ArticlePDF Available

Data-driven approach for dwell point positioning in automated storage and retrieval system: a metaheuristic-optimized ensemble learning

Authors:

Abstract and Figures

Dwell point positioning is one of the important decision factors in any automated material handling system (AMHS) by finding the ideal parking position during idle when waiting for the next incoming task. This study proposes a data-driven approach based on predictive analytics, as a new dynamic dwell point positioning method for Automated Storage and Retrieval System (AS/RS), a popular AMHSs for warehouse automation. The main idea is that if the next task can be predicted, then the idle AS/RS stacker can be positioned closer to the predicted task's location, leading to improved response time and traveling time by reducing unnecessary back-and-forth movements. However, predicting incoming tasks in the warehouse is challenging due to high uncertainty. Thus, a soft voting-based ensemble learning is developed, unifying three efficient machine learning models i.e. logistic regression, KNN, and decision tree where the hyper-parameters and voting weights are jointly optimized by Teaching-Learning-based Optimization. Based on five benchmark datasets, the proposed prediction algorithm is shown to be accurate, consistent, and efficient compared to individual learners, other metaheuristics i.e. Whale Optimization Algorithm and Jaya Algorithm, and other ensemble learning algorithms i.e. Adaptive Boosting, Cat Boosting, and Random Forest. The implementation is then conducted for a warehouse consisting of a single AS/RS with multiple item types. From simulation, data-driven approach provides the fastest response time and low travel time, outperforming other well-known methods such as locating idle AS/RS stacker in the Input Point, Output Point, Middle Point, and Last Visited. The sensitivity of prediction accuracy to AS/RS performance is also assessed where even with the poorest algorithm namely 54% accuracy, data-driven approach still can improve response time and traveling time. Lastly, this study also supports the realization of digital twin for smart warehouse.
This content is subject to copyright. Terms and conditions apply.
Authors version of the paper published in Annals of Operations Research
https://doi.org/10.1007/s10479-024-06342-5
Data-Driven Approach for Dwell Point Positioning in Automated
Storage and Retrieval System: A Metaheuristic-Optimized
Ensemble Learning

Department of Industrial Management, National Taiwan University of Science and Technology, No. 43,
Keelung Rd., Taipei 10607, Taiwan, ROC
Intelligent Manufacturing Innovation Center, National Taiwan University of Science and Technology, No. 43,
Keelung Rd., Taipei 10607, Taiwan, ROC
3Department of Public Finance, Feng Chia University, No. 100, Wenhua Rd., Taichung 40724, Taiwan, ROC
*Corresponding Author: ugihzakka@gmail.com
ABSTRACT
 !"!#" # " $!%"" &'# '"%# "$"& $"%  & ##"$
()*+,&"& !%!#"&%& "%"-"'$"#.##"&
!%!##&"&%/!!%',#&!%&'"/ "'##&$'& !"!#"$"&
% )"$"& "% & "%/  #"$ ()0+  " $#" !! % )*# % %#
"$".$&#"""-""#',!%&'"&""& )0#"'%',!#"&
' #%"" !%&'"& "#1# '" &"$!%/& %#!# "$ & "%/ "$, %&'
'##%,'&%"$/$"#./%!%&'"'$"##"%##' &
"'%"".##"/",#&#$,  %#&/ !&"%'"$'
%$& #.. #"'%%##22&&'#"%%"!%!%$"%#&/""#
%3" !"$&,'4%,#&5!"$".6#&/,'$%&"#"#"!%!#&
!%&'"  %"$ # # ",''%"'##""&'"'$!%&"&/&  %%# "%
$"%#"'#..7 5!"$") %"$&8) %"$&"%#$,  % %"$#
..)&!"/6#""6#"&&$9%#".$! $""#"'&'"&%%#
'##"# )0"$ "! "$"!#.6#&"#$ "-!%$"&"&%/!!%'
!%/&#"#"#"%#!#"$& "%/ "$"!%%$"% $"&##'# '"
& )0#"'%":!";"5"!";"*&& ;"&4#"<#"&.##"/"!%&'"
''%'")0!%%$'# #####&%/""!%#" %"$$ =>?''%'
&"&%/ !!%' #"  ' $!%/ %#!#"$&"%/ "$.4#" "##"& ##!!%"#"
% "&" "%#$%"%#.
Keywords@)0"%/ ;"5!"$"*'4%.
1. INTRODUCTION
A , '$$%' &#"$%'$! -#!! '.*,%##%
, "#!%"'$! -#!! ''$!"#"'%#"%#!%""'' 
 #$""%#!#/##%%&%  $"BC.:%&%"'!" %"'
!"#(#+"%##",'"/''%"&'"%# "
"&%"$"&$"% & ##"$BC.)"$"&"%&"%/ #"$
()0+#,'$'%# !! %%%&'$"#/'"/"#%&
#"%!%"#BCB>C./%)0"#/#"$"&!%" '#"#B=C#'
"'##"#'$!"%'"% &!%%$#''"&"/'%%# 
"#"'%" &0 &"$#"$"' '%&%'# BDC.#")0
'"% ! '## &,&#&#'" #!##, .
5"$!%""'"% ! '#)0#& !"!#"#$"$#
%%%&"# ;";%, $(;;+.;;#,"&"%$"!% '"
)0 #"'%" #&  "#"&,"%"-""#%%#"BEC.)&
&'#;;  &" %"%/ "$&%#!#"$BFC.#"#'"% 
! '"$!%/''& #%#!#/##''$$'#"&$-$
'#"$%#"#'"""$.')0# '$! -##"$&&$'"%
!"$ ;;  )0 ' , , '  BGC. ;%/# #"&# / !%!#&
 "' !!%'#"!"$)0;;BC./%"#!!%'#%&%
'%"" &"#!'')0 '%"#  & "$!%'"' ".9%"%
 "' !!%'###$)0",#""'( '"'' %"0&' %"+'
',''%"!%'"'BC.##$%#"'!!%'#%$ !%%%&
!%'"'BC#'#,!"""#"'%"#!''-& '"%3#"&%'" !""
"#"'%" #"/#"& '"B>C%" !%'"' "," ##$! '".
/%%#"'!!%'#"&"!%/&&%# "#.# "#"!
-#";; "%"%%$% -, $"&#&&%'"&%#!#/
)0!%"%%& ##)0#'%&""'& "'%"".
   "!%/#! &"&%/ !!%' #!%!#& ,#& *'
4%(*4+#!%&'"/ "'#" #!'' &#&%# /;;.$
&#"""-"%#"',!%&'"&"& #"'%',!"""' ##" '"
"-"%#"#""'##%"%/ &%#!#"$',%&'&.:&&"
"!%!#&&"&%/ !!%'' ##!!%" % &" "!! '"
#$%"%#B=C./%"%' !!%#$ )0H#%#"# 
'%"'',%&"!%&'"%#, '$!"""$&% $"&"%#%
/%, #.#"##"& !%!##  $& #' &  "<",#&I#$, 
(<I+ % "%"& " '4%,#& 5!"$" (465+ % 3"
!%!%$"%# & /" "# !"$".  !%&'"& -"%#" # "
"%#%$&"#!''& !" '".-!%$"#%#"'&'"&""#""
<I465H#''%'% ' ##'" !%, $#. '& " # "#"&" # "
$!'")0!%%$'/#$ ",#&-!%$"#.%# "%/ #"""
&"&%/!!%''!%/&''%"!%&'"'"   #%&',""
"%/ "$&%#!#"$'$!%&""% $"&#'',/%
# %%##$#"$/'#$%&#%#%"#  !%&'"#.
%$&%"##"&#%&# #.:'""% "&%#
%%&"& !"!#"$"&#%%/&%$" "%"%' &
"&/ !$" *4 ' ,#,  %$ '"!%&'".: '" "
%$% !%!#& &"&%/ !!%'# " &.: '">"'$!%#/
-!%$"#'&'"&""#""''%''##"'&''"!%!#&&"
&%/ !!%'# / = ,'$%#&"#"#&% "% &%"#'%#$ 
'$!%#"&/&  %%#'$!#"!%!#&#$,  %'$!%#
" "% $"%#"'  %"$# &'$!%# " "% #$,   %"$#. :
'" = " #$ " $& # &/ !& & " !%!#& &"&%/ !!%' #
$! $"&%)0& !"!#".9 '' #&"%&%'"%
/'"D.
2. RELATED WORKS ON AS/RS DWELL POINT POSITIONING
 !"!#"#"'"' &'##)0'"% ! 'BDC.:"%%#
" '"& )0#"'%"%"-"%#".:"%$#$"&"',
' ##&"  "' $"& & %#"'$"&. :"  "' $"&!%/#
#"&#!%!#&#/% ' #&%$-!%###&!&"#!''/%$"#'
#,#"#!%, $#' " '"!%, $$#%&,,#/&#"'
# # BC&$ "#  BDC %$#%&,'" %&#"' BGC.%"
#"&# #'#&%&%":!"05"!"(:05+ '"#"%!"&"!"% '"&
&3'"  BJC %!!#"  BEC./%"  "' $"&##$#&"%$#"'
'&"#" /% #!'')0'%" ' ', $!%'"' . :&&"
)0###$&"%"#""#'' %"&&' %" '""
"%&$'"'' &"''%' BJC.9%"%",'$#'$!"" 
