Site Search
Computer Science

Photos

Windsor WaterfrontWindsor Waterfront Park
Windsor Waterfront Park
Arunita Jaekel, Ph.D.Dr. Arunita Jaekel
Dr. Arunita Jaekel
Dr. Ziad Kobti lecturingDr. Ziad Kobti
Dr. Ziad Kobti
Dr. Luis RuedaDr. Luis Rueda
Dr. Luis Rueda
Xiaobu Yuan, Ph.D.Dr. Xiaobu Yuan
Dr. Xiaobu Yuan
Christie Ezeife, Ph.D.Dr. Christie Ezeife
Dr. Christie Ezeife
Dr. Robert KentDr. Robert Kent
Dr. Robert Kent
Alioune Ngom, Ph.D.Dr. Alioune Ngom
Dr. Alioune Ngom
Imran Ahmad, Ph.D.Dr. Imran Ahmad
Dr. Imran Ahmad
Jessica Chen, Ph.D.Dr. Jessica Chen
Dr. Jessica Chen
Robin Gras, Ph.D.Dr. Robin Gras
Dr. Robin Gras
Lambton TowerLambton Tower
Lambton Tower
Dr. Scott GoodwinDr. Scott Goodwin
Dr. Scott Goodwin

A Method for Mining the Frequent Itemsets Based on Kernel Sets and Extendable Sets

Add this event into your calendar using the iCAL format
  • Fri, 11/10/2017 - 11:00am - 12:06pm




ASP – A new efficient method for class-specific feature selection, applied on biological data

Computer Science Colloquium Series
Huy Quang Pham

Date:  Friday, November 10th, 2017
Time: 11:00 am
Location: Chrysler Hall North, G100

Abstract: Frequent itemset (FI) mining is an important task in data mining. They are necessary to induce the association rules which can be used for classification, system recommendation. For a given dataset, the number of FIs is usually very large, thus, mining them directly from data is almost infeasible due to time and memory limitation, especially, when users change the minimum support threshold (minsup), mining them again from scratch is an inappropriate choice. A more effective approach is to mine frequent closed itemsets (FCI) once, and then, use them to query the FIs according to the user’s needs. Furthermore, as minsup increases, there is no need to re-scan the database to obtain the new lattice; instead, we just need to extract the sub-lattice from the existing one. Furthermore, the set of all FCIs can partition all FIs into equivalent subclasses where each subclass is represented by a FCI. This inspires the parallel techniques to mine the FIs. In this study, we introduce a presentation the FIs in each subclass via the term “kernel” and “extendable set”. As a result, given a closed itemset and its maximal closed subsumed itemsets, we can easily and quickly find the itemsets belong to its equivalence class. This approach induces a compact way to store the FIs to deal with memory limitations. Particularly, finding the kernels and extendable sets is much faster than mining the frequent closed itemsets.

Bio: Pham Quang Huy received his Bachelor’s degree in computer science from the University of Dalat, Vietnam, in 2000, and his Master’s degrees in computer science from the Natural Science University of Ho Chi Minh City, in 2005. He is currently a PhD student in Computer Science at the University of Windsor. His research interests are mainly focused on data-mining, machine learning, and pattern recognition, mostly in the fields of closed frequent item-set mining, association rules mining, breast cancer therapy response prediction and drug-target interaction prediction.



csgradinfo@uwindsor.ca
(519)253-3000


See More: