Page 1
* Corresponding Author. Email address: [email protected] , Tel: +919042816194
122
Analysis on Criteria based Emotive Music Composition Selection
using a New Trapezoidal Fuzzy DEMATEL - TOPSIS Hybrid
Technique
S. Aseervatham1*, A. Victor Devadoss1
(1) Department of Mathematics, Loyola College, Chennai, India.
Copyright 2015 © S. Aseervatham and A. Victor Devadoss. This is an open access article distributed under the Creative
Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided
the original work is properly cited.
Abstract
The decision data of human judgments with preferences are often vague in many real life cases. Human
judgments with preferences are often unclear and hard to estimate by exact numerical values. So that the
traditional ways of using crisp values are inadequate. The relationship among criteria and choosing and
rating alternatives based on criterion are often expressed in terms of linguistic terms by the experts. These
causal relationships among criterion have been investigated by the Decision making trial and evaluation
laboratory (DEMATEL) with the use of trapezoidal fuzzy numbers. Furthermore, fuzzy TOPSIS method is
used to express the rankings of alternatives based on criterion. In this paper the case study on choosing
emotional music composition is discussed based on musical features by the proposed hybrid technique of
Fuzzy TOPSIS and DEMATEL using trapezoidal fuzzy number.
Keywords: Linguistic Variable, Trapezoidal fuzzy number, DEMATEL, TOPSIS.
1 Introduction
Fuzzy set theory is useful when the situation is full of uncertainty and imprecision due to the human
judgments making the decision very complex and unstructured. Human judgments with preferences are often
unclear and hard to estimate by exact numerical values has created the need for fuzzy logic. Further, Use of
linguistic assessments instead of numerical values is more sensible approach, in which all assessments of
criteria in the problem are evaluated by means of linguistic variables. The Decision making trial and
evaluation laboratory (DEMATEL) method is a powerful method for capturing the causal relationship
between criteria. This method is originated from Geneva research center of the Battelle Memorial Institute.
In recent years, the DEMATEL has become very popular because it can visualize the structure of
complicated causal relationships. Then alternatives ranking based on criterion should be determined which
can assist the decision making. TOPSIS, ELECTRE and VIKOR such techniques are applied for the ranking
Journal of Fuzzy Set Valued Analysis 2015 No. 2 (2015) 122-133
Available online at www.ispacs.com/jfsva
Volume 2015, Issue 2, Year 2015 Article ID jfsva-00239, 12 Pages
doi:10.5899/2015/jfsva-00239
Research Article
Page 2
Journal of Fuzzy Set Valued Analysis 2015 No. 2 (2015) 122-133 123
http://www.ispacs.com/journals/jfsva/2015/jfsva-00239/
International Scientific Publications and Consulting Services
process. Here the fuzzy TOPSIS (technique for order preference by similarity to an ideal solution) is
developed with fuzzy DEMATEL to rank all competing alternatives in terms of their overall performances.
This method was developed by Hwang & Yoon (1981). Two artificial alternatives are defined as positive-
ideal and negative-ideal solution. Maximization of the benefit of criteria is evaluated by the positive ideal
solution whereas negative ideal solution does vice-versa. TOPSIS selects the alternative which is the closest
to the positive ideal solution and farthest from negative ideal solution.
2 Preliminaries and notations
Definition 2.1. Linguistic Variable (LV):
A linguistic variable is a variable which represents word or sentence in a natural language but not a
number.
Definition 2.2. Trapezoidal Fuzzy Number (TzFN):
It is represented with four points as follows: (1) (2) (3) (4), , ,Z z z z z . Its membership function and
graphical representation defined as follows,
Figure 1: Membership and graphical diagram of TzFN
Definition 2.3. Basic Operations in TzFNs:
It is represent Let (1) (2) (3) (4)
1 1 1 1 1, , ,Z z z z z and (1) (2) (3) (4)
2 2 2 2 2, , ,Z z z z z be two hexagonal fuzzy numbers.
Then the addition and subtraction operations are defined by,
[i] (1) (1) (2) (2) (3) (3) (4) (4)
1 2 1 2 1 2 1 2 1 2, , ,Z Z z z z z z z z z
[ii] (1) (1) (2) (2) (3) (3) (4) (4)
1 2 1 2 1 2 1 2 1 2, , ,Z Z z z z z z z z z
Definition 2.3. Linguistic variables and its corresponding TzFNs:
Here some examples of using Trapezoidal fuzzy numbers for their corresponding linguistic variables are
given in the following tables.
