A Dynamic Approach to Medical Data
A Dynamic Approach to Medical Data
A Dynamic Approach to Medical Data
,QGLDQ+HDOWKFDUH
7DZVHHI$\RXE6KDLNKDQG5DVKLG$OL6HQLRU0HPEHU,(((
'HSDUWPHQWRI&RPSXWHU(QJLQHHULQJ$OLJDUK0XVOLP8QLYHUVLW\8WWDU3UDGHVK,QGLD
WDZVHHI#JPDLOFRPUDVKLGDOLDPX#UHGLIIPDLOFRP
$EVWUDFW²'DWDQRZDGD\VKDVEHFRPHWKHXWPRVWDVVHWIRU VFKHGXOLQJ LQGLYLGXDO PHGLFDO UHFRUGV UDGLRORJ\ LPDJLQJ
WDNLQJDQ\LQWHOOLJHQWEXVLQHVVGHFLVLRQDQGLQWKHDJHRI%LJ SKDUPDF\ ODERUDWRU\ EORRG EDQN SDWKRORJ\ WKH HPHUJHQF\
'DWD LW KDV EHFRPH EDFNERQH RI HYHU\ NQRFN DQG FRUQHU GHSDUWPHQW D PDVWHU SDWLHQW LQGH[ ILQDQFH ELOOLQJ KXPDQ
DQGWKXVLWKDVEHFRPHWKHIXHOIRUWKHDQDO\WLFVSKDVH,Q UHVRXUFHVDQGVXSSOLHV*LYHQWKHLQGLYLGXDOLW\RIHDFKSDWLHQW
%LJ 'DWD GDWD LV QRW RQO\ DYDLODEOH LQ EXON YROXPLQRXV YDULDWLRQV LQ SUDFWLFH DQG WKH GLVSDUDWH VRXUFHV RI GDWD DQ
DPRXQWEXWDOVRSRVVHVVFRPSOH[GLYHUVHIRUPDWVEHFDXVHRI DQDO\WLFDOQHHGFDQEHDQ\W\SHSURMHFW
WKHYDU\LQJVRXUFHVRIGDWD0RGHUQ+HDOWKFDUHJHQHUDWHV %LJGDWDLVHYHU\ZKHUHUDQJLQJIURPFRPPHUFHEDQNLQJ
DODUJHDPRXQWRIGLYHUVHGDWDUHODWHGWRSDWLHQWVLQGLJLWDO EXVLQHVV KHDOWK HQYLURQPHQW DJULFXOWXUH HWF %LJ 'DWD LV D
IRUPDW6LQFHPRGHUQZHEDSSOLFDWLRQVJLYHVDVWDWLFYLHZ FROOHFWLYHQDPHRIVHWRIWHFKQLTXHVDQGKDUGZDUHWRROVZKLFK
RIWKHSDWLHQWUHODWHGGDWDOLNH(+5 (OHFWURQLF+HDOWKFDUH DUH DEOH WR VROYH WKH SUREOHP RI WKH GDWD ZKLFK WUDGLWLRQDO
5HFRUG 3+5 3HUVRQDO +HDOWKFDUH 5HFRUG (05 GDWDEDVHVZHUHQRWDEOHWRVROYH,QKHDOWKFDUHELJGDWDUHIHUV
(OHFWURQLF 0HGLFDO 5HFRUG 051 0HGLFDO 5HFRUG WR HOHFWURQLF KHDOWK GDWD VHWV VR ODUJH DQG FRPSOH[ WKDW
1XPEHU 0+5 0RELOL]HG+HDOWK5HFRUG DQG(OHFWURQLF WUDGLWLRQDOVRIWZDUH DQGRUKDUGZDUH FDQ¶W PDQDJHWKHP>@
+HDOWKFDUH 3UHGLFWLYH $QDO\WLFV H+3$ LQ 86 KRVSLWDOV %HFDXVHRILWVYROXPHWKHUDWHRILWVJHQHUDWLRQDQGGLYHUVLW\
ZKLFK ODFN LQ IOH[LELOLW\ ZKHQ PXOWLSOH PHGLFDO GDWD DUH RIGDWDW\SHV%LJGDWDLQKHDOWKFDUHLVRYHUZKHOPLQJLQWHUPV
VKRZQ DW WKH VDPH WLPH 7KLV PD\ LJQRUH WKH XVHUV WR RIWKHVSHHGDWZKLFKLWPXVWEHPDQDJHG>@+HDOWKFDUHLVDOVR
FRQFHQWUDWHRQLPSRUWDQWDVSHFWVRIWKHLUKHDOWKVWDWXVDQG DQHPHUJLQJVRXUFHRIWKHELJGDWDEHFDXVHLWSURGXFHVGDWDLQ
SK\VLFLDQV WR ORVH FULWLFDO SDWLHQWV VLWXDWLRQV 7KLV SDSHU YDVWDPRXQWVE\WKHUDSLGGLJLWL]DWLRQRIWKHGDWDDQGDOVRZLWK
SURSRVHVDSURWRW\SHRIDG\QDPLFDQGIXOO\FXVWRPL]DEOH D ORW RI GLIIHUHQW GLYHUVH IRUPDWV RI GDWD %LJ 'DWD LV PDLQO\
*UDSKLFDO8VHU,QWHUIDFH *8, IRUWKH,QGLDQ+HDOWKFDUH FKDUDFWHUL]HGE\96
ZKLFKZLOOUHSODFHWKHVWDWLFZHESDJHVRISDWLHQWVLQRUGHU L 9ROXPH,WLVWKHKXJHDPRXQWRIGDWDDYDLODEOHQRZDGD\V
