This action might not be possible to undo. Are you sure you want to continue?
,
Vol. 8, No. 8, 2010
.
An Improved Fuzzy Time Series Model For
Forecasting
Ashraf K. AbdElaal
1
Department of Computer and
Information Sciences
The High Institute of Computer Science
Sohag, Egypt
ashrafsohag@yahoo.com
Hesham A. Hefny
Department of Computer and Information
Sciences,
Institute of Statistical Studies and Research,
Cairo University, Egypt
hehefny@ieee.org
Ashraf H. AbdElwahab
Department of Computer Sciences
Electronics Research Institute
National Center for Research
Cairo, Egypt
Abstract— Researchers introduce in this paper, an efficient fuzzy
time series forecasting model based on fuzzy clustering to handle
forecasting problems and improving forecasting accuracy. Each
value (observation) is represented by a fuzzy set. The transition
between consecutive values is taken into account in order to
model the time series data. Proposed model employed eight main
steps in timeinvariant fuzzy timeseries and timevariant fuzzy
time series models to increase the performance of the proposed
fuzzy time series model. The method of FCMI is integrated in the
processes of fuzzy time series to partition datasets. The proposed
model has been implemented to forecast the world production of
iron and steel and the enrollments of the University of Alabama.
The proposed model provide higher accuracy in forecasting. Our
results show that this approach can lead to satisfactory
performance for fuzzy time series
1
Keywords forecasting; fuzzy Clustering; fuzzy time series; iron.
I. INTRODUCTION
Traditional forecasting methods can deal with many
forecasting cases, but they cannot solve forecasting problems in
which the historical data are linguistic values. Song and
Chissom [12] presented the concept of fuzzy time series based
on the historical enrollments of the University of Alabama.
They presented the timeinvariant fuzzy time series model and
the timevariant fuzzy time series model based on the fuzzy set
theory for forecasting the enrollments of the University of
Alabama.
The fuzzy forecasting methods can forecast the data with
linguistic values. Fuzzy time series do not need to turn a non
stationary series into a stationary series and do not require more
historical data along with some assumptions like normality
postulates. Although fuzzy forecasting methods are suitable for
incomplete data situations, their performance is not always
satisfactory [9,11].
Huarng [6] proposed heuristic models; by integrating
problemspecific heuristic knowledge to improve forecasting.
1
Corresponding Author: Ashraf K. AbdElaal
Tsaur, et al [14] proposed an analytical approach to find
the steady state of fuzzy relation matrix to revise the logic
forecasting process. Based on the concept of fuzziness in
Information Theory, the concept of entropy is applied to
measure the degrees of fuzziness when a timeinvariant relation
matrix is derived. In order to show the forecasting
performance, the best fitted regression equations are applied to
compare with the proposed method.
Yu [15] proposed weighted models to tackle two issues in
fuzzy time series forecasting; namely, recurrence and
weighting. Weighted fuzzy time series models appear quite
similar to the weight functions in local regression models;
however, both are different. The local regression models focus
on fitting using a small portion of the data, while the fuzzy
relationships in weighted fuzzy time series models are
established using the possible data from the whole of the
database.
Jilani and Burney [7] presented two new multivariate
fuzzy time series forecasting methods. These methods assume
mfactors with one main factor of interest. Stochastic fuzzy
dependence of order k is assumed to define general methods of
multivariate fuzzy time series forecasting and control.
Cheng et al [4] proposed a novel multipleattribute fuzzy
time series method based on fuzzy clustering. The methods of
fuzzy clustering were integrated in the processes of fuzzy time
series to partition datasets objectively and enable processing of
multiple attributes.
Abd Elaal et al [12] proposed a novel forecasting fuzzy
time series model depend on fuzzy clustering for improving
forecasting accuracy. Kai et al [8] proposed a novel forecasting
model for fuzzy time series using Kmeans clustering
algorithm for forecasting.
In this paper, researchers propose an efficient fuzzy time
series forecasting model based on fuzzy clustering to handle
forecasting problems and improving forecasting accuracy. Each
value (observation) is represented by a fuzzy set. The transition
between consecutive values is taken into account in order to
model the time series data.
11 http://sites.google.com/site/ijcsis/
ISSN 19475500
(IJCSIS) International Journal of Computer Science and Information Security,
Vol. 8, No. 8, 2010
.
II. RELATED WORKS
In this section, two related works including: fuzzy clustering
and fuzzy time series.
