$9LVXDO$QDO\WLFV$SSURDFKWR'HWHFWLQJ6HUYHU

5HGLUHFWLRQVDQG'DWD([ILOWUDWLRQ
:HLMLH:DQJ %DLMLDQ<DQJ 9LFWRU<LQJMLH&KHQ
'HSWRI&RPSXWHUDQG,QIRUPDWLRQ 'HSWRI&RPSXWHUDQG,QIRUPDWLRQ 'HSWRI&RPSXWHU*UDSKLF
7HFKQRORJ\ 7HFKQRORJ\ 7HFKQRORJ\
3XUGXH8QLYHUVLW\
:HVW/DID\HWWH,186$
(PDLO^wang2056, byang, victorchen`#SXUGXHHGX

$EVWUDFW²+RZ WR EHWWHU ILQG SRWHQWLDO F\EHUDWWDFNV LV D QRUPDO DQG WKH HQG UHVXOWV RIWHQ FRQWDLQ WRR PDQ\ IDOVH
FKDOOHQJLQJ TXHVWLRQ IRU VHFXULW\ UHVHDUFKHUV DQG SUDFWLWLRQHUV SRVLWLYHVRUIDOVHQHJDWLYHV
,Q UHFHQW \HDUV YLVXDOL]DWLRQ KDV EHHQ DSSOLHG LQ WKH ILHOG RI
DQDO\]LQJF\EHUVHFXULW\LVVXHVEXWPRVWZRUNKDVQRWEHHQDEOH 9LVXDO $QDO\WLFV 9$ RIIHUV D GLIIHUHQW SHUVSHFWLYH WR
WRSURYLGHEHWWHUWKDQQRQYLVXDOL]DWLRQEDVHGWHFKQLTXHV,QWKLV GLVFRYHU ZKDW PLJKW EH KLGGHQ LQ WKH V\VWHP ,W LV RXU EHOLHI
SDSHU ZH LQQRYDWLYHO\ GHVLJQHG D YLVXDO DQDO\WLFV V\VWHP WR WKDWE\FDUHIXOO\GHVLJQLQJWKHV\VWHPRYHUYLHZDQGOHYHUDJLQJ
DOORZ DQDO\VWV WR RYHUYLHZ QHWZRUN WUDIILF DQG LGHQWLI\ VXFK WKH GRPDLQ NQRZOHGJH RI WKH H[SHUWV WKH 9$ PD\ SRVVLEO\
VXVSLFLRXV VXFK DFWLYLWLHV DV VHUYHU UHGLUHFWLRQ DWWDFN DQG GDWD GLVFRYHUQHZW\SHVRIDWWDFNVLGHQWLI\RQJRLQJNQRZQDWWDFNV
H[ILOWUDWLRQ %HFDXVH RI WKH QDWXUH RI WKH SUREOHP WKH RYHUYLHZ PXFK IDVWHU DQG EH DEOH WR GHWHUPLQH WKH WKUHVKROG EHWZHHQ
GHVLJQPXVWEHVFDODEOHDFFXUDWHDQGIDVW7KURXJKDJJUHJDWLQJ QRUPDO DQG DEQRUPDO ,QVSLUHG E\ RXU HDUOLHU VXFFHVV RQ
WUDIILF GDWD DORQJ WKH WZR GLPHQVLRQV RI GXUDWLRQ DQG SD\ORDG LGHQWLI\LQJ ERWK REYLRXV DQG VXEWOH SRUW VFDQV XVLQJ D 9$
WKH V\VWHP UHYHDOV NH\ QHWZRUN WUDIILF FKDUDFWHULVWLFV IRU WKH DSSURDFKZHEHJDQWREDWWOHWKUHDWVRQVHUYHUUHGLUHFWLRQDQG
DQDO\VW WR LGHQWLI\ VHFXULW\ HYHQWV 7KH V\VWHP LV HYDOXDWHG ZLWK GDWDH[ILOWUDWLRQLQWKLVZRUN
WKHWHVWGDWDVHWVIURP9$67PLQLFKDOOHQJH7KHUHVXOWV
DUHYHU\HQFRXUDJLQJDQGVKHGDPRUHSRVLWLYHOLJKWRQDSSO\LQJ ,QWKLVSDSHUZHLQWURGXFHDYLVXDODQDO\WLFVDSSURDFKWROHW
YLVXDODQDO\WLFVLQLQIRUPDWLRQVHFXULW\ QHWZRUNDQDO\VWVYLVXDOO\GHWHFWQHWZRUNWUDIILFUHODWHGVHFXULW\
SUREOHPV VXFK DV VHUYHU UHGLUHFWLRQ DQG GDWD H[ILOWUDWLRQ 7R
.H\ZRUGV²YLVXDO DQDO\WLFV QHWIORZ DQRPDO\ VHUYHU HYDOXDWHWKHV\VWHPZHXVHGWKHGDWDVHWIURPWKH,(((9$67
UHGLUHFWLRQGDWDH[ILOWUDWLRQ 0LQL&KDOOHQJH
7KH UHVW RI WKH SDSHU LV RUJDQL]HG DV IROORZV 6HFWLRQ 
, ,1752'8&7,21 LQWURGXFHVUHODWHGZRUNIROORZHGE\DQLOOXVWUDWLRQRIGDWDVHW
&\EHUDWWDFNVDQGGDWDEUDFKHVRQWKH,QWHUQHWDUHRFFXUULQJ DQG RXU GHVLJQ SKLORVRSKLHV LQ 6HFWLRQ  $Q LQQRYDWLYH
PRUHDQGPRUHIUHTXHQWO\DQGWKHGDPDJHLVEHFRPLQJPRUH RYHUYLHZGHVLJQDQG9$DQDO\VHVDUHWKHQH[SODLQHGLQ6HFWLRQ
VHYHUH7KH\EHFRPHUHDOWKUHDWVWRSHRSOH¶VZRUNDQGOLIHVW\OH  DQG WKH SDSHU FRQFOXGHV LQ 6HFWLRQ  ZLWK ZKDW KDV EHHQ
LQWKHQHZFHQWXU\+RZWREHWWHUVDIHJXDUG,7LQIUDVWUXFWXUHV OHDUQHGUHFRPPHQGDWLRQVDQGSODQQHGIXWXUHZRUN
DQG SUHYHQW GDWD EUHDFKHV DUH WKH ELOOLRQ GROODU TXHVWLRQV
VHFXULW\ UHVHDUFKHUV DQG SUDFWLWLRQHUV DUH DVNLQJ WKHPVHOYHV ,, 5(/$7(':25.
HYHU\ GD\ $OWKRXJK VRPH VHFXULW\ DWWDFNV DUH REYLRXV DQG
YLVLEOHVXFKDV'LVWULEXWHG'HQLDORI6HUYLFHV''26RWKHUV 7KLV6HFWLRQLQWURGXFHVUHODWHGZRUN,WEHJLQVZLWKDEULHI
DUH OHVV QRWLFHDEOH VXFK DV DFFHVVLQJ XQDXWKRUL]HG VHQVLWLYH LQWURGXFWLRQRI9LVXDO$QDO\WLFVLQWKHGRPDLQRILQIRUPDWLRQ
LQIRUPDWLRQ)RUREYLRXVDWWDFNVWKDWFDXVHVHUYLFHGLVUXSWLRQV VHFXULW\IROORZHGE\GLVFXVVLRQVRQVHUYHUVLGHUHGLUHFWLRQDQG
WKH PRVW XUJHQW LVVXH LV WR IROORZ WKH HVWDEOLVKHG LQFLGHQFH 'DWD([ILOWUDWLRQDWWDFNV
UHVSRQVHSURFHGXUHVDQGUHVWRUHWKHPLVVLRQ¶VFULWLFDOVHUYLFHV
DVVRRQDVSRVVLEOH+RZHYHUDQHYHQKDUGHUTXHVWLRQLVKRZ $ 9LVXDO$QDO\WLFVDQG,QIRUPDWLRQ6HFXULW\
GR\RXNQRZ\RXUQHWZRUNLVXQGHUDWWDFN" 2ULJLQDWHG GHDOLQJ ZLWK FRPSOH[ +RPHODQG VHFXULWLHV
7RILQGRXWLIWKHUHDUHDQ\RQJRLQJVLOHQWDWWDFNVH[LVWLQJ LVVXHVLQWKH8QLWHG6WDWHV-LP7KRPDVFRLQHGWKHWHUPYLVXDO
LQ \RXU V\VWHP WKH W\SLFDO DSSURDFK LV WR ILUVW FROOHFW GDWD DQDO\WLFV >@ ,W LV ³WKH VFLHQFH RI DQDO\WLFDO UHDVRQLQJ
HVWDEOLVK EDVHOLQHV DQG WKHQ DQDO\]H GDWD WR ILQG DQRPDO\ IDFLOLWDWHG E\ LQWHUDFWLYH YLVXDO LQWHUIDFHV´ ,W FRXSOHV KXPDQ
'LIIHUHQWVFKHPHVFDQEHXVHGWRDQDO\]HGDWD)RUH[DPSOHLI DQDO\VLV ZLWK PDFKLQH DQDO\VLV WR DWWHPSW VROYLQJ FRPSOH[
FHUWDLQ SDWWHUQV DUH NQRZQ UXOHV FDQ EH GHILQHG WR WULJJHU DQ SUREOHPVZKLOHEHLQJFRQFHUQHGZLWKDQDO\WLFDOSURFHVVKDYLQJ
DOHUW ,I SDWWHUQV DUH XQNQRZQ PRUHVRSKLVWLFDWHG WHFKQLTXHV LQWHUDFWLYH YLVXDO UHSUHVHQWDWLRQV  %\ YLVXDOO\ SUHVHQWLQJ WKH
VXFK DV VWDWLVWLFDO DQDO\VHV DQG PDFKLQH OHDUQLQJ FDQ EH FRPSOH[ GDWD LQ IURQW RI KXPDQV D SHUVRQ FDQ XVH KLVKHU
DSSOLHG WR ILQG RXW WKH DQRPDO\ 7KH FKDOOHQJH KRZHYHU LV H[SHULHQFH DQG NQRZOHGJH WR ILQG SDWWHUQV GHWHFW DQRPDO\
WKDW LW LV GLIILFXOW WR VHW WKH WKUHVKROG OHYHO WR GHILQH ZKDW LV DQGIRUPK\SRWKHVHVWKDWDUHGLIILFXOWWREHVROYHGE\FRPSXWHU
DORQH 9LVXDO DQDO\WLFV LV WKH LQWHUSOD\ RI GDWD DQDO\VLV