WR SURYLGH SDWLHQWV ZLWK FXUUHQW DQG KLVWRULFDO PHGLFDO ,WGHDOVZLWKVL]HRIWKHGDWD7KH86KHDOWKFDUHV\VWHPDORQH
GDWD DQG DOORZ WKHP WR DQDO\]H WKHLU OLIHVW\OH 7KLV UHDO WRXFKHG WKH ODQGPDUN LQ UHDFKLQJ WKH PDUN RI H[DE\WHV
WLPHKHDOWKPRQLWRULQJZLOOJLYHSDWLHQWVDEHWWHUDZDUHQHVV JLJDE\WHV LQ DQG ZLWK VXFK D JURZLQJ SDFH LV
RQWKHLURYHUDOOVWDWXV H[SHFWHGWRUHDFKWKH]HWWDE\WH JLJDE\WHV VFDOHVRRQDQG
.H\ZRUGV²%LJ'DWD(+5 (OHFWURQLF+HDOWK5HFRUG 'DWD QRWORQJIDUWKH\RWWDE\WH JLJDE\WHV >@
'ULYHQ+HDOWKFDUH2UJDQLVDWLRQ ''+$ LL 9HORFLW\,WLVWKHVSHHGRIFUHDWLQJVWRULQJDQGDQDO\]LQJ
WKHGDWD6LQFHWKH%LJ'DWDDSSOLFDWLRQVQHHGWKH 5HDO7LPH
,1752'8&7,21
3URFHVVLQJRIWKHGDWDIRUDFWLRQEDVHGUHVXOWVVRWKHUDWHQHHGHG
³%HWWHUFDUHKDSSHQVZKHQ\RXEHFRPHGDWDGULYHQ´ IRU GDWD GULYHQ DFWLRQV VKRXOG EH FRPSDWLEOH ZLWK WKH UDWH RI
JHQHUDWLRQ DQG SURFHVVLQJ RI WKH GDWD 7KH LQFUHDVH LQ WKH
:HDUHOLYLQJLQDQDJHRI%LJGDWD ZKLFKLVH[SHFWHGWR
YROXPHDQGYDULHW\RIKHDOWKFDUHGDWDLVKLJKO\UHODWHGWRWKH
FKDQJH HYHU\WKLQJ 8VLQJ %LJ 'DWD HIIHFWLYHO\ LQ KHDOWK FDUH YHORFLW\DWZKLFKLWLVSURGXFHGDQGWKHVSHHGQHHGHGWRUHWULHYH
GDWD FDQVDYH DQHVWLPDWHGRIWKHWULOOLRQLQDQQXDO DQGDQDO\]HWKHGDWDIRUWLPHO\GHFLVLRQPDNLQJ
86KHDOWKFDUHVSHQGLQJ>@,QLW\RXFDQPDSWKHSHUVRQDO
LLL 9DULHW\ ,W UHIHUV WR WKH &RPSOH[LW\ RI WKH GDWD ,QLWLDOO\
'1$IRU0RXQWDLQVRIVWUXFWXUHGXQVWUXFWXUHGDQGVHPL
'DWDZDVVWRUHGLQWKHWDEOHVOLNH5HODWLRQDOWDEOHVZKLFKZHUH
VWUXFWXUHGGDWDODNHVDUHJHQHUDWHGE\+HDOWKFDUH$EHG
SUHGHILQHGVWUXFWXUH%XWZLWKWKHGDWDDYDLODEOHIURPGLYHUVH
IDFLOLW\ZKHUHHDFKSDWLHQWUHFRUGSRWHQWLDOO\FRXOGFRQWDLQDV
VRXUFHV DQG SRVVHVVLQJ GLYHUVH IRUPDWV OLNH &OLQLFDO 1RWHV
PDQ\DVFKDUDFWHUVFRXOGSURGXFHa*%>@SHU\HDU /DE7HVWV0HGLFDO,PDJHV6WUHDPVIURP6PDUW6HQVRUVLWLV
RI VWUXFWXUHG GDWD LQ LQGLYLGXDO SDWLHQW UHFRUGV DORQH WKH XWPRVW QHHG WR LQWHJUDWH WKHVH GLYHUVH GDWD IRUPDWV VR DV
,QIRUPDWLRQLQWKHVHUHFRUGVLVUHDGLO\LGHQWLILDEOHDQGGLUHFWO\
GHULYHWKHSURGXFWLYHNQRZOHGJHZKLFKLVQRWSRVVLEOHIURPD
VXSSRUWVDQDO\VLVDOORZLQJH[DPLQDWLRQRI VXFK PDQDJHPHQW
VLQJOHVRXUFHRIGDWD
LQGLFDWRUVDVDYHUDJHOHQJWKRIVWD\SDWLHQWVSHUEHGSHU\HDU
LY 9DOXH ,W LV WKH WHFKQLTXH RI LQWHJUDWLQJ DOO WKH GLIIHUHQW
DQGQXPEHURIUHDGPLVVLRQVZLWKLQGD\V7KHYDVWDPRXQW IRUPDWVRIWKHGDWDLQRUGHUWRJHWYDOXDEOHLQVLJKWVIURPLWLQ
RIGDWDFUHDWHG²DVPXFKDV²LVXQVWUXFWXUHG WH[WYRLFH WKHIRUPRIYDOXH
DQQRWDWLRQVLPDJHV 7KHFKDOOHQJHEHFRPHVKRZWRXVHWKDW
7KH UHVW RI WKH SDSHU DV ODLG DV &KDSWHU GLVFXVVHV LQ
XQVWUXFWXUHGGDWDWRZDUGDEHQHILFLDOSXUSRVH+HDOWKFDUHGDWD
GHWDLODERXWWKHQHHGRIWKHG\QDPLFDSSURDFKRIWKHPHGLFDO
DUHFRQWDLQHGLQPXOWLSOHRIWHQXQFRQQHFWHGV\VWHPV+RVSLWDO