A. Fuzzy clustering (FCMI)
Fuzzy cmeans (FCM) is a method of clustering which
allows one piece of data to belong to two or more clusters.
Fuzzy CMean Iterative assume that: the existence of pattern
space X={x
1
, x
2
,…, x
m
) and c fuzzy clusters, whose centers
have initial values y
10
, y
20
,…,y
c0
. Every iteration the
membership function values updated and the cluster centers
also. The process terminates when the difference between two
consecutive clusters centers do not exceed a given tolerance
[5].
) ( ) ( k
i j
k
ij
y x d − =
(1)
Fuzzy clustering is carried out through an iterative optimization
of the objective function
ij
d
, with the update of membership
ij
u
and the cluster centers
i
y
by:
1
1
) 1 /( 2
) (
) (
) (
−
=
−


¹

\

=
∑
c
l
k
lj
k
ij k
ij
d
d
u
β
(2)
∑
∑
=
= +
=
m
j
k
ij
m
j
j
k
ij
k
i
u
x u
y
1
) (
1
) (
) 1 (
(3)
This iteration will stop when
ε <
−
∑
=
+
2 / 1
1
2
) ( ) 1 (
c
i
k
i
k
i
y y
(4)
B. Fuzzy time series
Song and Chissom [13] presented the concept of fuzzy
time series based on the historical enrollments of the University
of Alabama. Fuzzy time series used to handle forecasting
problems. They presented the timeinvariant fuzzy time series
model and the timevariant fuzzy time series model based on
the fuzzy set theory for forecasting the enrollments of the
University of Alabama. The definitions and processes of the
fuzzy timeseries presented by Song and Chissom are described
as follows [6,12].
Definition 1. (FTS) Assume Y (t) (t = . . 0, 1, 2, . . .) is a subset
of a real numbers. Let Y (t) be the universe of discourse
defined by the fuzzy set f
i
(t). If F(t) is a collection of f
1
(t), f
2
(t).
. . then F(t) is defined as a fuzzy timeseries on Y (t) (t = . . . ,
0, 1, 2, . . .).
Definition 2. (FTSRs) If there exists a fuzzy logical
relationship R(t − 1, t), such that F(t) = F(t − 1) × R(t − 1, t),
where “×” represents an operation, then F(t) is said to be
induced by F(t − 1). The logical relationship between F(t) and
F(t − 1) is F(t − 1) F(t).
Definition 3. (FLR) suppose F(t − 1) = A
i
and F(t) = A
j
. The
relationship between two consecutive observations, F(t) and F(t
− 1), referred to as a fuzzy logical relationship, can be denoted
by A
i
A
j
, where Ai is called the LeftHand Side (LHS) and
A
j
the RightHand Side (RHS) of the FLR.
Definition 4. (FLRG) All fuzzy logical relationships in the
training dataset can be grouped together into different fuzzy
logical relationship groups according to the same LeftHand
Sides of the fuzzy logical relationship. For example, there are
two fuzzy logical relationships with the same LeftHand Side
(A
i
): A
i
A
j1
and A
i
A
j2
. These two fuzzy logical
relationships can be grouped into a fuzzy logical relationship
group A
i
A
j1
A
j2
.
Definition 5. (IFTS & VFTS) Assume that F(t) is a fuzzy time
series and F(t) is caused by F(t − 1) only, and F(t) = F(t − 1) ×
R(t − 1, t). For any t, if R(t − 1, t) is independent of t, then F(t)
is named a timeinvariant fuzzy timeseries, otherwise a time
variant fuzzy timeseries.
a) Song and Chissom model
Song and Chissom employed five main steps in time
invariant fuzzy timeseries and timevariant fuzzy time series
models as follows:
Step 1: Define the universe of discourse U. Define the universe
of discourse for the observations. According to the issue
domain, the universe of discourse for observations is defined
as,
U=[D
min
– D
1
, D
max
+ D
2
] (5)
where, D
min
is the minimum value,
D
max
is the maximum value,
D
1
, D
2
is the positive real numbers.
Step 2: Partition universal of discourse U into equal intervals.
Step 3: Define the linguistic terms. Each linguistic observation,
A
k
can be defined by the intervals u
1
,u
2
,...,u
n
, as follows:
1 2
k 1 k k 1
n 1 n
1 0.5
k 1
u u
0.5 0.5 1
k u u u
0.5 1
k n
u u
A 2 k n 1
− +
−
+ =
+ =
¦
¦
= + + ≤ ≤ −
´
¦
¹
(6)
12 http://sites.google.com/site/ijcsis/
ISSN 19475500
(IJCSIS) International Journal of Computer Science and Information Security,
Vol. 8, No. 8, 2010
.