7KLVUHVHDUFKLVIXQGHGLQSDUWE\3XUGXH&R76HHG5HVHDUFKJUDQWDQG
VWDUWXSUHVHDUFKJUDQWV

978-1-4799-9889-0/15/$31.00 ©2015 IEEE 13

YLVXDOL]DWLRQDQGLQWHUDFWLRQPHWKRGV>@,QDVXFFHVVIXO9$ &RPPRQ GDWD H[ILOWUDWLRQ WHFKQLTXHV DSSO\ VWDWLVWLFDO
V\VWHPWKHGHYHORSHU PXVW GHDOZLWKLVVXHVRQGDWDFOHDQLQJ PRGHODQGFDWHJRUL]LQJWKHWUDIILFE\WKHW\SHRIDSSOLFDWLRQV
GDWD WUDQVIRUPDWLRQ YLVXDOL]DWLRQ GHVLJQ DQG LQWHUDFWLRQ WKHSDWWHUQRIWKHFRQWHQWDQGGHWHFWLQJWKHH[LVWHQFHRIFRYHUW
GHVLJQ FKDQQHOV >@ $O%DWDLQHK H[DPLQHG WKH W\SH RI GDWD
H[ILOWUDWLRQ WKURXJK +773 3267 PHWKRGV E\ EXLOGLQJ WKH
6HFXULW\YLVXDOL]DWLRQGHPDQGVQRYHOWHFKQLTXHVILQHWXQHG FODVVLILHU WKURXJK HQWURS\ DQG E\WH IUHTXHQF\ GLVWULEXWLRQ >@
IRU WKH SXUSRVH RI WKRURXJK DQDO\VLV >@>@  7KLV LV EHFDXVH ,Q 6,'' >@ /LX VXJJHVWHG WKDW FKDUDFWHULVWLFV RI WKH WUDIILF
VHFXULW\ ORQJ FRQWDLQV WHPSRUDO GDWD HJ WLPHVWDPS VSDWLDO SDWWHUQVVXFKDVWKHSDFNHWVL]HVDQGSDFNHWLQWHUDUULYDOWLPHV
GDWD HJ ,3 DGGUHVV DQG DUH PXOWLYDULDWH >@ ,Q DGGLWLRQ DUH LPSRUWDQW IDFWRUV ZKHQ GHWHFWLQJ GDWD H[ILOWUDWLRQ DWWDFNV
VHFXULW\ GDWD LV D ELJ GDWD SUREOHP ZLWK PDQ\ FKDOOHQJHV >@ 7KH YDOXHV RI YLVXDO UHSUHVHQWDWLRQV DQG YLVXDO DQDO\WLFV DUH
2QH LV DERXW YLVXDOL]DWLRQ RI WKH ODUJH YROXPH RI GDWD ZLWKLQ FRPPHQGHGDQGSUHVHQWHGLQ>@
WKH OLPLWHG VFUHHQ VSDFH 7KH WUDGLWLRQDO GLPHQVLRQUHGXFWLRQ
PHWKRG WULPV RXW WRR PDQ\ GHWDLOV DERXW WKH GDWD PDNLQJ ,Q VXPPDU\ WKH FKDOOHQJHV ZKHQ DSSO\LQJ 9$ LQ
YLVXDO UHDVRQLQJ DQG LQIRUPDWLRQ IRUJLQJ HYHQ KDUGHU 7KLV LQIRUPDWLRQVHFXULW\LVWKHGHVLJQRIRYHUYLHZLIWKHUHDUHWRR
GLUHFWO\UHODWHVWRFKDOOHQJLQJDXVHU¶VLQWHUDFWLRQZLWKELJGDWD PDQ\GHWDLOVKXPDQH\HVFDQQRWGHWHFWLWRQWKHRWKHUKDQGLI
DQDO\VLV ZKLFK LV DERXW GDWD VXPPDUL]DWLRQ DQG WULDJH IRU VRPH GHWDLOV DUH UHPRYHG IURP RYHUYLHZ WKHQ FHUWDLQ
LQWHUDFWLYHTXHU\6KLUDYLHWDOFRQFOXGHWKDWVHYHUDOLPSRUWDQW LQIRUPDWLRQ PLJKW JHW ORVW 7UDGLWLRQDO PDFKLQH OHDUQLQJ DQG
LVVXHV QHHG WR EH DGGUHVVHG LQ QHWZRUN VHFXULW\ YLVXDOL]DWLRQ VWDWLVWLFDO EDVHG DSSURDFKHV DUH EHFRPLQJ EHWWHU DQG PRUH
>@ VLWXDWLRQ DZDUHQHVV XVHU H[SHULHQFH VFDODELOLW\ DFFXUDWH <HW ZLWKRXW DQ\ EUHDNWKURXJK WKH DPRXQW RI GDWD
YLVXDOL]DWLRQ WHFKQLTXH SUHVHUYLQJ SULYDF\ DQG HYDOXDWLRQ EHLQJ ORJJHG PD\ HDVLO\ RXWJURZ WKH HIIHFWLYHQHVV RI WKH
2QH RI WKH HIIHFWLYH DSSURDFKHV LV WR XVH FRPSUHKHQVLYH DSSURDFKHV 7KH VFRSH RI WKLV ZRUN LV WKHUHIRUH WR HYDOXDWH LI
PXOWLSOHLQWHUOLQNHG YLVXDOL]DWLRQV WR YLVXDOL]H WKH ZH FDQ HIIHFWLYHO\ GHWHFW VHUYHU UHGLUHFWLRQ DWWDFNV DQG GDWD