Table 1: Linguistic variables for factors relationship
Scale Linguistic Variable for factor relationship Trapezoidal Fuzzy Number
1 Very Low (VL) (0, 0, 0, 0.25)
2 Low (L) (0, 0.05, 0.15, 0.25)
3 Medium Low (ML) (0.15, 0.25, 0.35, 0.45)
4 Medium (M) (0.35, 0.45, 0.55, 0.65)
5 Medium High (MH) (0.55, 0.65, 0.75, 0.85)
6 High (H) (0.75, 0.85, 0.95, 1)
7 Very High (VH) (0.95, 1, 1, 1)
Page 3
Journal of Fuzzy Set Valued Analysis 2015 No. 2 (2015) 122-133 124
http://www.ispacs.com/journals/jfsva/2015/jfsva-00239/
International Scientific Publications and Consulting Services
Table 2: Linguistic variables for alternatives ratings based on factors
Scale Linguistic Variable Trapezoidal Fuzzy Number
1 Very Poor (VP) (0, 0, 0, 2.5)
2 Poor (P) (0, 0.5, 1.5, 2.5)
3 Medium Poor (MP) (1.5, 2.5, 3.5, 4.5)
4 Medium (M) (3.5, 4.5, 5.5, 6.5)
5 Medium Good (MG) (5.5, 6.5, 7.5, 8.5)
6 Good (G) (7.5, 8.5, 9.5, 10)
7 Very Good (VG) (9.5, 10, 10, 10)
3 The Proposed Methodology
In this section, the fuzzy DEMATEL and fuzzy TOPSIS methods are combined to analyze the correlations
among factors and rating the alternatives for the corresponding criterion in an uncertain linguistic
environment. The working procedure of fuzzy DEMATEL for giving causal relationship between one factor
to another and then finding the ranking of alternatives for the factors are briefly explained as follows.
Method 3.1. Fuzzy DEMATEL
The correlation among factors in an uncertain linguistic environment is determined by using fuzzy
DEMATEL method. The set of attributes f1, f2, f3,…, fn are taken as the evaluation criterion. The correlation
among these criterion factors can be characterized by the link between one another. Particularly the link with
the direction represents the influential relationship of any factor fi on fj where the relationships between the
factors are expressed in appropriate linguistic terms by the group of expert’s opinion. These linguistic terms
are often converted by its corresponding fuzzy numbers. Here Trapezoidal fuzzy numbers are utilized to
convert the linguistic variables. Then the aggregation of fuzzy numbers is derived in following steps to create
a dynamical system.
Step 1: Collect the attributes from survey, theoretical studies, etc., which are related to the problem and sort
them as n-factors. Let F = {f1, f2, …, fn} be a finite set of factors and E = {E1, E2, …, En} be the finite
set of experts, where Ek denotes the kth expert. It is assumed that the experts have the identical
importance and their judgments on the intensities among factors are expressed in linguistic variables.
Step 2: Form the initial uncertain direct-relation matrix using linguistic variable terms responded by the kth-
expert as [ ]k k
ijU u where k =1,2,…, K. If there does not exist a correlation between fi and fj, then
denote ' 'k
iju . Particularly, there does not exist a correlation between fi itself. Now, the correlation
among the factors by Ekth expert’s opinion is,
f1 f2 . . . fn
12 11
2 21 2
1 2
. . .
. . .
. . . . . .
. . . . . .
. . . . . .
. . .
k k
n
k k
n
k
k kn
n n
f u u
f u u
U
fu u
and k =1,2,…, K
Page 4
Journal of Fuzzy Set Valued Analysis 2015 No. 2 (2015) 122-133 125
http://www.ispacs.com/journals/jfsva/2015/jfsva-00239/
International Scientific Publications and Consulting Services
Step 3: Consider the trapezoidal fuzzy number TzFN zk = (z1(k),z2(k),z3(k),z4(k)) [where z1(k) ≤ z2(k) ≤ z3(k) ≤ z4(k)]
for the corresponding linguistic term responded by the decision maker Ek, where k = 1,2, …, K. Now
transform the matrix [ ]k k
ijU u into [ ]k k
ijU z ; where (1) (2) (3) (4), , ,k k k k k
ij ij ij ij ijz z z z z and k =1,2,…, K
and ' ' (0,0,0,0)k k
ij iju z .
Step 4: The group uncertain direct-relation fuzzy matrix is denoted by G
and defined as follows: 1 2
...K
ijG U U U g
. This is done by aggregating the individual uncertain direct-relation
matrices. (ie.,) If (1) (2) (3) (4), , ,ij ij ij ijijg g g g g , then (1) (2) (3), ,ij ij ijg g g and
(4)
ijg are calculated by
(1) (1)
1
1 Kk
ij ij
k
g zK
, (2) (2)
1
1 Kk
ij ij
k
g zK
, (3) (3)
1
1 Kk
ij ij
k
g zK
and(4) (4)
1
1 Kk
ij ij
k
g zK
where i,j =
1,2,3,…,n .
