You are on page 1of 13

Scientific Research and Essays Vol. 6(25), pp.

5374-5386, 30 October, 2011


Available online at http://www.academicjournals.org/SRE
ISSN 1992-2248 ©2011 Academic Journals

Full Length Research Paper

A new fuzzy mathematical model for multi criteria


decision making: An application of fuzzy mathematical
model in a SWOT analysis
Dragan Pamučar1*, Goran Ćirović2, Dragoljub Sekulović3 and Aleksandar Ilić4
1
Management Department, University of Defence, Military Academy, Generala Pavla Jurisica Sturma 33, 11 000,
Belgrade, Serbia.
2
Faculty of Technical Science, University of Novi Sad, Novi Sad, Serbia.
3
Architectural and Civil Engineering Faculty, Banja Luka, Bosnia and Herzegovina.
4
Department of Material Resources, Ministry of Defence, Belgrade, Serbia.
Accepted 20 September, 2011

Analysis of strengths, weaknesses, opportunities and threats (SWOT) is a method to formulate the
strategy. Although the SWOT analysis successfully provides the key factors of the problem, it has some
drawbacks in selecting appropriate strategy for the evaluation and final decision steps. During recent
years, some multiple criteria decision making (MCDM) remove some of these deficiencies, but the
nature of these decision usually is very complex and using crisp datais not suitable. In this paper,
linguistic variable represented with fuzzy numbers are used to assess the ratings and weights. This
paper presents a new fuzzy mathematical model for evaluating the proposed alternatives. Fuzzy
linguistic descriptors were used for describing the criteria. In this way, fuzzy logic enables the
exploitation of tolerance that exists in imprecision, uncertainty and partial truth of the acquired
research results. The paper presents a model for designing the organisational structure of transport
support authorities in the Serbian Armed Forces. Various organisational structure options are proposed
in application of the given model, taking into account the fact that transport authorities should be
designed and dimensioned so as to achieve the rudimentary goals and tasks for fulfilment of which
they were established. Each task set before the transport authorities requires reliable and top-quality
performance in all environmental conditions. Since most of the acquired data is characterized by a high
degree of imprecision, subjectivity and uncertainty, fuzzy logic was used for displaying these.

Key words: Strengths, weaknesses, opportunities and threats analysis, organizational structure design, fuzzy
logic, multi-criteria decision making.

INTRODUCTION

Strategic management is the process by which managers current reforms of the defence system of the Republic of
formulate and implement strategies that enable Serbia, the Serbian Armed Forces are gradually leaving
organisations to achieve strategic objectives. Strategic the outdated principles of organisation and operation of
management in the broadest sense can be defined as the logistical support and embracing a modern logistic
conscious direction of the business system consistent concept. In this sense, properly structured system of
with its relevant environment. In accordance with the organisational management solutions to a large extent
contribute to the functional efficiency of these systems,
providing corresponding cost savings. In the process of
reorganisation of the Serbian Armed Forces, there are
*Corresponding author. E-mail: dpamucar@gmail.com. Tel: still some organisational forms proven inefficient in the
+38164 23 77 908, +38111 251 92 89. Fax: +38111 300 51 90. past and in particular unsuited for the future. Inefficient
Pamucar et al. 5375