-!#/"$,%#%' ## %.5""%&%#"'$"&"
#$! % #%!%!#&'##"#$! ! '")0"(+:!"!"(+
*&& !"(+5"!"!"&(>+&$' ! '"& !""4#"<#"&%
4#"4'" B>C.:!%'"'$ #"'#$%##" % %#"'$"&#&"
"#$! '".:"& !" '"#-&"& "$"#' &#""'$"&..
:!"!"*&& !"5"!"!"&"& !" '"'#"& "$
"#' &&$'$"&..4#"<#"&.%%"!%!#&&"&%/!!%'
',' ##&"&$'& !"$"&.
:"%$#)0$& "'""%#"#")0&/ !$""
"%/ "$$& #%% #&&!%!#&&%#!''%#/%$""
/ ")0 "%/ "$ !%%$' BFC BGC BC.)"% "%#"$"%' ""#
# '"& & / "& & !"!#" # %#!#"$   #"
$#%"%#!#/##""',# %$'#"$%!%#!'"/BCBC./%
"%/ "$ $& #   %!%#" " /% !%%$' & ##$ "   #""'
'&"#," #"%'%%$"$#",#%"$'#"!%'"' B>C.
""'$! -"&#"'#"'/%$"")0/%$""#$ "
$& !%/&#$%% #"'"/ ""!%%$')0BC.)#"&%$
BC" &'$!"%#$ ""'$!%#/% & !"% #&%&&'"&&
%&$&#"%$"&#"/ ""-!'"&"%/ "$&$-$$"%/ "$.
)"%#"&BC ##&#$ ""'$!% "' $"&"%#"'$"&
%& !"!#"&%&%"" " / #%/ """&%'#
$% .
:"##"&/ &"&%/!!%'#!%!#&%# /;;&/ "&
#'$!"%#$ ".:"%$#$!%&'"#*4#,'%# &!"&
% !%%$ ''%" !%&'"# B>C. /% % #$ '$! - !%, $# *4
!%%$'', &%&&. #$,  % !%&$ "$%#'$,
#/% &/&  %%#"# #"%% %%B=C.#"&#&/"#'
%%','$!%&&,'"%.5#$,  %"!##/".
/""# ',' ##&#%&/"'%#,#&$3%"####$"&#"
/"'%#,"&/%'!%&'"& !%,, " %' ' ## ,
$ ' ##%#. %#"!%,, "' ###"'##"!%&'"&' ##."
/"##&#'"!%/&#$% -, "###!''"#.;%/##"&#
/#&<I#''## %&,"#$ "#!%&'"BDC''%%#!%&'"BJC
$'"/"%'"BEC&"%"%#&"'"BFC"&%"&/& 
%%# & &%" "%" # # "  -, "  #$,  %.
2/%" ##"%#  #"&""!! #<I % "$"&$"% & ##"$
!%!###!' %&"%$)0& !"!#".
7""'#")0;;"% "&%#%#$$%&&'$!%&
""##"&  "%$#  #/% !%"' # $  ,3'"/ %!%#""'# 
!%%$'$#%:05!"#"!& !"$"&"!''%&"&$'"%
&"!!%'#&&"%$& !"!#".% "&%#%%/&
&#, .5%'"%,"#" &.9%#""'"&''%"*4$& #
!%!#&,#&<I %"%"&"$"%#"' %"$#!'' 465
%!"$!%!%$"%#&"#/"#$ "# .:#%""#%%%&#
<I465.'&/"/!! '""!%!#&' ##%$& #"%&'&
%)0& !"!%&'".#&&"  %"$# #!%!#&""%# ""
!%&'"&"#"& !"!#"'' &"$%'"&%#!#/
!%".",#"% &"#&"&%/!!%')0#/
#'"-#"& !"!#"$"&#%% , ",#&%#"'# 
 "' $& # %&%/%#"%'"##$!"#'% -, &$!%'"' .
, . "&7%# ;";#")0
Stud
y
Objective I/O Point Method Type Approach
Travel
Time
Response
Time Adjacent Opposite Static Dynamic Heuristic Analytica
lSimulation Data-
Driven
B>C
BGC
BC
BC
BJC
BC
BC
BC
BC
BEC
Ours
3. THE FRAMEWORK OF DATA-DRIVEN APPROACH
7&/ ! <I"" '$,#4#"'%## 2%#"2,%# &
'#%.#*4  %"$#% # '"& ,'#" % % "/ '" &
"%!%", .:"# &,"&"")0& !"!#"'#"& "$',
/%#%"#!' ""#"%/ #%!&&#"%,".#"'$!""
'$! -",'$#!%$".%%"##"&$!##" "''%',"
 #"''"!%&'"/$& .9%"%#')0'/$ "! "##&"
$ "! #"!%&'"!%, $,'$#$ "' ##' ##'"#!%/#& %.
I'*4 %"$#&#&#'%,&# #.
4#"'%##(4+##""#"' $"&#&%' ##'"!%, $#%"
 #"!%&'" "!%,, """#"', #"!%"' %' ## B>C.9%
$ "' ##' ##'" #"'%%## " #" "$-'" ## 
I""$#%"!%,, "
P
'"#$! 
xi
, "'%"' ##
k
&"&#
P(y=kxi)
%
w
%!%#"#" " /'"% "" # " %%##
''"/'"%&
b
#,#.$!%""4!%!%$"%#%# /%(+#&"
!"$$-$$  &,3'"/'"&#% %"#"%".
P(y=kxi)
K
e−(wk
Txi+b)
l=
c
e−(wk
Txi+b)
, k = ,….,c
(+
2%#"2,%#(22+##"%"%%& %"$""%"# -#"'##
&'"%#'##,####"%#$ %"#$#%##'#&#"'
'"#B=C.#""!&#"'(+#&,'$#$!%"" !%!%$"%.
9%"%"$,%,%#(+ # &#$!%""'"""&#","&.
'# %(+$! # %#"'$"&,#&"&$" !%'!  
%'%#/ #! """!"#!'"#,#"# &""% #"%'"%"'
/% $#%' ##!%"" #!'&#"!!'%"%#'/&BDC.A
$!%"#% #&##"!!'%"%##I"BJC%
#"
!%,, "!'&"!""' ##l.$$$$,%#$! #%%&"
," &(4+&"$$$$,%#$! #%%&"#! ""% &
(+%"!%!%$"%#""',"&.
Gini=
l=
c
(pi)
(+
'"!%%$'*4 %"$####"/""!%!%$"%##&"
!%!%$"%",'$#$!%"".9%"%<I""#/"'*4
!%&'"% && "" %# ".%%$"%#"' # #&%!%%$
#$ "# !%!%$"%# & "# !"$" " %' %  , !"$
# "#.:"##"&465##&"$$'" &"%#%%$"'%""
%%#%""##/ #% '"&,"%&#BEC.465#'#,'#"#
!%$"% ## %"$"" &# !! "#&$,% "%"##!"
!%$"%#.#-#"/!%$"%#""#', '"&./% !%!#&&"
&%/!!%'##9%%$"%#"' %"$%##""% !
&#$,  %%##"% !.
9%.<",#&I#$, 4%"4655!"$%
&" & !%'##" !%!#&&"&%/ !!%' #&#'%,&#  #
'##"=$#"!#.
. Population Initialization. :" # #"%"& , "  " !! " %&$ . I'
&/& %!%#"#"# ",/'"%
X
KB-L-C"KF##9%.
 - & - %!%#" " 4 !%!%$"%# - & -> %!%#" 22 !%
!%$"%#-= &-D%!%#"!%!%$"%#&"%#"/%, #$ -J
-E&-F%!%#""#"/""(7+%422&%#!'"/ .'
"!%!%$"%#!%$"%#&""#/&%"%#&/%, "!#
% '&&/%, ##&&&#'%""#&&%"%/%, #.&" &
%$"&'#/%, "!#.."%&&#'%""!%'##%#
, &"-$! # ""%#%$"##9%.
9%. "!%#""8"!%;%$"%#&7"#5!"$"
, .'#<%, #!#
Context Variable Range Discretization
4#"'%##
!%;%$"%#
(-+ GM> GN-O@ ,#N-O@#
N-O@#N-O>@"'
(-+ G.GGMGG 2&
22!%;%$"%#
(-+ M=G &
(->+ GM> GN->O@' &N->O@$""
N->O@$#N->O>@',#/
'#%!% 4(-=+ M=G &
Context Variable Range Discretization
;%$"%# (-D+ MGG &
"<"7"#
7(-J+ G.GGM 2&
7(-E+ G.GGM 2&
7(-F+ G.GGM 2&
9%.I-$!  "%# "
. Fitness Evaluation.I'&/& #"/ "&",""##/ .:"#'#
""###%!%#"&,"''%'#$,  %.#"##/ "
# &,/ "&,' ##'"!%&'".
. Individual Updating.,#""##"!! "## '"&#"'%(
Xteacher
+&
"%#% %%#.9%'&/& (
Xold
+"# "#!&"&(
Xnew
+"!##.
9%#"'%;###&#I"%
r
#%$(GM+%&$$,%
Tf
#"''"%"%%# '"&%&$ " !%,, "&
M
#
"$!! "' $#.'&"&";###&#I">%
#"&"!#%
Xi
&
Xj
%%&$ &/& ## '"&&
r
#"%%&$
$,%.
