!
Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)
Vol.!!03,!No.!11,!November!2023!
It#is-ISSN:!2807-8691,|,p-ISSN:!2807-839X#
,
IJSSR,Page!2826
!""#$%&&'()*(+,&-.*/0122&)3$$+*45)--*62577
This%work%is%licensed%under%a%Attribution-ShareAlike%4.0%International%(CC%BY-SA%4.0)
Identification+of+Fresh+and+Unfresh+Fish+Based+on+Eye+
Image+Using+The+Self-Organizing+Maps+(SOM)+Method!
!
Edwhin,Rantho,Rafafi
%1
,!Enny,Iije,Sela
2
!
1,2
Yogyakarta!University!of!Technology,!Indonesia
%
E-mail:[email protected]!
Keywords,
,
ABSTRACT,
!"#$%&'()*+,+*(-.)/01-2+031-4"5')#-
4"678'9:,
-
!"#$% "#%&%'())(*%+,(-."*%#(/,'.%&*0%.%-(%(2-&"*%"*%3*0(*.#"&4%2/-%
2.'&/#.%(5%"-#%$"6$%7&-.,%'(*-.*-4%5"#$%8/"'9:1%#+(":#;%!"#$%5,.#$*.##%
'&*% 2.% 0.-.'-.0% /#"*6% #.<.,&:% '(*<.*-"(*&:% ).-$(0#4% #/'$% &#%
'$.)"'&:% &*&:1#"#4% 2"('$.)"#-,14% )"',(2"(:(6"'&:% &*&:1#"#4% &*0%
#.*#(,1% .=&)"*&-"(*;% >*(-$.,% "0.*-"5"'&-"(*% ).-$(0% "*<(:<.#%
(2#.,<"*6%-$.%'(:(,%(5%-$.%5"#$?#%.1.#;%!"#$%"0.*-"5"'&-"(*%"#%',/'"&:%
2.5(,.% &*1% 5/,-$.,% +,('.##"*64% .*#/,"*6% -$&-% -$.% 5"#$?#% 8/&:"-1%
0.:"<.,.0% -(% '(*#/).,#% ,.)&"*#% $"6$;% @(% -&'9:.% -$.% +,(2:.)% (5%
0"55.,.*-"&-"*6% 2.-7..*% 5,.#$% &*0% *(*A5,.#$% 5"#$4% -$"#% ,.#.&,'$%
.)+:(1#%B.:5AC,6&*"D"*6%E&+#%FBCEG%&#%-$.%+,")&,1%).-$(0(:(61;%
@$"#%,.#.&,'$%5('/#.#%(*%"0.*-"51"*6%5,.#$%&*0%*(*A5,.#$%5"#$%/#"*6%
-$.%BCE%).-$(04%/#"*6%&'-/&:%0&-&%"*<(:<"*6%-":&+"&%&#%-$.%,.#.&,'$%
(2H.'-;%@$.%0&-&%"*':/0.#%.1.%")&6.#%(5%*.7%&*0%*(*A5,.#$%5"#$4%&*0%
<&,"(/#% +,('.0/,.#% &,.% ,.8/",.0% -(% (2-&"*% -$.% 0.#",.0% 0&-&;% @$"#%
0&-&%"#%-$.*%/#.0%&#%-,&"*"*6%&*0%-.#-"*6% 0&-&;%@$.%+,('.##%'(*-"*/.#%
7"-$%-$.%+,.+,('.##"*6%#-&6.4%7$"'$%"#%&%0&-&%)(0"5"'&-"(*%+,('.##%
-(%")+,(<.%+.,5(,)&*'.%"*%#/2#.8/.*-%#-.+#%&*0%5.&-/,.%.=-,&'-"(*%
/#"*6% IBJ% '(:(,% $"#-(6,&)#;% K:&##"5"'&-"(*% (5% +,('.##.0% 0&-&% "#%
'&,,".0% (/-% /#"*6% -$.% BCE% ).-$(0;% C*'.% '()+:.-.04% -$.%
"0.*-"5"'&-"(*%,.#/:-#%&,.%0"#+:&1.0;%@$"#%,.#.&,'$ %+,(0/'.#%&%#1#-.)%
5(,%"0.*-"51"*6%5,.#$%&*0%*(*A5,.#$%5"#$%2&#.0%(*%.1.%")&6.#%/#"*6%
BCE4%7$"'$%&'$".<.#%&%6((0%&''/,&'1%(5%LM;NOP;-
,
,
!