Step 5: Then the normalized uncertain group direct-relation matrix ijX x is determined as follows: If
(1) (2) (3) (4), , ,ij ij ij ij ijx x x x x , then (1) (2) (3), ,ij ij ijx x x and
(4)
ijx are calculated by
( )
( )
l
ijl
ij
gx
M where
(4)
11
max 0n
iji n
j
M g
and l = 1,2,3,4.
Step 6: To compute the total-relation uncertain matrix, we should have to establish and analyze this model
by ensuring the convergence of 1 2
lim ...l
lT X X X
, where these crisp value
matrices l
X ’s are taken from the decomposition of the normalized matrix X . This is done by
separating each trapezoidal entry from the matrix X . Then make them as four crisp value matrices.
(i.e.,)
( ) ( )
12 1
( ) ( )
21 2
( ) ( )
1 2
0 . . .
0 . . .
. . 0 . . .
. . . 0 . .
. . . . 0 .
. . . 0
l l
n
l l
n
l
l l
n n
x x
x x
X
x x
l = 1,2,3,4.
Step 7: Then construct the total-relation uncertain matrix asijT t , where (1) (2) (3) (4), , ,ij ij ij ij ijt t t t t and
1
( ) l ll
ijt X I X
l = 1,2,3,4 and i,j = 1,2,3,…,n .
Page 5
Journal of Fuzzy Set Valued Analysis 2015 No. 2 (2015) 122-133 126
http://www.ispacs.com/journals/jfsva/2015/jfsva-00239/
International Scientific Publications and Consulting Services
Step 8: All direct and indirect influence of factor fi on all other factors is denoted by ir and defined as
(1) (2) (3) (4) (1) (2) (3) (4)
1 1 1 1
, , , , , ,ij ij ij ij
n n n n
i i i i i
j j j j
r r r r r t t t t
and ir is called as the degree of
influential impact. And, both direct and indirect impacts on fj is influenced by all other factors is
denoted by jc and defined as (1) (2) (3) (4) (1) (2) (3) (4)
1 1 1 1
, , , , , ,ij ij ij ij
n n n n
j j j j j
i i i i
c c c c c t t t t
and jc
is called as the degree of influenced impact.
Step 9: Aggregate the weight of factors from ir and jc values using following formula. This will be
considered as initial weighting of factors in TOPSIS method to obtain fuzzy rating of alternatives.
The initial weight of factor is denoted by ( )w i and defined as,
( ) ( )
1
( ) ( )
1 1
( ) ( ) ( ) 1,2,..., 4
nl l
i j
jl l
n nl l
i j
i j
r c
w i w i w i l
r c
i = 1,2,3,…,n .
Method 3.2. Fuzzy TOPSIS
Here the TOPSIS method is developed to construct the casual relationship between factors and factor based
rating of alternatives. The algorithm is given as follows.
The survey, theoretical studies and expert opinions have been taken in to an account for deciding the problem
criterion where they were used in DEMATEL. Their corresponding alternative ratings are rated by the group
of experts in terms of appropriate linguistic variables in an uncertain environment.
Step 1: Consider the set of attributes { f1, f2, f3,…, fn } as the factors and { a1, a2, a3,…, am } as the alternatives
based on fi ; i = 1,2,…,n. This is converted into the dynamical system N for the expert-k as,
k k
ijn m
N x
, where k = 1,2,…,K.
Step 2: Convert the appropriate linguistic ratings of the factors based alternatives into corresponding
trapezoidal fuzzy numbers for the kth - expert as, kkijN x , Where
(1) (2) (3) (4), , ,k k k k k k
ij ij ij ij ij ijx za za za za za is TzFN of appropriate linguistic rating of alternative.
Step 3: Obtain the aggregated fuzzy rating ijx of alternative aj under criteria fi evaluated by experts using
trapezoidal fuzzy numbers of each matrices and take the aggregated fuzzy weight ( )w i of factor fi
from DEMATEL model procedure for TOPSIS calculation. (ie.) 1 21
...K
ij ij ij ijx x x xK
and
( )w i .
Step 4: Construct the fuzzy decision matrix D with the entries ijx as, ijD x and the weight of the
criteria is taken as, 1 2 3 4( ) ( ) , ( ) , ( ) , ( ) 1,2,...,w i w i w i w i w i i n .
