A rough sets based characteristic relation approach for dynamic attribute generalization in data mining

Research output: Contribution to journalArticlepeer-review

Standard

A rough sets based characteristic relation approach for dynamic attribute generalization in data mining. / Li, Tianrui; Ruan, Da; Wets, Geert; Song, Jing; Xu, Yang; Laes, Erik (Peer reviewer).

In: Knowledge-Based Systems, Vol. 20, No. 5, 06.2007, p. 485-494.

Research output: Contribution to journalArticlepeer-review

Author

Li, Tianrui ; Ruan, Da ; Wets, Geert ; Song, Jing ; Xu, Yang ; Laes, Erik. / A rough sets based characteristic relation approach for dynamic attribute generalization in data mining. In: Knowledge-Based Systems. 2007 ; Vol. 20, No. 5. pp. 485-494.

Bibtex - Download

@article{085cfb135883417b8c6e068ca9cb80d9,
title = "A rough sets based characteristic relation approach for dynamic attribute generalization in data mining",
abstract = "Any attribute set in an information system may be evolving in time when new information arrives. Approximations of a concept by rough set theory need updating for data mining or other related tasks. For incremental updating approximations of a concept, methods using the tolerance relation and similarity relation have been previously studied in literature. The characteristic relation-based rough sets approach provides more informative results than the tolerance-and-similarity relation based approach. In this paper, an attribute generalization and its relation to feature selection and feature extraction are firstly discussed. Then, a new approach for incrementally updating approximations of a concept is presented under the characteristic relation-based rough sets. Finally, the pproach of direct computation of rough set approximations and the proposed approach of dynamic maintenance of rough set approximations are employed for performance comparison. An extensive experimental evaluation on a large soybean database from MLC shows that the proposed approach effectively handles a dynamic attribute generalization in data mining.",
keywords = "Rough sets, Knowledge discovery, Data mining, Incomplete information systems",
author = "Tianrui Li and Da Ruan and Geert Wets and Jing Song and Yang Xu and Erik Laes",
note = "Score = 10",
year = "2007",
month = jun,
doi = "10.1016/j.knosys.2007.01.002",
language = "English",
volume = "20",
pages = "485--494",
journal = "Knowledge-Based Systems",
issn = "0950-7051",
publisher = "Elsevier",
number = "5",

}

RIS - Download

TY - JOUR

T1 - A rough sets based characteristic relation approach for dynamic attribute generalization in data mining

AU - Li, Tianrui

AU - Ruan, Da

AU - Wets, Geert

AU - Song, Jing

AU - Xu, Yang

A2 - Laes, Erik

N1 - Score = 10

PY - 2007/6

Y1 - 2007/6

N2 - Any attribute set in an information system may be evolving in time when new information arrives. Approximations of a concept by rough set theory need updating for data mining or other related tasks. For incremental updating approximations of a concept, methods using the tolerance relation and similarity relation have been previously studied in literature. The characteristic relation-based rough sets approach provides more informative results than the tolerance-and-similarity relation based approach. In this paper, an attribute generalization and its relation to feature selection and feature extraction are firstly discussed. Then, a new approach for incrementally updating approximations of a concept is presented under the characteristic relation-based rough sets. Finally, the pproach of direct computation of rough set approximations and the proposed approach of dynamic maintenance of rough set approximations are employed for performance comparison. An extensive experimental evaluation on a large soybean database from MLC shows that the proposed approach effectively handles a dynamic attribute generalization in data mining.

AB - Any attribute set in an information system may be evolving in time when new information arrives. Approximations of a concept by rough set theory need updating for data mining or other related tasks. For incremental updating approximations of a concept, methods using the tolerance relation and similarity relation have been previously studied in literature. The characteristic relation-based rough sets approach provides more informative results than the tolerance-and-similarity relation based approach. In this paper, an attribute generalization and its relation to feature selection and feature extraction are firstly discussed. Then, a new approach for incrementally updating approximations of a concept is presented under the characteristic relation-based rough sets. Finally, the pproach of direct computation of rough set approximations and the proposed approach of dynamic maintenance of rough set approximations are employed for performance comparison. An extensive experimental evaluation on a large soybean database from MLC shows that the proposed approach effectively handles a dynamic attribute generalization in data mining.

KW - Rough sets

KW - Knowledge discovery

KW - Data mining

KW - Incomplete information systems

UR - http://ecm.sckcen.be/OTCS/llisapi.dll/open/ezp_80899

UR - http://knowledgecentre.sckcen.be/so2/bibref/4268

U2 - 10.1016/j.knosys.2007.01.002

DO - 10.1016/j.knosys.2007.01.002

M3 - Article

VL - 20

SP - 485

EP - 494

JO - Knowledge-Based Systems

JF - Knowledge-Based Systems

SN - 0950-7051

IS - 5

ER -

ID: 314054