,
INTRODUCTION!
Fish!is! the!most!common!and!easy!source!of!protein! for!Indonesian!people!to!obtain,!but!because!
of!its!high-water!content,!fish!quickly!spoils.!With!abundant!fishing,!the!speed!of!identification!of!fish!
freshness!is!essential!in!process ing!large!fish.!Fresh!fish!have!the!same!characteristics,!color,!smell,!and!
texture!as!live!fish,!often!seen!through!changes!in!the!color!of!the!fish's!eyes!(Mohammadi!Lalabadi!et!
al.,!2020;!Ranjan!et!al.,!2023;!Rezende-de-Souza!et!al.,!2022;!Yang!et!al.,!2022).!
The!freshness!of!fish!can!be!detected!using!several!conventional!methods,!namely!chemical!or!
biochemical! analysis! of! fish,! analysis! of! microbiological! content! in! fish,! and! sensory! examination!
methods!(Maulida!et!al.,!2021;!Wang!et!al.,!2022).!Another!identification!method!is!to!look!directly!at!
the!color!of!the!fish's!eyes.!This!method!can!provide!accurate!fish!quality!information!and!quantitative!
results!but!requires!more!time!and!experienced!people.!It!is!a!complicated!process,!requires!high!costs,!
and!requires!human!physical!strength,!which!is!quite!vulnerable!and!quickly!tired! so!that!it!can!interfere!
with!fish!identification!activities!(ElMasry!et!al.,!2016;!Jahanbakht!et!al.,!2023;!Tokunaga!et!al.,!2020).!
Much!research!has!been!carried!out!regarding!fish!identification.!These!studies!include!(David!
et! al.,! 2022;! Uraini,! 2022;! Pariyandani! et! al.,! 2019;! Wanti,! 2021).! Research! by! David! (2022),! titled!
Application!of!Formalin!Fish!Recognition!Through!Eye!Detection!Using!the!Template!Matching!Method!
and!KNN!Classification!Method.!This!research!discusses!how !introducing!fresh!fish!and!formalin!can!be!
carried! out! using! the! KNN! (k-nearest! Neighbor)! classification! method! (Putra,! 2016).! Initially,! a!
thresholding!process!was!carried!out!to!separate!the!fish!object!from!the!background!image.!The!fisheye!
International,Journal,of,Asian,Education,!!
Edwhin!Rantho!Rafafi
%1
,!Enny!Iije!Sela
2
!
IJSSR Page!2827!
detection!process!was!carried!out!automatically!using!the!Template!Matching!method!(S.!Li!et!al.,!2020;!
T.!Li!et!al.,!2018;!Moreira! et!al.,!2021).!After!the!fisheye!image!is!detected,!a!traininand!recognition!stages!
are!carried!out.!The!application!can!catch!fresh!or!formalin-treated!fish!by!detecting!the!location!of!the!
fish's!eyes! using! the!template! matching! method!and! measuring! the!proximity! distance! between!the!
image!of!the!fish's!vision!and!the!image!of!the!fish's!eye!with!and!without!formalin!in!the!database!
(Penczak!et!al.,!2012;!Quijano!et!al.,!2023;!Tsai!et!al.,!2017).!
Other! related! research! is! entitled! Implementing! Artificial! Neural! Networks! Using! the! Self-
Organizing!Map!Method!in!Image!Classification!of!Snapper!Fish!Types!(Triwibowo!&!Sela,!2023).!This!
research!aims!to!implement!an!artificial!neural!network!using!the!Self!Organizing!Map!(SOM)!method,!
which!is!used!to!classify!types!of!snappers!based!on!each!snapper's!color!and!texture!characteristics!