Step 4: Fuzzify the historical data. Each historical data can be
fuzzified into a fuzzy set.
Step 5: Build fuzzy logic relationships. Build fuzzy logic
relationships. Two consecutive fuzzy sets A
i
(t1)and A
j
(t) can
be established into a single FLR as A
i
A
j
.
III. PROPOSED MODEL
In this section we proposed an efficient fuzzy time series
forecasting model based on fuzzy clustering to handle
forecasting problems and improving forecasting accuracy.
Most researchers have been taken the same way according to
processes of the fuzzy timeseries, which are presented by Song
and Chissom, but we introduce a novel model based on fuzzy
clustering to determine the membership values not as Song and
Chissom model, and to increase the performance. Proposed
model employed eight main steps in timeinvariant fuzzy time
series and timevariant fuzzy time series models as follows:
Step 1: Cluster data into c clusters: Apply fuzzy clustering
on a time series Y(t) with n observation to cluster this time
series into c (2 ≤ c ≤ n) clusters. FCMI is used because it is the
most popular one and well known in fuzzy clustering field.
Step 2: Determine membership values for each cluster: In
this step, membership values is determining after doing fuzzy
cluster. The proposed model selected the maximum
membership grade of each value for each cluster which it
belong to.
Step 3: Rank each cluster: Proposed model ranking clusters
by the center of each cluster, where first cluster has the
minimum center, and last cluster has the maximum center.
Step 4: Define the universe of discourse U: In this step, the
proposed model defines the universe of discourse as Song and
Chissom were defined it as in (5).
Step 5: Partition universal of discourse U into equal
intervals: According to this step, the proposed model, partition
the universe of discourse into c intervals.
Step 6: Fuzzify the historical data: In this step, proposed
model fuzzufy historical data, where the proposed model
determine the best fuzzy cluster to each actual data
Step 7: Build fuzzy logic relationships: Proposed model in
this step build fuzzy logic relationship as definition 3. if F(t−1)
= Ai and F(t) = Aj then the relationship between two
consecutive observations: Ai Aj
Step 8: Calculate forecasting outputs: The forecasting value
for each cluster is calculated by proposed model as:
∑
=
+ + +
=
m
j
j
df
m
df df df
i
A forecaste
1
m
X x ...
1
X x
1 1
X x
1
) (
(7)
Where dfj is the membership grade,
Xj is the actual value.
A. Evaluating of the proposed model
To evaluating the performance of the proposed model, the
researchers compare the forecasting values of enrollments of
the University of Alabama with some famous models such as
Jilani and Burney [7], Tsaur and Yang [14], Yu [15], Kai et al
[8], and Cheng, et al [4].
The forecasting accuracy is compared by using (NRMSE)
Normalized Root Mean Square Error. NRMSE, in statistic is
the square root of the sum of the squared deviations between
actual and predicted values divided by the sum of the square of
actual values.
∑
∑
=
=
−
=
N
i
i
N
i
i i
actual
predict actual
NRMSE
1
2
1
2
) (
) (
(8)
In this study, to evaluate the forecasting accuracy of the
proposed model, the researchers use the enrollments of the
University of Alabama as the forecasting target in the existing
forecasting models.
Based on the enrollments of the University of Alabama
from 1971 to 1992, we can get the universe of discourse
U=[13055,19337], partition U into 7 equal intervals, D
1
=13,
and D
2
=55. Hence, the intervals are u
1
; u
2
; u
3
; u
4
; u
5
; u
6
; u
7
;
where :
u
1
=[13024.00, 13933.71]
u
2
=[13933.71, 14843.43],
u
3
=[14843.43, 15753.14],
u
4
=[15753.14, 16662.86],
u
5
=[16662.86, 17572.57],
u
6
=[17572.57, 18482.29],
u
7
=[18482.29, 19392.00],
Table I lists the enrollment of the University of Alabama
from 1971 to 1992, and membership grades of enrollments for
each linguistic. Define the fuzzy set A
i
using the linguistic
variable "Enrollments of the University of Alabama", let A
1
=
(very very few), A
2
= (very few), A
3
= (few), A
4
= (moderate),
A
5
= (many), A
6
= (many many), A
7
= (too many).The
proposed model selected the maximum membership grade for
each cluster, the forecasting value for each cluster calculating
as in (7):
13563
1
(1972) x 1
)
1
( = = A forecaste
15145
8 . 0
(1984) x 8 . 0
)
2
( = = A forecaste
13 http://sites.google.com/site/ijcsis/
ISSN 19475500
(IJCSIS) International Journal of Computer Science and Information Security,
Vol. 8, No. 8, 2010
.
