<?xml version="1.0" encoding="UTF-8"?>
<record
    xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
    xsi:schemaLocation="http://www.loc.gov/MARC21/slim http://www.loc.gov/standards/marcxml/schema/MARC21slim.xsd"
    xmlns="http://www.loc.gov/MARC21/slim">

  <leader>03084nas|a2200409 a 4500</leader>
  <controlfield tag="005">20260818094227.0</controlfield>
  <controlfield tag="008">091112s2009    th uu|m rtt   0|  a1eng d</controlfield>
  <datafield tag="035" ind1=" " ind2=" ">
    <subfield code="a">.b12070385</subfield>
  </datafield>
  <datafield tag="099" ind1=" " ind2="9">
    <subfield code="a">AIT RSPR no.IM-09-01</subfield>
  </datafield>
  <datafield tag="100" ind1="1" ind2=" ">
    <subfield code="a">Rehman, Mariam</subfield>
  </datafield>
  <datafield tag="245" ind1="1" ind2="0">
    <subfield code="a">Duplicate record detection for database cleansing</subfield>
  </datafield>
  <datafield tag="260" ind1=" " ind2=" ">
    <subfield code="a">Pathum Thani, Thailand :</subfield>
    <subfield code="b">Asian Institute of Technology,</subfield>
    <subfield code="c">2009</subfield>
  </datafield>
  <datafield tag="300" ind1=" " ind2=" ">
    <subfield code="a">45 p. :</subfield>
    <subfield code="b">ill.</subfield>
  </datafield>
  <datafield tag="490" ind1="1" ind2=" ">
    <subfield code="a">Research studies project report  ;</subfield>
    <subfield code="v">no. IM-09-01</subfield>
  </datafield>
  <datafield tag="500" ind1=" " ind2=" ">
    <subfield code="a">A research study submitted in partial fulfillment of the requirements for the degree of  Master of Engineering  Information Management, School of Engineering and Technology</subfield>
  </datafield>
  <datafield tag="502" ind1=" " ind2=" ">
    <subfield code="a">Research Studies Project Report (M.Eng.) - Asian Institute of Technology, 2009</subfield>
  </datafield>
  <datafield tag="520" ind1=" " ind2=" ">
    <subfield code="a">Many organizations collect large amounts of data to support their business and decision making processes. The data collected from various sources may have data quality problems in it. These kinds of issues become prominent when various databases are integrated. The integrated databases inherit the data quality problems that were present in the source database. The data in the integrated systems need to be cleaned for proper decision making. Cleansing of data is one of the most crucial steps.  In this research, focus is on one of the major issue of data cleansing i.e. "duplicate record detection" which arises when the data is collected from various sources. As a result of this research study, comparison among standard duplicate detection algorithm, sorted neighborhood algorithm, duplicate elimination sorted neighborhood algorithm, and adaptive duplicate detection algorithm is provided. A prototype is also developed which shows that adaptive duplicate detection algorithm is the optimal solution for the problem of duplicate record detection </subfield>
  </datafield>
  <datafield tag="650" ind1=" " ind2="0">
    <subfield code="a">Database management</subfield>
  </datafield>
  <datafield tag="700" ind1="0" ind2=" ">
    <subfield code="a">Vatcharaporn Esichaikul,</subfield>
    <subfield code="e">Chairperson</subfield>
  </datafield>
  <datafield tag="700" ind1="0" ind2=" ">
    <subfield code="a">Vilas Wuwongse,</subfield>
    <subfield code="e">Examination Committee</subfield>
  </datafield>
  <datafield tag="700" ind1="1" ind2=" ">
    <subfield code="a">Jenecek, Paul,</subfield>
    <subfield code="e">Examination committee</subfield>
  </datafield>
  <datafield tag="710" ind1="2" ind2=" ">
    <subfield code="a">Higher Education Commission ( HEC), Pakistan,</subfield>
    <subfield code="e">Scholarship donor</subfield>
  </datafield>
  <datafield tag="810" ind1="2" ind2=" ">
    <subfield code="a">Asian Institute of Technology.</subfield>
    <subfield code="t">Research studies project report  ;</subfield>
    <subfield code="v">no. IM-09-01</subfield>
  </datafield>
  <datafield tag="856" ind1=" " ind2=" ">
    <subfield code="3">Full-Text</subfield>
    <subfield code="u">http://203.159.5.9/ait-thesis/detail.php?q=B01412</subfield>
  </datafield>
  <datafield tag="907" ind1=" " ind2=" ">
    <subfield code="a">.b12070385</subfield>
    <subfield code="b">mnait</subfield>
    <subfield code="c">u</subfield>
  </datafield>
  <datafield tag="902" ind1=" " ind2=" ">
    <subfield code="a">240329</subfield>
  </datafield>
  <datafield tag="998" ind1=" " ind2=" ">
    <subfield code="b">0</subfield>