Xnew=Xold +r
(
Xteacher−( Tf)M
)
(+
Xnew=Xold +r
(
XiXj
)
(>+
>. Greedy Selection. I' &&/& ' ,!&"&"&/& #,""%
"##/ .5"%#" &&/& #$"&.
=. Repeat"#"!" "$,%"%"##%'&#"%$"'%"%.
)"%"!%&'"$& #,!"$&&"',#&"!%&'""-""#
)0"!%&'"&"## &,"%#%$& " " & !" !#". #
"%#%$" %"$# #!%!#&#!%#"&, #;#&'&.2"""
#')0%## # ""!"""%#%$"..& !"!#"#
"%$  -#$  X %!%#" %" !#"& Z %!%#" /%"' 
!#".
, .;#&'&%#%$") %"$
Data-Driven Pseudocode for AS/RS Dwell Point Positioning
Input : ;%&'"&"#%%#")0
Output : )0 ;";#"(XPZ%&"+
Steps : Q
@ if"!%&'"&%#"##"%
@ 4'")0""!"!"#& !"!#"
@ else (!%&'"&%#"#%"%/ #!!#&"$+
>@ """" $,%"$(+"%'
Data-Driven Pseudocode for AS/RS Dwell Point Positioning
=@ forK"&
D@ *#%",#/&#"'%$"""!"!"
J@ end for
E@ %"""$#'& &# '""%#""$
F@ 4'""#"'%%""' # '"&"$#& !"!#"
G@ end if
@ "%"& !"!#"
4. EXPERIMENTS FOR PROPOSED DATA-DRIVEN APPROACH
##'"-$#"!%%$'"!%!#&&"&%/!!%'#$
 '##,"&%$!&"#"#.#"% !%%$'',####&.
 !%%$' # '$!%& &% #/% '$!%# #'%# $  + :&/& 
%%#'$!#%!%!#&!%&'"$& +5"%$"%#"' %"$#&+
5"%#$,  %$& #.
4.1 Dataset Information
9/,'$%&"#"#% "&"' ##'"!%, $#%#&#!%#"&
,  >. 6 # "# &" "% &%" -!%$"# % -'"& # !"
!%%$$ '$!"%"!%'##%:" R%SJG=GT.EGA(E
;#+U.A*$%@EF*6)*.:%&%"#%"'$!%#% , "
!%&'"/  ## ' !%&'" # / "&  "#$!  &" ,#&  %##
< &"%'&"#"##! ""G&%"%!# .
, >.;%!%"##""#"
No Dataset # Instances # Features # Classes Source
:%# =G > BFC
A ## > F D B>GC
& G J B>C
> 7 JE  B>C
= :#!% = > B>C
6%" &"#"# %#& &" !%!%'### '&'"& %#".' '
"%'&"#"$/&%"#' %$ "#!%%$&#I"
=% % &"(X+%#' & % ,#&"$$$&"(Xmin+&"$-$$
&"(Xmax+.:" $"&"%GM  ##$! "'$!"".%#
'"%' "% &"#"#'#&%&.#&"'&#"'##%."%"
/%, #%"!"&"% #!%!%'##&#'"%"%$'"%' ' ###.
#"%'/%"&/ , '&%#"" &" ,$%' / #.2"""
"%#"%# '" ##"#-!%$"#"" "%#%#&&"
!%%$'','#&3"!%!%$"%#&"#!"$".
9% '$!%"/  ## " !%%$' # $#%& &% '%"% $ 
''%' '##"' & '$! -" # !%#"&  I" D M E %#!'"/ .
 ##'"''%'#' ' "&,#&"'%%'" !%&'"&' ##"%%;#"/
(;+%%2"/(2+&"% !%&'"&' ##"%9 #;#"/(9;+%9 #
2"/(92+.##"'$#%#"&/"$ ''%'#%'%&&%$
#! "#&'$! -"$#%#"/%'$!"" "$!%&/& / "
#'&#.!! "###"#G&"$,%"%"###"#GG.
Xscaled=XXmin
XmaxXmin
(=+
Accuracy=
i=
N
(
TP(i)+TN (i)
TP(i)+FP (i)+TN (i)+ FN (i)
)
N
(D+
Consistency=
i=
N
(Accuracy (i)−Accuracy )
N
(J+
Complexity=Total Computation Time
Population ¿umber of Iterations
(E+
4.2 Experiment I: Comparison with Individual Learners
!%!#I-!%$":#"%/ <I465!%%$#'$!%&"'
%%'$!##$, $& $ 422&.$%'$!%# 
 %"$#% #'$,&""465 %"$%!%!%$"%#!"$".
#&""$#446522465&465.%# "##, 
=%", &&'"#",#"/ .:"',####&"""<I465##",
"$#"''%" '##&$#"'##""$'##.#3#"#""#$, 
%'%#-!'"&!%&'$%''%"$& #"&## 
$& .:"%$#'$! -"#"#"#"&22#" #"'$!""
  <I465 '$! -" # !!%-$"  " ""  "# &/& %%#.
/%"'$! -"##" ''!", #'"#'$!#&'"*4$& #.
, =.;%%$'$!%#":&/& 4%%#
Dataset Criteria SVE-TLBO LR-TLBO KNN-TLBO DT-TLBO
:%#
)''%' 0.9800 0.9800 G.FJ G.FDDJ
##"' G.G>J G.G>J G.G>> 0.0333
$! -" G.>J G.G=D G.E 0.0548
A ##
)''%' 0.7294 G.D=E> G.DJJ G.DDEG
##"' 0.0728 G.GEG G.GF=F G.==
$! -" G.>= G.E=J G.GDG 0.0546
&
)''%' 0.9524 G.F G.F G.FE
##"' G.GJGD G.GJ 0.0571 G.GJ>>
$! -" G.JJ G.F G.GJ 0.0530
7
)''%' 0.9944 G.FEEF G.FE G.FEEF
##"' 0.0167 G.G G.G== G.G
$! -" G.FD G.G G.GJ 0.0533
:#!%
)''%' 0.9290 G.EJF G.FG G.EG=
##"' G.G>JJ G.G=FF 0.0474 G.GD>
$! -" G.=JE G. G.F> 0.0737
4.3 Experiment II: Comparison with Other Metaheuristic Algorithms
I-!%$" :: !%/&# " '$!%#  <I465 , %! ' 465 "
&%" $"%#"' %"$#$ 7 5!"$") %"$(75)+B>>C &
8 ) %"$ (8)+ B>=C. #  %"$# % # '"& ,'# " / #$ %
'%'"%#"'465$ !%$"% ##.6##$ %#'&""
'$!""%##<I75)&<I8).%# "#%'!" "&, D.:"',#
""<I465#"$#"''%"$ $"%#"' %"$#'#&%& &
,<I8)&<I75).:"%$#'##"'<I465&<I8)%'$!""/
!%/&'##""''%'.:"%$#'$! -"<I8)#"#"#" %"$ 
'##&"-"%$ #$! ' ' "&<I465#" #"'$!""&"
$%'$! -' ' "&$%"##/ " <I75)#,".
, D.;%%$'$!%#"5"%*"%#"'#
Dataset Criteria SVE-TLBO SVE-WOA SVE-JA
:%#
)''%' 0.9800 G.FJ 0.9800
##"' 0.0427 G.G>> 0.0427
$! -" G.>J 0.1145 G.=J
A ##
)''%' 0.7294 G.JGD G.J>F
##"' 0.0728 G.GEDJ G.GE>>
$! -" G.>= G.>EF 0.1464
&
)''%' 0.9524 G.F>JD G.F>JD
##"' G.GJGD G.GJ 0.0619
$! -" G.JJ G.>> 0.1219
7
)''%' 0.9944 G.FEEF G.FEEF
##"' 0.0167 G.G G.G
$! -" G.FD G.> 0.1156
:#!%
)''%' 0.9290 G.FG> G.FEF
##"' G.G>JJ G.GDF 0.0425
$! -" G.=JE G.F= 0.1559
4.4 Experiment III: Comparison with Other Ensemble Learners
' <I465 # &/ !& ,#&  #$,  % & I-!%$" :::
!%/&#"'$!%#<I465""% #$,  %%$%#
#'#6#"%!%#"&,)&!"/6#"()6+B>DC&"6#"(6+B>JC""
%# #"  & 6 %!%#"& , &$ 9%#" (9+ B>EC "" %#
!%  .:%&%"$%'$!%#  %"$#% #!"$&""465
 %"$.#&""$#6465)6465&9465.I-!%$":::
%# "##, J.:"',#""<I465#"$#"''%"$#"'##
 &,64659465 & )6465. 9%"%$% <I465# #"
#"#" %"$$'## 6465#" #"'$!""&"'$! -
' ' ".#%# "#''%&'"B>FC'#""&"",#"&,',
'$!"" -!#/&' &",#.:" # &#" ##"%!%", "
$& "%%"$#"$"%##&.9465&6465%% "/ 
$%'##"" $'##. %%"#-!%$" !%/#"" "!%!#&<I
465#/%&!%%$''$!%&"""%#$,  %%#  ##"
$"''#'"# '$!#&#$! #"$"%#%&/&  %%#.