Page 6
Journal of Fuzzy Set Valued Analysis 2015 No. 2 (2015) 122-133 127
http://www.ispacs.com/journals/jfsva/2015/jfsva-00239/
International Scientific Publications and Consulting Services
Step 5: Transform this D into normalized fuzzy decision matrix which is denoted by R and defined as,
ijn m
R r
, where (1) (2) (3) (4)
* * * *, , ,
ij ij ij ijij ij
i i i i
za za za zar x
M M M M
and * (4)maxi ij
jM za .
Step 6: The weighted normalized fuzzy decision matrix is constructed from R to the different importance
of each criteria as, ijn m
V v
, where ( )ijijv r w i .
Step 7: Determine the fuzzy positive ideal solution (FPIS) and fuzzy negative ideal solution (FNIS) from
V . This can be obtained by, 1 2, ,..., nFPIS v v v
and 1 2, ,..., nFNIS v v v
, where
, , ,iv m m m m and , , ,iv m m m m
where (4)
maxij
jm v and
(1)
minij
jm v , since iv is weighted normalized TzFN’s.
Step 8: Calculate the distance of each effect from FPIS d and FNIS d
. The distance formula is
used to find the distance between two trapezoidal fuzzy numbers (1) (2) (3) (4)
1 1 1 1 1, , ,z z z z z and
(1) (2) (3) (4)
2 2 2 2 2, , ,z z z z z as,
2 2 2 2
(1) (1) (2) (2) (3) (3) (4) (4)
1 2 1 2 1 2 1 2 1 2
1,
4d z z z z z z z z z z
and 1
,n
ijj i
i
d d v v
and 1
,n
ijj i
i
d d v v
for j = 1,2,…,m.
Step 9: Calculate the closeness coefficient (CCj) and rank the order of alternatives according to the
coefficient. This is calculated by 1,2,...,j
j
j j
dCC j m
d d
.
Based on the value of closeness coefficient of each alternative, the ranking order of all alternatives from the
highest closeness to the lowest is determined.
4 Emotional Music Composition: A case study
This section intends to suggest the best composition selection for evoking emotions through music. Based
on the literature reviews and experts’ opinions, the important attributes of musical features for composition
selection are collected. The factors related to Western musical terms are mode (f1), tempo (f2), loudness (f3),
harmonization (f4), rhythmic structure (f5) and timbre quality of vocals and instruments (f6). The relational
mapping is given below.
Page 7
Journal of Fuzzy Set Valued Analysis 2015 No. 2 (2015) 122-133 128
http://www.ispacs.com/journals/jfsva/2015/jfsva-00239/
International Scientific Publications and Consulting Services
Emotional Music
Mode LoudTempo TimbreRhythmHarmony
A1 A2 A3 A4
Figure 2: Emotional Music Features Composition
The relation between each attribute with others for evoking emotions is given as follows with linguistic ratings
of two experts.
Table 3: Experts evaluation on factors
Experts Exp 1 Exp 2
Attribute f1 f2 f3 f4 f5 f6 f1 f2 f3 f4 f5 f6
f1 - MH ML VH L H - M L MH H MH
f2 M - L H VH M H - MH MH M H
f3 VL H - VH M VH L M - M H MH
f4 H L ML - H H H M ML - L M
f5 L M MH M - M M MH L VH - H
f6 H M MH VH M - VH H H MH L -
The group uncertain direct-relation fuzzy matrix is shown below with the aggregation of TzFNs’ for linguistic
variables responded by two expert opinions.
Table 4: Direct-relation fuzzy matrix
Fact
or f1 f2 f3 f4 f5 f6
f1 (0,0,0,0) (0.45,0.55,0.65
,0.75)
(0.075,0.15,0.2
5,0.35)
(0.75,0.825,0.87
5,0.925)
(0.375,0.45,0.55
,0.625)
(0.65,0.75,0.85,
0.925)
f2 (0.55,0.65,0.75
,0.825) (0,0,0,0)
(0.275,0.35,0.4
5,0.55)
(0.65,0.75,0.85,
0.925)
(0.65,0.725,0.77
5,0.825)
(0.55,0.65,0.75,
0.825)
f3 (0,0.025,0.075,
0.25)
(0.55,0.65,0.75
,0.825) (0,0,0,0)
(0.65,0.725,0.77
5,0.825)
(0.55,0.65,0.75,
0.825)
(0.75,0.825,0.87
5,0.925)
f4 (0.75,0.85,0.95
,1)
(0.175,0.25,0.3
5,0.45)
(0.15,0.25,0.35
,0.45) (0,0,0,0)
(0.375,0.45,0.55
,0.625)
(0.55,0.65,0.75,
0.825)
f5 (0.175,0.25,0.3
5,0.45)
(0.45,0.55,0.65
,0.75)
(0.275,0.35,0.4
5,0.55)
(0.65,0.725,0.77
5,0.825) (0,0,0,0)
(0.55,0.65,0.75,
0.825)
f6 (0.85,0.925,0.9
75,1)
(0.55,0.65,0.75
,0.825)
(0.65,0.75,0.85
,0.925)
(0.75,0.825,0.87
5,0.925)
(0.175,0.25,0.35
,0.45) (0,0,0,0)
The normalized uncertain group direct-relation fuzzy matrix is constructed as follows.