15446
2
(1982) x 1 (1975) x 1
)
3
( =
+
= A forecaste
15861
1
(1978) x 1
)
4
( = = A forecaste
16807
1
(1979) x 1
)
5
( = = A forecaste
18150
1
(1988) x 1
)
6
( = = A forecaste
18970
1
(1989) x 1
)
7
( = = A forecaste
TABLE I. DATA OF ENROLLMENTS OF THE UNIVERSITY OF ALABAMA
AND MEMBERSHIP GRADES.
Year
Actual
enrollm
A1 A2 A3 A4 A5 A6 A7
1971 13055 0.8 0.1 0 0 0 0 0
1972 13563 1 0 0 0 0 0 0
1973 13867 0.9 0.1 0 0 0 0 0
1974 14696 0.1 0.7 0.2 0.1 0 0 0
1975 15460 0 0 1 0 0 0 0
1976 15311 0 0.1 0.9 0 0 0 0
1977 15603 0 0.1 0.6 0.3 0 0 0
1978 15861 0 0 0 1 0 0 0
1979 16807 0 0 0 0 1 0 0
1980 16919 0 0 0 0 0.9 0 0
1981 16388 0 0 0.1 0.3 0.6 0 0
1982 15433 0 0 1 0 0 0 0
1983 15497 0 0 0.9 0.1 0 0 0
1984 15145 0 0.8 0.2 0 0 0 0
1985 15163 0 0.7 0.2 0 0 0 0
1986 15984 0 0 0 0.9 0 0 0
1987 16859 0 0 0 0 1 0 0
1988 18150 0 0 0 0 0 1 0
1989 18970 0 0 0 0 0 0 1
1990 19328 0 0 0 0 0 0 0.9
1991 19337 0 0 0 0 0 0 0.9
1992 18876 0 0 0 0 0 0.1 0.9
Figure 1. Forecasting enrollments of the University of Alabama by the
proposed model
TABLE II. DATA ENROLLMENTS THE UNIVERSITY OF ALABAMA,
LINGUISTIC VALUES, AND FORECASTED VALUES
Years Enrollments Linguistic Forecasted
1971 13055 A1 13563
1972 13563 A1 13563
1973 13867 A1 13563
1974 14696 A2 15145
1975 15460 A3 15446
1976 15311 A3 15446
1977 15603 A3 15446
1978 15861 A4 15861
1979 16807 A5 16833
1980 16919 A5 16833
1981 16388 A4 15861
1982 15433 A3 15446
1983 15497 A3 15446
1984 15145 A3 15446
1985 15163 A3 15446
1986 15984 A4 15861
1987 16859 A5 16833
1988 18150 A6 18150
1989 18970 A7 18970
1990 19328 A7 18970
1991 19337 A7 18970
1992 18876 A7 18970
Comparisons of the forecasting results of different models
13000
13500
14000
14500
15000
15500
16000
16500
17000
17500
18000
18500
19000
19500
1
9
7
1
1
9
7
2
1
9
7
3
1
9
7
4
1
9
7
5
1
9
7
6
1
9
7
7
1
9
7
8
1
9
7
9
1
9
8
0
1
9
8
1
1
9
8
2
1
9
8
3
1
9
8
4
1
9
8
5
1
9
8
6
1
9
8
7
1
9
8
8
1
9
8
9
1
9
9
0
1
9
9
1
1
9
9
2
Years
A
c
t
u
a
l
e
n
r
o
l
l
m
e
n
t
s Actual
Jilani 2008
Tsaur 2005
Yu 2005
Cheng 2008
Kai 2010
Proposed
Figure 2. Forecasting results curve of enrollments of the university of
Alabama
The forecasting value for year 1971 is 13563 while the
actual value was 13055. Fig.1 and Table II show linguistic
terms and forecasting values deduced by proposed model.
14 http://sites.google.com/site/ijcsis/
ISSN 19475500
(IJCSIS) International Journal of Computer Science and Information Security,
Vol. 8, No. 8, 2010
.