(Asri!&!Wulanningrum,!2021;!Kim!et!al.,!2023).!This!research!has!several! stages:! image!acquisition,!
image!segmentation,!color!and!texture!feature!extraction,!image!classification!using!a!Self-Organizing!
Map,!and!testing!the!existing!model!(Cui!et!al.,!2023;!Shi!et!al.,!2022).!
Based! on! several! related! studies,! fish! identification! is! important! before! the! fish! is! further!
processed.!By!doing!this,!consumers!can!get!fish!that!is!in!good!condition.!
To!overcome!errors!in!identifying!fresh!and!non-fresh!fish.!This!research!uses!Self!Organizing!
Maps!(SOM)! as! the!methodology! that! will!be! used.! Self-Organizing! Maps!(SOM)!is! a! neural!network!
trained!using!unsupervised!learning.!This!network!can!produce!a!separate!representation!of!the!input!
space! of! low-dimensional! (usually! two-dimensional)! training! samples.! This! representation! is! then!
referred!to!as!a!"map.”!This!research!also!uses!Hue!Saturation!Value!(HSV)!feature!extraction!to!reduce!
the!error!rate!in!identifying!fish.!
,
METHODS,
This!research!has!initial!conditions,!namely!that!the!identification!method!used!is!less!effective!
because!it!requires!much!time,!is!a!complicated!process,!requires!a!large!amount!of!money,!and!requires!
human!physical!strength,!which!is!quite!vulnerable!and!quickly!gets!tired!so!that!it!can!interfere!with!
fish!identification!activities.!So,!a!system!was!designed!to!assist!in!the!fish!identification!process.!This!
research!proposes!using!the!Self!Organizing!Maps!method!for!classification.!The!final!condition!expected!
from!this!research!is!correct!classification!results!with!high!accuracy.!
!
!
Figure,1.,Research,Framework,
Inrernational,Journal,of,Social,Service,and,Research!! https://ijssr.ridwaninstitute.co.id/!
IJSSR,Page!2828!
The! topic! discussed! in! this! research! is! identifying! fresh! and! non-fresh! fish! using! the! Self!
Organizing!Maps!(SOM)!method.!This!research!uses!accurate!data!using!tilapia!as!the!research!object.!
The!data!used!is!images!of!fresh!and!non-fresh!fisheyes.!The!data!is!correct,!so!several!procedures!are!
needed!to!get!the!desired!data.!The!following!method!is!used:!
a. Data!was!obtained!by!taking!photos!of!the!fish,!then!cropping!them!and!leaving!only!the!eyes!of!
fresh!and!non-fresh!fish.!
b. Data! sources! come! from! direct! observations,! experiments! and! documentation! carried! out! by!
researchers!independently.!
c. Data! was! obtained! from! tilapia! fish! from! the! Garongan! area's! fish! market.! The! data! collection!
process!took!approximately!9!hours,!counting!from!the!death!of!the!fish.!
d. Data!collection!was!carried!out!on! October!29,!2022.!At!07.30! WIB!or!half!past!eight!in!the! morning,!
until!16.30!WIB!or!half!past!five!in!the!afternoon.!
The!collected!data!will!be!used!as!training!data!and!test!data.!Next!is!the!pre-processing!stage;!
at!this!stage,!the!data!will!und ergo!several!modifications!to!improve!performance!in!the!next!stage.!The!
next!stage!is!the!feature!extraction!process!in!the!data.!The!feature!extraction!used!is!the!HSV!color!
histogram.!The!next!stage!is!classifying!the!data!that!has!been!processed.!At!this!stage,!the!data!will!be!
arranged!according!to!the!predictions.!This!stage!uses!the!Self!Organizing!Maps!(SOM)!method!as!the!
classification!method.!Once!the!process!is!complete,!it!will!display!the!identification!results!of!the!data!
selected!for!testing.!The!model!architecture!of!this!research!can!be!seen!in!Figure!2.!
