CASIA OpenIR  > 毕业生  > 硕士学位论文
Thesis Advisor王珏
Degree Grantor中国科学院研究生院
Place of Conferral中国科学院自动化研究所
Degree Discipline模式识别与智能系统
Keyword粒子计算 知识粒度 用户需求 Granular Computing Knowledge Granularity User Requirement
Abstract本文的研究是围绕着基于属性序的知识粒度模型展开的。粒子计算方兴未艾,本文 介绍了粒子计算的产生和发展,详细地阐述了基于Rough set理论提出的信息粒度模型。 本文以面向个人的机器学习为导向,基于用户需求建立了新的信息粒度概念,并将之定 义为知识粒度。 本文以Rough Set方法作为理论工具,研究用户从信息系统中所获得的知识的不同 层次或约简的程度,并建立了知识粒度模型。通过对UCI机器学习数据库中的10个样本 集的实验,验证了该模型的有效性。 目前还未呈现成熟的用户需求语言,本文阐述了个性化理论与用户需求之间的关系, 以及数据挖掘领域中的适应性问题。
Other AbstractThere is a rapid growth of interest in so-called granular computing. In this thesis, the origin and development of granular computing is addressed. Information granularity model based on Rough sets is introduced in detail. To develop individual-oriented machine learning, we purpose a concept of knowledge granularity which is based on user requirement. The objective of this thesis is to introduce a knowledge granularity model based on attribute order. Rough sets provides the basis for the approaches to helping users to get different levels of knowledge or different degrees of data reduction, which is the basis of knowledge granularity model. To test the validity and effectivity of the model, several data sets from UCI machine learning database are tested. The results are positive. There is no general model of user requirement. In this thesis, The relation between the theory of personalization and user requirement is discussed at first. Then adaptability in data mining is addressed.
Other Identifier601
Document Type学位论文
Recommended Citation
GB/T 7714
周燕舞. 基于属性序的知识粒度模型[D]. 中国科学院自动化研究所. 中国科学院研究生院,2001.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[周燕舞]'s Articles
Baidu academic
Similar articles in Baidu academic
[周燕舞]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[周燕舞]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.

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