Page 8
Journal of Fuzzy Set Valued Analysis 2015 No. 2 (2015) 122-133 129
http://www.ispacs.com/journals/jfsva/2015/jfsva-00239/
International Scientific Publications and Consulting Services
Table 5: Normalized direct-relation fuzzy matrix
F f1 f2 f3 f4 f5 f6
f1 (0,0,0,0) (0.109,0.133,0.
158,0.182)
(0.018,0.04,0.0
61,0.085)
(0.182,0.2,0.21
2,0.224)
(0.091,0.109,0.1
33,0.152)
(0.158,0.182,
0.206,0.224)
f2 (0.133,0.157,
0.182,0.2) (0,0,0,0)
(0.067,0.08,0.1
09,0.133)
(0.158,0.182,0.
206,0.224)
(0.158,0.176,0.1
88,0.2)
(0.133,0.158,
0.182,0.2)
f3 (0,0.006,0.01
8,0.061)
(0.133,0.158,0.
182,0.2) (0,0,0,0)
(0.158,0.176,0.
188,0.2)
(0.133,0.158,0.1
82,0.2)
(0.182,0.2,0.2
12,0.224)
f4 (0.182,0.206,
0.230,0.242)
(0.042,0.061,0.
085,0.109)
(0.036,0.06,0.0
85,0.109) (0,0,0,0)
(0.091,0.109,0.1
33,0.152)
(0.133,0.158,
0.182,0.2)
f5 (0.042,0.061,
0.085,0.109)
(0.109,0.109,0.
133,0.158)
(0.182,0.067,0.
08,0.109)
(0.158,0.176,0.
188,0.2) (0,0,0,0)
(0.133,0.158,
0.182,0.2)
f6 (0.206,0.224,
0.236,0.242)
(0.133,0.158,0.
1820.2)
(0.2,0.158,0.18
,0.206)
(0.182,0.2,0.21
2,0.224)
(0.042,0.061,0.0
85,0.109) (0,0,0,0)
The total-relation uncertain group direct-relation fuzzy matrix is calculated in the following table.
Table 6: Total-relation uncertain group direct-relation fuzzy matrix
F f1 f2 f3 f4 f5 f6
f1 (0.165,0.285,0
.548,1.243)
(0.219,0.352,0.
632,1.338)
(0.110,0.219,0.
459,1.065)
(0.351,0.509,0.
822,1.618)
(0.2,0.32,0.585,1
.238)
(0.306,0.464,0
.787,1.581)
f2 (0.293,0.444,0
.748,1.506)
(0.140,0.265,0.
547,1.284)
(0.162,0.278,0.
534,1.182)
(0.358,0.535,0.
881,1.736)
(0.274,0.402,0.6
76,1.367)
(0.312,0.483,0
.832,1.679)
f3 (0.178,0.307,0
.576,1.323)
(0.254,0.389,0.
662,1.377)
(0.103,0.197,0.
410,1.007)
(0.348,0.508,0.
813,1.627)
(0.25,0.376,0.63
4,1.299)
(0.342,0.496,0
.801,1.607)
f4 (0.297,0.427,0
.697,1.365)
(0.153,0.277,0.
548,1.220)
(0.113,0.219,0.
449,1.025)
(0.174,0.31,0.6
04,1.352)
(0.184,0.298,0.5
53,1.174)
(0.269,0.419,0
.730,1.485)
f5 (0.189,0.319,0
.592,1.285)
(0.211,0.339,0.
606,1.289)
(0.146,0.249,0.
476,1.061)
(0.316,0.467,0.
767,1.539)
(0.11,0.21,0.444,
1.062)
(0.275,0.426,0
.735,1.505)
f6 (0.369,0.519,0
.819,1.588)
(0.274,0.425,0.
735,1.504)
(0.245,0.369,0.
632,1.289)
(0.402,0.581,0.