F\EHUVHFXULW\IURPGLIIHUHQWSHUVSHFWLYHVWRJLYHWKHDQDO\VWD H[ILOWUDWLRQDWWDFNVE\DSSO\LQJ9$EDVHGDSSURDFK
IXOOVSHFWUXP XQGHUVWDQGLQJ RI WKH VLWXDWLRQ >@>@ ,Q WKLV
SDSHULQWHUPVRIQHWZRUNVHFXULW\YLVXDOL]DWLRQZHFRQWULEXWH ,,, '$7$6(76$1''(6,*13+,/2623+,(6
LQWKHDUHDRIVFDODELOLW\DQGYLVXDOL]DWLRQWHFKQLTXHV
$ 7KHGDWDVHW
% 6HUYHU6LGH5HGLUHFW
7R GHPRQVWUDWH RXU YLVXDO DQDO\WLFV DSSURDFK ZH XVHG WKH
6HUYHU VLGH UHGLUHFW LV D WHFKQRORJ\ RIWHQ XVHG E\ :HE GDWD VHW IURP ,((( 9$67  PLQL FKDOOHQJH  >@ 7KH
VHUYHUV WR UHGLUHFW DQ LQFRPLQJ UHTXHVW WR D GLIIHUHQW GDWD VHW LV D KLJKUHDOLVWLF VLPXODWLRQ RI D FRPSXWHU QHWZRUN
GHVWLQDWLRQ 7\SLFDO XVHV RI VHUYHUVLGH UHGLUHFW LQFOXGH ORDG LQWHQGHG WR HYDOXDWH F\EHUVHFXULW\ YLVXDO DQDO\WLFV VROXWLRQV
EDODQFLQJ DQG EDFNZDUG FRPSDWLELOLW\ ZLWK GLVFRQWLQXHG $V LOOXVWUDWHG LQ )LJ  WKH FRPSXWHU QHWZRUN LQFOXGHV WKUHH
VHUYHUVRURXWGDWHGVHUYLFHV+RZHYHUVRPHYLUXVHVRUZRUPV VLWHV HDFK KDYLQJ DERXW  FOLHQWV DQG D GR]HQ VHUYHUV
PD\ LQIHFW VHUYHUV DQG UHGLUHFW OHJLWLPDWH UHTXHVWV WR ERJXV
1HWZRUN WUDIILF LV FDSWXUHG DW WKH ERXQGDU\ RI WKH QHWZRUN
VLWHVWRFROOHFWXVHULQIRUPDWLRQRUVSUHDGZURQJLQIRUPDWLRQWR
WKHUHTXHVWHUV XVLQJWKHIRUPDWRI1HW)ORZZKLFKLQFOXGHVVXFKLQIRUPDWLRQ
DV VRXUFH ,3 DQG SRUW QXPEHUV GHVWLQDWLRQ ,3 DQG SRUW
$VSRLQWHGRXWLQ5%6HHNHU>@W\SLFDOFKDUDFWHULVWLFVRI QXPEHUV IORZ GXUDWLRQV DQG SD\ORDG VL]H 7KH GDWD VHWV
UHGLUHFWLRQ LQFOXGLQJ VKRUW IORZ GXUDWLRQ VPDOO SDFNHW VL]H LQFOXGHV WZR ZHHNV RI 1HW)ORZ UHFRUGV )ORZ UHFRUGV DUH
DQG VKRUW GXUDWLRQV EHWZHHQ IORZV 7R WDFNOH UHGLUHFWLRQV QRUPDOL]HG LQ VXFK D ZD\ WKDW VHQVLWLYH DQG SULYDWH
5%6HHNHUDGRSWHGDWHPSRUDOVSDWLDOVWDWLVWLFPRGHOWRLGHQWLI\ LQIRUPDWLRQ ZDV UHPRYHG EXW WKH FKDUDFWHULVWLFV RI W\SLFDO
WKH DWWDFNV ZLWKRXW H[DPLQLQJ HDFK SDFNHW 5%6HHNHU KDG QHWZRUN DWWDFNV DUH UHVHUYHG 7KH GDWD VHWV DUH DW IORZ OHYHO
GHPRQVWUDWHG VRPH JUHDW UHVXOWV HVSHFLDOO\ GLVFRYHULQJ
5HGLUHFWLRQ%RWQHWV5%1HWV,WQHHGVWRFROOHFWDQGFRUUHODWH
GDWD IURP YDULRXV VRXUFHV VXFK DV WKH 1HW)ORZ GDWD IURP
ILUHZDOOURXWHU DQG '16 ORJV IURP '16 VHUYHUV 6RPH
PDOLFLRXV5%1HWVEXLOGDFKDLQRIUHGLUHFWLRQVDQGFURVVRYHU
PXOWLSOHGRPDLQVWRPDNHWKHHQWLUHERWQHWVPRUHUHOLDEOHDQG
UHVLVWDQW WR GHIHQVH HQGHDYRUV $ QRYHO VROXWLRQ KDV EHHQ
SURSRVHG E\ OHYHUDJLQJ WKH SRZHU RI FURZG FRPSXWLQJ >@
.QRZOHGJH DQG RSLQLRQV RI :HE XVHUV ZHUH FROOHFWHG WR
GHWHUPLQHLIPDOLFLRXVUHGLUHFWLRQVZHUHRFFXUULQJ