GDWD,WGHVFULEHVWKHROGV\VWHPVZKHUHSDWLHQWGDWDZDVVWRUHG
LQIRUPDWLRQ WHFKQRORJ\ FDQ LQFOXGH GLVFUHWH V\VWHPV IRU
978-1-5090-6399-4/17/$31.00 2017
c IEEE 158
ZKLFKZDVLVRODWHGKDYLQJQRLQWHUDFWLYLW\DWDOOOHDGLQJWRD E\XVLQJ PRWLRQ VHQVRUV WKDW PRQLWRU FKDQJHVLQ WKH QHUYRXV
VWDWLFQDWXUH,QLWZHESRUWDORI$OO,QGLD,QVWLWXWHRI0HGLFDO V\VWHP EUDLQDFWLYLW\ $FFRUGLQJWR$%,UHVHDUFK>@DURXQG
6FLHQFHV $,,06 LQ,QGLDIRUWKHSDWLHQWLVDOVRGLVFXVVHGZLWK ILYHPLOOLRQZLUHOHVVPHGLFDO%RG\$UHD1HWZRUNV 0%$1V
LWV FRUUHVSRQGLQJ SLWIDOOV &KDSWHU GLVFXVVHV DERXW WKH QHZ ZLOOEHDYDLODEOHLQWKHQH[WILYH\HDUV
DQGG\QDPLFDSSURDFKRIGHDOLQJZLWKWKHSDWLHQWUHODWHGGDWD :HKDYHVWXGLHGDG\QDPLFDQGFXVWRPL]DEOHDSSURDFKWR
WKURXJKD*UDSKLFDO8VHU,QWHUIDFH *8, ZKLFKZLOOQRWRQO\ WKHSHUVRQDOPHGLFDOGDWDLQFRQWH[WRI,QGLDQ+HDOWKFDUHVRDV
UHGXFHFRWVEXWZLOOSURYLGHDVDWLVILHGWUHDWPHQWWRWKHSDWLHQWV WR LPSURYH ERWK SDWLHQW DQG FDUH SURYLGHU DZDUHQHVV RI WKH
LQWHUPVRIFXUH&KDSWHUGHVFULEHVDK\SRWKHWLFDOFDVHVWXG\ RYHUDOOSDWLHQW VKHDOWKVWDWXV7KLVLQYROYHVWKHXVDJHRIPDQ\
RIKRZWKHQH[WJHQHUDWLRQKHDOWKFDUHV\VWHPZLOOEHGHOLYHULQJ UHDOWLPH VHQVRUV ,QWHUQHW RI 7KLQJV ,R7 WR FDWFK GDWD DQG
LWVVHUYLFHV7KHQ&KDSWHULVWKHFRQFOXGLQJSDUWRIWKHSDSHU DOORZXVHUVWRFXVWRPL]HWKHZD\WKRVHDUHVKRZQ,QWKLVZD\
IROORZHGE\WKH5HIHUHQFHVDWWKHHQG ZKLOH SDWLHQWV FDQ PRQLWRU PHGLFDO GDWD DQG YLVXDOL]H WKHLU
KLVWRU\WRDQDO\]HWKHOLIHVW\OHFDUHSURYLGHUFDQSURPSWO\VSRW
67$7(0(172)352%/(0 DQ\ LVVXH DQG JLYH D IDVW DVVLVWDQFH )XUWKHUPRUH VKRZLQJ
WKRVHNLQGRILQIRUPDWLRQLQHYHU\XVHU VKRPHSDJHFDQOHDGD
6LQFHWKHODVWGHFDGHWKHZKROHZRUOGLVJHWWLQJFKDQJHG GHHSHUSDUDPHWHUPRQLWRULQJIRUHYHU\XVHU7KHDGRSWLRQRI
LQWR GLJLWDO IRUP WKDQNV WR UDSLG DGYDQFHPHQW LQ WKH
LQIRUPDWLRQ WHFKQRORJ\ DQG UHODWHG ILHOGV 7KLV ZDYH KDYH
PHUJHG HYHQ WKH +HDOWKFDUH 6\VWHP E\ WKH DGRSWLRQ RI
(OHFWURQLF 0HGLFDO 5HFRUG (05 3DWLHQW +HDOWK 5HFRUG
3+5 DQG (OHFWURQLF +HDOWK 5HFRUG (+5 >@>@ 3DWLHQWV
FDQNHHSWKHPVHOYHVLQWRXFKZLWKWKHLUSUHIHUUHGFDUHSURYLGHU
SK\VLFLDQVE\VHDUFKLQJLQWKHWUDGLWLRQDOFDVHLQZKLFKSDWLHQW
UHODWHG GDWD LV XVXDOO\ VWRUHG LQ HOHFWURQLF PHGLFDO UHFRUG
3DWLHQWVQHHGDVVLVWDQFHWRDFFHVVWKHLUSURILOHEHFDXVHRIWKH
VWDWLF QDWXUH RI WKLV DSSURDFK ZKLFK LQ WXUQ PD\ OHDG WR WKH
VLWXDWLRQRIODWHDVVLVWDQFHIURPFDUHJLYLQJVLGHEHFDXVHRIWKH
XQDYDLODELOLW\ RI WKH UHDOWLPH NQRZOHGJH IURP DQ\ SDWLHQW V
KHDOWKSDUDPHWHUZKLFKLVEHFRPLQJYHU\FUXFLDO
:LWK WKH UDSLG JURZWK RI WKH FHOO SKRQH DQG SHUVRQDO
VWUHDPLQJGDWDGHYLFHVXVDJHLQWKHIRUPRIV\PSWRPWUDFNHU
DSSRQL3KRQHWKHDPRXQWRIGDWDIURPWKHSDWLHQWKDVWRXFKHG