NRMSE for different models
0
0.005
0.01
0.015
0.02
0.025
0.03
0.035
Jilani 2008 Tsaur 2005 Yu 2005 Cheng 2008 Kai 2010 Proposed
Models
N
R
M
S
E
Figure 3. NRMSEchart for the existing models and the proposed model
The linechart comparison in Fig. 2 shows that the proposed
model has higher accuracy than the other models. And the
empirical comparison among the existing models in Table III
also shows that, the proposed model can further improve the
forecasting results than the other model.
Fig. 3 shows the comparisons among the existing models
by using NRMSE, where Jilani and Burney [7] model has 0.02,
Tsaur and Yang [14] model has 0.025, Yu [15] model has
0.026, Kai et al [8] model has 0.024, Cheng, et al [4] model has
0.028 and proposed model has 0.015.
TABLE III. FORECASTING ENROLLMENTS OF THE UNIVERSITY OF ALABAMA
Year
Actual
enrollments
Tsaur and
Yang
(2005)
Yu
(2005)
Jilani and
Burney
(2008)
Cheng et al
(2008)
Kai et al
(2010)
Proposed
1971 13055 13934 13934 13769 13563
1972 13563 13934 13934 13769 14242 13997 13563
1973 13867 13934 13934 13769 14242 13997 13563
1974 14696 15298 15298 14360 14242 13997 15145
1975 15460 15753 15623 15271 15474.3 15461.2 15446
1976 15311 15753 15623 15271 15474.3 15461.2 15446
1977 15603 15753 15623 15271 15474.3 15461.2 15446
1978 15861 16208 16511 16182 15474.3 15461.2 15861
1979 16807 17118 17269 17094 16146.5 16861.7 16833
1980 16919 17118 17269 17094 16988.3 17394 16833
1981 16388 16208 16511 16182 16988.3 17394 15861
1982 15433 15753 15623 15271 16146.5 15461 15446
1983 15497 15753 15623 15271 15474.3 15461.2 15446
1984 15145 15753 15623 15271 15474.3 15461.2 15446
1985 15163 15753 15623 15271 15474.3 15461.5 15446
1986 15984 16208 16511 16182 15474.3 15461.5 15861
1987 16859 17118 17269 17094 16146.5 16861.7 16833
1988 18150 18937 18937 18004 16988.3 17394 18150
1989 18970 18937 18937 18624 19144 18932.2 18970
1990 19328 18937 18937 18624 19144 18932.2 18970
1991 19337 18937 18937 18624 19144 18932.2 18970
1992 18876 18937 18937 18624 19144 18932.2 18970
NRMSE 0.025 0.026 0.02 0.028 0.024 0.015
15 http://sites.google.com/site/ijcsis/
ISSN 19475500
(IJCSIS) International Journal of Computer Science and Information Security,
Vol. 8, No. 8, 2010
.
IV. EMPIRICAL STUDY
Based on the data of the iron and steel production witch are
provided by the International Iron and Steel Institute in
Brussels, Belgium, and publications of the U.S. geological
survey from 1975 to 2008 (production values in thousand
metric tons), we can get the universe of discourse U=[457000,
954000], partition U into 7 equal intervals, D
1
=6000, and
D
2
=7000. Hence, the intervals are u
1
; u
2
; u
3
; u
4
; u
5
; u
6
; u
7
;
where :
u
1
=[ 451000.00, 523857.14]
u
2
=[ 523857.14, 596714.29],
u
3
=[ 596714.29, 669571.43],
u
4
=[ 669571.43, 742428.57],
u
5
=[ 742428.57, 815285.71],
u
6
=[ 815285.71, 888142.86],
u
7
=[ 888142.86, 961000.00],
Figure 4. Forecasting of the world production of iron and steel by the
proposed model
Table IV lists the World Production of Iron and Steel from
1975 to 2008, and membership grades of enrollments for each
linguistic. Define the fuzzy set A
i
using the linguistic variable
"World Production of Iron and Steel", let A
1
= (very very few),
A
2
= (very few), A
3
= (few), A
4
= (moderate), A
5
= (many), A
6
= (many many), A
7
= (too many).
Fig. 4 and Table V show linguistic terms and forecasting
values deduced by proposed model. The forecasting value for
year 1975 is 494875 while the actual value was 479000 and the
forecasting value for year 2008 is 943000 while the actual
value was 932000.
TABLE IV. DATA OF THE WORLD PRODUCTION OF IRON AND STEEL, AND
MEMBERSHIP GRADES.