& ,QWURGDWDH[ILOWUDWLRQ
'DWD H[ILOWUDWLRQ UHIHUV WR WKH SURFHVV RI WUDQVIHUULQJ
VHQVLWLYHGDWDRXWVLGHLWVSURWHFWHGGRPDLQ7KLVW\SHRIDWWDFN
DUH XVXDOO\ WDUJHWHG DQG ZLWK WKH LQWHQWLRQ RI VWHDOLQJ
LQWHOOLJHQFH XVHU LGHQWLWLHV DQG XVHU FUHGHQWLDOV 7KH PRVW
LPSRUWDQWLVVXHZKHQGHWHFWLQJGDWDH[ILOWUDWLRQLVWKHDELOLW\WR )LJ'DWDDQGV\VWHPLQ9$67>@
GLVWLQJXLVK OHJLWLPDWH GDWD WUDQVIHUULQJ IURP LOOHJDO FRS\LQJ
>@

14
QRW SDFNHW OHYHO ,Q D VSDQ RI WKHWZR ZHHNV WKHUH DUH DERXW ZLOOSXOOGDWDIURPWKH'%JHQHUDWLQJDJJUHJDWHGLQWHUPHGLDWH
 PLOOLRQ UHFRUGV RI HQWULHV $IWHU WKH FRPSHWLWLRQ ZDV GDWDDQGVWRULQJWKHPEDFNWRWKH'%,QRQOLQHPRGHWKHEDFN
FRPSOHWHG WKH 9$67  FRPPLWWHH UHOHDVHG WKH JURXQG HQG RI WKH ZHE VHUYHU SXOOV KLVWRULF SURFHVVHG GDWD IURP '%
WUXWKWRWKHUHVHDUFKWHDPVWKDWSDUWLFLSDWHGLQWKHFKDOOHQJHV DQGSXOOVUHDOWLPHSURFHVVHGGDWDIURPWKH'DWDSUHSURFHVVLQJ
,Q WKLV ZRUN ZH XVHG WKH JURXQG WUXWK LQIRUPDWLRQ DV WKH XQLW ,Q RIIOLQH PRGH RQO\ '% QHHGV WR EH FRQQHFWHG WR IHHG
DQVZHUNH\WRYDOLGDWHWKHILQGLQJVIURPRXU9$V\VWHP WKHSURFHVVHGGDWDWRWKHEDFNHQGRIWKH:HEVHUYHU7KHIURQW
HQG RI VHUYHU FRPPXQLFDWHV ZLWK WKH FOLHQWV XVLQJ -DYDVFULSW
% 'HVLJQ3KLORVSKLHV KWWSVFRQQHFWLRQV,QSDUWLFXODUGMVZDVXVHGLQWKLVZRUNWR
7KH NH\ FKDOOHQJH RI WKLV ZRUN LV WR PDNH DQ\ VXVSLFLRXV EXLOGYLVXDOL]DWLRQV
7KH IRFXV RI WKLV ZRUN LV WR LGHQWLI\ DEQRUPDO QHWZRUN
WUDIILF IRU H[DPSOH H[WUHPHO\ ODUJH RU VPDOO SD\ORDGV DQG
H[WUHPHO\ ORQJ DQG VKRUW GXUDWLRQV 7KH NH\ 1HW)ORZ
FKDUDFWHULVWLFVFDQKLQWVRPHDEQRUPDOVHFXULW\LVVXHV,QGDWD
JavaScript (https)
H[ILOWUDWLRQ WKH XVXDO SDWWHUQ LV ORQJ GXUDWLRQV DQG ODUJH
SD\ORDG VL]H )RU VHUYHU UHGLUHFWLRQ WKH WUHQG LV RSSRVLWH
H[WUHPHO\VKRUWGXUDWLRQVDQGVPDOOSD\ORDGVL]H
7R YLVXDOL]H WKHVH WZR LPSRUWDQW SDUDPHWHUV ZH GHVLJQHG
Visual
Visual Design
Design and
and Web
Web Server
Server
WKH GXUDWLRQSD\ORDG GLVWULEXWLRQ JUDSK VKRZQ LQ )LJ 
,QVWHDG RI VLPSO\ YLVXDOL]LQJ HDFK LQVWDQFHV RI WKH IORZ ZH
YLVXDOL]H WKH DJJUHJDWHG SDWWHUQ RI WKH WUDIILF WR DFKLHYH IDVW
SURFHVVLQJ VSHHG JUHDWHU VFDODELOLW\ DQG HDVLHU GHWHFWLRQV
:LWKVXFKDGHVLJQJRDOLQPLQGZHLQQRYDWLYHO\DJJUHJDWHWKH
GDWD VHWV LQWR GLPHQVLRQ JURXSV EDVHG RQ WKH UDQJH RI WKH
Netflow
Netflow DB
DB Data
Data PreProcessing
PreProcessing
 GXUDWLRQDQGSD\ORDGVL]H*URXSVDUHSORWWHGDVFHOOVZLWKHDFK
)LJ9$V\VWHPLQWKLVZRUN FRQWDLQLQJDWLPHVHULDOEDUJUDSK)LJ
:HEUHDNWKHVHVVLRQGXUDWLRQVLQWRJURXSVLQWKHUDQJHRI
     a a a ! LQ VHFRQGV WR
DFWLYLWLHV VWDQG RXW IURP WKH RYHUYLHZ ,Q WKLV ZRUN ZH GLVWLQJXLVK H[WUHPH VKRUW SHULRGV   UHJXODU GXUDWLRQV
SULPDULO\ IRFXV RQ D VLQJOH GDWD VRXUFH ZKLFK LV WKH WUDIILF a OLWWOH GHOD\ a GHOD\HG a DQG YHU\ ORQJ
1HW)ORZUHFRUGV7KHJRDOVRIRXUGHVLJQDUHDVIROORZV aDQGH[WUHPHORQJ!;D[LVLQ)LJ3D\ORDG
x ,W PXVW EH DEOH WR VXSSRUW ERWK RIIOLQH DQG RQOLQH VL]HLVGLYLGHGLQWKHORJDULWKPEDVHVFDOHWKDWLV
PRGHV «XSWRWKHORJYDOXHRIWKHODUJHVWGDWDLQWKHVHW<
x ,WQHHGVWREHVFDODEOHDQGUHDVRQDEO\IDVW D[LV LQ  )LJ   :KHQ RQH UHFRUG RI WKH QHWZRUN WUDIILF LV
UHWULHYHG IURP '% RU WKH SUHSURFHVVLQJ XQLW LW ZLOO EH
x ,WQHHGVWREHIDLUO\VWUDLJKWIRUZDUGDQGDFFXUDWH FODVVLILHGDQGDJJUHJDWHGLQWRRQHJURXSDFFRUGLQJWRWKHUDQJH
RILWVVHVVLRQGXUDWLRQWLPHVDQGSD\ORDGVL]H
7KH IORZ RI RXU 9$ V\VWHP LV VKRZQ LQ )LJ  1HW)ORZ
'DWDDUHILUVWVWRUHGLQGDWDEDVH'%7KHGDWDSUHSURFHVVXQLW ,Q HDFK FHOO D EDUFKDUW OLNH JUDSK LV SORWWHG WR VKRZ WKH