, J.;%%$'$!%#"5"%I#$, 4%%#
Dataset Criteria SVE-TLBO CB-TLBO AB-TLBO RF-TLBO
:%#
)''%' 0.9800 G.FJ G.FDGG G.FDDJ
##"' G.G>J 0.0327 G.G>> G.G
$! -" 0.2247 .GD G.EDJ G.EFDE
A ##
)''%' G.JF> 0.7712 G.DDE> G.J>E
##"' G.GJE G.GFJ= 0.0658 G.>D
$! -" 0.2451 D.J> .>F .FJE
& )''%' 0.9524 G.FED G.F G.FED
Dataset Criteria SVE-TLBO CB-TLBO AB-TLBO RF-TLBO
##"' G.GJGD G.GE G.GJJ> 0.0682
$! -" 0.2177 >.G> G.>>= G.D>FG
7
)''%' 0.9944 G.FEEF G.FEEF G.FE
##"' 0.0167 G.G G.G G.G==
$! -" G.FD >.J=D G.=EG 0.2000
:#!%
)''%' G.FFG 0.9516 G.F>=E G.F>=E
##"' G.G>JJ 0.0443 G.G>DF G.G>=
$! -" 0.2578 .GG .EG G.>EEE
4.5 Pairwise Comparison
9%#$$%"'$!%#$ -!%$"#, E!%#"#"!%#
'$!%#&'""%"!%!#&<I465#,""%%#% ('#
"+""'$!""%#.9%$=,'$%!%, $#"#-!%$"!%/#""<I465
!%%$#,""%""%  %"$# $#" '##"%$#''%'&
'##"'.$ % " "!%, $ #" " '$! -. ' ##"!%%$'
''%#<I465#'$!%&"""%#$,  % %"$#.6"<I
465#" !%/&#,""%'$! -"#'"#'$!#&#" %%#.6"''%'&
'$! -"%'" /%$!%""$"%'##!' "#$! $"&"%
% "$&'#!%, $ '##"'#$!%""%#% ''%'&/"
$%"%&"%/.7""'#''%'$"%'%"%-!%$"
'"= '#'$!%"&%"#$,  %"$#.
, E.;%#$!%#)$) I-!%$"#
SVE-TLBO vs.
Accuracy Consistency Complexity
Better Wors
eEqual Bette
rWorse Equa
lBetter Worse Equal
4465 > > >
22465 = =
465 = = >
<I75) = = =
<I8) > >
6465
)6465 > >
9465 Q Q
"  =  = D 
5 IMPLEMENTATION FOR AS/RS DWELL POINT PREDICTION
##'"!%/&#"&" &$! $"""!%!#&&"&%/!!%'
% )0& !"!#". : "##"&'$!"%#$ "# #&#'"'
''$$&""&$',/%")0B=GC.#"$ %%$%#
&/ !&%)0!%"#, "9 -$#&#'%"/"#$ "#"%
&*4,#&!%&'"/$& #$,&&&#&#$ "!%%$.-!%$" 
 ##9%>.9%#"#$ "$& # &,, "."#"%' &"%
%"&%$#$ ".9"%%&!%&'"/$& #%"!%%$&
%$ #"%' &". "%& $& # " $,&&& # &"&%/ !!%' 
#$ ".7/%)0%#"& "!%&'"/$& !%&'"#"-"%#".
#"!%!#&"%#%$" %"$"!%&'"&-"%#"#"%#%$&"
& !"!#".)"%"#$ "##&")0!%%$'#/ "&.
9%>.I-!%$" 9 "%/)!!%':$! $""
5.1 Problem Description
!%, $#&!"&%$B=C'"#"%#P)0"
#"'#'$!# . 6'##  " & )0" &$#"%" "
!%%$'"!%!#&&"&%/!!%'"#!''")0&%#
%#"!#!%#"&, F.
, F.!''")0&7%#
AS/RS Warehouse
*-$$%" #!&K$0#
*-$$/%"' #!&K.=$0#
I-"#%9%!&K$0#
)'' %"&' %"K$0#
)0'"%/ ,"/%"' &
%" #$ "# 
)0'!'"#! "!%"%/
)0" #,%&'' 
9:95##&#%#"#'
 "&"%/ # '"&!&#"
' ##"")0
:!"&"!"!"#% '"&!!#" 
 # # '"&,""# &!%'#
I'%'#>G' $#&D %#
I'%'#%#!#, "#"%&%""$"!#
"%$ &#"%,"&
 ##,#&#"%##&
%##!''#"%"'#&%&"%'
; "&$##&"K "K"KG.
$"%
$&&#!! %%$ &#"%,"&UN(14,
3)#'&#!%"
$!%"" $#%# % #'"  '"& & " & !" !#"
&'#$ "%/ "$&%#!#"$.6"%# ' '"&"'"%.
%/ "$% '"#"''")0.&'"%/ "$$ #%&'
"'#"&" % % '#$!". #!# "$ % '"# " %#!#/## 
  "%'/&"#.) %%#!#"$' &"%'#"$%#"#'"&
%,%.%%,"$"%'#%/ "&%I"F$#%#""%/ 
"$!%"(
TT
+&I"G$#%#"%#!#"$!%"(
RT
+'
NZ
&"#"$,%"###&,)0""$".2"""I"F"
"%/ "$' &#""%/ $!"($/"""$ &&+&""%/ 
&&.:&&""# #' &#""%/ )0$/#"& !"!#".
:I"G"%'/"$#""$""##,%'/&,"##"$&
"#"$#""$"%'/&"###"%"&",!%'##&.6""#
%$,&&&"9 -$#$ "#"%#!%%$'$#%#.
TT =Total Traveling Empty Time+Total Traveling Loaded Time
N
(F+
RT =
n=
N
(Finishing Time
(
n
)
Receiving Time
(
n
)
)
N
(G+
5.2 AS/RS Simulation Model
''!" $& &#'%," /"&%/ )0 !%" ## 
9%=%$""#%%/ " ")0& .:"',#"""& !"#"%"#
  &")0#"# "&'#"%"  &"&%"& !"
!#".# '%" '""%/ "$,"")0"#" '"%%$"
-""#"%#!#"$ , %.:" #',"&"""!%!#&&"&%/
!!%'&#"!%&'""-""#%#"&""& !"!#"',"%# "&
%$"!%&'"&"#./%)0#" &#"""!%'##"!%&'"&"##'
"!%&'"$,%.#$ "$& #"&/ !&##9%D
%!%#"""!/"%#&9%J%!%#""%#(+,%
!%"&(,+!%"'&"%#!'"/ .
9%=.'!" *& )05!%"
 #!!  & &$& !% # % &%/ , %$ &#"%," $"" "
#"'#"'"  "# %"  !%'"'. %% #' " #!!  & &$& %
'%"&&" '#"%"#&&&"#%"""%#/&#/%'!'"&
#"# #.:'%""!!%&'"#% .. $#"$!"""!%&'""! ,
#!! &""##"$&%'" .:'%""!!%&'" $#"-'&#'!'""
%'"!%&'" ,#!! &" #!'#/ , "%'." "
!%'### !%%$$& , / %&$ "## & !%&'"# #&" %# # ""
%$!&"'"', '"&. #$ "$& #,/%&,#"%'"%&
 "%&,#"""$& #%%$%%%&-'!".:" ##,
/ &"& , !%%$ $" B=C -"%$ '&" B=C & -!%$""
/ &"B=C.:"#&"#%"""$& 1#,/%% '"#% % &,/%,
/# ''"!%" ,/%####"$& "!"&%-"%$!"#
&#%"$& %##"&#""'&".
9%D.!<$ "*& %)05!%"
(+6%5!%" (,+:5!%"
9%J.7%#$ "*&
)"%"#$ "$& #,, ""-"#"!#"#", #"''"
"&"&%/ %"$, ";".;%'## #, "#!%#"&9%E.9%
%'%&#"%' &"' &"!%&'"%#%& !"!%&'" "##"%"&,
%""&%'%&""$/%)0& /"!!#.""#
" "%#""##,"&."#"!#"%'%&&"%"##!! ..#"%"$
%&$&..%"%/#!''"$"!.#&"%#"%&9 -$A , , .
2-""%"#"%' &"%#&%"%&"&%/ %"$#"%&"
!%&'".!%&'"##"%"&/%)0#& .:%&%"%&"%'#"&& 
!"" , ###&""",#&""#"!"%#!! %&$&.:"#
"#!! "#& !"!#"#&%'" &"%$&#'":!";"# #"
#$%"$"!#"#'#"'%&"#(FG+.:"#"&$&"#
%#%$") %"$#!%%$&$,&&&9&:"$.
9%E.;%" ;%%$$"'%&&& ;"9 -$
5.3 Data Acquisition and Feature Analysis
 #"%' &" % %"& %$ #$ " $& /% " )0
-!%'#& .:"%%&#"&"%%'%&&"%#"# "."
/%, #%"$ +  "$ " )0# &  &+ "%#""#"!
%'/&,)0"%& .2"""""#)0,#' '##"##"%&
%"%/.'"$"!#"#$!"!""##"%"#',&"&#
G %"%/"#',&"&,i&!&""$"!i#''"$ 
/&%" '""%'' .#""#"!#'&&#$ &""!%
' ##.:"#'#>&%""$"!#%'#&%&.%%"%%="##
"" $ G(#"%+(%"%/"$+(%"%/"$+(%"%/"$+&>
(%"%/"$ >+.:!%'"' ,"&" %#  ,"&/ 7%#*$"
#"$(7*+%"$"&%#"'"% ! '# #!! &%$7*"
)0.