927,1.799)
(0.198,0.337,0.6
32,1.353)
(0.219,0.379,0
.719,1.577)
The degree of influential impact and the degree of influenced impact of factors are shown with the final
weightings of attributes as follows.
Table 7: Weightings of the factors
i Influence of factor fi on
others j
Impacts of fj influenced by
others Wgt.
Final weight of the
factor
r1 (1.351,2.148,3.832,8.082) c1 (1.492,2.302,3.98,8.308) w(1) (0.1627,0.1633,0.1645,0.1
648)
r2 (1.539,2.408,4.218,8.753) c2 (1.252,2.046,3.73,8.014) w(2) (0.1737,0.173,0.1727,0.17
16)
r3 (1.475,2.271,3.896,8.241) c3 (0.879,1.532,2.96,6.628) w(3) (0.17,0.1679,0.1659,0.166
4)
r4 (1.190,1.951,3.581,7.621) c4 (1.948,2.909,4.81,9.673) w(4) (0.1533,0.1559,0.1592,0.1
602)
r5 (1.248,2.010,3.620,7.743) c5 (1.215,1.943,3.52,7.494) w(5) (0.1566,0.1581,0.16,0.161
4)
r6 (1.707,2.611,4.464,9.111) c6 (1.723,2.667,4.61,9.434) w(6) (0.1836,0.1805,0.1779,0.1
752)
Then construct the decision making matrix for choosing alternative with respect to factors as follows.
Page 9
Journal of Fuzzy Set Valued Analysis 2015 No. 2 (2015) 122-133 130
http://www.ispacs.com/journals/jfsva/2015/jfsva-00239/
International Scientific Publications and Consulting Services
Table 8: Alternative rating of Experts
Experts Exp 1 Exp 2
Attribute a1 a2 a3 a4 a1 a2 a3 a4
f1 G MP G MG M G M P
f2 M P VG MP MG G VG G
f3 MP MG M G G M G MG
f4 VG M VG MP VG VG G G
f5 M G M P MP P MP MG
f6 G M G VG G G M VG
Substituting trapezoidal fuzzy numbers for linguistic variables present in the above table then construct the
normalized fuzzy decision matrix as follows and weight of the criterion given in the left side.
Table 9: Normalized fuzzy relation matrix with factor weights
F Wgt. Final weight of the
factor a1 a2 a3 a4
f1 w(1) (0.1627,0.1633,0.1645
,0.1648)
(0.667,0.788,
0.909,1)
(0.545,0.667,0.
788,0.879)
(0.667,0.79,0.90
9,1)
(0.333,0.424,
0.545,0.667)
f2 w(2) (0.1737,0.173,0.1727,
0.1716)
(0.45,0.55,0.6
5,0.75)
(0.375,0.45,0.5
5,0.625) (0.95,1,1,1)
(0.45,0.55,0.6
5,0.725)
f3 w(3) (0.17,0.1679,0.1659,0.
1664)
(0.486,0.595,
0.703,0.784)
(0.486,0.595,0.
703,0.811)
(0.595,0.7,0.811
,0.892)
(0.703,0.811,
0.919,1)
f4 w(4) (0.1533,0.1559,0.1592
,0.1602) (0.95,1,1,1)
(0.65,0.725,0.7
75,0.825)
(0.85,0.93,0.975
,1)
(0.45,0.55,0.6
5,0.725)
f5 w(5) (0.1566,0.1581,0.16,0.
1614)
(0.4,0.56,0.72
,0.88)
(0.6,0.72,0.88,
1)
(0.4,0.56,0.72,0.
88)
(0.44,0.56,0.7
2,0.88)
f6 w(6) (0.1836,0.1805,0.1779
,0.1752)
(0.75,0.85,0.9
5,1)
(0.55,0.65,0.75
,0.825)
(0.55,0.65,0.75,
0.825) (0.95,1,1,1)
The weighted normalized fuzzy decision matrix is formulated in the below table.