)LJ2YHUYLHZRIGXUDWLRQSD\ORDGGLVWULEXWLRQ

15
QHWZRUNWUDIILFKLVWRU\IRUWKHJURXS7KH;D[LVUHSUHVHQWVWKH QRW UHOHYDQW WR HLWKHU W\SH RI DWWDFNV ZH EHOLHYH IXUWKHU
WLPHOLQH *LYHQ WKDW D VPDOO VSDFH QHHGV WR GLVSOD\ D ODUJH LQYHVWLJDWLRQV DUH QHHGHG VLQFH LW GHPRQVWUDWHV VRPH XQXVXDO
DPRXQW RI GDWD WKH WZR ZHHN WLPHOLQH LV EURNHQ LQWR HDFK EHKDYLRUV )RU H[DPSOH WKH ERWWRP ULJKW RI WKH RYHUYLHZ
KRXU7KH<D[LVUHSUHVHQWVWKHQXPEHURIWKHIORZV1RWHWKDW VKRZV VRPH WUDIILF KDV VPDOO SD\ORDG VL]HV \HW ORQJ VHVVLRQ
WKHQXPEHUFRXQWVYDULHVJUHDWO\EHWZHHQHDFKJURXSG\QDPLF GXUDWLRQV7KHFDXVHPLJKWVLPSO\EHORQJ TXHXHLQJGHOD\RQ
VFDOLQJLVDSSOLHGRQ<D[LVWRDOORZKXPDQVEHWWHUGHWHFWLRQRI WKH QHWZRUN SURFHVVRUV RU ,2V  ,W FRXOG DOVR EH FRYHUW
SDWWHUQV DQG FKDQJHV 7KH GDUNHU WKH FHOO WKH KLJKHU UDWLR RI FKDQQHOVRUVRPHSHUVLVWHQWVLOHQWDWWDFNV
VFDOLQJLVDSSOLHGWRWKHEDUJUDSK7KHUHIRUHHDFKYHUWLFDOEDU
LQ D FHOO GHQRWHV WKH UHODWLYH QXPEHU RI IORZV WKDW RFFXUUHG 7KH RYHUYLHZ FKDUW FDQ EH GUDZQ IRU WKH HQWLUH V\VWHP DV
GXULQJWKDWSDUWLFXODUKRXU7KHEDUVLQDGDUNHUFHOOPHDQVLWV ZHOO DV IRU HDFK VHUYHU 7KRXJK VRPH TXHVWLRQHG WKH
QXPEHULVLQKLJKHUPXOWLWXGHWKDQWKHEDUVLQOLJKWHUFHOOV3XW FRQYHQWLRQDORYHUYLHZILUVWDQGWKH]RRPLQQH[WDSSURDFKLQ
GLIIHUHQWO\GDWDDUHILUVWFODVVLILHGLQWRHDFKJURXSEDVHGRQWKH WKH 9$ GHVLJQ ZH EHOLHYH WKH SDUDGLJP LV QRW EURNHQ :KDW
UDQJH RI VHVVLRQ GXUDWLRQV DQG SD\ORDG VL]H DQG WKH\ DUH ZDV EURNHQ LV WKDW D VLPSOH RYHUYLHZ VKRZLQJ RQO\
IXUWKHU DJJUHJDWHG HYHU\  PLQXWHV WR LPSURYH SHUIRUPDQFH XQSURFHVVHGGDWDLVLQFDSDEOHRIILQGLQJQHHGOHVLQWKHVHFXULW\
VFDODELOLW\ DQG HDV\ FRPSUHKHQVLRQV KXPDQV 6KRXOG WKH KD\VWDFNV
WLPHOLQH EH GLIIHUHQW WKH WLPH VSDQ RI WKH DJJUHJDWLRQ FDQ EH ,I D FHOO LV VHOHFWHG WKH ]RRPLQ GHWDLOV ZLOO SORW D ODUJH
VHW GLIIHUHQWO\ SHUKDSV  PLQXWHV LI SHRSOH DUH PRUH YLHZRIWKHFHOOJUDSKVKRZQLQ)LJE,IDGRWLQWKHODUJH
FRQFHUQHG DERXW HYHQWV RFFXUULQJ LQ RQH GD\ LQVWHDG RI WZR
ZHHNV
7KHUHIRUH LQ WKH RYHUYLHZ FHOOV LQ WKH PLGGOH DUH TXLWH
OLNHO\WREHQRUPDOGDWDZLWKSD\ORDGVIURPWRE\WHV
DQG GXUDWLRQ IURP  WR  VHFRQGV &HOOV RQ WKH HGJHV DQG
FRUQHUVDUHYHU\OLNHO\WREHTXHVWLRQDEOH,IZHOLQNWKHWUDIILF
FKDUDFWHULVWLFVWR WKH RYHUYLHZWKHQ FHOOV LQWKH UHJLRQ RI WRS
ULJKW DUH PRVW OLNHO\ UHODWHG WR GDWD H[ILOWUDWLRQ HYHQWV DQG
FHOOV RQ WKH OHIW VLGH FDQ EH XVHG WR LGHQWLI\ SRWHQWLDO VHUYHU
UHGLUHFWLRQDWWDFNV7KRXJKFHOOVRQWKHERWWRPRIWKHFKDUWDUH