!
!
Figure,2.,Model,architecture,
RESULTS!!
!This!research!produces!a!system!for!identifying!fresh!and!non-fresh!fish!based!on!eye!images!
using!the!Self!Organizing!Maps!(SOM)!method.!This!process!begins!by!preparing!image!data,!usually!
International,Journal,of,Asian,Education,!!
Edwhin!Rantho!Rafafi
%1
,!Enny!Iije!Sela
2
!
IJSSR Page!2829!
called!a!dataset.!The!number!of!shots! used !as!a!dataset!is!48,!with!24!pictures!each!for!fresh!fish!and!24!
ideas!for!non-fresh!fish.!The!dataset!will!then!be!divided!into!2!for!each!file.!70%!is!used!as!training!data,!
and!30%!as!test!data.!After!the!data!has!been!prepared!properly,!the!next!step!in!applying!the!Self!self-
organizing!maps!method!is!to!prepare!the!model!used!for!training.!The!model!that!will!be!built!will!later!
be!used!for!training.!This!research!uses!Visual!Studio!Code!software!for!the!training!and!testing!process.!
The!following!is!the!process!carried!out!in!classifying!fresh!and!non-fresh!fish.!
Preprocessing,,
!This!is!the!initial!process!where!all!the!image!data!held!is!changed!to!be!suitable!for!further!
analysis.!The!process!that!occurs!is!to!crop!the!image!of!the!fish!you!have!and!only!leave!the!eye!part!of!
the!image.!This!process!can!be!done!directly!after!the!picture!is!taken!or!by!using!other!software!that!
can! help.! The! image! cropping! process! in! this! research! was! carried! out! manually! using! the! Adobe!
Photoshop!application.!It!produced!a!fisheye! image!with!a!width!of!480!pixels!and!a!height!of!450!pixels.!
An!example!of!the!processed!image!can!be!seen!in!Figure!3.!
!
!
Figure,3.,Image,of,processing,results,
Feature,Extraction,
Feature!extraction!is!carried!out!to!obtain!information!contained!in!the!fish!image.!HSV!color!
histogram!feature!extraction!is!used!to!identify!fresh!and!non-fresh!fish.!The!HSV!histogram!value!is!
obtained!by!equation!(1).!
𝐶𝑎𝑝𝐻𝑖𝑠𝑡𝑜𝑔𝑟𝑎𝑚
(
𝐻, 𝑆, 𝑉
)
= ℎ𝑖𝑠𝑡(𝐻, 𝑆, 𝑉)!!! ! ! ! ! ! (1)!
!
! The!hist!in!equation!(1)!can!be!searched!for!with!equation!(2).!
!
ℎ𝑖𝑠𝑡
(
𝐻, 𝑆, 𝑉
)
= 𝑛𝐻4𝑥4𝑛𝑆4𝑥4𝑛𝑉! ! ! ! ! ! ! (2)!
! Information:!
! H!=!Hue!component!of!each!image!pixel!
! S!=!Saturation!component!of!each!image!pixel!
! V!=!Value!component!of!each!image!pixel!
! nH!=!number!of!bins!used!on!Hue=!8!
! no!=!number!of!containers!used!at!Saturation=!8!
! nV!=!number!of!containers!used!at!Value=!8!
An!example!of!an!HSV!histogram!graph!can!be!seen!in!Figure!4.!
!
Inrernational,Journal,of,Social,Service,and,Research!! https://ijssr.ridwaninstitute.co.id/!
IJSSR,Page!2830!
!
Figure,4.,Graph,Histogram,HSV,
The!features!that!have!gone!through!extraction!will!then!be!normalized!and!converted!into!a!
one-dimensional!array.!Converting!it!to!a!1-dimensional!array!helps!avoid!errors!in!identifying!fish!later.!
An!example! of!feature!values!that!have!been!converted!into!a!1-dimensional!array!can!be!seen!in!Figure!
