CS 680B Advanced Topics on Data Mining
This seminar course focuses on advanced techniques and algorithms in data mining and applications of mining complex data. Topics include feature selection, semi-supervised learning, anomaly detection, co-clustering, sequential pattern mining, graph mining, spatiotemporal mining, text and web mining, stream mining, biomedical mining, privacy-preserving mining, and other emerging topics in data mining.
This course is designed for CS graduate students, while graduate students from other departments who are interested in applying data mining to their research can take this course with instructor approval.
|Class Schedule: T TH 10:05 AM - 11:30 AM|
|Telephone: (607) 777-6250|
|Email: lyu AT cs DOT binghamton DOT edu|
|Office Location: N 26, Engineering Building|
|Office Hours: T TH 12:30PM - 1:30PM or by appointment|
CS 535 (Introduction to Data Mining) or instructor approval
This course does not require any textbook, however, the following textbook is highly recommended.
Data Mining: Concepts and Techniques, Jiawei Han and Micheline Kamber, Morgan Kaufmann, 2005 (2nd Edition).
Paper Reading and Presentation:
This is a seminar course that will focus on recent literature on advanced techniques and algorithms in data mining and their applications to problems from a range of different areas, including business, bioinformatics, network security, and Web. After introductory lectures, subsequent classes will focus on research papers.
Each student is required to study recent research papers on the identified topics, and present two papers in class. The presenters will also be responsible for conducting group discussions and answering questions.
Each student will form a group of two to carry out a small scale research project. One type of project can be a comparative study of existing data mining algorithms for a particular data mining task or a particular data type. Another type of project can be development of a new data mining algorithm which improves the existing ones. A third type of project can be novel data mining applications. Each group is required to submit and present in class a project proposal in the beginning of the semester, and submit and present a final project report at the end of the semester.
Final grades will be based on class participation (10%), paper presentation (40%), and project (50%).
Last updated on 01/31/2006