Year Production A1 A2 A3 A4 A5 A6 A7
1975 479000 1 0 0 0 0 0 0
1976 498000 1 0 0 0 0 0 0
1977 488000 1 0 0 0 0 0 0
1978 506000 0 0 0 0 0 0 0
1979 532000 0 1 0 0 0 0 0
1980 514000 0 0 0 0 0 0 0
1981 502000 1 0 0 0 0 0 0
1982 457000 0 0 0 0 0 0 0
1983 463000 0 0 0 0 0 0 0
1984 495000 1 0 0 0 0 0 0
1985 499000 1 0 0 0 0 0 0
1986 495000 1 0 0 0 0 0 0
1987 509000 0 0 0 0 0 0 0
1988 539000 0 1 0 0 0 0 0
1989 546000 0 1 0 0 0 0 0
1990 531000 0 1 0 0 0 0 0
1991 509000 0 0 0 0 0 0 0
1992 503000 1 0 0 0 0 0 0
1993 507000 0 0 0 0 0 0 0
1994 516000 0 0 0 0 0 0 0
1995 536000 0 1 0 0 0 0 0
1996 516000 0 0 0 0 0 0 0
1997 540000 0 1 0 0 0 0 0
1998 535000 0 1 0 0 0 0 0
1999 539000 0 1 0 0 0 0 0
2000 573000 0 0 1 0 0 0 0
2001 585000 0 0 1 0 0 0 0
2002 608000 0 0 1 0 0 0 0
2003 673000 0 0 0 1 0 0 0
2004 720000 0 0 0 1 0 0 0
2005 802000 0 0 0 0 1 0 0
2006 881000 0 0 0 0 0 1 0
2007 954000 0 0 0 0 0 0 1
2008 932000 0 0 0 0 0 0 1
The proposed model selected the maximum membership
grade for each cluster, the forecasting value for each cluster
calculating as in (7):
16 http://sites.google.com/site/ijcsis/
ISSN 19475500
(IJCSIS) International Journal of Computer Science and Information Security,
Vol. 8, No. 8, 2010
.
94875 4
8
(1992) x 1 (1986) x 1 (1985) x 1 (1984) x 1 (1981) x 1 (1977) x 1 (1976) x 1 (1975) x 1
)
1
( =
+ + + + + + +
= A forecaste
537250
8
(1999) x 1 (1998) x 1 (1997) x 1 (1995) x 1 (1990) x 1 (1989) x 1 (1988) x 1 (1979) x 1
)
2
( =
+ + + + + + +
= A forecaste
588667
3
(2002) x 1 (2001) x 1 (2000) x 1
)
3
( =
+ +
= A forecaste
696500
2
(2004) x 1 (2003) x 1
)
4
( =
+
= A forecaste
802000
1
(2005) x 1
)
5
( = = A forecaste
881000
1
(2006) x 1
)
6
( = = A forecaste
943000
2
(2008) x 1 (2007) x 1
)
7
( =
+
= A forecaste
TABLE V. DATA OF THE WORLD PRODUCTION OF IRON AND STEEL,
LINGUISTIC VALUES, AND FORECASTED VALUES
Year Production Linguistic Forecasted
1975 479000 A1 494875
1976 498000 A1 494875
1977 488000 A1 494875
1978 506000 A1 494875
1979 532000 A2 537250
1980 514000 A1 494875
1981 502000 A1 494875
1982 457000 A1 494875
1983 463000 A1 494875
1984 495000 A1 494875
1985 499000 A1 494875
1986 495000 A1 494875
1987 509000 A1 494875
1988 539000 A2 537250
1989 546000 A2 537250
1990 531000 A2 537250
1991 509000 A1 494875
1992 503000 A1 494875
1993 507000 A1 494875
1994 516000 A1 494875
1995 536000 A2 537250
1996 516000 A1 494875
1997 540000 A2 537250
1998 535000 A2 537250
1999 539000 A2 537250
2000 573000 A2 537250
2001 585000 A2 537250
2002 608000 A3 588667
2003 673000 A4 696500
2004 720000 A4 696500
2005 802000 A5 802000
2006 881000 A6 881000
2007 954000 A7 943000
2008 932000 A7 943000
The researchers used famous models: Huarng[6], Tsaur and
Yang [14], Yu [15], Jilani and Burney [7] to test the proposed
model by forecasting of the world production of iron and steel
as in Table VI.