and uneconomic operation demands adequate solutions. or in other words, whose optimization includes just one
The process of transport authorities administrative criterion. The main goal of multiple criteria methods is
support reorganisation requires a design team, time and determination of the priorities among specific variants
financial resources. This paper presents a model of or criteria in situations where a number of decision
designing organisational scheme of administrative makers are taking part, and where there are a number
structure of the Serbian Armed Forces. In complex of decision making criteria and multiple time periods.
organisational systems operating in a changing There are many ways to classify the methods of multiple
environment such as the armed forces, a large number of criteria decision making. However, the classification of
issues whose solutions are accompanied with different these methods in accordance with those ways is often
types of imprecision and uncertainty exist at all levels of avoided because the models in accordance to which
management. They can be described using linguistic these methods operate are quite similar. Their enlisting is
expressions and modelled by uncertain numbers. In the favoured instead. The most frequently used methods are:
classical approach, uncertainty modelling is based on the
application of probability theory, where uncertainty is i) Points method,
modelled in random sizes with different distribution. This ii) ELECTRE method,
manner of uncertainty treatment has certain limitations. iii) PROMETHEE method,
One is that the probability calculation of any random size iv) TOPSIS method,
requires a large quantity of the data recorded, and also v) AHP method (analytic of hierarchical processes),
the fact that the combination of different uncertainties vi) Fuzzy multicriteria decision making,
leads to a complex probability distribution, which requires vii) ANFIS models,
complex mathematical expressions and increases the viii) Models based on neuron networks,
complexity and volume of calculations. ix) Models based on fuzzification of the already existing
Development of new mathematical areas facilitated multiple criteria decision making methods.
describing imprecision and uncertainty in a more realistic
way. In other words, soft computing methods are The choice of evaluation methods depends on:
alternatives to the classical approach in uncertainty
treatment. One of the methods of soft computing is the i) Character, that is importance of the decision to be
fuzzy theory. Designing organisations, in particular the made on the basis of evaluation,
stage of organisational model development is a highly ii) The place where the decision is to be made,
complex process in which optimal solutions should be iii) Kind of the decision because of which evaluation is
offered. SWOT analysis is a useful "tool" for planning being made,
design strategies in which organisational internal iv) The ways of financing implementation of a new
strengths and weaknesses are weighed against the solution (finance construction).
external opportunities and threats. The organisation
should mobilise its forces, overcome weaknesses, exploit In case of a responsible decision making, special
opportunities and resist threats. Associating opportunities methods for multiple criteria analysis and indirect
and risks on one hand and strengths and weaknesses on optimization are commonly used. The methods of soft
the other, the organisation aims at providing a conceptual optimization are used in the first place to describe
framework for the selection of strategic options of the multiple objectives, with some of them being maximized
organisational model. However, the result of SWOT and others minimized. Then, conflicts of priorities
analysis is often merely a listing or an incomplete between the different participants in decision making
qualitative examination of the internal and external process are modelled, and at the end, a solution that is
factors. For this reason, SWOT analysis cannot the closest to the ideal point, the best compromise, etc. is
comprehensively appraise the strategic-making process. searched for. Most often, decision making means
Applying fuzzy multi-criteria decision making (FMDM) in evaluation of sets of possible solutions or alternatives.
the SWOT analysis eliminates the weakness in the When evaluation is made in accordance with one
measurement and evaluation steps of the SWOT criterion, the solution (alternative) which brings the target
analysis. function to an extreme is determined and the procedure
is denoted as single criterion optimization or simply
optimization. The situation is getting more complex with
MULTICRITERIA MATHEMATICAL METHODS two or more criteria, when instead of the optimal solution
the best possible solution needs to be provided. Any
Multiple criteria decision making refers to decision grouping of the criteria into one criterion (total
making in a situation with a number of possibly scalarisation) and reducing the task to a single criterion
conflicting criteria. This is the greatest advantage of generates deficiencies limiting the range of the analysis
multiple criteria decision making, since in practice and the accuracy of the results. Instead of total
there are a few problems influenced by one factor only, scalarisation, a multiple criteria problem is usually dealt
5376 Sci. Res. Essays

with in its original form, while the level of target function relatively recent decision making climate in the Armed
scalarisation is controlled by the decision maker or the Forces of Serbia. This climate has brought new
analyst. In other words, the decision maker often terminology and in a certain way a new application of
evaluates criteria against each other, or attaches the mathematics and optimization theory in the realistic
ranks of importance directly, thus shaping the target conditions of planning and decision making. In the Armed
function in accordance with his own preferences. Forces of Serbia today, standard and fuzzy versions of
Regardless whether it is done directly or indirectly, in the multiple criteria methods are used in parallel, but new
given phase of the decision making process, a matrix of models of multiple criteria decision making based on
alternatives and criteria is created. This matrix is fuzzy logic modelling and neuro-fuzzy modelling are
analysed and processed so that weighing grades for the being developed (Pamučar and Božanić, 2010; Pamučar,
alternatives, based on which they can be ranked may be 2009, 2010; Pamučar et al., 2011). By modelling of fuzzy
established. logic systems and training of the neuro-fuzzy model, very
The weighing grades and ranks may be used powerful tools for decision making, based on experiential
individually or integrally, depending on the kind of a knowledge of the officers of the Armed Forces of Serbia
problem. If only the best alternative is searched for, only are created. Officers experiential knowledge is
ranking will mostly suffice. With respect to allocation transformed to automatic management (decision making)
problems, grades can signify the proportions of allocation strategy through modelling of such systems. Fuzzy sets
resources in accordance with the ranks of the enable quantification of linguistic; that is qualitative and
alternatives. The third possibility is that identification of inaccurate information. Therefore, fuzzy reasoning is
several best alternatives and the degree to which they increasingly used in the Armed Forces of Serbia as a
participate in the total resource allocation are searched technique by which heuristic rules are translated into
for. Multiple criteria and hierarchical structures are part of automatic management; that is decision making, strategy.
a complex environment facing analysts when they deal Application of the fuzzy theory and fuzzy sets in multi-
with problems of decision making and creation of quality criteria decision making has come into use since decision
methods for their resolution in practice. The presence of makers often act in the conditions of uncertainty or so
different criteria, some of which have to be maximised called partial truths.
and some minimized, means that decisions are made in Fuzzification of standard multiple criteria methods was
the conflicting conditions and that instruments more done in such a way that triangular fuzzy numbers were
flexible than a rigid mathematical technique related to used for determination of fuzzy weighing values for
genuine optimization have to be applied. Special analysis criteria and alternatives, due to their simplicity in
and solution techniques have been developed for such comparison to trapezoid ones, while altogether, fuzzy
tasks. Among the most important are PROMETHEE arithmetic was, of course, used (Pamučar, 2010). A new
(Brans et al., 1986), ELECTRE (Roy, 1968), AHP (Saaty, fuzzy mathematical method presented in this paper has
1980), TOPSIS (Hwang and Yoon, 1981) and CP been developed for research in the Armed Forces of
(Zeleny, 1982). These techniques fall into the category of Serbia. The developed method is based on evaluation of
soft optimization, since they use heuristic parameters, alternatives by application of fuzzy linguistic descriptors.
distance measurements, value scales, etc. in addition to It makes the procedure of alternatives ranking much
mathematical structures and instruments. Kujacić and easier in situations where a great number of
Bojović (2003) proposed the model for selecting the characteristics and parameters for decision making are
organisational structure using the fuzzy multi-criteria present. If there are more levels of criterion importance in
analysis. The developed fuzzy multi-criteria methodology the problem of alternative ranking, the described
takes into consideration the uncertainty and imprecision procedure is conducted at each observed level. At each
of the input data. Each method earlier mentioned has level, the coefficients of criterion- sub criterion importance
several versions (for example, Promethee 1 and 2). They having an impact on the course of ranking is defined, with
all have advantages and disadvantages and their the level of ranking being not necessarily the same for all
application in different areas indicates that those methods the criteria. The final ranking of the alternatives is made
are getting increasingly indispensible in backing at ranking zero level. Characteristics of some multiple
responsible decision making. criteria methods has been presented in the first part of
Recently, standard and fuzzy versions of methods are the paper. In the continuation, a new model for the
used in parallel so that the complex of human selection of optimal variants of organisation based on
subjectivity, expert knowledge and inclination to use fuzzy logic has been developed starting from the relevant
verbal instead of numerical grades may be included theory approach. Fuzzy mathematical model (FMM) is
(Triantaphyllou and Lin, 1996; Bender and Simonovic, applied in the SWOT analysis (FM'WOT model) to
2000; Deng, 1999; Srđevic et al., 2002; Pamučar, 2009). optimize the existing organisational structure of the
The methods used for modelling subjectivism, governing bodies of transport support. The choice of
approximate reasoning and expert knowledge of decision organisational models is made using Fuzzy multi-criterion
makers, as well as various forms of heuristics are part of and standard techniques of multi-criterion decision
Pamucar et al. 5377

