Close
READ ME --> This is a "vanilla plain" jqModal window. Behavior and appeareance extend far beyond this. The demonstrations on this page will show off a few possibilites. I recommend walking through each one to get an understanding of jqModal before using it.

You can view the sourcecode of examples by clicking the Javascript, CSS, and HTML tabs. Be sure to checkout the documentation too!

NOTE; You can close windows by clicking the tinted background known as the "overlay". Clicking the overlay will have no effect if the "modal" parameter is passed, or if the overlay is disabled.
Syllabus

Infomation of Course

Program Master/Doctorate [석/박사과정] Course Type Elective(Graduate) [ 선택(석/박사) ]
Course Code 31.801 Course No IE801
Section D English English
L:L:C(AU) 3:0:3.0(0) Exam time
(classroom)
- Thu: 13:00~15:45
()
Course Title Special Topics in Industrial Engineering II<Sensor Data Science> [ 산업공학특수논제Ⅱ<센서 데이터 사이언스> ]
Class time
(classroom)
Tue: 14:30~16:00 / (E2)Industrial Engineering & Management Bldg. [ (E2)산업경영학동 ] (1122)
Thu: 14:30~16:00 / (E2)Industrial Engineering & Management Bldg. [ (E2)산업경영학동 ] (1122)
Notice Code Share KSE801A

Information of Professor

Name 이의진(Lee, Uichin)
Department 산업및시스템공학과(Department of Industrial & Systems Engineering)
Phone 042-350-1616
E-Mail uclee@kaist.ac.kr

Plan of Lecture

Syllabus File KSE801A_IE801D_ Sensor Data Science Fall 2019.pdf
Syllabus URL
Summary of Lecture The goal of this course is to learn the basics of how to use sensor data for designing intelligent mobile and IoT services. The course covers the entire process of sensor data science: data collection, pre-processing, feature extraction, and machine learning modeling. Mobile and wearable sensors will be mainly used, and the types of sensor data covered include motion (e.g., vibration/acceleration, GPS), physiological signals (e.g., heart rate, skin temperature), and interaction data (e.g., app usage). Students will learn the basic digital signal processing and feature extraction techniques. Basic machine learning techniques (e.g., clustering, supervised learning, time-series learning, and deep learning) will be reviewed, and students will master these techniques with in-class practices with Google Co-lab (or Jupyter Notebook). A final project will help students to apply the techniques learned in the class to solve real-world sensor data science studies. A large-scale mobile/wearable dataset collected from KAIST will be used for the final project (e.g., personality identification, mood classification).
Material for Teaching Machine Learning for the Quantified Self: On the Art of Learning from Sensory Data,
by Mark Hoogendoorn, Burkhardt Funk (2018) Springer
https://www.amazon.com/Machine-Learning-Quantified-Self-Monographs/dp/3319663070
Evaluation Criteria Participation (10%)
Critique (10%)
Homework (20%)
Exam (20%)
Project (40%)
Lecture Schedule Week 1 Introduction & Paradigm
9/3 T Introduction to Sensor Data Science
9/5 R Sensor Data Science Paradigm: Sensing & Analysis & Actuation

Week 2 Sensor Data Science Processes
9/10 T Overview of Sensor Data Science Processes
9/12 R Holiday

Week 3 Sensor-based Intelligent Computing + Sensor Data Basics
9/17 T Sensor-based Intelligent Computing
9/19 R Basics of Sensory Data & Setup (MLQS Chapter 2)

Week 4 Sensor Data Pre-processing
9/24 T Handling Noise and Missing Values in Sensory Data (MLQS Chapter 3)
9/26 T Dimension Reduction (MLQS Chapter 3): Principal Component Analysis (PCA) + Autoencoder

Week 5 DSP Basics
10/1 T Digital Signal Processing Basics I (DSP Chapter X)
10/3 R Holiday

Week 6 DSP Basics + Feature Eng.
10/8 T Digital Signal Processing Basics II (DSP Chapter X)
10/10 T Feature Engineering based on Sensory Data I (MLQS Chapter 4)

Week 7 10/14-18 Mid-term

Week 8 Feature Eng. + Supervised Learning
10/22 T Feature Engineering based on Sensory Data II
10/24 R Learning Based on Sensory Data: Supervised Learning Basics (MLQS Chapter 6)

Week 9 KAIST SuggestBot Dataset Challenge (Term Project Topics)
10/29 T Sensor Data Applications: Mental Health I (Emotion)
10/31 R Sensor Data Applications: Context-Aware Computing I (Personality)

Week 10 Supervised Learning Practices
11/5 T Learning Based on Sensory Data: Supervised Learning (Practice I)
11/7 R Learning Based on Sensory Data: Supervised Learning (Practice II)

Week 11 Supervised Learning (Time Series)
11/5 T Learning Based on Sensory Data: Time Series Learning I (MLQS Chapter 7)
11/7 R Learning Based on Sensory Data: Time Series Learning II

Week 12 Unsupervised Learning + Interactive/Active Machine Learning
11/19 T Learning Based on Sensory Data: Clustering Basics (MLQS Chapter 5)
11/21 R Learning Based on Sensory Data: Interactive/Active Machine Learning

Week 13 Sensor Data Applications
11/26 T Sensor Data Applications: Mental Health II
11/28 R Sensor Data Applications: Activity Recognition

Week 14 Sensor Data Applications
12/3 T Sensor Data Applications: Condition-based Maintenance & Structural Health Monitoring
12/5 R Sensor Data Applications: Context-Aware Computing II

Week 15 Final Presentation

Memo