6#"#&""#$% "$#%#' ##'"%#'"#'
!%&'"!%, $.:%&%"'"!%%$'!%&'"/!%"% ##
#'&'"&%#","%#%$""' ##'"#!%/#&!%, $,'%"#$
"%#.9%F#%!%#""&""%#%$"#"%#"=#$! 
&".%#""%"%#%$&&"%!%#"#"&%'"$'%"/%, 
"$"%/ ,"& .%#""%#%'%"&,#& &/%, #(4<+.
'"%%="##"#'#= &/%, #%'#&%&.:"',#""
"%#"/%#// #.#"%%$/&.:"" "%%F' #$! 
&"%"&%$E%#)0!%".
9%F."%#%$"
5.4 Experimental Results and Discussion
5.4.1 Predictive Analytics Performance on Simulation Data
# &"%"&%$#$ "J=?%#&%"%&=?%"#".
'"%' "%#%"%#%$&"&$$/%, #.!%!#&<I465#
!"$&#"% &" /'%##/ &"!!%'" G"" #! "#%&%"
,"%!"$ !%!%$"%#&"#.!"$&$& #"#&"!%&'"
"%&"#"&".#''%'# #"%&%' "$%%'%&&.
$ %## #!! &""%#$,  %"$#%'$!%#!%!##'"
!%%$"'$!""/,#&"!%/#-!%$".
#"#$!%$"%##"!%/#-!%$"" %'%/##
9%G!%#"''%'"-#&"$,%"%"#"--#.6#&
%'%/" !%!#&<I465!%/&#"#" ''%''%##/ &"
'"-".9%"%"%#%"%$!%/$"'"$,%"%"##%'&=
$  %"$#.#&'"#"""-"'"#"%"%#&"
#!&$%'$!"" "$" GG"%"#.'$!"" %# "#%#
, G#"''%'""" "%"$#'&#&%' "$!%&"$
#'&#.:"',#"""!%!#&<I465!%&'#",#"''%',""
"%&"#"&"$"%$"&#.I/,""%<I465 ##"#"#"
'$!"" "$ '$!%&" "%#$,  %%#," "% &"#" &"
 %#", #%"'"#"%&% "$&'#./%" ##$#
"" ")0& !"!%&'"#/%'$! -!%, $"" %# "# JD?
''%'"%&"&D=?''%'"#"&".
9%G.4%%/%)0 ;";%&'"
, G.;%%$'$!%#)0 ;";%&'"
Dataset Criteria SVE-TLBO CB-TLBO AB-TLBO RF-TLBO
%
)''%' 0.7639 G.DEGD G.===D G.J
%$ 348 >JD.> E.> F
#" )''%' 0.6458 G.D=G G.=>J G.DG>
' $ 2.15.E-05 >.J.IG= >.J.IG= .=.IG>
5.4.2 AS/RS Simulation Results and Discussion
 "%& <I465#"$! $"&# &"&%/ $& % !%&'"
)0& !"!#"""#&"."%/ "$&%#!#"$%
%'%&&"E%#!%".&%"'$!%##%'&'"&.9%#""
!%!#&$"&#'$!%&""> % #'##"!"")0:!"
;"*&& ;"5"!";"&4#"<#"&.'&"!%!#&$"&#'$!%&
"""%&"&%/ %"$###"!%/##'"$ 6465)6
465&9465#"""##"/"''%'")0!%%$'',
####&.
%#"'$!%#%# "#!%#"&9%.:"%$#%#!#"$"
!%!#&&"&%/$& !%/&#" #"/ $"%$"&#.:"%%&#
"%#!# "$ ', %&'&" #'".# #,'#" &"&%/$& 
 #)0""&%'" "!#"%"#' ##"""!%&'"&-""#.
#'&#"#"%#!#"$#,"&,*&& ;" &,:!";"4#"<#"&
&5"!";".5"!";",'$#"%#"#'"# ' #""%"%/ "##
"$"!#' ##,#&#"% "#"%"#"%$"!"!"%"#"%
"###"%"&.5""%&":!";"# ' #""#"%"#,""%
%$%"%/ "#&*&& ;""#"$&!","""!%%$,""%"
:!"&5"!"$"&#.
:"%$# "%/ "$ "#%"#" "%/  "$# ,"&,4#" <#"&
 &,&"&%/!!%'*&& ;":!";"&5"!";"%#!'"/ .
!%!#&&"&%/!!%'## " %#" #"/#"&#'"%#!##, "
!%&'"%%%.5'"!%&'"#%" &#)0"$// &"
%"%/ "$.5""%&4#"<#"&% &#"&)0"$/%
" "-"'%""##%'/&/&'##%$/$"""%-""##
"' #""& !"!#".#%# "#''%&'""!%/##"&BC
%4#"<#"&% !%/&#" #""%/ "$./%#'#'4#"
<#"&!%/&#"#'& #"%#!#"$$"%$"&#. :"#$!%"""
%$$,%"" "&%'#$###$ "#$"%'#!%#""/%"$%
'"$".:"!%#!'"/" "$%"" "$" %"#$ "
%"$&"%$,%"$#'#&%&"&%'# ,/$%
#'".:"#  # %" """%#!#"$ # % ""%/ "$#'
%#!#"$ % '"#"""$ "$# "%/ "$ $#%#"
)0$/$""$.%%"&#%"$,%'$"##" %"
%#!#"$ ,.
D ata-D riv e n L as t V i s i t e d I np u t M id d le O u t p u t
30
35
40
45
50
55
60
65
70
75
80
58.29
74.69
68.42
65.5
78.29
35.72 34.73
37.54 37.45 39.72
Response Time Traveling Time
Dwell Point POSITIONING Methods
Time (SECOND)
9%.$!%#"%" ;"*"&#
##"/"&%"&"&%/ %"$#$ "!%!#&<I465
6465)6465&9465"")0!%%$'#!%#"&9%.:
"%$#%#!#"$"!%!#&&"&%/$& #" !%/&#"#%"#"%#!#"$
$"% %"$# &,64659465&)6465%#!'"/ .:
"%$#""%/ "$"%&%%$#"#$"!%!#&<I465!%/&#"
#%"#""%/ "$ &,64659465&)6465%#!'"/ .6"
!%%$'# % "%#"    " " ''%'  '  %"$.  %
$#' ##'"%%%  %"$  '")0 " "% & !" !#"
&"%%#!#"$&"%/ "$&"'##%,'&%".
/%/"!%#" %"$..)6465"=>?''%'""#"&"#" 
!%/&# ,""% %#!# "$ & "%/  "$ '$!%& " " %#"' $"&#
#!'' #""'$"&#.#%$"#-!%$""','' &&"","%#!#
"$&"%/ "$',%&'&#&"&%/!!%'%# "$%'"
&%#!#/!%".%"''%'"%"$!%/$"#',$&.
S VE-TL B O CB-T L B O A B - T L B O R F-T L B O
30
35
40
45
50
55
60
65
70
58.29 60.19
63.31 62.21
35.72 35.97 36.72 36.21
Response Time Traveling Time
dATA-dRIVEN aLGORITHMS
Time (SECOND)
9%.$!%#"%""%/) %"$#
6 CONCLUSION
:"##"&&"&%/!!%'#,!%!#&#&$'& !"
!#" $"&  )"$"& "% & "%/ #"$ ()0+. :" %# ,
!%&'""-"'$"#" '"")0& !"!#"""' ##"
'""-"!%&'"&"#.!%!#&!!%'#, ",#&"<"
,#&I#$,  %"%"&"'4%,#&5!"$"(<I465+
#&"3" !"$"!%!%$"%#&/&  %%#&/""#.
#$,  %%#'$!#&4#"'%##2%#"2,%&'#
%$"''&"%!%", ".<I465#,"#"&=,'$%
&"#"# & '$!%& " &/& %%# &%" $"%#"'  %"$# &
&%"#$,  %%#!%/"#, ""!%/& % ''%'& '##"'
 $"'$! -".#$ "$& #", "%/%"'"/"
 !%!#& !!%' $"" " &"& )0 !%" &% #"'#"' "#
%".6#&-!%$"&"&%/!!%' &#"#'"  %%#!#
"$'$!%&"> % #$ :!";"*&& ;"5"!";"&4#"
<#"&./%&""!##, "!%&'"%%#(%%%!%&'" &"
'##%)0$/$"#+""%/ "$',# " %"4#"<#"&
% ,"#"  %""%#.:"' #,$#%&""/"%#"'##'%"
&"&%/!!%'"=>?''%'""#"&"#" !%/&#,""%%#!#"$
&"%/ "$.#"%#,""%)0'' &" %!%" '#"&
$#" $!%"" ,""%)0%#!#/## &"" %'#"$%#"#'".
#%# "# &#%&%$!%'"' !%#!'"/#!' %%##$
#"$/'#$%&#%#%"#  !%&'"#%"#",#" $&,"
#" $"''.:"#%"""""$!%/$"$"&&!&#
&#"%#" "#(#!! &&$&%"#+.%" "'
&"" %)0& /"#""$ &" %$!%/$"&" %
" "' &""%& /"#""$ &"%"%$!%/$".)!%"%$
"$!%/& )0!%%$' "&"&%/!!%'  ##!!%"# "&"  "
% "%#$%"%#%"% "$&'#',!%/&&"$# .