A  x,  A  x   x  X , 0   A  x   1 ,

Where A  x is a membership function which shows to


what extent x  X meets the criterions for membership
in a set A . For the membership function
0   A  x   1 , for every x  A ,that is  A : X  0,1 .
According to the fuzzy theory, the choice of membership
functions that is, the form of the function and confidence
intervals width are usually made based on subjective
estimates or experience. The most commonly used are
trapezoidal and triangular fuzzy numbers. Triangular
fuzzy numbers with membership functions shown in
Figure 1 are used in this paper. Triangular fuzzy numbers
Figure 1. Triangular fuzzy number. are usually given in the form A  (a1 , a2 , a3 ) , where a2 is
the value where the membership function of the fuzzy
number is 1.0, a1 is the left distribution of the confidence
interval and a3 the right distribution of the confidence
interval of the fuzzy number A . Fuzzy number A
membership function is defined as:

 0, x  a1
 x  a1
 , a1  x  a2
a2  a1
 A  x    a3  x
 , a2  x  a3
 a3  a2
 0, x  a3

For defuzzification and mapping of the fuzzy number,


Figure 2. Defuzzification.
A  (a1 , a2 , a3 ) value into a real numbers, numerous
methods are used (Figure 2). Two methods have been
making. used in this paper:
The aforementioned model is shown in the following
section of the paper. i) The centre of gravity:
defuzzy A=  a3  a1    a2  a1 31  a1
FM'WOT MODEL ii) The total integral value:
defuzzy A=  a3  a2  1    a1 21
In the process of designing the organisational structure,
certain decisions have to be made. Subjective evaluation (with  ,   0,1 being an optimism index).
of certain parameters differ from one decision-maker to
another, it is worth pointing out. Quite a convenient
approach in quantifying these parameters is fuzzy set Basic model
theory.
It is characteristic for all multi-criteria problems that there
are multiple criteria in decision-making and various
Fuzzy sets alternatives to select the most appropriate action.
Different organisations evaluate variant solutions and
Fuzzy sets theory defines fuzzy set A as a set of ordered optimal variants using the FMM model described in the
pairs (Zadeh, 1965): continuation. SWOT analysis is used for assessing what
5378 Sci. Res. Essays

to eliminate, partially keep or keep to define design variables are represented by triangular fuzzy numbers
strategies for designing organisational structure. Using A  (a1 , a2 , a3 ) .
analysis of strengths, weaknesses, opportunities and
threats for the given organisation, optimisation model of
functioning is proposed. Fuzzy mathematical model
includes the following steps: Step 3

Normalisation of the optimisation criterion: For the


Step 1 value  
f ki i  1, A, k  1, K to be comparable, it is
Identify SWOT sub-factors and determinate the necessary to normalise them. If the optimisation criteria
alternative strategies according to the SWOT sub-
factors: Determine the importance degrees of the SWOT
are given as linguistic values f ki i  1, A, k  1, K  ,
factors; if the model used for evaluation of alternatives of
the already proposed organisational structure ki ki
f  f , 
f
ki
 , normalisation is performed as follows:
alternatives, this step is omitted. The following steps will
represent a general case where K is considered from i) For the benefit criterion k  k  K  normalisation is
the point of different optimality criteria in terms of which
the best alternative for a finite set of alternatives is performed as follows:
determined A  a1 , a2 ,, an  ,  n  2  . Optimum f
criterions are formally given as K  1,, k ,, K  ,  f ki n  ki
(1)
f k max
where K is the overall number of the criteria considered.
Multiple-attribute problem in the decision-making is
Where f k max is max value of the fuzzy number
represented by the matrix F dimension K  A .
f (k  1,, K ) , for 
ki f
ki
 fki   0
A1 ... An  m  An
ii) For the cost criterion k  k  K  normalisation is
K1  f11  f1n  m  f n  performed as follows:
     f  f min
 fik n  1  ki k (2)
F  K k  f k1  f kn m  f kn  f k max
 
