EEC 525 Data Mining Syllabus

ECE 525 Data Mining

Syllabus (Fall 2009)

Instructor:Yongjian Fu	Office: SH 432	Email : y.fu@csuohio.edu
Prerequisites: graduate standing	Credit Hours: 4
Classes : MW 4:00-5:50pm, SH 324	Office Hours: MW 1:00-3:00pm or by appointment
WWW: http://academic.csuohio.edu/fuy/ECE 525

Objective/Description:

This course introduces basic concepts, tasks, methods, and techniques in data mining. The emphasis is on various data mining problems and their solutions. Students will develop an understanding of the data mining process and issues, learn various techniques for data mining, and apply the techniques in solving data mining problems using data mining tools and systems. Students will also be exposed to a sample of data mining applications.

Required Textbook:

Han, J. and Kamber, M., Data Mining: Concepts and Techniques, 2nd Edition, Morgan Kaufmann, 2006 .

Other Materials:

P. Tan, M. Steinbach and V. Kumar, Introduction to Data Mining, Addison Wesley, 2006.
Related papers from various conferences and journals will be provided by the instructor.

Grading:

Assignments:                    30%.
Project:                        30%.
Midterm:                        20%.
Final:                          20%.

90%-100%                        A
87%-89%                         A-
83%-86%                         B+
80%-82%                         B
76%-79%                         B-
60%-75%                         C
0%-59%                          F

There are 3-5 homework assignments.
A group project, which applies the concepts and ideas learned in the class, is required. Details of the project will be given later.
A few quizzes will be given randomly for bonus points, which will be credited to homework assignments.

Course Topics:

Class Date	Topic	Readings
8/24	Introduction	Ch. 1
8/26	Data preprocessing	Ch. 2
8/31	Classification	Ch. 6.1-6.2
9/2-9/9	Decision trees	Ch. 6.3
9/14-9/16	Bayesian	Ch. 6.4
9/21-9/23	Backpropagation	Ch. 6.6
9/28	Rule-based classification	Ch. 6.5
9/30	kNN	Ch. 6.9
10/5	Ensemble and Evaluating	Ch. 6.13-6.14
10/7	Midterm exam
10/14	Clustering	Ch. 7.1-7.3
10/19-10/21	Partitioning	Ch. 7.4
10/26-10/28	Hierarchical clustering	Ch. 7.5
11/2-11/4	Density-based methods	Ch. 7.6
11/9	Cluster evaluation
11/11	Association rule mining	Ch. 5.1
11/16-11/18	Apriori	Ch. 5.2.1-5.2.2
11/23-11/30	FP-growth	Ch. 5.2.3-5.2.4
12/2	Project presentation and demonstration
12/7	Final exam

Course Policies:

Attendance to all classes is required. Each student is responsible for his/her missed classes.
A student who misses two submissions must see the instructor immediately with an explanation.
Homework is due in class on the specified date. Late homework will receive the penalty of 10% per day up to two calendar days. No homework will be accepted two calendar days after the due date.

Discussions on homework are allowed, but all homework must be independent work. Any forms of cheating may cause penalties, from getting an F in the course to academic actions according to the department guidelines and university regulations.The ethics policy of the Electrical and Computer Engineering Department can be found at http://www.csuohio.edu/engineering/ece/docs/Ethics%20Policy.doc.