)LJD2YHUYLHZ6XVSLFLRXVFHOOJUDSKKLJKOLJKWHGLQUHGER[


)LJD/DUJHYLHZRIWKHFHOOJUDSKLQWKHRYHUYLHZ

 )LJE/DUJHYLHZRIWKHVXVSLFLRXVFHOOJUDSK

 
)LJE)ORZDQDO\VLVRIWKHUHGGRWLQD )LJF)ORZDQDO\VLVZLWKSDUDOOHOFRRUGLQDWHV


16
YLHZ LV VHOHFWHG D PRUH GHWDLOHG IORZ DQDO\VHV JUDSK ZLOO EH
VKRZQWRGLVSOD\LQIRUPDWLRQDERXWZKRPDGHFRQQHFWLRQVWR
ZKRPIRUKRZORQJLOOXVWUDWHGLQ)LJF

,9 &$6(678',(6
,Q WKLV VHFWLRQ ZH GHVFULEH KRZ WKH RYHUYLHZ DQG RQ
GHPDQG IORZ DQDO\VLV FDQ EH DSSOLHG WR LGHQWLI\ SRWHQWLDO
DWWDFNV

$ 'DWDH[ILOWUDWLRQ 
)LJXUH D LV D V\VWHP RYHUYLHZ LQ WKH VSDQ RI WKH WZR )LJD2YHUYLHZZLWKWZRFHOOJUDSKVKLJKOLJKWHGLQUHGER[
ZHHNVLQTXHVWLRQ$VGHVFULEHGLQ6HFWLRQ,,,%WKHWRSULJKW
FRUQHURIRYHUYLHZKDVWKHSDWWHUQRIFODVVLFDOGDWDH[ILOWUDWLRQ
EHFDXVH WKRVH VXEJUDSKV DUH LQ WKH FDWHJRU\ RI ODUJH SD\ORDG
VL]HDQGORQJVHVVLRQGXUDWLRQV7ZRVXEJUDSKVVWDQGRXWIURP
WKH RYHUYLHZ WKH\ DUH LQ WKH FDWHJRU\ RI  
VHVVLRQGXUDWLRQVDQGSD\ORDGVL]HRI%\WHVRU0%
&OLFNLQJ RQ WKH  VXEJUDSK VKRZV WKH ]RRPHGLQ
VXEJUDSK VKRZQ LQ )LJ E ,Q WKLV SDUWLFXODU H[DPSOH LW
KDSSHQV WKDW WKHUH ZDV RQO\ RQH VHVVLRQ LQYROYHG DQG LW ZDV
RFFXUULQJ RQ $SULO  ]RRPLQJ WR WKH QH[W OHYHO DV VKRZQ LQ 
)LJ F ,W WKHQ EHFDPH HYLGHQW WKDW DQ H[WHUQDO ,3  )LJE/DUJHUYLHZRI&HOOVHFVL]H
KDVUHWULHYHGDERXW0%RILQIRUPDWLRQIURPDQLQWHUQDO,3
DQGVHVVLRQVODVWHGIRU DERXWVHFRQGV7KLVLV
FHUWDLQO\ DQ DEQRUPDO EHKDYLRU DQG ZDV ODEHOHG DV GDWD
H[ILOWUDWLRQ DWWDFN LQ WKH JURXQG WUXWK SURYLGHG E\ WKH 9$67
FRPPLWWHH
7KHGHWHFWLRQRIGDWDH[ILOWUDWLRQLQWKHJLYHQGDWDVHWZDV
REYLRXVVLQFHWKHUHDUHQRRWKHUGDWDPDWFKVLPLODUSDWWHUQV,Q
UHDOLW\ WKRXJK ZLWK WKH HYHUSRSXODU VWUHDPLQJ PHGLD RQ WKH
,QWHUQHWWKHSDWWHUQRIGDWDH[ILOWUDWLRQPLJKWJHWEXULHGLQVLGH 
WKH PXOWLPHGLD WUDIILF )XUWKHU ILOWHULQJ RU RWKHU WHFKQLTXHV )LJF/DUJHUYLHZRI&HOOVHFVL]H
PLJKWEHQHFHVVDU\ZLWKWKHSURSRVHG9$RYHUYLHZWRQDUURZ
WKHUHDOWKUHDWVPRUHTXLFNO\

% 5HGLUHFWLRQV
*HQHUDOO\ LQ WKH RYHUYLHZ GLVWULEXWLRQ HDFK FHOO JUDSK
VKRXOGKDYHDQRUPDOYDULDWLRQZKHUHDVROHO\SHDNRUVHYHUDO
SHDNV VKRXOG QHHG IXUWKHU LQYHVWLJDWLRQ 7KH EDFNJURXQG
NQRZOHGJHVWDWHGWKDWVHUYHUVZHUHGRZQVRPHZKHUHEHWZHHQ
$SULO  DQG $SULO  6R HDFK JUDSK VKRXOG KDYH VLPLODU
DFWLYLWLHVEHIRUH$SULOIROORZHGE\QRWKLQJGXULQJGRZQWLPH
DQGUHVXPLQJVLPLODUSDWWHUQVDIWHU$SULO)URP)LJLWLV 
HYLGHQWWKDWWKHVXEJUDSKRIWLPHGXUDWLRQaDQGSD\ORDGa )LJG)ORZDQDO\VLVRIDGRWLQ&HOO
DUH TXHVWLRQDEOH EHFDXVH VXEJUDSKV KDYH YHU\ XQEDODQFHG
DFWLYLWLHV $ FORVHU ORRN UHYHDOV WKDW PRVW RI WKH HYHQWV ZHUH
UHODWHGWRLQWHUQDOVHUYHU7KHUHIRUHWKHRYHUYLHZRI
WKDWVHUYHULVGLVSOD\HGDVVKRZQLQ)LJDZLWKWKHEURNHQ
SDWWHUQVRI&HOOVHFRQGV%\WHVDQG&HOOVHFRQGV
%\WHVKLJKOLJKWHGLQUHGER[HV
7KHODUJHRYHUYLHZRI&HOOVKRZQLQ)LJEVKRZVWKH
VHUYHU KDV QR DFWLYLWLHV DIWHU D FHUWDLQ WLPH RQ $SULO 
,QWHUHVWLQJO\LQ)LJ&WKHODUJHRYHUYLHZRI&HOOVKRZV
WKDWWKHUH ZHUHQRDFWLYLWLHVIURPWKHEHJLQQLQJ\HWDFWLYLWLHV
VWDUWHGWRSRSXSDWWKHWLPHZKHQWKHFHOOORVWDFWLYLWLHV7KLV
FOHDUO\ LQGLFDWHV WUDIILF SDWWHUQ VKLIWV RQ $SULO  ERWK WKH 
GXUDWLRQRIWKHWLPHDQGWKHVL]HRISD\ORDGDUHUHGXFHGTXLWH )LJH)ORZDQDO\VLVRIDGRWLQ&HOO
VLJQLILFDQWO\ 7KHIORZDQDO\VLVLQ &HOOVKRZQLQ)LJG