     Where f k
min
is minimum value of the fuzzy number

K K  f K 1  f Kn m  f Kn  f (k  1,, K ) , for 
ki f
ki
 f ki   0 .

The normalised value of the criterion k (k  K ) for


 
Where f ki i  1, A, k  1, K is the linguistic or numerical
a (a  A) alternative is described by fuzzy number:
value of the optimum criterion k  K for alternatives
a  a  A . If at least one criterion is described by
 f    f
ik
n
ik n  ,  f
ik
 (3)
linguistic expression in the description of the optimum
criterion, step 2 is taken. If the optimality criteria are described in numerical values
 
f ki i  1, A, k  1, K , normalisation is performed as
Step 2 follows:

Defining the set of linguistic descriptors: Criterion K


f ki
values are described by a set of linguistic descriptors
f ki  ,  f ki  1
S  l1 , l2 ,, li  , i  H  0,, T  , where T is the

K (4)
f
k 1 ki
k 1
overall number of linguistic descriptors. Linguistic
Pamucar et al. 5379

Step 4 members (e  1, 2,..., n) of the group G are considered


equal in the decision making and that all the evaluation of
Evaluation criteria: K  1,, k ,, K  is a set of the optimality criterion for the given hierarchy have been
optimality criteria, where K is the overall number of the performed, there are two ways for prioritising the
considered criteria. Every criterion can be disaggregated alternatives relative to the goal. One is to aggregate all
the obtained priority criterion vectors for every decision-
into sub-criteria. If k j is the overall number of sub-criteria maker using the following equation:
th
in j criterion, the overall number of criterions can be
given as: n
wiG    e wi (e)
n e 1 (7)
K  kj (5)
j 1
Where wi (e) is the weight value which is the n th
Every criterion has to be divided into sub-criteria. In that member of the group G , (e  1, 2,..., n ) for the
case k j of the criterion equals 1. This is important for alternative Ai , e is the weight value (significance) of
understanding the aggregation process of judgments the n th member of the group and wiG is the ultimate
made at two consecutive hierarchical levels, where
criteria and sub-criteria are located. Here, criteria and priority of the alternative Ai . Individual weights of the  e
sub-criteria are aggregated by shifting criteria at the sub- group members have first been additively normalised.
criteria level. After that shift, the whole criteria level does The drawback of the presented procedure is that it is not
not exist anymore. Relative importance of the optimality applicable in case of group synthesis with incomplete
criterion k  k  K  ,Wk  k  1,, K  is different. The information, as there are no composite vectors for certain
members of the group.
value representing the importance of the optimality
Another way is to immediately aggregate all the
criteria is determined by forming a matrix W   w
 
kij  . individual preference assessments on all hierarchical
K K
levels.
Elements of the matrix are linguistic descriptors and
numerical values used to describe the importance of the 1

 j w    n   n  
criterion k  k  K  to criterion k   k   K  . Having
1n 1n 1n
 n   n
wi    j aij   
     
k

 w j
  a    a  
 j 1 j wk j  j 1   i1   j 1   
kij K j ij j ij
 j 1 
established W matrix, normalisation of the weight
coefficients is performed:
K
 ò 0,1

 j w K w k  1, wk (8)
 
w
k j
, w  ò 0,1
  1, w (6)
j 1

 
kij k k
 w
K
j 1
j 1 j k j
Where  j represents the preference of the decision-
Where  j represents the preference of decision maker to maker to attribute . i
attribute i . N case of group synthesis with incomplete information,
The process of designing the organisational structure is microaggregation of the  i, j  position at the given
most often in the hands of more than one expert that is matrix is done by geometric mean of the assessments of
decision-maker. In this case, optimality criteria evaluation
those group members who expressed preference Ei
of all the group members should first be obtained to pass
on to the necessary synthesis and then to step 5. In other compared to the element E j . The requirement in this
cases, step 6 is taken.
case is for at least one decision maker to declare on the
value of aij . Modifying the previous expression:
Step 5
1
  n   n   
G
 j w
1n 1M
 n
1M
 n 
wG i    j aij  l        j aij      j aij   
k
Evaluating the criteria in case of group evaluation: In 
 w j

 G
kij
 w   i 1   j 1   
K
 lL  j 1 j k  j 1
group decision-making, there is group synthesis with K
j

 ò  0,1 (9)
complete and incomplete information. In case of group w
  1, w
k
j 1
k
synthesis with complete information, provided that all the
5380 Sci. Res. Essays

