情報科学研究科Graduate School of Computer and Information Sciences
HUI500K1（人間情報学 / Human informatics 500）情報システム特別演習２Ａ、２ＢSpecial Seminar on Information Systems 2A, 2B
馬 建華Ma JIANHUA
授業コードなどClass code etc
| 学部・研究科Faculty/Graduate school | 情報科学研究科Graduate School of Computer and Information Sciences |
| 添付ファイル名Attached documents | |
| 年度Year | 2024 |
| 授業コードClass code | TZ647 |
| 旧授業コードPrevious Class code | |
| 旧科目名Previous Class title | |
| 開講時期Term | |
| 曜日・時限Day/Period | |
| 科目種別Class Type | |
| キャンパスCampus | 小金井 |
| 教室名称Classroom name | 各学部・研究科等の時間割等で確認 |
| 配当年次Grade | |
| 単位数Credit(s) | |
| 備考（履修条件等）Notes | |
| 実務経験のある教員による授業科目Class taught by instructors with practical experience | |
| カテゴリーCategory |
すべて開くShow all
すべて閉じるHide All
Outline (in English)
The course is for students to study data data processing, and make corresponding programs for experimental data including experiment design, data collection, processing and analysis. At least four hours must be spent each week according to university criterion policy. Overall evaluation will be based on research effort (20%), performance (30%) and output (50%).
授業で使用する言語Default language used in class
英語 / English
授業の概要と目的（何を学ぶか）Outline and objectives
This course is for students to study various technologies for data collection and data processing in practical research.
到達目標Goal
Students are expected to master basic approaches and programming skill in processing data from various sensors and apply these techniques in practical applications.
この授業を履修することで学部等のディプロマポリシーに示されたどの能力を習得することができるか（該当授業科目と学位授与方針に明示された学習成果との関連）Which item of the diploma policy will be obtained by taking this class?
ディプロマポリシーのうち、「DP3」と「DP4」に関連
授業で使用する言語Default language used in class
英語 / English
授業の進め方と方法Method(s)（学期の途中で変更になる場合には、別途提示します。 /If the Method(s) is changed, we will announce the details of any changes. ）
Main sensor-based data collection technologies will be first introduced, then detailed experiment design, device preparation, and various data processing techniques will be applied and implemented. Students' problems and next improvements will be given in class.
アクティブラーニング（グループディスカッション、ディベート等）の実施Active learning in class (Group discussion, Debate.etc.)
あり / Yes
フィールドワーク（学外での実習等）の実施Fieldwork in class
なし / No
授業計画Schedule
授業形態/methods of teaching：対面/face to face
※各回の授業形態は予定です。教員の指示に従ってください。
1[対面/face to face]：Introduction
General review about data collection and processing
2[対面/face to face]：Experiment Design
Design of experiments for data collection
3[対面/face to face]：Wearable Devices
Preparation of wearable devices used in experiment
4[対面/face to face]：Monitoring Devices
Preparation of monitoring devices used in experiment
5[対面/face to face]：Experiment Environment Setting
Preparation of experimental environment
6[対面/face to face]：Experiment Environment Testing
Test of experimental environment
7[対面/face to face]：Data Collection
Soring data collected from experiments
8[対面/face to face]：Data Cleansing
Cleansing data collected from experiments
9[対面/face to face]：Data Preprocessing
Data normalization, segmentation and partition
10[対面/face to face]：Data Correlation
Data correlation analyses
11[対面/face to face]：Time Feature Extraction
Feature extraction in time domain
12[対面/face to face]：Frequency Feature Extraction
Feature extraction in frequency domain
13[対面/face to face]：Data Processing
Machine learning based data processing
14[対面/face to face]：Review
Final report, presentation and discuss
授業時間外の学習（準備学習・復習・宿題等）Work to be done outside of class (preparation, etc.)
Design and conduct experiments for data acquisition from sensors especially radar, analyze these data, and prepare reports. At least four hours must be spent each week according to university criterion policy.
テキスト（教科書）Textbooks
No
参考書References
Provided by this instructor.
成績評価の方法と基準Grading criteria
Research effort (20%), performance (30%) and output (50%).
学生の意見等からの気づきChanges following student comments
N/A