WKHVNLHVDQGSURSHUDQGFRQWLQXRXVPRQLWRULQJRIZKLFKZLOO
OHDGWRDKHDOWK\VRFLHW\1HZ0RELOHSKRQHVDUHHTXLSSHGZLWK
GLIIHUHQWNLQGVRIVHQVRUV HJPRWLRQVHQVRUVORFDWLRQVHQVRUV
DQGKDSWLFVHQVRUV (YHU\WLPHDSHUVRQXVHVKLVKHUFHOOSKRQH
KXJH DPRXQWV RI VWUHDPLQJ GDWD LV JHQHUDWHG (0&
&RUSRUDWLRQDELJVWRUDJHFRPSDQ\HVWLPDWHVWKDWWKHDPRXQW
RISHUVRQDOVHQVRULQIRUPDWLRQVWRUDJHZLOOEDODQFHIURP
WRLQWKHQH[WGHFDGH>@7KHPRVWSRZHUIXOZD\WRNQRZ
DERXW D SHUVRQ¶V EHKDYLRU LV WR FRPELQH WKH XVH RI VRPH
VRIWZDUHZLWKGDWDIURPSKRQHDQGIURPRWKHUVRXUFHVVXFKDV
VOHHSPRQLWRUPLFURSKRQHDFFHOHURPHWHUVFDPHUD%OXHWRRWK 7DEOHEULHIO\LQWURGXFHVVRPHFRPPHUFLDOSURGXFWVWKDW
YLVLWHGZHEVLWHHPDLOVDQGORFDWLRQ FROOHFWELRORJLFDOGDWDDQGXVHLWLQKHDOWKFDUH
7RJHWDSLFWXUHRIKRZUHDOLW\PLQLQJFDQLPSURYHKHDOWKFDUH
V\VWHPKHUHDUHVRPHH[DPSOHV WKHHOHFWURQLFPHGLFDOUHFRUGUDWKHUWKDQWKHFODVVLFDORQHLVD
8VLQJVSHFLDOVHQVRUVLQPRELOHVVXFKDVDFFHOHURPHWHUVRU ZD\WRUHYROXWLRQL]HSHRSOH VDSSURDFKWRKHDOWK>@%HFDXVH
PLFURSKRQHVRPHGLDJQRVLVGDWDFDQEHH[WUDFWHG,QIDFWIURP RI WKH PRGHUQ SHUYDVLYH V\VWHPV RI VHQVRUV HJ ,QWHUQHW RI
WKHZD\DSHUVRQWDONVLQFRQYHUVDWLRQVLWLVSRVVLEOHWRGHWHFW 7KLQJV ,R7 GHYLFHV DQGWKHDGYDQWDJHRIWKHPRGHUQVPDUW
YDULDWLRQVLQPRRGDQGHYHQWXDOO\GHWHFWGHSUHVVLRQ>@ SKRQHDSSOLFDWLRQVSHRSOHJHWLQYROYHGLQDKHDOWKLHUOLIHVW\OH
6XSHUYLVLQJ D PRELOH¶V PRWLRQ VHQVRUV FDQ FRQWULEXWH WR >@,QWHJUDWLQJGDWDWRJHWKHUWRJHWDIXOOSLFWXUHRIHQWLWLHVOLNH
UHFRJQL]HVRPHFKDQJHVLQJDLWDQGFRXOGEHDQLQGLFDWRURIDQ SDWLHQWVSK\VLFLDQVSURFHGXUHVILQDQFLDOVDQGIDFLOLWLHV DQG
HDUO\VWDJHRI3DUNLQVRQ¶VGLVHDVH VRRQ LVWKHEUHDGDQGEXWWHURIVPDUWKHDOWKFDUH:HFRXOGQRW
&RPPXQLFDWLRQ ORJV RU VXUYH\V UHFRUGHG E\ PRELOHV RU ILQGDQ\VLQJOHUREXVWSDSHULQZKLFKDXQLILHGSODWIRUPLVJLYHQ
FRPSXWHUVJLYHMXVWDSDUWRIWKHSLFWXUHRIDSHUVRQ¶VOLIHDQG ZKHUH XVHUV FDQ HDVLO\ JHW DQ RYHUYLHZ >@>@ EHFDXVH
EHKDYLRU %LRPHWULF VHQVRUV FDQ JR IXUWKHU WR WUDFN EORRG +HDOWKFDUH EHLQJ D QHZ ILHOG LQ WKH ,7 ZRUOG ,Q IDFW HDFK L
SUHVVXUH SXOVH VNLQ FRQGXFWLYLW\ KHDUWEHDWV EUDLQ RU VOHHS KHDOWKVHQVRURUDSSOLFDWLRQKDVLWVRZQSURSULHWDU\ VRPHWLPHV
DFWLYLW\$VLJQRIGHSUHVVLRQIRULQVWDQFHFDQEHUHYHDOHGMXVW
2017 International Conference On Big Data Analytics and computational Intelligence (ICBDACI) 159
)LJXUH&XUUHQW3DWLHQW+RPHSDJH $,,06
160 2017 International Conference On Big Data Analytics and computational Intelligence (ICBDACI)
FRQWH[W RI WKH JLYHQ V\VWHP ³, KDYH EHHQ IDOOLQJ LOO IURP
DIWHUQRRQDIWHUFRPLQJEDFNIURPP\MRE,ZDVYHU\H[KDXVWHG
DQG IHHOLQJ HQHUJ\ OHVV DQG H[SHFWLQJ VRPH GL]]\ VSHOOV DQG
RWKHURGGVHHPLQJO\XQUHODWHGV\PSWRPV²H\HǦWZLWFKLQJHDUǦ
