MARC보기
LDR00000nmm u2200205 4500
001000000330470
00520241031185134
008181129s2018 ||| | | | eng d
020 ▼a 9780438371583
035 ▼a (MiAaPQ)AAI10845463
035 ▼a (MiAaPQ)purdue:23258
040 ▼a MiAaPQ ▼c MiAaPQ ▼d 248032
0491 ▼f DP
0820 ▼a 004
1001 ▼a Rezig, Elkindi.
24510 ▼a Online Data Cleaning.
260 ▼a [S.l.] : ▼b Purdue University., ▼c 2018
260 1 ▼a Ann Arbor : ▼b ProQuest Dissertations & Theses, ▼c 2018
300 ▼a 140 p.
500 ▼a Source: Dissertation Abstracts International, Volume: 80-02(E), Section: B.
500 ▼a Advisers: Walid G. Aref
5021 ▼a Thesis (Ph.D.)--Purdue University, 2018.
520 ▼a Data-centric applications have never been more ubiquitous in our lives, e.g., search engines, route navigation and social media. This has brought along a new age where digital data is at the core of many decisions we make as individuals, e.g., l
520 ▼a Dirty data is the product of many factors which include data entry errors and integration of several data sources. Data integration of multiple sources is especially prone to producing dirty data. For instance, while individual sources may not h
520 ▼a There is a wide spectrum of errors that can be found in the data, e,g, duplicate records, missing values, obsolete data, etc. To address these problems, several data cleaning efforts have been proposed, e.g., record linkage to identify duplicate
520 ▼a We first present a framework that supports online record linkage and fusion over Web databases. Our system processes queries posted to Web databases. Query results are deduplicated, fused and then stored in a cache for future reference. The cach
520 ▼a To address integrity constraints violations, we propose a novel way to approach Functional Dependency repairs, develop a new class of repairs and then demonstrate it is superior to existing efforts, in runtime and accuracy. We then show how our
590 ▼a School code: 0183.
650 4 ▼a Computer science.
650 4 ▼a Engineering.
690 ▼a 0984
690 ▼a 0537
71020 ▼a Purdue University. ▼b Computer Sciences.
7730 ▼t Dissertation Abstracts International ▼g 80-02B(E).
773 ▼t Dissertation Abstract International
790 ▼a 0183
791 ▼a Ph.D.
792 ▼a 2018
793 ▼a English
85640 ▼u http://www.riss.kr/pdu/ddodLink.do?id=T15000062 ▼n KERIS
980 ▼a 201812 ▼f 2019
990 ▼a 관리자 ▼b 관리자