9%"%%#%''!! "!%!#&&"&%/!!%'% '"& !"!#"
&%"$"% & ##"$##'#,"'*, 9  $"#"$(*9+&
)"$#<' "%&"%/ #"$()<0+#'"###"$# /
#$ %'"% ! '#.)####"$!'")0%'#$!"  #!%&'
"%#"#"#'%%#,'$#%"''%%'" B=>C.)!! 
"% !"$" & *4 "' $  # $!%/ " ''%'  &"&%/
!!%'""' &"" %%#!#"$&"%/ "$.:"# #"%#""
!! %%'$" %%$%" "%"& '#&%"# #' # /"%
$$"B==C./%"# &,"&"""''" %"$,'$#
/%$!%"",'#)0& !"!#"'"-"& "$',/%#%"
#!' "%!&"#"%/ #.) &! %$"&$!%/&,""%
''%',"/% "''',#, ",$! $"&.
CREDIT AUTHORSHIP CONTRIBUTION STATEMENT
Zakka Ugih Rizqi@ '!" " *"&  "% :/#"" 7%" M
% &%"7%"M %/P &" "'%" <# ". Shuo-Yan Chou@
9& '#" !%/# 9%$  ## ;%3'" &$#"%". Tiffany Hui-
Kuang Yu@!%/#9%$  ##< &".
DECLARATION OF COMPETING INTEREST
 "%# &' % "" " /   '$!" ' "%#"# % !%#
% "#!#""' &/!!%&" '"%%!%"&"#!!%.
DATA AVAILABILITY
&" &&"%/ , %$"'%%#!&"%!%#".
ACKNOWLEDGEMENT
#%##!!%"&!%",":" "*'"%:/""%%$"
9"%&)%##%'"% ;%%$ " " %$%"%I&'"
!%";%3'","*#"%I&'".
REFERENCES
BC . .2.&% & 2.- V '" %# '" %
 , #!!  '@ ) '# #"&W IIMB Management Review GE &@
G.GD03.$,.GE.GE.GGF.
BC 4.&.4V) "%"%%/#$%"%#!%"#$$"W
Frontiers of Engineering Management.G.&@G.GGJ0#>=>GGJEF.
BC ).I&%&. <.9%".4$%&).6%%V)"$"&"%
&"%/ #"$#@))""%'"/ "%%,7%#H##", 
/ !$"W Sustainability (Switzerland) / . > . = G &@
G.FG0#>=F=E.
B>C . . )$" 9%'X  *Y'" #  V)"$"' "% & "%/ 
#"$ ( ) 0  + 6#& 5 %"# ," 9% 4& 9&:&#"%W 12th
International Workshop on Research and Education in Mechatronics !!.EMED
G.
B=C ....&..V;%%$' "'%)"$"&
"%&"%/ #"$()0+", !%"W2023 IEEE
5th Eurasia Conference on IOT, Communication and Engineering (ECICE):III
G!!.DEMDEJ.
BDC .8.&,%&:.9.).<#V)#%/ "%"%"$"&#"%&
%"%/ ##"$#WEuropean Journal of Operational Research/ .F>.!!.>M
DGGF&@G.GD03.3%.GGE.G.GE.
BJC . .  & ..  V* "#!& '%"  )0 $&#"
%#!#/## & % '' "%&@ $"$& ,#& #$ "M
!"$"WThe International Journal of Advanced Manufacturing Technology!!.
MEG>&@""!#@00&.%0G.GGJ0#GGJGG>>GD.
BEC 2.6#.I$&&."!V%#'& % &#  !'@
$! -" & '" # "# ,#&  " /'  %" !%, $W EURO
Journal on Transportation and Logistics/ .G&@G.GD03.3" .G.GGGE=.
BFC 8.;.<&6%V) "'-!%###%"!"$ & !""$"&
#"%0%"%/ ##"$WInternational Journal of Production EconomicsGG&@
G.GD0GF==J(G+GG>FF.
BGC . *. . ). & ). . V )"$"' "% & "%/ #"$@ )
5/%/WInternational Journal of Computer Applications/ .JJ.D!!.DM>
GF&@G.=G03'GFFFDG.
BC .&8.*.4$V%/!"$  & !"  "#"%0%"%/
$'"$"&#"%0%"%/ ##"$WInternational Journal of Production
ResearchFF&@G.GEG0GGGJ=>FGEF=DEE=.
BC 8.;.A %&8.&&).V*& #%"$"&#"%&%"%/ 
##"$#@) "%"%%/WInternational Journal of Production Research/ .=G.
>!!.JGMJ=G&@G.GEG0GGGJ=>.G.D>.
BC ;.8.I, &..7 V) '$!%#  & !" % #   "$"&
#"%0%"%/ ##"$WInternational Journal of Production Research/ ..
!!.==M=GFF&@G.GEG0GGGJ=>FGEF=DEEG.
B>C .).6%&8. ). 7" V%/ "$ $& # %"$"&#"%0%"%/
##"$#W IIE Transactions (Institute of Industrial Engineers) FF> &@
G.GEG0GJ>GEJE>GEFJ==.
B=C ..  .. &7. 2. V)#$ ",#& " %
#$%"%#@%&##"&%&"WDecision Analytics Journal/ ..
GG=GFG>&@G.GD03.&3%.G>.GG=GF.
BDC . . *. I. 9.& ).A V #&%$$& #%& !"
'"#$ "# "$"&#"%&%"%/ ##"$WInternational Journal
of Industrial and Systems EngineeringG=&@G.=G>0:8:I.G=.GDEG.
BJC 6.).;"%# 8..$"& . . V #&%$ $& #%&"%$"
!"$ & !" '""$"&#"%&%"%/ ##"$#WInternational
Journal of Production ResearchFFD&@G.GEG0GGGJ=>FDGEFG>FF=.
BEC .& .V5!"$#"&  !"! '#%)0# "!" &
"!" !" " !!#" &#QQ"Q# W International Journal of Production
ResearchGF&@G.GEG0GGGJ=>.GF.=JGJJ.
BFC Z.Z. ( +AZ.9A. &6. V%/ "$$& & 
'$$&'' #'$!'")0" %$&!":05& !"! 'W
International Journal of Production Research/ .=D.>!!.DGMD>GE&@
G.GEG0GGGJ=>.GJ.DG>F.
BGC 7..#$4.6.'%&..A%/#V5!"$ "%)##$"
)"$"'7%##"$#WManagement Science/ ..D!!.DFMDE
FJD&@G.EJ0$#'..D.DF.
BC ..A%/#7..#$&4.6.'%V"%"%/ :"% /
)"$"'7%##"$#WManagement Science/ ..F!!.F=MF>=
FJJ&@G.EJ0$#'..F.F=.
BC .. * % & ). *"" V)0 & [!" #"%" # '""
##"$" "@ )#$ "#"& "/#"" " $"& ","W
International Journal of Production Research/ .>.>!!.=JM=JGG=
&@G.GEG0GGGJ=>G=GG=DJ.
BC ).*""&4.*"V#", #"%##$"&& !"! '#
%"$"&#"%&%"%/ ##"$#WProduction Planning and Control/ .>
.D!!.=M=GG&@G.GEG0GF=JEJ.G.DJ==.
B>C .<.%/ I.*.;%%&8..%&#V*' %"%!%", "@)
#%/  $"&# & $"%'#W Electronics (Switzerland). GF. &@
G.FG0 '"%'#EGEGE.
B=C ).*$$&& .% V)'$!%#/%/ #$,  &! %@
5!!%""# & ' #W Journal of King Saud University - Computer and
Information Sciences.G.&@G.GD03.3#'.G.G.G>.
BDC . $%.$%& *.*"" V)#$, !!%'%' ##'" &
!%&'" &,"#$ "# ##" /"' ##%W International Journal of
Cognitive Computing in EngineeringG&@G.GD03.3''.G.G.GG.
BJC 2.\%$' *.% ) . I  .I  &2. V"
<"' %'" ''%%#!%&'",#&I4:'$!"#W Informatics in
Medicine UnlockedG&@G.GD03.$.G.GGJG.
BEC ).) ,#%V<4@)$'"/"%'"$"&##"/"&# 
%WAlgorithmsG&@G.FG0>GEG>=.
BFC *.).2. :,  :$% .8$ &.. $ V) !"$& #$, 
!%&'"$& #)"*4,#&#"/"' ##%%"%"%#
&"'"W Journal of Network and Computer Applications G &@
G.GD03.3'.G.G=DG.
BGC ;.8.I, V9%$%%&$'!#"#"%0%"%/ $'#
"$"&#"%0%"%/ ##"$W International Journal of Production Research
FF&@G.GEG0GGGJ=>FGEFGG>D.
BC ).""%A."% .*&).;%#'V$!'"& !"
! ')"$"&"%0"%/ #"$WInternational Journal of Production
ResearchG&@G.GEG0GGGJ=>.G.JJDEE.
BC 6.. ;%V) !"$ &  !"! ' %"$"&#"%0%"%/ ##"$#
"%$ &#"%,"&%'" % %'#W International Journal of Production
ResearchGG&@G.GEG0GGGJ=>GGGG=E.
BC *.<# *.<# . $% & ;. *"% V) #&9%$*& %
%/ $! "; "%$)"$"&"%&"%/ #"$I!!&"
:!"05"!"""#W9th International Conference on Modeling, Optimization
& SIMulationG.
B>C 2. . ;& 8. . ;" 8. 2. *" & . 6 V) /  4#"'
%##*&' #%'WNational Journal of Community Medicine.G.&@
G.==>EF03'$.>G.
