Professional Documents
Culture Documents
3034
Authorized licensed use limited to: Murdoch University. Downloaded on June 15, 2009 at 03:22 from IEEE Xplore. Restrictions apply.
Indeterminacy
Falsity BPNN
GRNN
GiS input data layers
Output
Falsity GRNN
where
TA is the truth-membership function,
IA is the indeterminacy-membership function, and
FA is the false-membership function.
The operations of interval neutrosophic sets are also applied in this paper. Details of the operations can be found
in [14].
111. UNCERTAINTY
ESTIMATION USING INTERVAL
NEUTROSOPHIC
SETSAND ENSEMBLE
NEURAL
NETWORKS
This paper applies GIs input data to ensemble neural networks for the prediction of favourability for gold deposits and
Output
Falsity PNN
3035
Authorized licensed use limited to: Murdoch University. Downloaded on June 15, 2009 at 03:22 from IEEE Xplore. Restrictions apply.
membership and false-membership is high then the nncertainty is low. In conmst, if the difference between both
values is Inw then the uncertainty is high.
In Fig. 1, the proposed neural network ensembles contain
t h ~ components
e
which each consists of a pair of neural
networks. The first pair is feed-forward backpropagation
neural networks (truth BPNN and falsity BPNN). The second
pair is general regression neural networks (truth GRNN
and falsity GRNN). The third pair is polynomial neural
networks ( n t h PNN and faIsity PNN3. Each pair of neural
networks is trained to predict degrees of favourability for deposits (truth-membership values) and degrees of favourability
for barrens (false-membership values). The indeterminacymembership values are calculated from the different between
truth-m~mbershipand fzlse-memhrship values. Therefore,
we have three interval neutrosophic sets which are outputs
from those three pairs of neural netwarks. We can define
these outputs as the following.
Let X j be the set of outputs from the neural netrvork.
In our case, we have three sets of outputs, i.e. XI,
X2and
representitag output sets from BPNN, GRNN and PNN
respectively. Each set Xjcontains the outputs from each pair
of the neural networks. The output set for BPNN is therefore
represented as Xr = {xlr,2 1 2 , .-.,.~ l i --.,
, xln} where s r f is
a cell in the output from the BPNN at Iwation i.
Let AT be an interval neutrosophic set of X j . A j can be
defined as
&.
3036
Authorized licensed use limited to: Murdoch University. Downloaded on June 15, 2009 at 03:22 from IEEE Xplore. Restrictions apply.
3037
Authorized licensed use limited to: Murdoch University. Downloaded on June 15, 2009 at 03:22 from IEEE Xplore. Restrictions apply.
ohlailled Tl.nrn nur p~,nposedtech~liques i~sirig holh tl.iltllrnemhet.ship and false-mernhersliip values is sinlilnr to the
oucuriicy ublaincd froin thc cxisting tcuhniqucs using unly
truth-mcmburship valucs and alsu similar lo ~ h ci i c c u l ~ i l ~ ~
Tlu.c.;tlold
valhc
0. I
0.2
KPNS
GKNS
IPNS
(k CO~TCI Tk C O ~ T C I (k C O ~ Y C I
50.79
58.02.
5h.79
59.26
62.46
59.26
0.3
V,4
71.60
72.84
75,31
0.5
72.84
0.b
U,7
70..37
81,48
$0.25
76.54
4 . 4
W.2V
43.2 1
4,8
64.20
.%.O'L
U,9
39,38
65.43
67.41)
69. I4
b4.10
6?3b
59.26
50.62
lal 11etnn1-ksusing dyrialnic weight, ave~.ngirigby considering the cornparison between tr.utli-membership and falsen~cinbashipvalucs (Y'U(g) > k h ( g ) ) . Vuantification of
uncei-hin ~ ycan suppor! thu dcci si un making. For ex;jmplc,
the third row ~f tliih table contain the uncertainty value
0.2949 in which the decision ~nakercall accept this result
for 3 cell is
with innre corifidence. Sometirrles, ~~ncei-tairlty
high. ]:or cxomplc. rhc rourth row and rhc scvcnth row of this
3038
Authorized licensed use limited to: Murdoch University. Downloaded on June 15, 2009 at 03:22 from IEEE Xplore. Restrictions apply.
TABLE V
C [ . ~ S S I IIC.31 ION . l C C L l < ! ~ C " lI t1K ~ [ ~ l l t . ' [ ' l ' S ' l ' [ > \ ~ [ ~ * r S l " l ' l l SIIIE.
lS~i
[O] I. K. I~~IIWII
ii[ltI l', S a l i ~ ~ l i o [l~a1Ic111
l.
!liiilI>\i> ilii~lb l ~ l c l i i ~ l111Ielc
I~;CIIK. /EKE T r - ( ~ i f . i ( ~ [ t[ it iot ~P~C/IVI-II
~.+
A I I ( I / ~ LIIIO
, > ~ h\ l ~ ~ < , / ~111irl!iirzc
t'KOl'r~St'l?'['I:C'tlN[()CI:S ASl)-[Ill. l ' X I S ' ~ l Y <'['l:C'tlK[()Cl:S
i
$ ~ , r ? r . ~ .vc>].12. PI). 99-7-1 ( D l . I 490.
