https://pure.aber.ac.uk/portal/files/73231/FS-PSO.pdf

Feature selection based on rough sets and particle swarm optimization

Topological approaches to covering rough sets

http://www.yuhuaqian.net/Cms_Data/Contents/SXU_YHQ/Folders/JournalPapers/~contents/KD22X6U6AUY584JT/Positive%20approximation-an%20accelerator%20for%20attribute%20reduction%20in%20rough%20set%20theory.pdf

Positive approximation: An accelerator for attribute reduction in rough set theory

Attribute reduction in decision-theoretic rough set models

Generalized rough sets based on relations

Attribute reduction is an important issue in rough set theory and has already been studied from the algebra viewpoint and information viewpoint of rough set theory respectively. However, the concepts of attribute reduction based on these two different viewpoints are not equivalent to each other. In this paper, we make a comparative study on the quantitative relationship between some basic concepts of rough set theory like attribute reduction, attribute significance and core defined from these two viewpoints. The results show that the relationship between these conceptions from the two viewpoints is rather an inclusion than an equivalence due to the fact that the rough set theory discussed from the information point of view restricts attributes and decision tables more specifically than it does when considered from the algebra point of view. The identity of the two viewpoints will hold in consistent information decision tables only. That is, the algebra viewpoint and information viewpoint are equivalent for a consistent decision table, while different for an inconsistent decision table. The results are significant for the design and development of methods for information reduction.

A Comparative Study of Algebra Viewpoint and Information Viewpoint in Attribute Reduction

In the research of knowledge acquisition based on rough sets theory, attribute reduction is a key problem. Many researchers proposed some algorithms for attribute reduction. Unfortunately, most of them are designed for static data processing. However, many real data are generated dynamically. In this paper, an incremental attribute reduction algorithm is proposed. When new objects are added into a decision information system, a new attribute reduction can be got by this method quickly.

Incremental attribute reduction based on elementary sets

Attribute reduction is an important issue of rough set theory and has already been separately studied in algebra view and information view. However, conceptions of attribute reduction based on the two views are not necessarily equivalent, they are the same only in consistent decision systems. In this paper, we theoretically study the quantitative relation between some basic notions of rough set theory like attribute reduction, attribute significance and attribute core defined in the two views. The results show that the relation between those corresponding conceptions in algebra view and information view is typically inclusion rather than equivalence, and its reason is that information view restricts attributes and systems more specifically than algebra view. The results are necessary and significant for the development and application of attribute reduction methods.

Theoretical study on attribute reduction of rough set theory: comparison of algebra and information views

One main technical means of anti-Spam is to build filters in email transfer route. However, the design of many junk mail filters hasn't made use of the whole security information in an email, which exists mostly in mail header rather than in the text and accessory. In this paper, data mining based on rough sets is introduced to design a new anti-Spam filter. Firstly, by recording and analyzing the header of every collected email sample, we get all necessary original raw data. Next, by selecting and computing features from the original header data, we obtain our decision table including several condition attributes and one decision attribute. Then, a data mining technique based on rough sets, which mainly includes relative reduction and rule generation, is introduced to mine this decision table. And we obtain some useful anti-Spam knowledge from all the email headers. Finally, we have made tests by using our rules to judge different mails. Tests demonstrate that when mining on selected baleful email corpus with specific Spam rate, our anti-Spam filter has high efficiency and high identification rate. By mining email headers, we can find potential security problems of some email systems and cheating methods of Spam senders.© (2003) COPYRIGHT SPIE--The International Society for Optical Engineering. Downloading of the abstract is permitted for personal use only.

New anti-spam filter based on data mining and analysis of email security

Granular computing has been applied in many fields to solve problems or describe problem spaces at different granularities and hierarchies. In this paper, a rule generation algorithm based on granular computing (RGAGC) is developed. RGAGC is a valid method to generate rules from the granule space. Compared with many classic decision tree algorithms, RGAGC generates a single rule granule in each step instead of selecting a suitable attribute. It is a more general algorithm for rule generation, since it could generate rules from the granule space without considering the problem of selecting an attribute according to some measure. On the other hand, in order to improve the performance of rule granule generation, the "false preserving" property of quotient space theory is used as a strategy to control the process of rule granule generation, so that RGAGC could generate rule granules from the granule space quickly. Our simulation experiment results prove that RGAGC is valid.

Yu Wu

Papers

A Comparative Study of Algebra Viewpoint and Information Viewpoint in Attribute Reduction

Incremental attribute reduction based on elementary sets

Theoretical study on attribute reduction of rough set theory: comparison of algebra and information views

New anti-spam filter based on data mining and analysis of email security

A rule generation algorithm based on granular computing