Note: This website is not updated anymore and may contain outdated information. The new website is at

Seminar: Carson Leung, "Tree-Based Frequent Pattern Mining from Uncertain Data," Sept. 24, 2:30 pm, CL418 (Expired)

Title: Tree-Based Frequent Pattern Mining from Uncertain Data
Speaker: Dr. Carson K. Leung, University of Manitoba

Date: September 24
Time: 2:30 p.m. - 3:20 p.m.
Room: CL418


Data mining aims to search for implicit, previously unknown, and potentially useful information that is embedded in the data. Since its introduction, frequent pattern mining (e.g., the mining of frequently purchased products or of frequently co-occurring events) has been the subject of numerous studies. Many mining algorithms developed in these studies find frequent patterns from traditional transaction databases, in which the content of each transaction-namely, items (e.g., commercial products, events, URLs)-is definitely known and precise. For example, by checking a Web log, we know for sure whether a URL is present in (or is absent from) a Web session, indicating whether or not the user has visited certain Websites. However, there are many real-life situations (e.g., secret-ballot vote, laboratory tests, medical diagnosis) in which the content of transactions is uncertain. For example, a physician may highly suspect (but cannot guarantee) that a patient suffers from flu. In this talk, I present tree-based mining algorithms to deal with these situations. The algorithms efficiently find frequent patterns from uncertain data, where each item in the transactions is associated with an existential probability value. Experimental results show the efficiency of these algorithms.

Breaking News

Recent News

Do You Have News for the Department of Computer Science?

  • Please send a plain text version of your posting, which can include URL links, to
To Top of Page