Where l is a set of group members who have evaluated (Liou and Wang, 1992) is considered to be a good choice
the pair of elements  Ei , E j  and M is the number of
for performing the task efficiently and, therefore, has
been proposed within this methodology. For the given
such members.
triangular fuzzy number A  (a1 , a2 , a3 ) ,
the total
integral value is defined as:
Step 6

Evaluating alternatives: Having determined the values IT (A)= a3  a2  1    a1 21,  0,1 (13)
of the weight coefficients for all the assessed criterions, a
matrix F  cij  is formed where the matrix elements In Equation 13,  represents an optimism index which
F W
expresses the decision maker’s attitude towards risk. A
cij are obtained using the following expression: larger value of  indicates a higher degree of optimism.
In practical applications, values 0, 0.5 and 1 are used
respectively to represent the pessimistic, moderate and
f optimistic views of the decision maker. For given fuzzy
cij  ki 
w (10)  
 i1 fki numbers A and B , it is said that if IT (A)<IT (B) ,
j kij

then A B ; if IT (A)  IT (B) then A B ; and if


f
 
Where ki is the value of the criterion function for the IT (A)  IT (B) , then A  B . The final ranking of
i (i  1, A) k k  K  
w kij alternatives means to adopt certain level λ of optimism of
alternative and criterion , and
is the value of the weight coefficient for the criterion the decision-maker, then to apply Equation 13 on fuzzy
numbers of Equation 12 and finally to rank alternatives
k k  K  
regarding obtained values for IT ( Fi ), i  1,..., N .
.
Additive synthesis has been assumed here and the
final alternative performance weights with respect to The best alternative from the set is represented as

 
overall goal are calculated by the summation of elements
in the rows of the performance matrix F  cij  as: fVi  max fVi , i  1,.., A . The presented
F W
method significantly simplifies the procedure of ranking
K the alternatives in situations where there are a number of
ci   cij w

j (11) characteristics and parameters of decision making. On
j 1 the basis of the proposed algorithm, a system for
decision support in the programming language C was
 for every assessed developed.
Value of the criterion functions Vi
alternative is obtained from the F matrix using the
expression: DESIGNING THE MANAGEMENT ORGANISATIONAL
STRUCTURE OF THE TRAFFIC SUPPORT USING
FM'WOT MODEL
K
Vi  cj , (k  K ) (12)
Designing a military management system has a large
influence on the creation, adaptation, existence and
j 1 quality of the system operation. No organisational system
within the military can operate independently of its
To finally rank the alternatives, the prioritisation of management subsystem responsible for issuing
 is a commands for the desired “behaviour” of the system,
aggregated assessments is required. Since each V i while the actual behaviour can deviate from the desired.
triangular fuzzy number, it is necessary to apply the To meet the requirements of a large number of traffic and
method of ranking triangular fuzzy numbers. There are transport services users and at the same time efficiently
several methods that can do this such as the centre of and primarily servicing the requirements of the military,
gravity method, the dominance measure method, the  - an organisational structure that will successfully
cut with interval synthesis method and the total integral implement all these must exist. As part of the General
value method. The last one – total integral value method Staff and the Logistics Department, traffic management is
Pamucar et al. 5381

the highest professional traffic authority of the Serbian using the logistic approach and functional principle of
Armed Forces. Traffic management is responsible and organisation of the prescribed authority, as a specific
accountable for the conditions, development, manifestation of the internal division of labour,
management, organisation, monitoring, training, differentiation and specialisation, organisational units and
normative regulation and traffic control support and other holders of command and control.
tasks within its competence. Events from the 90's, called
for a review of the organisational structure of the
transport support governing bodies. This situation Assessment, synthesis and ranking
highlights the need for further study of the organisational
structure of traffic management. First steps in the application of the fuzzy mathematical
model would be defining the set of linguistic descriptors.
Linguistic variables are represented by a set of linguistic
An illustrative application of SWOT analysis
descriptors S  {l1 , l2 ,..., li }, i  H  {0,1,..., T }, where
This section presents an illustration of the proposed T is the overall number of linguistic descriptors. In this
approach summarized previously. In order to define the
governing bodies for traffic support design strategy, a case, the number of linguistic descriptors is T  9 :
SWOT analysis of influence; that is opportunities and unessential – U, very low – VL, fairly low – FL, low – L,
threats from the environment on the management of the medium – M, high – H, medium high – MH, very high –
traffic support has been done (Figure 3). SWOT analysis VH and perfect – P. Linguistic descriptors have the
is used to manage the total organisation, the overall following values Figure 3.
pattern of structural components and arrangement.
Having applied the SWOT analysis, four varieties of the  0, 0 x 
traffic support governing bodies organisational structure l    (14)
are defined:
U
(0.125  x) / 0.125 0  x  0.125

 x / 0.125, 0  x  0.125 
Alternative 1 ( A1 ) l    (15)
VL
(0.250  x) / 0.125, 0.125  x  0.25
The current organisation of the governing bodies of the
traffic support, defined on the basis of normative ( x  0.125) / 0.125, 0.125  x  0.250 
l    (16)
 (0.375  x) / 0.125 0.250  x  0.375
regulation for determining the organisational solutions in FL

the military formations and experience of those


participating in making decisions. The current
organisation consists of two organisational units: ( x  0.50) / 0.125, 0.50  x  0.625
Department of Traffic Operations and Department of l    (17)
Transport (Figure 4). H
 (0.75  x) / 0.125 0.625  x  0.75