5.!
!
!
Figure,5.,Feature,Extraction,Value,
Implementation,of,Self-Organizing,Map,
!The!method!used!to!identify!fresh!and!non-fresh!fish!is!the!Self!Organizing!Map.!This!process!
goes!through!several!stages,!from!dataset!normalization!to!SOM!initialization!and!class!identification.!
Normalize!the!dataset!using!Min-Max!Scaler,!and!the!results!are!obtained!with!equation!(3).!
!
𝑋
!"#$%&'()*
= 4
+,-+
!"#
+
!$%
,-+
!"#
!! ! ! ! ! ! ! (3)!
!
Self-organizing!maps!is!a!type!of!artificial!neural!network!that!is!trained!using!the!unsupervised!
learning! method.! This! network! can! produce! a! separate! representation! of! the! input! space! of! low-
dimensional!(usually!two-dimensional)!training!samples.!This!representation!is!then!referred!to!as!a!
"map.”!SOM!is!also!a!method!for!performing!dimensionality!reduction!on!trained!models.!In!general,!
updating!the!weights!in!the!SOM!can!use!equation!(4).!
Subscript
(
𝑡 + 1
)
= 4 𝐼𝑁
'.
(
𝑡
)
+ 4𝑎
(
𝑡
)
4× 4ℎ
(
𝑖, 𝑗, 𝑏
)
4×4 (𝑋
(
𝑡
)
− 𝐼𝑁
'.
(
𝑡
)
)! !
! (4)!!
!The!training!process!will!be!carried!out!first!to!form!a!model,!which!will!also!be!used!for!the!
testing!process!later.!The!system!in!this!research!also!creates!a!save!model!button,!which!saves!the!
model!resulting!from!the!training!process,!and!a!load!model!button,!which!works!to!upload!the!model!
you!want!to! use! later!in!the! testing! process.!Based!on!the! explanation! of!the!system!created! in! this!
International,Journal,of,Asian,Education,!!
Edwhin!Rantho!Rafafi
%1
,!Enny!Iije!Sela
2
!
IJSSR Page!2831!
research,!users!create!a!GUI!that!uses!the!Tkinter!library!to!make!things!easier!for!users.!An!example!of!
a!GUI!display!can!be!seen!in!Figure!6.!
!
!
Figure,6.,Fish,Identification,System,Interface,Display,
Model,Testing,
! Model!testing!can!use!newly!trained!models!or!previously!trained!models.!This!test!is!carried!
out!to!determine!the!performance!of!the!chosen!model.!The!test!data!consists!of!14!fisheye!images,!
where!each!fresh!and!non-fresh!fish!will!be!tested!with!seven!shots.!Testing!is!carried!out!by!matching!
the!results!of!the!identification!carried!out!by!the!system!with!existing!factual!data.!Accuracy!is!
determined!using!equation!(5).!
𝐴𝑐𝑐𝑢𝑟𝑎𝑐𝑦 =
∑
0123)$-4#)*'53'"!
∑
6"3%&-7%3%
!! ! ! ! ! (5)!
The!test!results!for!identifying!fresh!and!non-fresh!fish!can!be!seen!in!Table!1.!
Table,1.,Accuracy,Test,Results,
Fish!Criteria!
Number!of!Test!Data!
Number!of!Correct!
Identifications!
Accuracy!(%)!
Fresh!fish!
7!
6!
85.71%!
Fish!Not!Fresh!
7!
6!
85.71%!
Total,
14,
12,
85.71%,
!
Table!1!shows!the!accuracy!of!the!fresh!and!non-fresh!fish!identification!system,!created!by!
matching!the!system's!identification!results!with!the!factual!image!data!being!tested.!The!accuracy!
results!have!been!calculated!using!equation!(5),!producing!85.71%!for!fresh!fish!image!accuracy!and!
85.71%!for!non-fresh!fish!image!accuracy.!The!total!accuracy!of!the!system!is!85.71%!
CONCLUSION!
