Location:Home > Engineering science > Computer Science > Applied Computer Technology > Research on Knowledge Discovery Methods Based on Rough Set
Details
Name

Research on Knowledge Discovery Methods Based on Rough Set

Downloads: []
Author
Tutor: LiuDaYou
School: Jilin University
Course: Applied Computer Technology
Keywords: Knowledge Discovery,Rough Sets,Statistical relational learning,Containing the se
CLC: TP182
Type: PhD thesis
Year:  2006
Facebook Google+ Email Gmail Evernote LinkedIn Twitter Addthis

not access Image Error Other errors

Abstract:
Knowledge Discovery in Database (KDD) is the non-trivial extraction of implicit, unknown, and potentially useful information from data. Rough Set (RS) developed by Z. Pawlak in 1982 is one of the KDD methods. RS approximates inexact concepts using known knowledge or information to deal with vagueness and uncertainty in data analysis, while preliminary or additional information about data is not necessary. In recently two decades, RS has been successfully applied in many areas, such as machine learning, knowledge acquisition, decision analysis, knowledge discovery, expert system and pattern recognition, and becomes a highlight in the computer science. Data in the real world are always incomplete, ordered, uncertain, and multiple relational with each other. KDD methods based on Rough Set have academic and practical advantage while dealing with these kinds of data.Currently the KDD research on uncertain data is the emphases and difficulty. In this thesis, we conduct research on KDD methods for uncertain data using Rough Sets. The research work on Rough Sets and Statistical Relational Learning (SRL) is overviewed. We study data mining methods based on Containing Order Rough Set (CORS), extended relation models facing incomplete data and Statistical Relational Learning methods combined with RS, taking ordered data, incomplete data and multiple relational data as objects. Hence the thesis designs and realizes KDD prototype system based on RS.The main contributions and results included in the thesis are as follows:Firstly, the thesis gives the overview of state of arts in Rough Sets and Statistical Relational Learning.The main works include: introducing the basic theory, background and state of arts of RS, analyzing the feasibility and advantages of RS dealing with uncertainty, introducing the concepts, methods and applications of SRL, and the research on SRL based on RS, proposing a classification method of SRL, introducing some basic theories related to RS and SRL, such as data mining and Inductive Logic Programming (ILP). All the further research is based on these
Dissertation URL:
Related Dissertations
Last updated
Sponsored Links
Home |About Us| Contact Us| Feedback| Privacy | copyright | Back to top