Comparisons of the forecasting results of different models
450000
550000
650000
750000
850000
950000
1
9
7
5
1
9
7
7
1
9
7
9
1
9
8
1
1
9
8
3
1
9
8
5
1
9
8
7
1
9
8
9
1
9
9
1
1
9
9
3
1
9
9
5
1
9
9
7
1
9
9
9
2
0
0
1
2
0
0
3
2
0
0
5
2
0
0
7
Years
A
c
t
u
a
l
e
n
r
o
l
l
m
e
n
t
s
Actual
Huarng 2001
Tsaur 2005
Yu 2005
Jilani 2008
Proposed
Figure 5. Forecasting results curve of the world production of iron and steel
NRMSE for different models
0
0.01
0.02
0.03
0.04
0.05
0.06
0.07
Huarng 2001 Tsaur 2005 Yu 2005 Jilani 2008 Proposed
Models
N
R
M
S
E
Figure 6. NRMSEchart for the existing models and the proposed
17 http://sites.google.com/site/ijcsis/
ISSN 19475500
(IJCSIS) International Journal of Computer Science and Information Security,
Vol. 8, No. 8, 2010
.
The linechart comparison in Fig. 5 shows that the proposed
model has higher accuracy than the other models. And the
empirical comparison among the existing models in Table VI
also shows that, the proposed model can further improve the
forecasting results than the other model.
Fig. 6 shows the comparisons among the existing
models by using NRMSE, where Huarng[6] model has 0.0496,
Tsaur and Yang [14] model has 0.0598, Yu [15] model has
0.0551, Jilani and Burney [7] model has 0.0399, and proposed
model has 0.0296.
TABLE VI. FORECASTING OF THE WORLD PRODUCTION OF IRON AND STEEL
Year Actual Huarng 2001 Tsaur 2005 Yu 2005 Jilani 2008 Proposed
1975 479000 504571 523857 510762 509514 494875
1976 498000 504571 523857 510762 509514 494875
1977 488000 504571 523857 510762 509514 494875
1978 506000 504571 523857 510762 509514 494875
1979 532000 545714 560286 560286 555508 537250
1980 514000 504571 523857 510762 509514 494875
1981 502000 504571 523857 510762 509514 494875
1982 457000 504571 523857 510762 509514 494875
1983 463000 504571 523857 510762 509514 494875
1984 495000 504571 523857 510762 509514 494875
1985 499000 504571 523857 510762 509514 494875
1986 495000 504571 523857 510762 509514 494875
1987 509000 504571 523857 510762 509514 494875
1988 539000 545714 560286 560286 555508 537250
1989 546000 545714 560286 560286 555508 537250
1990 531000 545714 560286 560286 555508 537250
1991 509000 504571 523857 510762 509514 494875
1992 503000 504571 523857 510762 509514 494875
1993 507000 504571 523857 510762 509514 494875
1994 516000 504571 523857 510762 509514 494875
1995 536000 545714 560286 560286 555508 537250
1996 516000 504571 523857 510762 509514 494875
1997 540000 545714 560286 560286 555508 537250
1998 535000 545714 560286 560286 555508 537250
1999 539000 545714 560286 560286 555508 537250
2000 573000 545714 560286 560286 555508 537250
2001 585000 545714 560286 560286 555508 537250
2002 608000 706000 706000 706000 628923 588667
2003 673000 742429 742429 754571 702221 696500
2004 720000 742429 742429 754571 702221 696500
2005 802000 851714 851714 851714 775435 802000
2006 881000 924571 924571 924571 848587 881000
2007 954000 924571 924571 924571 898939 943000
2008 932000 924571 924571 924571 898939 943000
NRMSE 0.0496 0.0598 0.0551 0.0399 0.0296
18 http://sites.google.com/site/ijcsis/
ISSN 19475500
(IJCSIS) International Journal of Computer Science and Information Security,
Vol. 8, No. 8, 2010
.
V. DISCUSSION AND CONCLUSION
The research proposed an efficient fuzzy time series
forecasting model based on fuzzy clustering with high
accuracy. The method of FCMI is integrated in the processes of
fuzzy time series to partition datasets. Experimental results of
enrollments of the University of Alabama, and the comparison
between the existing models: Jilani and Burney [7], Tsaur and
Yang [14], Yu [15], Kai et al [8], and Cheng, et al [4] and the
proposed model show that, the proposed model can further
improve the forecasting results than the other models and also
the experimental results of the world production of iron and
steel, and the comparison between the existing models:
Huarng[6], Tsaur and Yang [14], Yu [15], Jilani and Burney[7]
and the proposed model show that, the proposed model has
higher accuracy than the other models.