This!research!has!applied!the!Self!Organizing!Map!(SOM)!method!to!identify!fresh!and!non-fresh!
fish!based!on!eye!images.!This!research!uses!HSV!feature!extraction,!where !the!HSV!values!are!obtained!
from!the!photos!used.!The!feature!extraction!can!extract!information!from!the!picture,!making!it!easier!
to!identify!the!fish.!The!feature!extraction!results!are!then!converted!into!a!1-dimensional!array!to!help!
Inrernational,Journal,of,Social,Service,and,Research!! https://ijssr.ridwaninstitute.co.id/!
IJSSR,Page!2832!
avoid!errors!in!the!identification!process.!The!feature!extraction!results!obtained!are!used!as!input!for!
the!SOM!algorithm!to!identify!fish.!The!system’s!accuracy!is!also!good,!with!a!value!of!85.71%.!
However,! fish! identification! results! can! be!even!better! by!increasing! the!image! data!available.!
Improve!the!performance!of!feature!extraction!to!identify!fish!better!and!more!accurately.!Improve!the!
Self!Organizing!Map!(SOM)!algorithm!used!or!use!another!more!modern!algorithm!with!back-processing!
features!to!minimize!fish!identification!errors!and!optimize!accuracy.!
!
REFERENCES!
Asri,!P.!P.,!&!Wulanningrum,!R.!(2021).!Implementation!of!SOM!(Self!Organizing!Maps)!for!Identification!
of!Tomato!Fruit!Maturity.!;<=>!?-;5'*)#-!+06"@-<"#"98@5*+9)0+-=#"96'8*+9)-!+06"@-A8*6'8#-B87"'-
!+06"@-C)*-A8@/56"',!D(2),!185–192.!
Cui,!B.,!Créput,!J.!C.,!&!Zhang,!L.!(2023).!Self-organizing!maps!and!full!GPU!parallel!approach!to!graph!
matching.! >8@/56"'- >8@@5*+E)6+8*0,! DFG,! 217–227.!
https://doi.org/10.1016/J.COMCOM.2022.12.005!
David,!D.,!Robet,!R.,!&!Raymond,!R.!(2022).!Aplikasi!Pengenalan!Ikan!Berformalin!Melalui!Deteksi!Mata!
Menggunakan!Metode!Template!Matching!Dan!Metode!Klasifikasi!KNN.!;5'*)#-H#@+)3->8'"-H<?-
>8@@5*+6I-J"0")'E3-H*$8'@)6+8*-<"E3*8#8(I,!DK(4).!
ElMasry,!G.,!Nakazawa,!N.,!Okazaki,!E.,!&!Nakauchi,!S.!(2016).!Non-invasive!sensing!of!freshness!indices!
of!frozen!fish!and!fillets!using!pretreated!excitation–emission!matrices.!!"*08'0-)*L-ME65)68'0-
N?->3"@+E)#,!OOG,!237–250.!https://doi.org/10.1016/J.SNB.2016.01.032!
Jahanbakht,!M.,!Azghadi,!M.!R.,!&!Waltham,!N.!J.!(2023).!Semi-supervised!and!weakly-supervised!deep!
neural! networks! and! dataset! for! fish! detection! in! turbid! underwater! videos.! =E8#8(+E)#-
H*$8'@)6+E0,!PG,!102303.!https://doi.org/10.1016/J.ECOINF.2023.102303!
Kim,!S.!H.,!Cho,!K.!J.,!Kim,!T.!S.,!Lee,!C.!S.,! D hakal,!T.,!&!Jang,!G.!S.!(2023).!Classifying!habitat!characteristics!
of! wetlands! using! a! self-organizing! map.! =E8#8(+E)#- H*$8'@)6+E0,! PQ.!
https://doi.org/10.1016/J.ECOINF.2023.102048!