[ l O] 7 -Q. Stlcii aiid r.-S.Kon;. Dyn;l~iiic;~lly wh.ci;lirtJ c r ~ \ c r ~ i hr~cural
l~I
L
I
H a i ~ c l ccll
l
Tr)ral cell
i i c ~ w o r k sl ' t ~r c f r ~ h ~ i PIU~~CIII\.
o~i
PIT?^.. I ~ TC / I ~/ J I! I ~P I ~ I L ~ I ~ ( C'OIII~~(~/
f<,i-(,~~<
or!
, ( , ~l-lrct,llir~c,
Lctrl-ifir~g
<rrzrl C?hr~-~roii,.i.
Sli:i~i:t~ai. 2004. 3492E i ~ a c r ~ i hTl ~c .c t ~ r ~ i q ~ ~ c
1 5CCHIVCI)
I'd co~i*.cl) t9cui-rccrl
Myni~r)~ n ~ i n[; T i
H2,Sh
78.2(1
80.25
349 h.
[ I I ] C'. C'. Flwng. V, 151": W. l<r~>u,n.; ~ t i ( l K. tV. ';!(>iig.
Cotnp;~r,ing ihc
\I a,i<ii-i~y~i31iiis
i bb
7 1 4.3
80 VO
X0.1'.
IWI ti>1-1~13iic'~'
~t~dll'l;.~-cnt n c u ~ n nctn.i>l-h~
l
arcli~tcc~llrc\
ii11- tlic ],~cd~ct~i>n
klajrii-ity ~ c l ~ i iii I'&;P)
y
h 8 57
8h
79.0 1
niL~ i i ~ n c r a
] +l ~ n ~ p c c t i ~/'171i-.
i ~ y . flit, I + I L ~ ~ I // II ~ ~ ~ , ~ I I ( I ~ ~ I (> 'I ~I (II I/ ? / ~ * Itm
,(,II~
Lluic>i-iry ~ o l i i ~( I'h
g P)
83 71
7h 09
fin.??
: W L ~ ~ , /f.r>~~rr~iff,q
I I I I ( , L I ~ (I'3 ~/ W I , I I P I ~ C - . (I(':\ii.('
\
2oM1. ( ~ i u a ~ y / h o u(-lii
. II~.
,Avt.r,;i:i~~g ( T i
Y2.86
78.36
80.25
2 W 5 . -393-39X.
,Avcr.:~gi~~g
(P)
YO.00
80.43
8U.25
1 111 A. CJ. I>ilLhiiciiLt~.I ' o l y n ( ~ [ ~ iThct~i->
i~l
t i [ Cr)iuplc.x Syxlcii~s,l t t t 2
Avcraginp rT&I:)
80.00
80.43
80.25
I ~ Y I I I , \ L I C , ! on
~ ~ I SI .x~ r f r * ~ ~Mcrr~
~ . r . r111r1I-'rht.~-rzr,!~r,r.
~(11.1, pp. 1h.3-378.
4 ~ c r a ~ i i!.I'/F)
ig
KI.iih
78,lh
80.23
1971.
D y i i a n ~ i c:~vcr;lging (T)
110 00
1;l01
X 1.11;
[ 131 F,S i ~ ~ a i ~ i > [ i ~/II i ~L!rzi{li~~,y
~ t ~ c . i,-i<,/riill L < y i <. i , ~ Y < , ~ I ~ I ~ ? ,Loyii,.
TOJJII~LI ) y i ~ a i ~ uIIL.CI.~~:~[~::
c
ir )
80.00
78.26
79.0 1
t
:
~5 , C I I ~i I O Pmhtrhilif~
I ~
orrtl S/trfi.>~ic.~.
nyii:jiiiic nvc~,ngirl; ( T k F )
YO.00
82.61
8 1.4s
1111t,dcdil~otl.Xiclun~i.Phoct~ir.2003.
1lyii;jnilc ovcrngltly (T,Irl
Y2.86
78.36
80.25
[ 1-11 1 I, Wat~;. 1. Sninrai>dnct~c.Y.-V. %hat>;. nnd K ,Sundcrr;~n~on.
rrrfcr-rcri
: i 1 r ~ ~ / ~ ~ ~SL,~),
. i ~ <~I jI jI l~ hl<i~-:
f ~ t . T J ~ C O <I I; I~I ~~ \ l ) I ~ / l c ~ ( iif1
i i ~C(IIII/>II
?~i~ Ii111:: i l ~ f t / ! ~ ~ . i&ooA
o / ~ / fSct,ics
~ t , :Vo.J. ~ I I I ~ ~ ~ / / ~ I ~ ~ ~ ~ . ~ ~
TABLF. VI
:lccc~.;cd Junc 2M5.
s,it%il'[,l:OLl'~t,L l'5 f:KO\I t , . l Y l \ i H [ , t : (!I Nt:L I<,\l, \l.:l!AOKKX
LlYIN(i
[ I S ] I, V. TCI~W, T, 1, iik\ciitn;l. i'V,
,Vvlkovictl. i ~ r l i lI>, Y2 F i l i p w ,
r)unltjrrt: ~ Y I ~ I ~ , I IAVI
I
K A ( , I X ( ~ ( ' I ' 2 1, ) I.(II< 1 1 1 1 r1.s I I).II.\ st:-l
\'i~-tuifI C O I I I ~ Y I ~ I ( IL-h<,ri~i,>tr:r
~ ~ ( > I I L ILi!h~~-lr!o~>-.