17
FOHDUO\VKRZVDW\SLFDOGXUDWLRQWLPHRIDURXQGVHFRQGVDQG 5()(5(1&(6
SD\ORDG VL]H RI DURXQG  WR  E\WHV :KHUHDV LQ )LJ >@ --7KRPDVDQG.$&RRN,OOXPLQDWLQJWKH3DWK7KH5HVHDUFKDQG
H WKH SD\ORDG VL]H RI &HOO  LV DERXW  E\WHV DQG WKH 'HYHORSPHQW $JHQGD IRU 9LVXDO $QDO\WLFV /RV $ODPLWRV &$ 8QLWHG
W\SLFDO UHVSRQVH WLPH LV UHGXFHG WR  VHFRQGV ZKLFK PHDQV 6WDWHV86 3DFLILF 1RUWKZHVW 1DWLRQDO /DERUDWRU\ 311/ 5LFKODQG
OHVVWKDQVHFRQG7KLVLVHYLGHQWWKDWVRPHWKLQJKDVFKDQJHG :$86,(((&RPSXWHU6RFLHW\
RQ$SULOUG,WFRXOGKDYHVLPSO\EHHQGXHWRSODQQHGFKDQJHV >@ '$.HLP)0DQVPDQQ-6FKQHLGHZLQG-7KRPDVDQG+=LHJOHU
9LVXDODQDO\WLFV6FRSHDQGFKDOOHQJHV6SULQJHU
VXFKDVDVHUYHUJHWWLQJQHZKDUGZDUHQHZZHESDJHRUQHZ
,3%XWLIQRWLWPXVWKDYHEHHQKDFNHGE\YLUXVZRUPVERWQHW >@ *&RQWL6HFXULW\GDWDYLVXDOL]DWLRQJUDSKLFDOWHFKQLTXHVIRUQHWZRUN
DQDO\VLV1R6WDUFK3UHVV
FDXVLQJ WKH VHUYHU WR EH UHGLUHFWHG WR PDOLFLRXV VLWHV ,Q WKH
>@ 5 0DUW\ $SSOLHG 6HFXULW\ 9LVXDOL]DWLRQ 8SSHU 6DGGOH 5LYHU 1-
JLYHQ GDWD VHW QR FKDQJHV ZHUH PDGH RQ WKDW GD\ WKH $GGLVRQ:HVOH\
DEQRUPDO EHKDYLRU LV FOHDUO\ OLQNHG WR VHUYHU UHGLUHFWLRQ >@ * -LDQJ DQG * &\EHQNR ³7HPSRUDO DQG VSDWLDO GLVWULEXWHG HYHQW
DWWDFNV FRUUHODWLRQ IRU QHWZRUN VHFXULW\´ LQ $PHULFDQ &RQWURO &RQIHUHQFH
3URFHHGLQJVRIWKHYROSS±
& 5HVXOWV6XPPDU\ >@ 3&:RQJ+:6KHQ&5-RKQVRQ&&KHQDQG5%5RVV³7KH
7RS&KDOOHQJHVLQ([WUHPH6FDOH9LVXDO$QDO\WLFV´,(((&RPSXWHU
&RPSDUHG ZLWK JURXQG WUXWK UHOHDVHG E\ WKH 9$67  *UDSKLFVDQG$SSOLFDWLRQVYROQRSS±
FRPPLWWHHWKHILQGLQJVZHGLVFRYHUHGRQGDWDH[ILOWUDWLRQDUH >@ +6KLUDYL$6KLUDYLDQG$$*KRUEDQL³$VXUYH\RIYLVXDOL]DWLRQ
LGHQWLFDOQRPRUHQROHVV7KRXJKRXUGHVLJQZDVQRWWHVWHG V\VWHPV IRU QHWZRUN VHFXULW\´ 9LV &RPSXW *UDSK ,((( 7UDQV 2Q
RQ RWKHU GDWD VHWV LW LV VWLOO HQFRXUDJLQJ WKDW RXU GHVLJQ YROQRSS±
KDSSHQVWRKDYHQRIDOVHQHJDWLYHVRUIDOVHSRVLWLYHV >@ 9 < &KHQ $ 0 5D]LS 6 .R & = 4LDQ DQG ' 6 (EHUW ³0XOWL
DVSHFW YLVXDO DQDO\WLFV RQ ODUJHVFDOH KLJKGLPHQVLRQDO F\EHU VHFXULW\
7KHUHVXOWVRQUHGLUHFWLRQZHUHQRWDVVWUDLJKWIRUZDUGDVWKH GDWD´,QI9LVYROQRSS±
GDWDH[ILOWUDWLRQ2QWKHSRVLWLYHVLGHDOOWKHUHGLUHFWLRQDWWDFNV >@ <=KDR;/LDQJ;)DQ<:DQJ0<DQJDQG)=KRX³096HF
VWDWHG RQ WKH µDQVZHU VKHHW¶ FDQ EH HDVLO\ LGHQWLILHG IURP WKH PXOWLSHUVSHFWLYH DQG GHGXFWLYH YLVXDO DQDO\WLFV RQ KHWHURJHQHRXV
RYHUYLHZ 7KH PRUH FRPSOH[ VLGH RI WKH VWRU\ ZDV WKDW ZH QHWZRUNVHFXULW\GDWD´-9LVYROQRSS±
ZHUHDEOHWRILQGPRUHDWWDFNVWKDQWKHµDQVZHUVKHHW¶\HWZH >@ $$O%DWDLQHKDQG*:KLWH³$QDO\VLVDQGGHWHFWLRQRIPDOLFLRXVGDWD
ZHUH QRW VXUH LI WKRVH ILQGLQJV ZHUH IDOVH SRVLWLYHV 7KLV LV H[ILOWUDWLRQ LQ ZHE WUDIILF´ LQ 0DOLFLRXV DQG 8QZDQWHG 6RIWZDUH
0$/:$5(WK,QWHUQDWLRQDO&RQIHUHQFHRQSS±
EHFDXVH WKH VXVSLFLRXV EHKDYLRUV KDYH WKH H[DFW VDPH SDWWHUQ
LQ WKH JUDSK UHODWLYH ODUJHU SD\ORDG DQG ORQJHU VHVVLRQ >@ <0 :DQJ ' %HFN ; -LDQJ 5 5RXVVHY & 9HUERZVNL 6 &KHQ
DQG 6 .LQJ ³$XWRPDWHG ZHE SDWURO ZLWK VWULGHU KRQH\PRQNH\V´ LQ