B=C :.*# $.%).#.&*.).!"%V$!%"/) ##
2%#"2,%&*&&2%#"2,%) %"$%9' 7 
6" ##'"WJournal on ComputingG.
BDC .. & .4V'#"% $"&#@ !! '"#%' ##'" &
!%&'"W Shanghai Archives of Psychiatry G= &@ G.FF03.##.GG
GEF.=G>>.
BJC . %  VI/ " " $!'"  A:2: &- & %$"  
' ##'" # &'# "% ' ##%  %"$W International Journal of
Advanced Computer Science and Applications GG &@
G.>=DF03'#.GG.GGJJ.
BEC .<.<.8./#&.;.<%V' %,#&!"$"@
) / $"& % '#"%& $'' &# !"$" !%, $#W CAD
Computer Aided DesignG&@G.GD03.'&.GG..G=.
BFC . ). 9#% V:%#W : *' 4% !#"%. B5 C. )/ , @
""!#@00&.%0G.>>0=DJD
B>GC 6. A%$ VA ## :&"'"W : *' 4% !#"%. B5 C.
)/ , @""!#@00&.%0G.>>0=77;
B>C *.%"'8.2'#;. '';. #&.4#V&#W
: *' 4% !#"%. B5 C. )/ , @
""!#@00&.%0G.>>0=G
B>C .),%%& &*. 9% V7W: *'4% !#"%.B5 C.
)/ , @""!#@00&.%0G.>>0=;J8
B>C <. ".74.""&.6%V:#!%W:*'4%
!#"%.B5 C.)/ , @""!#@00&.%0G.>>0=7G6
B>>C . *%3   & ). 4# V 7  5!"$" ) %"$W Advances in
Engineering SoftwareGD&@G.GD03.&/#".GD.G.GGE.
B>=C . <"  V8@ ) #$!  &  !"$"  %"$ % # /
'#"%& & '#"%& !"$" !%, $#W International Journal of
Industrial Engineering ComputationsGD&@G.=DJ03.3'.G=.E.GG>.
B>DC . 7&.2# V) ##% ", " %&%")&6#"
/%"# ,#&  ' ##'" & %%## "%#W Journal of Electrical and
Computer EngineeringG=&@G.==0G=0E==J.
B>JC ...&&&..6%V"6#")!!%'%)$ "'"
:6#&$%"$I/%$"WSmart Innovation, Systems and Technologies
G.&@G.GGJ0FJEFEDF>>JF]=D.
B>EC 2.) "$& *. %#VI#$, $"&#@ , &%&$%#"#W
Nature MethodsGJ&@G.GE0$".>>E.
B>FC ;. 6Y $ & 6.  V)  ,W Annals of Statistics. GG. &@
G.>0#0GDEFG>.
B=GC . Z. 7.  .7 & 8. V$ " &) ##  "
$! -$'6/%!! :/"%#"$%$%"'#
;%#!'"/#WComplexity/ .GGGG&@G.==0GG0JFE>E.
B=C A.  & 4. * V# & $ "  "% 4'" 5!"$"
*& )06#&94IZ:*WInternational Journal of Intelligent Systems
and Applications/ ..!!.M>GGG&@G.=E=03#.GG.G.G=.
B=C ). 6' V$ "@ " !%'"'  $& &/ !$" & #W Journal of
Simulation/ ..!!.DJMDJGGE&@G.G=J0! %/.3#.>=GG.
B=C .A.%"V<%'"& / &"#$ "$& #W Proceedings -
Winter Simulation ConferenceGG!!.DDME.&@G.GF07.GG.=DJFDD.
B=>C ....&).%#V* ",3'"/#$ "!"$"
%"%"&"$"& #"% &%"%/ ##"$# !  '#&%%
'#$!"W Computers & Industrial Engineering / . GFFJF G> &@
""!#@00&.%0G.GD03.'.G>.GFFJF.
B==C ..&..V2%/ "%%'$" %%$ "' 
/"%!"$" " & /% !"# & '%"&#'"W Engineering
Applications of Artificial Intelligence / . > . * !. GEDJG G> &@
G.GD03.!!.G>.GEDJG.
... Third, modifying the actions taken by directly including energy consumption metric instead of distance may give better impacts. Lastly, it can be further optimized by including other AS/RS decision factors at a time such as dwell-point positioning (Rizqi et al. 2024c) and multi-speed configuration leading to global optimal solution. ...
Article
Full-text available
Global e-commerce growth forces traditional warehouses to shift from manual to fully automated operations. One popular way is to adopt Automated Storage and Retrieval System (AS/RS). However, AS/RS consumes a significant amount of energy to load/unload bulky and heavy items. One way to reduce AS/RS energy usage is by optimizing the crane scheduling, as it plays a crucial role in determining the sequence of tasks to be completed. This study proposes a novel dynamic scheduling for minimizing energy consumption while ensuring responsiveness based on Learning-based Simulation–Optimization (LSO) approach. LSO integrates Discrete-Event Simulation as environment and Deep Reinforcement Learning as agent which is optimized by Non-Dominated Sorting Genetic Algorithm II (NSGA-II) to cope with multi-objective problem. For the experiment, a single AS/RS was modeled virtually for training and testing under demand and supply uncertainties. The LSO approach is then compared with other well-known policies such as First Come First Serve, Nearest Neighbor, and Shortest Leg. The result shows that the LSO approach statistically outperforms other policies for both objectives, leading to greener and more responsive operations. Finally, managerial implications are provided where the LSO approach improves AS/RS utilization leading to more robust operation with the capability in providing real-time decisions.
... Comprehensive evaluations underscore the applications and methodologies of ensemble learning [26], [27]. Ensemble learning conventionally amalgamates machine learning models from several sectors, including warehouse automation [28], healthcare, agriculture, energy [11], oil and gas, and finance. Consistent findings indicate that ensemble approaches achieve more accuracy than individual models, positioning the advancement of sophisticated ensemble models as a key priority in supervised learning research. ...
Article
Full-text available
Portfolio theory underpins portfolio management, a much-researched yet uncharted field. Stock market prediction is a challenging and essential endeavour in financial research, owing to the nonlinear, volatile, and stochastic characteristics of financial time series data. Conventional statistical techniques often fall short to encapsulate complex interdependencies, resulting in diminished predictive accuracy. This research proposes an ensemble model that integrates Long Short-Term Memory (LSTM), Convolutional Neural Networks (CNN), and Temporal Convolutional Networks (TCN) for effective stock market prediction. The Nifty 50 index dataset is utilized for the empirical evidences. Wavelet-based denoising is utilised as a preprocessing measure to mitigate the intrinsic noise in stock market data. The model’s efficacy is assessed utilising error metrics, such as Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and R-squared ( R 2). The five-fold cross-validation is utilized to establish the robustness of the models. Furthermore, we ascertain the statistical significance of performance enhancements by parametric t-tests, including normality assessments via the Shapiro-Wilk test. Moreover, current state-of-the-art models advocates in favour of proposed study.
Article
Full-text available
The warehouse automation market has experienced significant growth due to the necessity for quick responses to customer needs. The adoption of Automated Storage and Retrieval System (AS/RS) aims to enhance operational efficiency and expedite order fulfillment, although environmental considerations are frequently overlooked. This study introduces the implementation of energy harvesting using Regenerative Braking System (RBS) on AS/RS to minimize the carbon emission impact. The best configuration of storage assignments and Input/Output (I/O) points is examined to improve travel time, response time, and carbon emission as sustainability indicators. This study employs a discrete-event simulation mimicking the AS/RS and warehouse environment under uncertainty. Simulation-based experiment was performed under 96 different scenarios and the result was assessed through statistical tests revealing the main and interaction effects between factors to performance indicators, including the trade-off between them. The result reveals that the implementation of RBS in AS/RS can result in 13% energy saving on average or equal to additional travel range of 28,800 meters indicating the suitability adoption towards green operation. However, the lowest carbon emission is followed by higher travel time and response time. Thus, metamodel-based optimization was also performed via desirability function analysis. The optimization result reveals that the sustainable AS/RS configuration is obtained with a single-side for I/O point, non-class for storage classification, closest open location with column-order for slot selection, and closest open location with row-order for retrieval selection.
Article
Full-text available
Cyber–physical systems are developed to meet the need to improve process flexibility, optimality, and transparency through Digital Twin (DT). Unfortunately, the application of DT is still limited in practice, and there is no standard way to achieve integration. An Asset Administration Shell (AAS) appears as a promising concept for realizing DT in a standard manner. A literature review shows that most studies only reached static DT and only considered a few specific assets, especially unmovable ones. This study contributes to DT development by proposing 3D-based computer simulation technology as dynamic DT based on the AAS Framework. The proposed concept enables DT to conduct dynamic monitoring, optimization, and direct controlling. A smart warehouse in Taiwan is used to verify the proposed concept. Assets considered include Automated Guided Vehicles (AGVs), Operator, Conveyor, Forklift, and Storage Rack. AAS structure, simulation model built in FlexSim software, and system integration architecture have been constructed. Two advantages of using simulation for DT are demonstrated: multi-objective simulation–optimization for AGV capacity planning and creating dynamic dashboards. Based on the proposed concept, industry 4.0 scenarios can be integrated comprehensively.