ULQJLQJVXGGHQZHLJKWFKDQJHVDSSHWLWHOHVVDQGGLIILFXOW\LQ
VOHHSLQJ , FDOO P\ FDUH FRRUGLQDWRU ZKR UHSUHVHQWV ERWK WKH
LQVXUDQFHFRPSDQ\DQG P\SURYLGHUDVWKHV\PSWRPVVWDUWHG
JHWWLQJ HQODUJHG $ ORRN ZDV EHHQ PDGH RQ P\ KLVWRU\
LQFOXGLQJ WKH UHFHQW DGGLWLRQ RI P\ '1$ SURILOH WKDW ,¶YH
UHFHLYHG WKURXJK DQ LQGHSHQGHQW RUJDQL]DWLRQ %DVHG RQ P\
JHQHWLF ULVN IDFWRUV RI DJH JHQGHU DQG VR RQ , ZDV
UHFRPPHQGHGWRFRQVXOWDQHQGRFULQRORJLVW$QDSSRLQWPHQWLV
E
VFKHGXOHGULJKWWKHQDQGDIWHUIHZGD\V ODWHU, ZHQWLQWRWKH
)LJXUH7KHSURSRVHG*UDSKLFDO8VHU,QWHUIDFH+HDOWKFDUH
FOLQLFIRUDWKRURXJKFKHFNXS7KHUHZDVQRDQ\VRUWRISDSHU
$UFKLWHFWXUH D WKHSDWLHQWKRPHSDJH E WKHDYDLODEOH
ZRUNZKLFK,ZDVVXSSRVHGWRILOOWKH\NQRZZKR,DPZK\
SDUDPHWHUVDFFHVVLEOHWRWKHSDWLHQWIURPLWVKRPHSDJH
,¶P WKHUH P\ ELUWK GDWH DQG DOO RWKHU UHOHYDQW LQIRUPDWLRQ
,QLWLDOO\WKH\PDGHDVVHVVPHQWDQGEORRGSUHVVXUH7KHQXUVH
IURP WKH ZD\ PRGHUQ VPDUWSKRQH 2SHUDWLQJ 6\VWHPV DOORZ
DVNVLIDQ\WKLQJKDVFKDQJHGVLQFHWKHSKRQHFDOODQGFRQILUPV
XVHUVWRFXVWRPL]HDQGUHDUUDQJHLFRQVRQWKHGLIIHUHQWVFUHHQV
DQ\QHZPHGLFDWLRQVVLQFHWKHODVWUHFRUGLQJ,GHQLHGWKDWDQG
0RUHRYHU ZLWK WKLV LQWHUDFWLYH DSSURDFK >@ D PRUH
ZLWKLQ D IHZ PRPHQWV WKH QXUVH VHQGV PH WR ODE IRU D EORRG
FRQVWDQWFRQWUROFDQEHWDNHQE\WKHSDWLHQWRIKLVSURILOHHYHU\
GUDZ
WLPHKHVKHORJLQLQWRWKHZHESRUWDO 2XUDSSURDFKLVWRWDOO\
GLIIHUHQWDVZHKDYHLQFRUSRUDWHGWKH%LJ'DWDFRQFHSWLQDOVR
7KHQDIWHUDVKRUWZDLWWKHGRFWRUFRPHVLQDQGVLWVDFURVV
XQOLNHWKHDFWXDOVHUYLFHVGHYHORSHGE\VRPHPDMRUWHFKQRORJ\
IURPPHWRKDYHDGLVFXVVLRQ+ROGLQJDWDEOHWLQKHUKDQGWKHUH
FRPSDQLHVVXFKDV0LFURVRIWZLWK+HDOWK9DXOWDQG$SSOHZLWK
LVQRFRPSXWHUVFUHHQDQ\ZKHUHLQWKHURRPDQGVKHPDNHVQR
L26 +HDOWK >@ :KLOH FRPPHUFLDO VROXWLRQV FRQFHQWUDWH RQ
DWWHPSW WR GLVWUDFW KHUVHOI IURP RXU FRQYHUVDWLRQ DERXW P\
GDWDFROOHFWLRQDQGYLVXDOL]DWLRQDVNLQJIRUDPHGLFDOVXSSRUW
KHDOWKDVNLQJPHMXVWDERXWP\V\PSWRPVWKHLUIUHTXHQF\DQG
ZKHQQHHGHGRXUDSSURDFKDOORZVSDWLHQWVDQGSK\VLFLDQVWR
WKHOHYHOWRZKLFKWKH\GLVUXSWP\GDLO\OLIH6RRQWKHODEUHVXOWV
PHHWDQGVKDUHPHGLFDOUHFRUGVSKDUPDFRORJLFDOWKHUDSLHVHWF
UHWXUQRQ KHUWDEOHWZLWKDVXEWOHSRSXSER[7KH\FRQILUP
7KH SK\VLFLDQV DUH FRQWLQXRXVO\ PRQLWRULQJ WKH KHDOWK
ZKDWWKHGDWDVXSSRUWHGP\WK\URLGVHHPVWREHRXWRIEDODQFH
SDUDPHWHUVRIWKHSDWLHQWOLNHEORRGSUHVVXUHKHDUWUDWHLQVXOLQ
7RPDQDJHWKHSURJUHVVLRQWRZDUGPDQDJHPHQWRIP\WK\URLG
OHYHOE\XVLQJWKHPRGHUQVXSSOLFDWHGVPDUWVHQVRU 2XU
SUHVFULSWLRQZDVJLYHQWRPHZKLFK,ZDVWRIROORZ$SK\VLFDO
DSSURDFK OHWV FDUHSURYLGHUV WR NHHS WUDFN LQ UHDO WLPH WKH
H[DPVKRZHGQRVLJQRIDWXPRUVRQRDGYDQFHGLPDJLQJWHVW
