東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

A study on XML querying and mining.

Zhang, Ming.

Linked to FindBook

Google Book

Amazon

博客來

A study on XML querying and mining.

Record Type:	Electronic resources : Monograph/item
Title/Author:	A study on XML querying and mining./
Author:	Zhang, Ming.
Description:	78 p.
Notes:	Source: Masters Abstracts International, Volume: 44-01, page: 0419.
Contained By:	Masters Abstracts International44-01.
Subject:	Computer Science. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=MR04019
ISBN:	9780494040195

A study on XML querying and mining.
Zhang, Ming.

A study on XML querying and mining. - 78 p.

Source: Masters Abstracts International, Volume: 44-01, page: 0419.

Thesis (M.Sc.)--The University of Regina (Canada), 2005.

The eXtensible Markup Language, XML, is a new standard for data representation on the Internet. The semi-structured data model of XML requires new techniques for querying and mining XML data.

ISBN: 9780494040195Subjects--Topical Terms:

626642
Computer Science.

A study on XML querying and mining.
LDR:02663nmm 2200277 4500 001 1821684
005 20061113090129.5
008 130610s2005 eng d
020 $a 9780494040195
035 $a (UnM)AAIMR04019
035 $a AAIMR04019
040 $a UnM $c UnM
100 1 $a Zhang, Ming. $3 1023468
245 1 2 $a A study on XML querying and mining.
300 $a 78 p.
500 $a Source: Masters Abstracts International, Volume: 44-01, page: 0419.
502 $a Thesis (M.Sc.)--The University of Regina (Canada), 2005.
520 $a The eXtensible Markup Language, XML, is a new standard for data representation on the Internet. The semi-structured data model of XML requires new techniques for querying and mining XML data.
520 $a An XML query is a user's formally phrased request for information from the XML data source. XML queries typically consist of tree patterns with some value predicates on the nodes. Tree patterns are used to match the portions of the data source. The prior work for tree pattern matching usually produces large useless intermediate results. In this thesis, we propose an algorithm TreeMatch to directly find all distinct matchings of a query tree pattern in XML data source. TreeMatch does not produce any intermediate results and is more efficient than the prior methods.
520 $a XML data mining aims at discovering hidden knowledge from an XML data source. Researchers in the data mining community have paid little attention to XML. There is still no XML data mining algebra which is an operational language that provides a step-by step procedure to obtain the answer of data mining tasks. In this thesis, we examine the XML data mining tasks and give the guideline for designing an XML data mining algebra. The main idea is to decompose the complicated mining task into easily implemented and reusable sub-tasks and assign each sub-task to one operator.
520 $a Feature selection can be viewed as a sub-task of classification. An heuristic search is usually adopted in the feature selection process. In this thesis, we propose a new rough set based heuristic, Parameterized Average Support Heuristic (PASH) for feature selection. PASH considers the overall quality of the potential rules, thus producing a set of rules with balanced support distribution over all decision classes. In addition, PASH uses a parameter to adjust the level of approximation and keeps the predictive rules ignored by prior methods.
590 $a School code: 0148.
650 4 $a Computer Science. $3 626642
690 $a 0984
710 2 0 $a The University of Regina (Canada). $3 1017617
773 0 $t Masters Abstracts International $g 44-01.
790 $a 0148
791 $a M.Sc.
792 $a 2005
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=MR04019