Li,!S.,!Chon,!T.!S.,!Park,!Y.!S.,!Shi,!X.,!&!Ren,!Z.!(2020).!Application!of!temporal!self-organizing!maps!to!
patterning! short-time! series!of! fish! behavior!responding!to! environmental! stress.!=E8#8(+E)#-
.8L"##+*(,!RSS.!https://doi.org/10.1016/J.ECOLMODEL.2020.109242!
Li,!T.,!Sun,!G.,!Yang,!C.,!Liang,!K.,!Ma,!S.,!&!Huang,!L.!(2018).!Using!self-organizing!map!for!coastal!water!
quality!classification:!Towards!a!better!understanding!of!patterns!and!processes.!!E+"*E"-8$-63"-
<86)#-=*T+'8*@"*6,!UOGVUOF,!1446–1459.!https://doi.org/10.1016/J.SCITOTENV.2018.02.163!
Maulida,! M.,! Wijaya,! E.! S.,! &! Anwar,! M.! R.! (2021).! DETEKSI! IKAN! TONGKOL! BERFORMALIN!
BERDASARKAN! CITRA! MATA! IKAN! DENGAN! METODE! NAÏVE! BAYES! CLASSIFIER.! AWHA%
AX.BXWM4-;XJ4MW-HW.X-A&.BX<=J,!G(3),!305–313.!
Mohammadi!Lalabadi,!H.,!Sadeghi,!M.,!&!Mireei,!S.!A.!(2020).!Fish!freshness!categorization!from!eyes!and!
gills! color! features! using! multi-class! artificial! neural! network! and! support! vector! machines.!
MY5)E5#65')#-=*(+*""'+*(,!FK.!https://doi.org/10.1016/J.AQUAENG.2020.102076!
Moreira,!L.!S.,!Costa,!F.! S.,!Machado,!R.!C.,!Nogueira,!A.! R.!A.,!Gonzalez,!M.!H.,!da!Silva,!E.!G.! P.,!&!Amaral,!C.!
D.! B.! (2021).! Self-organizing! map! applied! to! the! choice! of! internal! standards! for! the!
determination!of!Cd,!Pb,!Sn,!and!platinum!group!elements!by!inductively!coupled!plasma!mass!
spectrometry.!<)#)*6),!OSS.!https://doi.org/10.1016/J.TALANTA.2021.122534!
Nuraini,! R.! (2022).! Implementasi! Jaringan! Syaraf! Tiruan! Menggunakan! Metode! Self-Organizing! Map!
Pada!Klasifikasi!Citra!Jenis!Ikan!Kakap.!N5+#L+*(-8$-H*$8'@)6+E01-<"E3*8#8(I-)*L-!E+"*E"-ZNH<
International,Journal,of,Asian,Education,!!
Edwhin!Rantho!Rafafi
%1
,!Enny!Iije!Sela
2
!
IJSSR Page!2833!
Penczak,! T.,! Głowacki,! Kruk,! A.,! &! Galicka,! W.! (2012).! Implementation! of! a! self-organizing! map! for!
investigation!of!impoundment!impact!on!fish!assemblages!in!a!large,!lowland!river:!Long-term!
study.!=E8#8(+E)#-.8L"##+*(,!OOP,!64–71.!https://doi.org/10.1016/J.ECOLMODEL.2011.12.006!
Putra,!W.!S.!E.!(2016).!Klasifikasi!citra!menggunakan!convolutional!neural!network!(CNN)!pada!caltech!
101.!;5'*)#-<"9*+9-H<!,!Q(1).!
Quijano,! D.,! Salas,! S.,! Monroy-García,! C.,! Dreyfus-León,! M.,! &! Torrres-Irineo,! E.! (2023).! Identifying!
fisheries!operations!in!tropical!multispecies!fisheries:!A!comparative!analysis!of!multivariate!
approaches! and! neural! networks.! 2+03"'+"0- J"0")'E3,! OUS.!
https://doi.org/10.1016/J.FISHRES.2023.106692!
Ranjan,!R.,!Sharrer,!K.,!Tsukuda,!S.,!&!Good,!C.!(2023).!Effects!of!image!data!quality!on!a!convolutional!
neural! network! trained! in-tank! fish! detection! model! for! recirculating! aquaculture! systems.!