Table 10: Weighted normalized fuzzy decision matrix
F a1 a2 a3 a4
f1 (0.11,0.13,0.15,0.16) (0.09,0.11,0.13,0.14) (0.11,0.13,0.15,0.16) (0.05,0.07,0.09,0.11)
f2 (0.08,0.10,0.11,0.13) (0.07,0.08,0.09,0.11) (0.17,0.17,0.17,0.17) (0.08,0.10,0.11,0.12)
f3 (0.08,0.10,0.12,0.13) (0.08,0.10,0.12,0.13) (0.10,0.12,0.13,0.15) (0.12,0.14,0.15,0.17)
f4 (0.15,0.16,0.16,0.16) (0.10,0.11,0.12,0.13) (0.13,0.14,0.16,0.16) (0.07,0.09,0.10,0.12)
f5 (0.06,0.09,0.12,0.14) (0.09,0.11,0.14,0.16) (0.06,0.09,0.12,0.14) (0.07,0.09,0.12,0.14)
f6 (0.14,0.15,0.17,0.18) (0.10,0.12,0.13,0.14) (0.10,0.12,0.13,0.14) (0.17,0.18,0.18,0.18)
The fuzzy positive-ideal solution (FPIS) and fuzzy negative-ideal solution (FNIS) are given as follows.
FPIS = ( [0.16,0.16,0.16,0.16], [0.17,0.17,0.17,0.17], [0.17,0.17,0.17,0.17], [0.16,0.16,0.16,0.16],
[0.16,0.16,0.16,0.16], [0.18,0.18,0.18,0.18] )
FNIS = ( [0.05,0.05,0.05,0.05], [0.07,0.07,0.07,0.07], [0.08,0.08,0.08,0.08], [0.07,0.07,0.07,0.07],
[0.06,0.06,0.06,0.06], [0.1,0.1,0.1,0.1] )
The distance of each alternative from FPIS and FNIS with respect to each factors are shown in the following
table.
Page 10
Journal of Fuzzy Set Valued Analysis 2015 No. 2 (2015) 122-133 131
http://www.ispacs.com/journals/jfsva/2015/jfsva-00239/
International Scientific Publications and Consulting Services
Table 11: Distances of alternatives from FPIS and FNIS
S Distance from FPIS Distance from FNIS
F a1 a2 a3 a4 a1 a2 a3 a4
f1 0.0307 0.04702 0.0307 0.082 0.0904 0.0713 0.0904 0.0373
f2 0.0691 0.08522 0.0033 0.0697 0.0385 0.0229 0.1006 0.0369
f3 0.0651 0.06447 0.0479 0.0317 0.0327 0.0345 0.0488 0.066
f4 0.0075 0.04462 0.017 0.0688 0.0854 0.0486 0.0783 0.0296
f5 0.065 0.0414 0.065 0.0627 0.0515 0.0723 0.0515 0.0517
f6 0.0257 0.0583 0.0583 0.0038 0.0606 0.0292 0.0292 0.0771
Then the d+, d- and the closeness coefficient are obtained for rank the order of alternatives as follows.
Table 12: Ranking of alternatives
Alternative d+ d- CCj Rank
a1 0.2631 0.3592 0.5773 2
a2 0.341 0.279 0.4497 4
a3 0.222 0.3989 0.6423 1
a4 0.3187 0.299 0.4837 3
The automatic compositional techniques of music can be developed with these ratings for better emotional
outcomes. The third alternative combination of musical features with necessary importance has a better
ability to promote emotions rather than others.
5 Conclusion
In this paper the causal relationships among criterion and its importance through weightings have been
discussed. The Modified DEMATEL technique is utilized for making causal relationship among factors with
the use of expert’s opinion. Then the combination of fuzzy TOPSIS technique with DEMATEL is utilized
as more appropriate tool for evaluating alternatives ranking based on factors. This method is useful when
the relationship among factors and choosing the alternatives relations with factors are expressed in an
uncertain linguistic environment. Moreover the case study on emotive music compositional techniques can
be observed for better compositional selection. The result can provide a suggestion to the music technicians
to decide the suitable ratings of musical features in compositions.
Acknowledgements
This research work is supported by UGC scheme MANF. Award Letter No.: F1-17.1/2011-12/MANF-
CHR-TAM-7467/(SA-III/Website).
References
[1] Abhinav Bansal, Trapezoidal Fuzzy Numbers (a,b,c,d): Arithmetic Behavior, International Journal of
Physical and Mathematical Sciences, (2011) 39-44.
[2] Akbar Alam-Tabriz, Neda Rajabani, Mojtaba Farrokh, An Integrated Fuzzy DEMATEL-ANP-TOPSIS
Methodology for Supplier Selection Problem, Global Journal of Management Studies and Researches, 1
(2) (2014) 85-99.