/
l011-Ii11h.cl !lv;lll~lbl~~:
th11p;/il4h. 107.2 17.17t;/l;~t~1]~1111fu1~1~~.t1~i11l.
i ~ c ~ c > a rY, rd? \ c ~ l l t x2005.
r
FillhcI~i~I~~~i-~~iir~iicy
,4cruul
1'1-c<licrr.d
Trut11\fc[>~l>c[,\l~ip \fc[>~lhc[,\l~ip \fcr~~t>c[,>I~ip
Ccll Typt Ccll Typt
r ) t ] > < + \ i ~ I:)t]>~i\i~
O.tlk26
+539
701
r')t11n\i1
H;uirii
0.41 48
U.676?
0.7136
t 1 i
I 1 i
0.8342
0.1198
0,2449
r')t110\i1
l ; ) t ] ~ ~ i \ i ~ 0.Sh75
U.5149
0.9475
H;uicij
H~uicii
0.1h29
U.8hY6
11.2943
HAIICI~
I:)?]\o\il
0.6105
U.4336
0.8432
H;uicij
I:)t]w+i~
0,5 I 8 I
0.4X9t;
0.g716
HAIICI~
HL~II~II
0.3079
U,bS.%
U,b5J1
(,
Pawalai Krnipeet.npun is supported by postgraduate rcsearch scholarship fsoln the Royal Thai Govcrnlncnt.
300f
151 A. -5Li1t>iii-. \4i1icrd l>t)tci~~iilI
r~iilp~>ir~;
~lyiri: l ' ~ ~ d - I ' o l - ~[lcural
a~d
L
I-I
w<~rk\.P I ~ J L~ , .1 !rz#i,~
7 ~ I I ~ I I I O I I ( I / JNII! C ~ ~ ~ r ~ i( ?~I ) r: ~(' <~J ~ rI td!
Iz <
:~'<CIII
~ ~ i11-A,+.
~
3003. 1813 1819.
[ h ] \i. 1)c.l. C , C. Fung. W. V.i(lr,wn, illid T. C c d c r ~ ~A
i . gtiic[,:~l~,c;rc\\ioii
[ I C L I ~[ ~l c ~ ~ ( ph[ ka d [~it)dcII'UT [iiiiicrd l ' i ~ v t u ~ h i l prh.ct!i~li<>~n.
i~y
PIYIL,.
rlrc Fijtt~ ~ ? s I ~ I - M ~ I [ ( IL!<~c/~-ic~ir
/ L ,
E t ~ g i ~ i t ~ t ~( rI iI tI ~~CpO I I I ~ WS IJ ~
, I IJ II ~ J I A I I I ) ) I tI'l:l<t-.7 ?OO/).
I%i-~li.W-rstvrii ,411~1~1li:~.
3004. 207 209>
[ 7 ] V. I y.C. C, rung. W. Hi<,wn, iliiil T.C c d c r ~ ~Lhr+*d
i.
~ ) ( ~ l y i iill~ ~11c11ril1
ii~i
r~clv,r?rkI u r ~ ~ t ~ i i i ~~>rri' lolu ] ~ c c l .l ~\ ~i ~ ~y l l >In\ iaGIS
\
cr~riioii1ilcii1.P111i:
rlrc lEEf1 Ht'pir)~~
10 C-vrdi,rt,rzc,c,i7r.ffro11
2004). Cliiilrl; Mai. Tliai lalirl.
3004. 4 1 1-414.
[U] C. C. Fung. V. Iy. W. Riown. illid K. W. \i'oiip. S ~ u r i Sc1w11rk
l
E I I ~ ~ I I I ~ I I~~ISL.CI
L~
.A]I~I[~~ICII lur L l i ~ ~ c rl 'i rl o \ l w ~ l ~I +I I~' i - c ~ I i c l l ~P~f ~ )~i., .
1j3c I E H ,4t,Fir>1110 c ~ ~ r ~ i ~ (rT~P~I Ir ~z J200.7).
< J~I (I ~ \ ~ c l l ~ r ~ ~ ,~4 r1~1 isc~i.:j.~ i l
2005 (TI>-KOY. 5 pil;o\l.
3039
Authorized licensed use limited to: Murdoch University. Downloaded on June 15, 2009 at 03:22 from IEEE Xplore. Restrictions apply.
~~/~I