Please use this identifier to cite or link to this item: http://scholarbank.nus.edu.sg/handle/10635/14405
Title: Effective use of data mining technologies on biological and clinical data
Authors: LIU HUIQING
Keywords: data mining, feature generation, feature selection, classification, gene expression profile, DNA sequence
Issue Date: 26-Oct-2004
Source: LIU HUIQING (2004-10-26). Effective use of data mining technologies on biological and clinical data. ScholarBank@NUS Repository.
Abstract: We apply the data mining techniques of feature generation, feature selection, and feature integration with learning algorithms to tackle the problems of disease phenotype classification and patient survival prediction from gene expression profiles, and the problems of functional sites prediction from DNA sequences. Our main contributions include (1) a new feature selection method for identifying genes relevant to disease phenotype classification and survival status; (2) a new process for patient outcome prediction; and (3) a novel idea of generating feature space for sequence data. All the proposed approaches are tested on a variety of data sets, including public ones and our own extracted ones. The large amount of experimental results achieved demonstrate the effectiveness and robustness of our new methods. Besides, extensive comparisons between our approaches and some widely used technologies in the relevant domains are also addressed.
URI: http://scholarbank.nus.edu.sg/handle/10635/14405
Appears in Collections:Ph.D Theses (Open)

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
LiuHQ.pdf5.76 MBAdobe PDF

OPEN

NoneView/Download

Page view(s)

239
checked on Dec 11, 2017

Download(s)

165
checked on Dec 11, 2017

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.