GHVLUHGSDWLHQW VKHDOWKSDUDPHWHU RUSDUDPHWHUV 2QSDWLHQW V
ZDVRUGHUHGVDYLQJ$GGLWLRQDOFDUHSURYLGHUVZHUHDGGHGWR
VLGHWKHYLVXDOL]DWLRQRIKHDOWKLQIRUPDWLRQPD\OHDGWRDVHOI
P\WHDPLQFOXGLQJDQDFXSXQFWXULVWZKRKHOSVPHZLWKVRPH
DZDUHQHVVRIWKHOLIHVW\OHDQGWKHRYHUDOOKHDOWKVWDWXV>@
RIWKHV\PSWRPVDQGVWUHVVPDQDJHPHQWZKLFKVHHPVWRKDYH
'LIIHUHQWDQGFXVWRPL]DEOHYLHZVDOORZLQJXVHUVWRUHDUUDQJH
H[DFHUEDWHGP\V\PSWRPV
WKHLUSURILOHWKHZD\WKH\IHHOFRPIRUWDEOH
+RXUO\GDLO\JUDSKVIRUHDFKGHVLUHGVHQVRU
,NQRZWKLVEHFDXVH,NHSWDQDSSOLFDWLRQ DSS DV\PSWRP
+LVWRULFDOJUDSKVIRUWKRVHSDUDPHWHUVWKDWFDQQRWEHGDLO\
WUDFNHURQP\L3KRQHWKDWVHQWGDWDWRP\GRFWRU,WZDVMXVW
RUKRXUO\PRQLWRUHG
RQH DSS RI D FRXSOH WKDW ZHUH XVHG WR WUDFN P\ PHGLFDWLRQ
2QWKH$GGQHZJUDSKER[DWWKHLQWKHILJXUH D SDWLHQW
DGKHUHQFHLPSRUWDQWZKHQPDQDJLQJP\WK\URLGDQGWU\LQJWR
FDQDOWHUDQGDGGQHZSDWLHQWUHODWHGLVVXHVWRKLVKHUSURILOH
ILQG WKH ULJKW SKDUPDFHXWLFDO PL[ LW WUDFNHG P\ IRRG LQWDNH
6LPLODUO\WRGHOHWHDQXQGHVLUHGJUDSKLWFRXOGULJKWFOLFNRQLW
DFWLYLW\ DQG VWUHVV OHYHO VHQGLQJ DOO RI WKH LQIRUPDWLRQ
DQG FKRRVH WKH GHOHWH RSWLRQ RQ WKH FRQWH[WXDO PHQX $OO
ZLUHOHVVO\EDFNWRP\HOHFWURQLFKHDOWKUHFRUGV (+5V ZKHUH
DYDLODEOHJUDSKVFRXOGSRSXSWRWKHXVHURQFHWKH$GGQHZ
P\ FDUH FRRUGLQDWLRQ WHDP WKH RQH , RULJLQDOO\ FDOOHG FRXOG
JUDSKER[LVFOLFNHG )LJXUH E :LWKWKLVDSSURDFKHDFK
WUDFNWKDWGDWDDQGLQFRRSHUDWLRQZLWKP\SK\VLFLDQGHWHUPLQH
SDWLHQW FDQ FXVWRPL]H LWV RZQ KRPH SDJH E\ DGGLQJ QHZ
WKHQH[WEHVWVWHSVLQP\FDUH²DOOZLWKRXWVWHSSLQJIRRWLQWRD
SDUDPHWHUVRUGHOHWLQJFXVWRPW\SHVRIYLHZVKRZLQJFROOHFWHG
FOLQLF$QDGGLWLRQDODSSKHOSVPHNHHSWUDFNRIWKHH[SHQVHV
GDWDIURPDOOVHQVRUVDQGGHYLFHVKHVKHKDV
LQFOXGLQJ ELOOV IRU WKH FDUH , UHFHLYHG DQG WKH EDODQFH RI P\
KHDOWKVDYLQJVDFFRXQW +6$ ,WHYHQDOORZVPHWRSD\WKHELOO
&$6(678'<)520$%29(',6&866,21 RUVHQGTXHVWLRQVWRWKHFODLPVGHSDUWPHQW,GLGQ¶WHYHQKDYH
)RUP WKH DERYH IUDPHZRUN ZH DUH KHUH GUDZLQJ D FDVH WRFDOOWRJHWSUHDSSURYDOIRUP\DFXSXQFWXULVWEHFDXVHVKHZDV
VWXG\ RI DQ DQRQ\PRXV SHUVRQ $NKLO ZKR VXSSRVHG LV QRW SDUWRIWKHFDUHWHDP´
IHHOLQJ ZHOO %HORZ LV KRZ KH FDQ QDUUDWH KLV VWRU\ IURP WKH
2017 International Conference On Big Data Analytics and computational Intelligence (ICBDACI) 161
>@ ' 3HQWODQG ' /D]HU 7 %UHZHU DQG 7 +HLEHFN
³,PSURYLQJ 3XEOLF +HDOWK DQG 0HGLFLQH E\ XVH RI 5HDOLW\
0LQLQJ´KWWSKGPHGLDPLWHGX5:-)5HDOLW\0LQLQJ
&21&/86,21$1':25.$+($' VXPPDU\SGI)HEUXDU\>$FFHVVHG)HE@
,QWKHWUDGLWLRQDOFDVHWKHSDWLHQWUHODWHGGDWDLVVWRUHG >@+0RXVDQQLIDQG,.KDOLO³7KH+XPDQ)DFHRI0RELOH´
,QIRUPDWLRQDQG&RPPXQLFDWLRQ7HFKQRORJ\/HFWXUH1RWHV