Article
Full-text available
Automated Storage and Retrieval System (AS/RS) is driven by multiple motors for loading and unloading the items (z-axis) onto the fork or stacker, then moving the items horizontally (x-axis) and vertically (y-axis) at a time. Thus, it is practical to determine the speed configuration for each movement. To be responsive, it is reasonable to set the speed as fast as possible. However, high speed leads to high energy consumption which is undesirable in the context of green warehousing. Given that the speed changes dynamically, it is important to have an advanced optimization model for balancing both objectives and providing accurate estimation. This study proposed metamodel-based simulation–optimization (MSO) allowing to jointly optimize four speed-related variables namely horizontal speed (x), vertical speed (y), fork or depth speed (z), and acceleration/deceleration under the dynamicity of AS/RS. A case study was given in a warehouse comprising five cranes and ten racks. Using Desirability Function Analysis, the optimal speed configuration is obtained efficiently for minimizing travel time and energy consumption of AS/RS. The result also shows that row-based storage provides better responsiveness and energy efficiency than random-based storage. Further, rack design also indicates a significant impact on the AS/RS speed configuration.
Article
Full-text available
The advanced information technology has enabled supply chain to make centralized optimal decision, allowing to make a global optimal solution. However, dealing with uncertainty is important in inventory management. Besides demand and supply uncertainties, supplier discounts also often arise unexpectedly. Further, suppliers or third-parties typically offer various delivery options in which trade-off occurs between cost and lead time. Thus, this study introduces new problem namely Multi-Echelon Inventory Optimization with Delivery Options and Uncertain Discount (MEIO-DO-UD). As a solution, Neuroevolution Reinforcement Learning (NERL) framework is developed for minimizing total system cost. The environment is modeled via System Dynamics (SD) and actor is presented by integration of Artificial Neural Network and Evolutionary Algorithm (EA), creating an effective decision-making model under dynamic uncertainty. The experimental study has been conducted where two different supply chain networks are given namely serial and divergence. Three EA algorithms are compared namely Differential Evolution (DE), Memetic Algorithm (MA), and Evolution Strategy (ES). Furthermore, NERL is also compared with the EA-optimized classical continuous review model namely (s,Q). The result shows that regardless what EA type is used, the proposed NERL always outperforms EA-optimized (s,Q) model. The more complex the problem, the further improvement can be made i.e. cost reduction up to 58%, followed by the fill rate improvement. The result also shows that NERL can avoid overfitting. Managerial implications are highlighted where NERL provides the more stable inventory level among all supply chain partners and bull-whip effect can be damped.
Article
Full-text available
An Automated Storage and Retrieval System (AS/RS) is one of modern technologies in warehouse operation. Despite many advantages offered by AS/RS such as improving accuracy, efficiency, and safety, AS/RS operation is very complex started from strategical, tactical, to operational level. Reaching optimal combination for all decisions become important. However, due to the dynamic and combinatorial complexity as well as uncertainty in supply – demand, it cannot be solved through the general mathematical optimization. Therefore, this study introduces simulation–optimization (SO) framework for integrated AS/RS planning considering 7 decisions at a time. Furthermore, a comprehensive mathematical model for measuring AS/RS energy consumption is formulated. The proposed framework is implemented in the China’s warehouse company for optimizing multi-objective namely energy consumption and travel time per unit. Non-dominated Sorting Genetic Algorithm II (NSGA-II) is developed as metaheuristics algorithm and discrete-event simulation is modeled based on FlexSim. The results produce non-dominated solutions that are further summarized through clustering algorithm resulting in 4 different clusters with significantly different impacts. This study provides insightful analysis and managerial implications for reaching near-global optimum in AS/RS planning towards green operation.
Conference Paper
Full-text available
An automated storage and retrieval system (AS/RS) is one of the computer-controlled Material Handling Systems (MHSs), playing an important role in modern warehousing operations. With the rapid development of e-commerce, the efficiency and accuracy of warehousing operations are crucial to the competitiveness of enterprises. Among them, the stacker crane, as the core equipment of AS/RS, has a key role in storing and retrieving goods. However, maximizing its efficiency as well as improving storage space remains a challenging issue. In this study, dual stacker AS/RS was developed with parallel processing capabilities. Through the simulation-based experiment via FlexSim, the performance of dual stacker AS/RS was evaluated for the double-deep rack and compared to traditional AS/RS under different order rates, storage assignment methods, and input/output configurations. The experimental results showed that the dual stacker AS/RS had 21−78% higher throughput, and 22−51% lower travel distance, but 63−251% longer response time than single stacker AS/RS since it required longer exploration time. However, the faster the order rate, the response time impact became less obvious. The idle rate of dual stacker was consistently higher than single stacker leading to a more robust system to cope with order uncertainty and potentially lower energy consumption. The better performance of both single stacker and dual stacker AS/RS was achieved with class-based storage and double input/output configuration.
Article
Full-text available
Nutrition and lifestyle factors are closely related to the incidence of Colorectal Cancer (CRC). Indeed, the adoption of a healthy lifestyle can potentially minimize the risk of CRC in the long term. Identifying people at risk of developing CRC will guide them to screening and motivate behavior change. We therefore developed and validated a model to predict CRC risk based on age and Extended Healthy Lifestyle Index (EHLI) components in a Moroccan population. The CCR Nutrition database was used to drive and validate the proposed model. It is a database from a multicenter case-control study of the Moroccan population with 1496 pairs. In a comparative study, thirteen machine learning models, ten simple and three combined, were developed to find the best one. For a better applicability in daily medical practice, a web application was developed. For the training and testing, 5-fold cross-validation was used. The Soft-Voting classifier based on CatBoost, LightGBM and Gradient-Boosting models provided an increase performance with an average accuracy equal to 0.6583 ± 0.054. Soft-Voting CRC risk prediction based on age and EHLI components would identify individuals at risk of colorectal cancer in the Moroccan population and could contribute to improve prevention by encouraging the adoption of a healthy lifestyle.
Article
Full-text available
To relieve human order pickers from unproductive walking through a warehouse, parts-to-picker systems deliver demanded stock keeping units (SKUs) toward picking workstations. In a wide-spread parts-to-picker setup, a crane-operated automated storage and retrieval system (ASRS) delivers bins with demanded SKUs toward an end-of-aisle picking workstation and returns them back into the rack once the picks are completed. We consider the scheduling of the crane that operates subsequent dual commands. Each dual command combines a retrieval request for another SKU bin demanded at the picking workstation with a storage request, where a bin that has already been processed and passed through the bin buffer is returned to its dedicated storage position in the ASRS. This system setup in general and the resulting crane scheduling problem in particular have been an active field of research for more than 30 years. We add the following contributions to this stream of research: We finally prove that the crane scheduling problem is strongly NP-hard. Furthermore, we show that, although only a single vehicle (namely, the crane) is applied, the problem is equivalent to the traditional vehicle routing problem (VRP). This opens the rich arsenal of very efficient VRP solvers, which substantially outperform existing tailor-made algorithms from the literature.
Article
In machine learning, two approaches outperform traditional algorithms: ensemble learning and deep learning. The former refers to methods that integrate multiple base models in the same framework to obtain a stronger model that outperforms them. The success of an ensemble method depends on several factors, including how the baseline models are trained and how they are combined. In the literature, there are common approaches to building an ensemble model successfully applied in several domains. On the other hand, deep learning-based models have improved the predictive accuracy of machine learning across a wide range of domains. Despite the diversity of deep learning architectures and their ability to deal with complex problems and the ability to extract features automatically, the main challenge in deep learning is that it requires a lot of expertise and experience to tune the optimal hyper-parameters, which makes it a tedious and time-consuming task. Numerous recent research efforts have been made to approach ensemble learning to deep learning to overcome this challenge. Most of these efforts focus on simple ensemble methods that have some limitations. Hence, this review paper provides comprehensive reviews of the various strategies for ensemble learning, especially in the case of deep learning. Also, it explains in detail the various features or factors that influence the success of ensemble methods. In addition, it presents and accurately categorized several research efforts that used ensemble learning in a wide range of domains.
Article
Traditional ML based IDS cannot handle high-speed and ever-evolving attacks. Furthermore, these traditional IDS face several common challenges, such as processing large amounts of network profiling data, low accuracy and detection rates, and data imbalance. Therefore, there is an immense demand for a security system for multi-purpose network applications to mitigate intrusion in network profiling data to protect users’ privacy and property across the Internet. This study presents an OE-IDS model using AutoML based on a soft voting method for detecting intrusion in the network environment. The proposed study uses an AutoML framework to select optimal supervised classifiers for developing an optimal ensemble strategy using a soft voting method to maximize accuracy and minimize false alarm rates. Furthermore, our proposed study uses different sampling methods to extend data to solve the problem of data imbalance and minority classes. In addition, our proposed OE-IDS is validated using two benchmark datasets, such as UNSWNB15 and CICIDS2017, to achieve a higher detection rate. Both original and re-sampled data samples are considered to validate the proposed OE-IDS to ensure the generalizability and stability of the proposed OE-IDS model. The performance assessment shows that the proposed OE-IDS model detects intrusions with high accuracy in the network intrusion environment. The detection rate of the OE-IDS model based on reduced features set for UNSWNB15 and CICIDS2017 is 0.98% and 0.973%, respectively. Moreover, our proposed model is compared with conventional ML-based IDS; it is found that our proposed OE-IDS has produced higher accuracy and better detection rate.