Alternative 2 ( A2 ) ( x  0.375) / 0.125, 0.375  x  0.50 


l    (18)
M
 (0.625  x) / 0.125 0.50  x  0.625
Organisational structure of the governing bodies of the
traffic support after the NATO standard.
( x  0.50) / 0.125, 0.50  x  0.625
l    (19)
Alternative 3 ( A3 )
H
 (0.75  x) / 0.125 0.625  x  0.75

Organisational structure established according to the ( x  0.625) / 0.125, 0.625  x  0.75


processes where organisational units are defined for l    (20)
each of those processes. Specialists indispensable for
MH
 (0.875  x) / 0.125 0.75  x  0.875
implementing these processes are present in each group.
If traffic management is viewed as the governing body or
management of the transport support, then it is the holder ( x  0.75) / 0.125, 0.75  x  0.875
of the implementation of certain processes. l    (21)
VH
 (1  x) / 0.125 0.875  x  1 

Alternative 4 ( A2 ) ( x  0.875) / 0.125, 0.875  x  1


l    (22)
The structure of the traffic support governing bodies
P
 1, x 1 
5382

Capable and competent personnel (S1)


Tactical-operational units swift dislocation
capability (S2)
Sci. Res. Essays

Strong management team (S3)


Large number of hierarchical levels (W1)
Weak personnel motivation possibilities (W2)
Insufficient organisational structure efficiency (W3)

Figure 3. FMM model for SWOT.


Bad coordination (W4)
Insufficient experience sharing with foreign armed Alternative 1
forces (W5)
Strengths (S) Partial optimisation (W6)
Poor resources exploitation (W7) Alternative 2

To determine the relative importance of the evaluation


criteria SWOT, they were pair-wise compared with
Weaknesses (W) Determining the best
Better cooperation with foreign armed forces (O1) alternative
Oppurtunities (O) Alternative 3
Liberalisation of personnel education abroad (O2)

Threats (T) Modern informational technologies development in


the area of business organisation (O3) Alternative 4
Establishing of logistic support organisation capable
of satisfying command demands (O4)
Grouping of organisational units according to
NATO standards (O5)
Minimum number of hierarchical levels (O6)
Political and economic instability in Serbia (T1)
Qualified personnel outflow (T2)
Changes in logistic support doctrine (T3)
Changes in the country’s defence doctrine (T4)

evaluation of linguistic criterions for each of the presented


respect to the goal by using the fuzzyfied. In Table 1, the
Pamucar et al. 5383

Table 1. Optimality criterion level of influence on the observed alternatives.

Linguistic criteria Benefit-cost criteria


Criteria and sub-criteria
A1 A2 A3 A4 Min Max
Strengths
Capable and competent personnel M MH H H 
Tactical-operational units swift dislocation capability M VH H MH 
Strong management team M VH H MH 

Weaknesses
Number of hierarchical levels H M M M 
Personnel motivation possibilities L VH H H 
Organisational structure efficiency L VH M MH 
Coordination VL VH M VH 
Sharing experience with foreign armed forces VL VH M P 
Partial optimisation VH VL L FL 
Resources exploitation M VH H VH 

Opportunities
Cooperation with foreign armed forces L VH MH VH 
Liberalisation of personnel education abroad M VH MH VH 
Modern informational technologies introduction in the area of business organisation L VH M VH 
Establishing of logistic support organisation capable of satisfying command demands VL VH M H 
Grouping of organisational units according to NATO standards L H M VH 
Participation in logistic support of the NATO forces VL MH M VH 

Threats
Political and economic instability in Serbia VH M VH H 
Qualified personnel outflow VH MH VH MH 
Changes in logistic support doctrine VH M H H 
Changes in the country’s defence doctrine VH M H H 

alternatives according to observed optimality criterions


are given. Linguistically expressed preferences among
criteria have been used to create a judgment matrix W as
given in step 4. Following the decision-maker’s criterion
assessment, normalisation of optimality criteria using
Equations 1 and 2 is performed. The weighting vector
 of criteria matrix W was determined by applying
w kij
Equation 6. Each entry of this vector is the sum of
elements in the related row of matrix W and divided by
the sum of all its elements.

 ws  (0.32, 0.30, 0.27)   0.33 


 w   (0.40, 0.36, 0.32)   0.29 
WSWOT   w     
 wo   (0.16, 0.18, 0.21)   0.20 
     
Figure 4. Linguistic descriptors.  wt   (0.12, 0.15, 0.20)  0.17 
5384 Sci. Res. Essays

Table 2. The priorities of the SWOT factors and groups.

