Programming Report

Graduate School of Information Science

Course: IT440 데이터마이닝 특론, Data Mining, 1st Semester, 2002, Monday

Professor: Hwan-Seung Yong, http://dblab.ewha.ac.kr/hsyong

Goal of this Course

Learn comprehensive coverage of concepts and technique for Data Mining related area and study recent research results through paper working
By doing term project, each student can do personal data mining research project.

Textbook and Slide informations

Textbook: Jiawei Han, Micheline Kamber, Data Mining: Concepts and Techniques, Morgan Kaufmann, 2000.
Lecture Notes: http://www.cs.sfu.ca/~han/DM_Book
Reference information

용환승 역, "객체-관계 DBMS," 이한출판사, 1997년 , 원서: M. Stonebraker, "Object-Relational Database Systems," Morgan-Kaufmann, 1996.
용환승 역, "데이타 마이닝", 도서출판 그린, 1998년, Pieter Adriaans, Dolf Zantinge저, Data Mining, Addison-Wesley Longman, 1996.
Tutorial on High Performance Data Mining
Classification Slide update http://www.cs.ualberta.ca/~zaiane/courses/cmput690/slides/Chapter7/index.htm

Assignments and Evaluation

Report and Term Project: 30%, Paper Presentation: 10 %, Final Exam: 50 %, Attendance and others: 10%

Course Schedule

1st Week: Chap1 Introduction
2nd Week: Chap 1 Introduction
3rd Week: Chap 2 Data Warehouse and OLAP Technology
4th Week: Chap 2 Data Warehouse and OLAP Technology
5th Week: Chap 3 Data Preprocessing
6th Week: Chap 4 Data Mining Primitives
7th Week: Chap 5 Concept Description: Characterization and Comparison
8th Week: Chap 5 Concept Description: Characterization and Comparison
9th Week: Chap 6: Mining Association Rules in Large Databases
11th Week: Chap 7 Classification and Prediction
12th Week: Chap 8: Cluster Analysis
13th Week: Chap 9: Mining Complex Data, Time Series and Text, Web MINING

14th Week: Chap 9: Mining Complex Data, Time Series and Text, Web MINING

15th Week: Term Project Presentation:
16th Week: Final Exam

Every Student should do in this semester

1 Paper Presentation ( PAPER SCHEDULES)

Every student should select one paper in the list and give a presentation once during semester.
Select one paper in the list and send it to me via Mail.
Students should submit presentation slide file before her presentation day.
Paper Proceeding List: 원문 서비스는 ACM/IEEE의 디지털 라이브러리 회원가입 또는 학술정보원 또는 국가과학기술도서관 (http://ndsl.or.kr ) 등의 서비스를 받아서 각자 구할 것.

ACM SIGKDD 2001
ACM Proceedings of the International Conference on Knowledge Capture 2001
IEEE International Conference on Data Mining, 2001
기타 VLDB 2001, SIGMOD 2001 의 논문도 가능함.
3월 18일까지 논문을 1편 정해서 메일로 알려주기 바람. (저자, 제목, 발표지면, 논문 원본을 보냄)
발표자는 발표시 발표자료와 논문 1부를 인쇄하여 제출.

Term Project: Project Information

Data Mining Application Development

Using ORACLE or MS SQL Server etc.
ORACLE 9i Data Mining Package는 오라클 사이트에서 다운로드 사용가능

Microsoft SQL server (Data Mining 기능 포함) 은 120일간 사용가능한 버전 다운로드 가능하니 사용바람.

Schedule of Term Project

4월 28까지, 연구주제를 선정하여 계획서를 메일로 제출한다.

추천 주제

Grid Computing: Grid 컴퓨팅 소프트웨어 설치 및 응용 예제 개발
Wikiwiki Multi Web Authoring System 설치 및 예제 개발, 보완 연구 등

Data Mining (Prediction) Project for SIGKDD Cup Contest (3 students team is possible)

Refer KDnuggets.com or ACM SIGKDD Homepage

XML Database Product http://www.rpbourret.com/xml/XMLDatabaseProds.htm

Select one product and Evaluate using XML Benchmarking: X-Mach1

CLUTO v2.0 - A Clustering Toolkit
Other paper work and implementation work is possible.

DATABASE, XML server related implementation work
Confirm to Professor before starting.