LQ WKH (OHFWURQLF +HDOWK 5HFRUG +(5 3HUVRQDO +HDOWK LQ &RPSXWHU 6FLHQFHV 6SULQJHU 9ROXPH SS
5HFRUG 3+5 ZKLFKLVKDYLQJSRVVHVVLQJVWDWLFVWUXFWXUH
DVWKHUHLVQRLQWHUDFWLYLW\RIWKHGDWDEHWZHHQWKHSDWLHQW >@ ³+RPH _ $%, 5HVHDUFK´ >2QOLQH@
UHODWHG GDWD DQG WKH SK\VLFLDQV 7R UHSODFH WKLV VWDWLF $YDLODEOHKWWSVZZZDELUHVHDUFKFRP>$FFHVVHG$SU
@>$FFHVVHG0DUFK@
V\VWHP ZH KDYH SURSRVHG DV G\QDPLF *UDSKLFDO 8VHU >@³%RG\0HGLD5HDFK<RXU+HDOWK )LWQHVV*RDOVZLWK
,QWHUIDFH *8, ZKHUHDQ\SDWLHQWFDQFUHDWHDSURILOHDQG %RG\0HGLD ),7´ >2QOLQH@ $YDLODEOH
DGGRUGHOHWHWKHLPSRUWDQWKHDOWKFDUHUHODWHGSDUDPHWHUV KWWSZZZERG\PHGLDFRP>$FFHVVHG)HE@
7KHSDWLHQWZLOOEHFRQWLQXRXVO\VHQGLQJWKHUHDOWLPHGDWD >@ ³0RELOH &DUGLDF 2XWSDWLHQW 7HOHPHWU\ 0&27
&DUGLDF 7HOHPHWU\ _ &DUGLR1HW (YHQW 0RQLWRUV´ >2QOLQH@
IURP WKH VPDUW VHQVRUV ZKLFK ZLOO EH FRQWLQXRXVO\ $YDLODEOH KWWSVZZZFDUGLRQHWFRP >$FFHVVHG )HE
PRQLWRUHGE\WKHFDUHWDNHUV ,IDWDQ\WLPHWKH\ILQG @
DQ\ DEQRUPDOLW\ LQ WKH QRUPDO ZDYH VLJQDO WKH\ FDQ >@³([FOXVLYH6OHHSFRDFKFRPSDQ\=HRLVVKXWWLQJGRZQ_
LQIRUP WKH ULJKW SDWLHQW DW WKH ULJKW WLPH IRU LPPHGLDWH PRELKHDOWKQHZV´ >2QOLQH@ $YDLODEOH
KWWSPRELKHDOWKQHZVFRPH[FOXVLYHVOHHSFRDFK
SRVLWLYH VWHSV WR EH WDNHQ 7KLV DSSURDFK QRW RQO\ ZLOO FRPSDQ\]HRLVVKXWWLQJGRZQ>$FFHVVHG)HE@
UHGXFHFRVWVEXWZLOOSURYLGHQREOHWUHDWPHQWWRWKHSDWLHQWV >@³6OHHSWUDFNHUE\0RWLRQ;_6OHHSWUDFNHUFRP´>2QOLQH@
EDVHG RQ KLVKHU UHDO GDWD :H DOVR GLVFXVVHG DERXW WKH $YDLODEOHKWWSZZZVOHHSWUDFNHUFRP>$FFHVVHG)HE
WUDGLWLRQDODSSURDFKRIKRZWKH$,,06 $OO,QGLD,QVWLWXWH @
>@ ³+56, 6HQVRU :LN,' WKH ,QGXVWULDO 'HVLJQ
RI0HGLFDO6FLHQFH LVKDQGOLQJWKHSDWLHQWVLQWKHGLDJUDP (QJLQHHULQJ ZLNL´ >2QOLQH@ $YDLODEOH
,QIXWXUHPRUHZRUNFDQEHGRQHLQRUGHUWRPDNHWKLV*8, KWWSZZZZLNLGHXLQGH[SKS+56,B6HQVRU
PRUHXVHUIULHQGO\VRWKDWHYHQWKHDYHUDJHSHUVRQFDQFDUH >$FFHVVHG)HE@
DERXWKLVKHUZHOOEHLQJ >@5+LOOHVWDG-%LJHORZ$%RZHU)*LURVL50HLOL
5 6FRYLOOH DQG 5 7D\ORU ³ &DQ HOHFWURQLF PHGLFDO UHFRUG
V\VWHPV WUDQVIRUP KHDOWK FDUH" 3RWHQWLDO KHDOWK EHQHILWV
5HIHUHQFHV VDYLQJVDQGFRVWV´+HDOWK$IIDLUV9ROXPH ,VVXHSS
>@ . 0DUFRQL DQG + /HKPDQQ ³ %LJ 'DWD DQG +HDOWK
$QDO\WLFV´ 7KH *UDGXDWH 6FKRRO 8QLYHUVLW\ RI 0DU\ODQG >@ $ 5HFWRU : 1RZODQ 6 .D\ & *REOH DQG 7
8QLYHUVLW\&ROOHJH+DUROG/HKPDQQ6FKRRORI0HGLFLQH7KH +RZNLQV³$IUDPHZRUNIRUPRGHOOLQJWKHHOHFWURQLFPHGLFDO
-RKQV +RSNLQV 8QLYHUVLW\ &5& 3UHVV 7D\ORU DQG )UDQFLV UHFRUG´ 0HWKRGV RI LQIRUPDWLRQ LQ PHGLFLQH 9ROXPH
*URXSSS,6%1 ,VVXHSS
>@ + 0RXVDQQLI , .KDOLO DQG 6 2ODULX ³&RRSHUDWLRQ LQ >@+)UDVHU3%LRQGLFK'0RRGOH\6&KRL%0DPOLQ
VWDWLFDQGPRELOHVHQVRUEDVHGSODWIRUPVIRUVLWXDWLRQDFWLYLW\ DQG 3 6]RORYLWV ³ ,PSOHPHQWLQJ HOHFWURQLF PHGLFDO UHFRUG