SWOT Local priority SWOT factors Global priorities


Capable and competent personnel 0.39
Strengths 0.33 Tactical-operational units swift dislocation capability 0.26
Strong management team 0.35

Number of hierarchical levels 0.12


Personnel motivation possibilities 0.13
Organisational structure efficiency 0.14
Weaknesses 0.29 Coordination 0.17
Sharing experience with foreign armed forces 0.10
Partial optimisation 0.16
Resources exploitation 0.18

Cooperation with foreign armed forces 0.15


Liberalisation of personnel education abroad 0.18
Modern informational technologies introduction in the area of business organisation 0.09
Opportunities 0.20
Establishing of logistic support organisation capable of satisfying command demands 0.20
Grouping of organisational units according to NATO standards 0.12
Participation in logistic support of the NATO forces 0.12

Political and economic instability in Serbia 0.35


Qualified personnel outflow 0.07
Threats 0.17
Changes in logistic support doctrine 0.30
Changes in the country’s defence doctrine 0.27

In the next step the judgment matrices for sub-criteria alternatives is obtained by applying Equation 13. The
related to respective criteria were obtained. Related sub- normalised values presented in Table 4 show that
criteria weighting vectors were calculated as defined by Alternative 2 is the best. It is followed by Alternative 4, 3
Equations 6 (Table 2). Having determined the value of and 1 respectively, regardless of the decision-maker’s
the weighing coefficients for each of the observed level of optimism. By using the centre of gravity method

F  cij 
to defuzzify the V values given earlier, the final weights
criterions, matrix is formed (Table 3). of alternatives obtained after normalization were: 0.213
F W
(Alternative 1), 0.297 (Alternative 2), 0.220 (Alternative 3)
Where the matrix elements cij are calculated using
and 0.253 (Alternative 4). Obviously, the final ranking is
equal to the previous one.
Equation 10.

A1 A2 A3 A4 DISCUSSION
(0.30,0.32,0.36) (0.36,0.32,0.30) (0.16,0.19,0.21) (0.12,0.16,0.19)   0.33
 (0.20,0.21,0.23) (0.24,0.26,0.23) (0.19,0.21,0.23) (0.30,0.33,0.35)   0.29 
F 
Organisation is not a sum of mechanical parts, rather an
 (0.07,0.08,0.11) (0.29,0.31,0.32) (0.26,0.27,0.29) (0.26,0.27,0.29)  0.20  "organic whole" with a purpose and mission. In the
   
(0.14,0.14,0.17) (0.30,0.31,0.32) (0.21,0.23,0.25) (0.29,0.31,0.34)  0.17  process of designing the organisational structure it is
necessary, having defining the objectives and design
The assessment of alternatives has been performed criteria, to analyse the state of the organisation. In
using relations 10 and 12. The final alternative addition to organisations operating in an uncertain
performance weights with respect to the overall goal have environment, there is a degree of uncertainty and
been calculated by Equation 32 as: imprecision of criteria used in the process of
organisational design. Fuzzy multi-criteria approach
V1   (0.20, 0.21, 0.23)  developed in this paper allows the quantification of these
V   (0.28, 0.29, 0.32)  criteria and selection of the best alternative out of
V   2    proposed organisational models. The presented model
V3   (0.20, 0.22, 0.24)  enables the evaluation of the proposed options of
    organisational structure, regardless of the number of
V4  (0.22, 0.26, 0.27)  optimality criteria and sub-criteria. The model allows for
the choice of best alternative from a set described using
For the typical values of  that express the decision- K optimality criteria and sub-criteria. The criteria
maker’s attitude toward risk, the final ranking of described can be of benefit or cost type. The criteria
Pamucar et al. 5385

Тable 3. Additive synthesis.

SWOT factors Alternative 1 Alternative 2 Alternative 3 Alternative 4 W2 W1


S1 (0.119,0.113,0.109) (0.119,0.113,0.109) (0.078,0.084,0.088) (0.078,0.084,0.088) 0.39
0.33
Strengths S2 (0.129,0.103,0.092) (0.129,0.103,0.092) (0.000,0.026,0.037) (0.000,0.026,0.037) 0.26
S3 (0.116,0.108,0.102) (0.116,0.108,0.102) (0.077,0.080,0.083) (0.040,0.053,0.062) 0.35

W1 (0.027,0.028,0.030) (0.027,0.028,0.030) (0.018,0.021,0.024) (0.046,0.042,0.036) 0.12


W2 (0.030,0.031,0.032) (0.045,0.042,0.039) (0.030,0.031,0.032) (0.030,0.031,0.032) 0.13
W3 (0.024,0.027,0.030) (0.036,0.036,0.037) (0.024,0.027,0.030) (0.060,0.053,0.045) 0.14
Weaknesses W4 (0.016,0.022,0.028) (0.046,0.045,0.046) (0.030,0.033,0.037) (0.076,0.067,0.056) 0.17 0.29
W5 (0.028,0.027,0.027) (0.028,0.027,0.027) (0.018,0.020,0.022) (0.028,0.027,0.027) 0.10
W6 (0.040,0.040,0.040) (0.040,0.040,0.040) (0.040,0.040,0.040) (0.040,0.040,0.040) 0.16
W7 (0.025,0.029,0.035) (0.063,0.058,0.052) (0.025,0.029,0.035) (0.063,0.058,0.052) 0.18

