | Work experience and relevance to the course content if applicable |
|---|---|
| N/A | N/A |
Last modified : Sat Sep 09 07:22:17 JST 2023