    <subfield code="c">091112</subfield>
    <subfield code="d">m</subfield>
    <subfield code="e">a  </subfield>
    <subfield code="f">u</subfield>
    <subfield code="g">0</subfield>
  </datafield>
  <datafield tag="945" ind1=" " ind2=" ">
    <subfield code="l">mnait</subfield>
  </datafield>
  <datafield tag="945" ind1=" " ind2=" ">
    <subfield code="l">mnait</subfield>
  </datafield>
  <datafield tag="945" ind1=" " ind2=" ">
    <subfield code="l">mnarc</subfield>
  </datafield>
  <datafield tag="942" ind1=" " ind2=" ">
    <subfield code="c">20</subfield>
  </datafield>
  <datafield tag="942" ind1=" " ind2=" ">
    <subfield code="c">40</subfield>
  </datafield>
  <datafield tag="909" ind1=" " ind2=" ">
    <subfield code="a">Barcode : 30050120722557</subfield>
    <subfield code="b">CREATED : 2009-12-11</subfield>
    <subfield code="c">RECORD # : i12623507</subfield>
    <subfield code="d">LPATRON : 1025685</subfield>
    <subfield code="e">LCHKIN : 2015-01-30</subfield>
    <subfield code="f"># RENEWALS : 0</subfield>
    <subfield code="g"># OVERDUE : 0</subfield>
    <subfield code="h">IUSE3 : 0</subfield>
    <subfield code="i">TOT CHKOUT : 3</subfield>
    <subfield code="j">TOT RENEW : 0</subfield>
  </datafield>
  <datafield tag="909" ind1=" " ind2=" ">
    <subfield code="a">Barcode : 30050120722565</subfield>
    <subfield code="b">CREATED : 2009-12-11</subfield>
    <subfield code="c">RECORD # : i12623519</subfield>
    <subfield code="d">LPATRON : 0</subfield>
    <subfield code="e">LCHKIN : -</subfield>
    <subfield code="f"># RENEWALS : 0</subfield>
    <subfield code="g"># OVERDUE : 0</subfield>
    <subfield code="h">IUSE3 : 0</subfield>
    <subfield code="i">TOT CHKOUT : 0</subfield>
    <subfield code="j">TOT RENEW : 0</subfield>
  </datafield>
  <datafield tag="909" ind1=" " ind2=" ">
    <subfield code="a">Barcode : 30050160108683</subfield>
    <subfield code="b">CREATED : 2016-08-04</subfield>
    <subfield code="c">RECORD # : i12934343</subfield>
    <subfield code="d">LPATRON : 0</subfield>
    <subfield code="e">LCHKIN : -</subfield>
    <subfield code="f"># RENEWALS : 0</subfield>
    <subfield code="g"># OVERDUE : 0</subfield>
    <subfield code="h">IUSE3 : 0</subfield>
    <subfield code="i">TOT CHKOUT : 0</subfield>
    <subfield code="j">TOT RENEW : 0</subfield>
  </datafield>
  <datafield tag="999" ind1=" " ind2=" ">
    <subfield code="c">31836</subfield>
    <subfield code="d">31836</subfield>
  </datafield>
  <datafield tag="952" ind1=" " ind2=" ">
    <subfield code="0">0</subfield>
    <subfield code="1">0</subfield>
    <subfield code="4">0</subfield>
    <subfield code="7">0</subfield>
    <subfield code="a">MAIN</subfield>
    <subfield code="b">MAIN</subfield>
    <subfield code="c">mnait</subfield>
    <subfield code="d">2026-08-18</subfield>
    <subfield code="g">50.00</subfield>
    <subfield code="l">0</subfield>
    <subfield code="o">AIT RSPR no.IM-09-01</subfield>
    <subfield code="p">30050120722557</subfield>
    <subfield code="r">2026-08-18 09:42:27</subfield>
    <subfield code="t">1</subfield>
    <subfield code="w">2026-08-18</subfield>
    <subfield code="y">20</subfield>
  </datafield>
  <datafield tag="952" ind1=" " ind2=" ">
    <subfield code="0">0</subfield>
    <subfield code="1">0</subfield>
    <subfield code="4">0</subfield>
    <subfield code="7">0</subfield>
    <subfield code="a">MAIN</subfield>
    <subfield code="b">MAIN</subfield>
    <subfield code="c">mnait</subfield>
    <subfield code="d">2026-08-18</subfield>
    <subfield code="g">50.00</subfield>
    <subfield code="l">0</subfield>
    <subfield code="o">AIT RSPR no.IM-09-01</subfield>
    <subfield code="p">30050120722565</subfield>
    <subfield code="r">2026-08-18 09:42:27</subfield>
    <subfield code="t">2</subfield>
    <subfield code="w">2026-08-18</subfield>
    <subfield code="y">20</subfield>
  </datafield>
  <datafield tag="952" ind1=" " ind2=" ">
    <subfield code="0">0</subfield>
    <subfield code="1">0</subfield>
    <subfield code="4">0</subfield>
    <subfield code="7">0</subfield>
    <subfield code="a">MAIN</subfield>
    <subfield code="b">MAIN</subfield>
    <subfield code="c">mnarc</subfield>
    <subfield code="d">2026-08-18</subfield>
    <subfield code="l">0</subfield>
    <subfield code="o">AIT RSPR no.IM-09-01</subfield>
    <subfield code="p">30050160108683</subfield>
    <subfield code="r">2026-08-18 09:42:27</subfield>
    <subfield code="t">1</subfield>
    <subfield code="w">2026-08-18</subfield>
    <subfield code="y">40</subfield>
  </datafield>
</record>