VI. REFERENCES
[1] A. K. Abd Elaal, H. A. Hefny, and A. H. AbdElwahab, "A novel
forecasting fuzzy time series model", in: Proceeding of International
Conference on Mathematics and Information Security, Sohag Univ.,
Egypt, 2009.
[2] A. K. Abd Elaal, H.A. Hefny, and A. H. AbdElwahab, "Constructing
Fuzzy Time Series Model Based on Fuzzy Clustering for a
Forecasting", J. Computer Sci., vol. 7, 2010, pp. 735739.
[3] T.L. Chen, C.H. Cheng, and H.J. Teoh, "Highorder fuzzy time
series based on multiperiod adaptation model for forecasting stock
markets", Physica A, vol.387, 2008, pp. 876–888
[4] C.H. Cheng, J.W. Wang, and G.W. Cheng, "Multiattribute fuzzy
time series method based on fuzzy clustering", Expert Systems with
Applications, Vol.34, 2008. pp. 1235–1242.
[5] M. Friedman and A. Kandel, "Introduction to pattern recognition
statistical, structural, neural and fuzzy logic approaches", Imperial
college press, London, 1999, p. 329.
[6] K. Huarng, "Effective lengths of intervals to improve forecasting in
fuzzy time series", Fuzzy Sets and Systems, vol.123, 2001, pp. 387–
394.
[7] T.A. Jilani and S. Burney, "Multivariate stochastic fuzzy forecasting
models", Expert Systems with Applications, vol.35, 2008, pp. 691–
700.
[8] Kai, F. FangPing, and C. WenGang, "A novel forecasting model of
fuzzy time series based on Kmeans clustering", IWETCS, IEEE,
2010, pp.223–225.
[9] G. Kirchgässner and J. Wolters, "Introduction to modern time series
analysis", SpringerVerlag.Berlin, Germany, 2007, p.153.
[10] H.T. Liu, "An improved fuzzy time series forecasting method using
trapezoidal fuzzy numbers". Fuzzy Optimization and Decision
Making, vol. 6, 2007, pp.6380.
[11] A.K. Palit and D. Popovic, "Computational intelligence in time series
forecasting theory and engineering applications", Springer
Verlag.London, UK, 2005, p.18.
[12] Q. Song and B.S. Chissom, "Forecasting enrollments with fuzzy time
series. I", Fuzzy sets and systems, vol. 54, 1993, pp. 19.
[13] Q. Song and B.S. Chissom, "New models for forecasting enrollments:
fuzzy time series and neural network approaches", ERIC, 1993 p. 27,
http://www.eric.ed.gov
[14] R.C. Tsaur, J.C. Yang, and H.F. Wang, "Fuzzy relation analysis in
fuzzy time series model", Computers and Mathematics with
Applications, vol.49, 2005, pp. 539548.
[15] H.K. Yu, "Weighted fuzzy time series models for TAIEX
forecasting", Physica A, vol.349, 2005, pp.609–624.
AUTHORS PROFILE
Mr. Ashraf Khalaf Abd Elaal is a Ph.D. student in
Computer Sciences Department at the Institute of Statistical
Studies and Research, Cairo University. His Ph.D. in the
filed of Computational Intelligence. His research interests
include fuzzy time series, Fuzzy clustering
Dr. Hesham Ahmed Hefny is an assistant professor and the
head of Computer & Information Sciences Department at
the Institute of Statistical Studies and research, Cairo
University. His research interests include Artificial Neural
Networks, Fuzzy Systems, Genetic Algorithms, Swarm
Intelligence, Pattern Recognition, and Data Mining. Dr.
Hesham has published over 35 peer refereed papers in academic journals
and conferences on topics within Artificial Intelligence and related areas.
Prof. Ashraf Hassan Abdelwahab is a professor of
computer engineering, Electronics Research Institute,
Cairo, Egypt. He received his M. Sc. in 1988, Faculty of
Engineering, Cairo University in the area of Artificial
Intelligence, and in 1992 he received his Ph.D. in Machine
Learning and Evolutionary Algorithms. He has published
over 60 technical papers in National, and International journals and
conferences in the areas of Evolutionary Algorithms, Machine Learning,
and Data Mining.
19 http://sites.google.com/site/ijcsis/
ISSN 19475500