DQGJRDODZDUHQHVV´6$*$ZDUH3URFHHGLQJVRIWKH V\VWHPV LQ GHYHORSLQJ FRXQWULHV´ -RXUQDO RI ,QQRYDWLRQ LQ
LQWHUQDWLRQDO ZRUNVKRS RQ 6LWXDWLRQ DFWLYLW\ JRDO +HDOWK,QIRUPDWLFV9ROXPH,VVXHSS
DZDUHQHVV%HLMLQJ&KLQD SS± >@ '0 +DQ DQG -+ /LP ³6PDUW KRPH HQHUJ\
>@ 5 ,VWHSDQLDQ 6 +X 1 3KLOLS DQG $ 6XQJRRU ³ 7KH PDQDJHPHQW V\VWHP XVLQJ LHHH DQG ]LJEHH
SRWHQWLDORILQWHUQHWRIPKHDOWKWKLQJVPLRWIRUQRQLQYDVLYH &RQVXPHU (OHFWURQLFV´ ,((( 7UDQVDFWLRQV RQ 9ROXPH
JOXFRVH OHYHO VHQVLQJ´ ,Q (QJLQHHULQJ LQ 0HGLFLQH DQG ,VVXHSS
%LRORJ\ 6RFLHW\ (0%& $QQXDO ,QWHUQDWLRQDO >@5<DQJDQG0:1HZPDQ³/HDUQLQJIURPDOHDUQLQJ
&RQIHUHQFHRIWKH,(((SS WKHUPRVWDW OHVVRQV IRU LQWHOOLJHQW V\VWHPV IRU WKH KRPH´ LQ
>@ )URVW DQG 6XOOLYDQ ³'URZQLQJ LQ %LJ 'DWD" 5HGXFLQJ 3URFHHGLQJVRIWKH$&0LQWHUQDWLRQDOMRLQWFRQIHUHQFH
,QIRUPDWLRQ 7HFKQRORJ\ &RPSOH[LWLHV DQG &RVWV IRU RQ 3HUYDVLYH DQG XELTXLWRXV FRPSXWLQJ 8EL&RPS
+HDOWKFDUH 2UJDQL]DWLRQV´ KWWSZZZHPFFRP =XULFK6ZLW]HUODQGSS
FROODWHUDODQDO\VWUHSRUWVIURVWVXOOLYDQUHGXFLQJLQIRUPDWLRQ >@ + :LOOLDPV . 6SHQFHU & 6DQGHUV ' /XQG ($
WHFKQRORJ\FRPSOH[LWLHVDUSGI>$FFHVVHG)HE@ :KLWOH\ - .D\H DQG :* 'L[RQ ³'\QDPLF FRQVHQW D
>@61LJDP³,+777UDQVIRUPLQJ+HDOWK&DUHWKURXJK%LJ SRVVLEOH VROXWLRQ WR LPSURYH SDWLHQW FRQILGHQFH DQG WUXVW LQ
'DWD 6WUDWHJLHV IRU OHYHUDJLQJ ELJ GDWD LQ WKH KHDOWK FDUH KRZHOHFWURQLFSDWLHQWUHFRUGVDUHXVHGLQPHGLFDOUHVHDUFK´
LQGXVWU\´KWWSLKHDOWKWUDQFRPZRUGSUHVVLKW -0,0HGLFDO,QIRUPDWLFV9ROXPH,VVXHSS0DUFK
&%UHOHDVHVELJGDWDUHVHDUFKUHSRUWGRZQORDG
WRGD\>$FFHVVHG)HE@ >@ ' +R ' )HQJ DQG .&KHQ ³'\QDPLF ,PDJH 'DWD
>@6-:DQJ%0LGGOHWRQ/$3URVVHU&*%DUGRQ&' &RPSUHVVLRQLQ6SDWLDODQG7HPSRUDO'RPDLQV7KHRU\DQG
6SXUU 3- &DUFKLGL $) .LWWOHU 5& *ROGV]HU '* $OJRULWKP´,(((7UDQVDFWLRQVRQ,QIRUPDWLRQ7HFKQRORJ\LQ
)DLUFKLOG DQG $- 6XVVPDQ ³ $ FRVWEHQHILW DQDO\VLV RI %LRPHGLFLQH9ROXPH,VVXHSS
HOHFWURQLF PHGLFDO UHFRUGV LQ SULPDU\ FDUH´ 7KH $PHULFDQ >@ . &DEDOOHUR DQG 5 $NHOOD ³'\QDPLFDOO\ 0RGHOLQJ
MRXUQDORIPHGLFLQH9ROXPH,VVXHSS 3DWLHQW¶V +HDOWK 6WDWH IURP (OHFWURQLF 0HGLFDO 5HFRUGV $
>@560DUJDOLW'5RWHU0$'XQHYDQW6/DUVRQDQG6 7LPH 6HULHV $SSURDFK´ LQ 3URFHHGLQJ RI .'' WK
5HLV ³(OHFWURQLF PHGLFDO UHFRUG XVH DQG SK\VLFLDQ ^SDWLHQW $&0 6,*.'' ,QWHUQDWLRQDO &RQIHUHQFH RQ .QRZOHGJH
FRPPXQLFDWLRQDQREVHUYDWLRQDOVWXG\RI,VUDHOLSULPDU\FDUH 'LVFRYHU\ DQG 'DWD 0LQLQJ 6\GQH\ 16: $XVWUDOLD ²
HQFRXQWHUV´3DWLHQWHGXFDWLRQDQGFRXQVHOLQJ9ROXPH $XJXVWSS
,VVXHSS
162 2017 International Conference On Big Data Analytics and computational Intelligence (ICBDACI)