Page 11
Journal of Fuzzy Set Valued Analysis 2015 No. 2 (2015) 122-133 132
http://www.ispacs.com/journals/jfsva/2015/jfsva-00239/
International Scientific Publications and Consulting Services
[3] D. R. Babak, T. E. Saputro, Supplier selection using integrated fuzzy TOPSIS and MCGP: a case study,
Procedia-Social and Behavioral Sciences, 116 (2014) 3957-3970.
http://dx.doi.org/10.1016/j.sbspro.2014.01.874
[4] J. K. Chen, I. S. Chen, Using a novel conjunctive MCDM approach based on DEMATEL, fuzzy ANP, and
TOPSIS as an innovation support system for Taiwanese higher education, Expert Systems with
Applications, 37 (3) (2010) 1981-1990.
http://dx.doi.org/10.1016/j.eswa.2009.06.079
[5] E. Fontela, A. Gabus, The DEMATEL Observer, DEMATEL 1976 Report, Battelle Geneva Research
Centre,Geneva, (1976).
[6] A. Gabus, E. Fontela, Perceptions of the world problematique: communication procedure, communicating
with those bearing collective responsibility (DEMATEL Report no.1), Battelle Geneva Research Centre,
Geneva, (1973).
[7] A. Kaufman, M. M. Gupta, Introduction to fuzzy arithmetic: theory and applications, Van Nostrand
Reinhold, New York, (1985).
[8] Kwang H. Lee, First Course on Fuzzy Theory and Applications, Advances in Soft Computing, Springer,
(2006) 145-146.
[9] C. J. Lin, W. W. Wu, A Fuzzy extension of the DEMATEL method for Group Decision Making, European
Journal of Operational Research, 156 (2004) 445-455.
[10] C. J. Lin, W. W. Wu, A Causal Analytical Method for Decision-Making under Fuzzy Environment, Expert
Systems with Applications, 34 (1) (2008) 205-213.
http://dx.doi.org/10.1016/j.eswa.2006.08.012
[11] Mahdi Mahmoodi, S. F. Gelayol, A New Fuzzy DEMATEL-TODIM Hybrid Method for evaluation
criteria of Knowledge management in supply chain, International Journal of Managing Value and Supply
Chains, 5 (2) (2014) 29-42.
http://dx.doi.org/10.5121/ijmvsc.2014.5204
[12] Marcel Zentner, Didier Grandjean, Klaus R. Scherer, Emotions Evoked by the Sound of Music:
Characterization, Classification and Measurement, Emotion, 8 (4) (2008) 494-521.
http://dx.doi.org/10.1037/1528-3542.8.4.494
[13] S. K. Patil, R. Kant, A hybrid approach based on fuzzy DEMATEL and FMCDM to predict success of
knowledge management adoption in supply chain, Applied Soft Computing, 18 (2014) 126-135.
http://dx.doi.org/10.1016/j.asoc.2014.01.027
[14] J. D. Richard, K. R. Scherer, H. Hill Goldsmith, Handbook of Affective Sciences, Series in Affective
Sciences, Oxford University Press, (2003).
[15] Sylvain Le Groux, Paul F. M. J. Verschure, Subjective Emotional Responses to Musical Structure,
Expression and Timbre Features: A Synthetic Approach, 9th ISCMMR, (2012) 160-176.
Page 12
Journal of Fuzzy Set Valued Analysis 2015 No. 2 (2015) 122-133 133
http://www.ispacs.com/journals/jfsva/2015/jfsva-00239/
International Scientific Publications and Consulting Services
[16] G. H. Tzeng, W. H. Chen, R. C. Yu, M. L. Shih, Fuzzy decision maps: a generalization of the DEMATEL
methods, Soft Computing, 14 (11) (2010) 1141-1150.
http://dx.doi.org/10.1007/s00500-009-0507-0
[17] A. Victor Devadoss, A. Felix, A Fuzzy DEMATEL approach to study cause and effect relationship of
youth violence, International Journal of Computing Algorithm, 02 (2013) 363-372.
[18] G. W. Wei, Uncertain Linguistic hybrid geometric mean operator and its application to group decision
making under uncertain linguistic environment, International Journal of Uncertainty, Fuzziness and
Knowledge-Based Systems, 17 (02) (2009) 251-267.
http://dx.doi.org/10.1142/S021848850900584X
[19] L. A. Zadeh, The concept of a linguistic variable and its application to approximate reasoning (Part II),
Information Sciences, 8 (1975) 301-357.
http://dx.doi.org/10.1016/0020-0255(75)90046-8
[20] L. A. Zadeh, Fuzzy sets, Information Control, 8 (3) (1965) 338-353.
http://dx.doi.org/10.1016/S0019-9958(65)90241-X
[21] Xu. Zeshui, Uncertain linguistic aggregation operators based approach to Multiple Attribute Group
Decision Making under uncertain linguistic environment, Information Sciences, 168 (1–4) (2004) 171-
184.
http://dx.doi.org/10.1016/j.ins.2004.02.003