Course details
(1) General
Faculty | Engineering | ||
Department | Electrical and Computer Engineering | ||
Education level | Postgraduate / Master of Science | ||
Course code | E4 | Semester | 2 |
Course title | Data Mining | ||
Independent teaching activities | Hours per week | ECTS | |
Lectures | 2 | ||
Practice | 3 | ||
Total | 5 | 4 | |
Coursetype | General setting course, skills development | ||
Prerequisite courses |
|
||
Teaching and assessment language | English | ||
Course URL | https://elearning.auth.gr/course/view.php?id=16279 |
(2) Learning outcomes
Objective
The course aims to introduce students to the knowledge discovery process with a focus on data mining/ machine learning techniques. Within the context of the course the following concepts will be discussed and elaborated: data mining principles (data mining), supervised machine learning techniques (prediction and characterization – classification), unsupervised machine learning techniques (grouping and aggregation – clustering), anomaly detection (outlier analysis).
Knowledge and Capacities
Upon successfully completing this course, students will be familiar with:
- Know the basic principles of data mining theory and the main application domains
- Understand the fundamental data mining techniques
- Apply well-known machine learning algorithms to health-related pilot problems
- Assess the performance of algorithms on a given problem and given requirements
- Formulate and answer data mining hypotheses
Capacities
The course participants upon completion will be able to:
- Query big data infrastructures
- Visualize and (pre)process big data collections
- Understand the fundamental machine learning techniques and algorithms
- Apply machine learning techniques (classification, clustering, regression analysis, outlier/deviation detection) to pilot problems
- Select the most efficient algorithm, based on problem requirements
Design the methodology for big data analysis problems of medium complexity
(3) Course contents
- 1. Introduction to Data Mining/Machine Learning:
– Definitions Examples Application areas
– Data Exploration
2. Data Preprocessing
3. Data mining/machine learning techniques (Part I): Classification
– Overview
– Definitions
– Algorithms
4. Data mining/machine learning techniques (Part II): Clustering
– Overview
– Definitions
– Algorithms
5. Advanced Data Mining Topics:
– Dimensionality reduction
– Ensemble methods
– Outlier Analysis
(4) Teaching and learning methods – evaluation
Teaching methods | Face to face Distance learning |
|
Use of information and communication technologies (ICT) |
|
|
Module structure | Work Hours per Semester | Activity |
Lectures | 30 | |
Exercises (Quiz) | 15 | |
Exercises (Online discussion fora) | 15 | |
Exercises (Study relevant papers) | 10 | |
Quiz preparatory work | 60 | |
Overall work for the course | 130 | |
Assessment Methods |
1. An assessment on three online quizzes (Basic Classification - 30%, Advanced Classification / Preprocessing – 30%, Clustering - 30%) 2. Participation at the course forum (10%) The final mark is the sum of 1. plus 2. |
(5) Recommended Bibliography
-Recommended Bibliography:
- Practical Machine Learning in R, K. Chatzidimitriou et al., Leanpub publishing, 2021.
- Introduction to Data mining, P. Tan, M. Steinbach & V. Kumar, Addison Wesley, 2005.
- Data Mining; Concepts and Techniques, 2nd edition, J. Han and M. Kamber, Morgan Kaufmann, 2006.