GXUDWLRQVDWWKHEHJLQQLQJDQGWKHQPRYHGWRWKHVXEJURXSWKDW 3URFHHGLQJV RI WKH  1HWZRUN DQG 'LVWULEXWHG 6\VWHP 6HFXULW\
KDV D VPDOOHU SD\ORDG DQG PXFK VKRUWHU GXUDWLRQV 7KHUHIRUH 6\PSRVLXPSS±
ZHUHDVRQDEO\EHOLHYHWKHUHVXOWVDUHQRWIDOVHSRVLWLYHV >@ % :X DQG % ' 'DYLVRQ ³&ORDNLQJ DQG 5HGLUHFWLRQ $ 3UHOLPLQDU\
6WXG\´LQ$,5:HESS±
9 &21&/86,216$1')8785(:25. >@ $*LDQL9+%HUNDQG*9&\EHQNR³'DWDH[ILOWUDWLRQDQGFRYHUW
FKDQQHOV´ LQ 'HIHQVH DQG 6HFXULW\ 6\PSRVLXP  SS ±
,Q WKLV ZRUN ZH SUHVHQWHG D 9$EDVHG GHVLJQ WKDW FDQ 
GHWHFWVHUYHUUHGLUHFWLRQDQGGDWDH[ILOWUDWLRQDWWDFNV7KHWHVW >@ < /LX & &RUEHWW . &KLDQJ 5 $UFKLEDOG % 0XNKHUMHH DQG '
UHVXOWVRQWKH9$67GDWDVHWVSURYHGWKHHIIHFWLYHQHVVRI *KRVDO ³'HWHFWLQJ VHQVLWLYH GDWD H[ILOWUDWLRQ E\ DQ LQVLGHU DWWDFN´ LQ
WKHDSSURDFKDQGUHLQIRUFHGRXWEHOLHIVWKDWD9$DSSURDFKFDQ 3URFHHGLQJV RI WKH WK DQQXDO ZRUNVKRS RQ &\EHU VHFXULW\ DQG
LQIRUPDWLRQ LQWHOOLJHQFH UHVHDUFK GHYHORSLQJ VWUDWHJLHV WR PHHW WKH
EH XVHG WR GLDJQRVH FRPSOH[ VHFXULW\ LVVXHV :H EHOLHYH WKH F\EHU VHFXULW\ DQG LQIRUPDWLRQ LQWHOOLJHQFH FKDOOHQJHV DKHDG  S
NH\ LV WR GHVLJQ FOHDQ \HW UHSUHVHQWDWLYH V\VWHP RYHUYLHZV 
6SHFLILF WHFKQLTXHV DUH  WR GLVSOD\ SURFHVVHG GDWD QRW UDZ >@ $ '¶$PLFR DQG 0 .RFND ³,QIRUPDWLRQ DVVXUDQFH YLVXDOL]DWLRQV IRU
GDWD WKDW FDQ WUXO\ UHIOHFW VHFXULW\UHODWHG HYHQWV DQG  WR VSHFLILF VWDJHV RI VLWXDWLRQDO DZDUHQHVV DQG LQWHQGHG XVHV OHVVRQV
DJJUHJDWH GDWD WR LPSURYH SHUIRUPDQFH DQG VFDODELOLW\ ,W OHDUQHG´ LQ 9LVXDOL]DWLRQ IRU &RPSXWHU 6HFXULW\ 9L]6(& 
VKRXOG EH QRWHG WKDW DOWKRXJK ZH HPSOR\HG DQ DJJUHJDWHG ,(((:RUNVKRSRQSS±
FKDUDFWHULVWLFVEDVHG DSSURDFK WR SURFHVV GDWD WKH IUDPHZRUN >@ ; +X 0 .Q\V] DQG . * 6KLQ ³5%6HHNHU $XWRGHWHFWLRQ RI
5HGLUHFWLRQ%RWQHWV´LQ1'66
LWVHOI FDQ ZRUN ZLWK DQ\ RWKHU H[LVWLQJ GDWD SURFHVVLQJ
>@ * 6WULQJKLQL & .UXHJHO DQG * 9LJQD ³6KDG\ SDWKV OHYHUDJLQJ
DSSURDFK VXFK DV VSDWLDOWHPSRUDO DQDO\VLV DQG VXSHUYLVHG VXUILQJFURZGVWRGHWHFWPDOLFLRXVZHESDJHV´SS±
PDFKLQHOHDUQLQJ
>@ < /LX & &RUEHWW . &KLDQJ 5 $UFKLEDOG % 0XNKHUMHH DQG '
%HFDXVH RI WKH FRQVWUDLQWV RI DYDLODEOH GDWD VHWV DQG *KRVDO³6,''$IUDPHZRUNIRUGHWHFWLQJVHQVLWLYHGDWDH[ILOWUDWLRQE\
DQ LQVLGHU DWWDFN´ LQ 6\VWHP 6FLHQFHV  +,&66¶ QG +DZDLL
HTXLSPHQWWKHVFRSHRIWKHZRUNZDVOLPLWHGWRDVLQJOHGDWD ,QWHUQDWLRQDO&RQIHUHQFHRQSS±
VRXUFHILUHZDOODQGDVLQJOHIRUPDW1HW)ORZDQGWZRW\SHV
>@ - 5 *RRGDOO DQG 0 6RZXO ³9,$VVLVW 9LVXDO DQDO\WLFV IRU F\EHU
RIQHWZRUNDWWDFNV,QWKHIXWXUHZHZLOODSSO\WKHVDPHGHVLJQ GHIHQVH´LQ7HFKQRORJLHVIRU+RPHODQG6HFXULW\+67¶,(((
SKLORVRSKLHVWRXQLI\VHYHUDORYHUYLHZVWRDOORZWKHDQDO\VWWR &RQIHUHQFHRQSS±
GHWHFW PRVW QHWZRUNUHODWHG F\EHUDWWDFNV VXFK DV ''R6 SRUW >@ 9$67 &KDOOHQJH  0LQL&KDOOHQJH  $FFHVVHG 
VFDQVERWQHWVVHUYHUUHGLUHFWLRQVDQGGDWDH[ILOWUDWLRQ KWWSYDFRPPXQLW\RUJ9$67&KDOOHQJH$0LQL&KDOOHQJH

$&.12:/('*0(17
7KHDXWKRUVZRXOGOLNHWRWKDQNWKH&ROOHJHRI7HFKQRORJ\
DW3XUGXH8QLYHUVLW\ IRUVXSSRUWLQJWKLVUHVHDUFKZLWKDVHHG
UHVHDUFKJUDQW

18