O1 (0.017,0.021,0.027) (0.043,0.042,0.040) (0.043,0.042,0.040) (0.043,0.042,0.040) 0.15


O2 (0.023,0.028,0.034) (0.058,0.055,0.050) (0.058,0.055,0.050) (0.035,0.037,0.042) 0.18
O3 (0.012,0.014,0.017) (0.031,0.029,0.026) (0.031,0.029,0.026) (0.012,0.014,0.017) 0.09
Opportunities 0.20
O4 (0.023,0.028,0.036) (0.058,0.056,0.054) (0.058,0.056,0.054) (0.058,0.056,0.054) 0.20
O5 (0.018,0.021,0.025) (0.046,0.042,0.037) (0.009,0.014,0.019) (0.046,0.042,0.037) 0.12
O6 (0.014,0.017,0.022) (0.035,0.034,0.032) (0.035,0.034,0.032) (0.035,0.034,0.032) 0.12

T1 (0.050,0.059,0.071) (0.127,0.118,0.106) (0.050,0.059,0.071) (0.127,0.118,0.106) 0.35


T2 (0.009,0.011,0.013) (0.022,0.021,0.019) (0.013,0.014,0.016) (0.022,0.021,0.019) 0.07
Threats 0.17
T3 (0.076,0.076,0.076) (0.076,0.076,0.076) (0.076,0.076,0.076) (0.076,0.076,0.076) 0.30
T4 (0.069,0.069,0.069) (0.069,0.069,0.069) (0.069,0.069,0.069) (0.069,0.069,0.069) 0.27

Table 4. Final ranking of alternatives.

Index of optimism
Decision alternative Final rank
λ = 0.0 (pessimistic) λ = 0.5 (moderate) Λ = 1.0 (optimistic)
Alternative 1 0.205 0.212 0.220 4
Alternative 2 0.285 0.295 0.305 1
Alternative 3 0.210 0.220 0.230 3
Alternative 4 0.245 0.255 0.265 2

relevant to the design of organisations as well as their The complex environment, in which these governing
influence on the choice of alternatives have their values bodies act, does not tolerate organisational improvisation,
displayed as numerical values or fuzzy linguistic rather requires a planned and methodological
descriptors. Since the process of organisational design organisational project and its constant modification and
often involved a number of experts, the model allows for adaptation.
a possibility of optimality criteria values synthesis in case Selection of the appropriate organisational structure is
of group decision-making. Decision-making in a group one of the most significant decisions, as the capabilities
differs from individual decision-making on methodological of the governing system will be significantly slowed down
and mathematical levels. Group syntheses with complete if an organisational structure is inadequate for the
and incomplete information are discussed in the model. circumstances in which the organisation is. Although the
In addition, the model enables comparison of the criterion model application was shown on the example of
functions output values using two methods namely: designing governing bodies within the armed forces, it
dephasification of the centre of gravity and the total possesses great flexibility and can be adapted to any
integral value method. Application of the given model is particular problem. Very easily, with minor modifications,
shown on the example of designing the organisational it can be applied for the selection of organisational
structure of the governing bodies of transport support. structure of any business system.
5386 Sci. Res. Essays

REFERENCES Pamucar D, Bozanic D, Dorovic B, Milic A (2011). Modelling of the fuzzy


logical system for offering support in making decisions within the
Bender MJ, Simonovic SP (2000). A fuzzy compromise approach to engineering units of the Serbian army. Int. J. Phys. Sci., 3: 592-609.
water resources systems planning under uncertainty. Fuzzy Set. Roy B (1968). Ranking and selection in the presence of multiple
Syst., 115: 35-44. viewpoints. Comput. Oper. Res., 8: 57-75.
Bozanic D, Pamucar D (2010). Evaluating locations for river crossing Saaty TL (1980). The analytic hierarchy process. McGraw-Hill, New
using fuzzy logic. Milit. Tech. Cour., 1: 129-145. York.
Brans JP, Vincke P, Mareschal B (1986). How to select and how to rank Srdevic B, Medeiros Y, Srdevic Z, Schaer M (2002). Evaluating
projects by the Promethee method. Eur. J. Oper. Res., 24: 228-238. management strategies in Paraguacu river basin by analytic
Deng H (1999). Multicriteria analysis with fuzzy pairwisecomparison. Int. hierarchy process. First Biennial Meeting Int. Environ. Modeling
J. Approx. Reason., 21: 215-231. Software Soc., 1: 42-47.
Hwang CL, Yoon KS (1981). Multiple attribute decision making: Triantaphyllou E, Lin CT (1996). Development and evaluation of five
methods and applications. Springer, Berlin. multiattribute decision making methods. Int. J. Approx. Reason., 14:
Kujacic M, Bojovic N (2003). Organizational design of post corporation 281-310.
structure using fuzzy multicriteria decision making. Comput. Math. Zadeh LA (1965). Fuzzy sets. Inf. Control. 8: 338-353.
Organ. Theory, 9: 5-18. Zeleny M (1982). Multiple citeria decision making. McGraw-Hill Book
Liou TS, Wang MJJ (1992). Ranking fuzzy numbers with integral value. Company, New York.
Fuzzy Set. Syst., 50: 247-256.
Pamucar D (2009). Design of the organisational structure using fuzzy
logic approach. Master paper. Serbia: Faculty of Transport and
Traffic Engineering, Belgrade.
Pamucar D (2010). Using fuzzy logic and neural networks during
decision making proces in transport. Milit. Techn. Cour., 3: 125-143.

You might also like