>8@/56"'0- )*L- =#"E6'8*+E0- +*- M('+E5#65'",! OKQ.!
https://doi.org/10.1016/J.COMPAG.2023.107644!
Rezende-de-Souza,!J.!H.,!de!Moraes-Neto,!V.!F.,!Cassol,!G.!Z.,!Camelo,!M.!C.!dos!S.,!&!Savay-da-Silva,!L.!K.!
(2022).! Use! of! colorimetric! data! and! artificial! neural! networks! for! the! determination! of!
freshness!in!fish.!288L->3"@+06'I-MLT)*E"0,!D.!https://doi.org/10.1016/J.FOCHA.2022.100129!
Shi,!C.,!Ji,!Z.,!Yang,!X.,!Jia,!Z.,!Dong,!R.,!&!Shi,!G.!(2022).!Nondestructive!determination!of!the!freshness!
change!in!bighead!carp!head s!under!variable!temperatures!by!using!excitation-emission!matrix!
fluorescence!and!back-propagation!neural!networks.!;85'*)#-8$-2565'"- 288L0,!O(2),!160–166.!
https://doi.org/10.1016/J.JFUTFO.2022.03.009!
Tokunaga,! K.,! Saeki,! C.,! Taniguchi,! S.,! Nakano,! S.,! Ohta,! H.,! &! Nakamura,! M.! (2020).! Nondestructive!
evaluation!of!fish!meat!using!ultrasound!signals!and!machine!learning!methods.!MY5)E5#65')#-
=*(+*""'+*(,!GF.!https://doi.org/10.1016/J.AQUAENG.2020.102052!
Triwibowo,!M.!I.,!&!Sela,!E.!I.!(2023).!Implementasi!Extreme!Learning!Machine!untuk!Pengenalan!Jenis!
Sepatu.!!@)'6->8@/?-;5'*)#*I)-&')*(-B+*6)'-A8@/56"',!DO(4),!1098–1108.!
Tsai,!W.!P.,!Huang,!S.!P.,!Cheng,!S.!T.,!Shao,!K.! T.,!&!Chang,!F.!J.!(2017).!A! data-mining!framework!for!
exploring! the! multi-relation! between! fish! species! and! water! quality! through! self-organizing!
map.! !E+"*E"- 8$- 63"- <8 6)#- =*T+'8*@"*6,! QPF,! 474–483.!
https://doi.org/10.1016/J.SCITOTENV.2016.11.071!
Wang,!Y.,!Yu,!X.,!Liu,!J.,!An,!D.,!&!Wei,!Y.!(2022).!Dynamic!feeding!method!for!aquaculture!fish!using!multi-
task! neural! network.! MY5)E5#65'",! QQD.!
https://doi.org/10.1016/J.AQUACULTURE.2022.737913!
Wanti,!E.!P.!(2021).!\)*6+1-=:-B:-ZOKOD[:-B"*(+L"*6+$+9)0+)*->+6')-H9)*-N"'$8'@)#+*-L"*()*-."*((5*)9)*-
."68L"-.5#6+#)I"'-B"'E"/6+8*-.!
Yang,!G.,!Ma,!J.,!Deng,!Y.,!Sun,!S.,!Fu,!B.,!&!Fathi,!G.!(2022).!Blackbox-based!model!identification!of!solid!
oxide! fuel! cells! by! hybrid! Ridgelet! neural! network! and! Enhanced! Fish! Migration! Optimizer.!
=*"'(I-J"/8'60,!G,!14820–14829.!https://doi.org/10.1016/J.EGYR.2022.11.020!
!
Copyright,holder:,
Edwin!Rantho!Rafafi
%
,!Enny!Iije!Sela
!
(2023)!
,
First,publication,rights:,
International!Journal!of!Social!Service!and!Research!(IJSSR)!
,
This,article,is,licensed,under:,
,
,
!
