ELEKTRONIKA IR ELEKTROTECHNIKA, ISSN 1392-1215, VOL. 19, NO.

2, 2013

AbstractIn this paper we present a new method for
detection and classification of power quality disturbances. Two
discrete wavelet transforms with different wavelet filters are
used in the feature extraction process. In this way we eliminate
the problem of the selection of the most adequate wavelets in
the current methods for classification of power quality
disturbances. For the classification of the power disturbances
we use a support vector machine. In order to reduce the
computational cost of the proposed method, binary decision
tree is created and a support vector machine classifier is trained
for every node of the tree. The obtained experimental results
show high accuracy of the proposed method.

Index TermsPower quality, disturbances; classification,
wavelets, support vector machine.
I. INTRODUCTION
The quality of the power is with increasing importance
due to the great damage caused by power quality (PQ)
disturbances. The damage is clearly noticeable at great
public or industrial facilities where the PQ disturbances
cause malfunction in the equipment [1]. In order to improve
the power quality, the sources of PQ disturbances should be
known before appropriate mitigating action can be taken.
This can be achieved by detection of different power system
disturbances. The detected disturbances are subsequently
classified and information describing localization, duration
and type of the disturbance is reported. Manual approach of
analyzing and identifying PQ disturbances such as visual
inspection of disturbance waveforms is laborious. The
conventional techniques for analyzing these problems are
too simple and rigid to capture all the relevant disturbance
structure. A reliable automated system for disturbance
detection and classification has many advantages over a
manual one. These advantages include the speed of
processing, amount of data that can be processed, ease of
data collection and storage, reliability and cost.
Several methods for automated detection and
classification of disturbances have been proposed recently.
Some frequently used artificial intelligence (AI) based
classifiers are rule-based expert systems, fuzzy classification

Manuscript received February 12, 2012; accepted April 29, 2012.
This work was supported by the EC project SEE ERA NET PLUS under
grant ERA 078/01.


systems, artificial neural networks (ANN), and support
vector machines (SVM) [2]. All these techniques use feature
vectors derived from disturbance waveforms to classify
power quality events. Different digital signal processing
techniques can be used in the process of extraction features
that characterize PQ disturbances [3]. Among them, wavelet
transform has been used extensively in the last years.
Wavelet transform analysis approach is able to give
information about frequency contents of the recorded signal
and information about components time appearance. These
features make the wavelet transform well suited for the
analysis of the power system transients caused by various
PQ disturbances [4]. In [5], a comprehensive review on
using wavelet transform approach for processing of the
power quality disturbances is given. Here, we will consider
three wavelet based methods that are used for comparison
purposes later in the paper. In [6], Abdel-Galil et al. use a
learning-based method in order to classify the power
disturbances. A decision tree is created, using wavelet
analysis in the feature extraction process. The signal, which
is tested for power disturbances, is decomposed in 11 levels
and the energy of every obtained signal is calculated. The
reported overall accuracy is 90.4%. In [7], Haibo He et al.
use the same feature vector as [6], however they use a
different learning-based method. A type of neural network,
called SOLAR (self-organizing learning array), is used for
the classification of the power disturbances. The reported
overall accuracy is 94.93%. They have also done a
comparative study using SVM, obtaining accuracy, which is
in some cases are very close to the accuracy obtained using
SOLAR. In [8], wavelet norm entropy-based effective
feature extraction method for power quality disturbance
classification problem is presented. The disturbance
classification schema is performed with the wavelet neural
network (WNN). It performs a feature extraction and a
classification algorithm composed of a wavelet feature
extractor based on norm entropy and a classifier based on a
multi-layer perceptron. The reported overall accuracy is
95.71%.
In this paper, we present a new wavelet based method for
power quality disturbances detection and classification.
Similarly to [6] and [7], wavelet feature extraction technique
based on energy of detail and approximation coefficients is
used for automatic PQ disturbances classification. In order
Classification of Power Quality Disturbances
using Wavelets and Support Vector Machine
A. Milchevski
1
, D. Kostadinov
1
, D. Taskovski
1

1
Faculty of Electrical Engineering and Information Technologies, Ss Cyril and Methodius University-
Skopje,
Ruger Boskovik bb, 1000 Skopje, R. Macedonia, phone: +389 2 3099 107
[email protected]
http://dx.doi.org/10.5755/j01.eee.19.2.1213
25
ELEKTRONIKA IR ELEKTROTECHNIKA, ISSN 1392-1215, VOL. 19, NO. 2, 2013
to overcome the problem with the choice of the appropriate
wavelet we use two discrete wavelet transforms (DWT), one
with short filter and another with long filter in the proposed
automatic disturbance recognition and classification
procedure. The idea is to equally treat the analyzed data by
the both filters and to use representation that emphasizes the
uniqueness, selectivity and characterization of every
distinctive class of disturbance. The feature vector can be
constructed by concatenating the feature vectors obtained
after applying wavelet transform with both filters as shown
in Fig. 1. In most wavelet based methods rms values of
different sub-bands are used as feature vectors.
In order to classify the power disturbances we use SVM
as a classification method. Analyzing the properties of the
power disturbances we designed binary decision tree and a
SVM model is created for every node of the tree.
DWT using short filter DWT using long filter
compute rms value for
every subband
compute rms value for
every subband
concatenate rms values
Feature vector
Original input waveform

Fig. 1. Feature vector construction procedure.
II. DISCRETE WAVELET TRANSFORM
The continuous wavelet transform of a signal f(t) is
defined as
( , ) ( ) ( )
ab
CWT a b f t t dt

=

, (1)
where
1
( ) , ; 0
ab
t b
t a b a
a a

| |
=
|
\
.
The function (t) is the base function or the mother
wavelet and a and b, are the dilation and translation
parameters, respectively. Since the transformation is
achieved by dilating and translating the mother wavelet
continuously, it generates substantial redundant information.
Therefore, instead of continuous dilation and translation, the
mother wavelet may be dilated and translated discretely by
selecting
0
m
a a = and
0 0
m
b nb a = , where a
0
and b
0
are fixed
constants with a
0
> 1 and b
0
> 0, , m n Z and Z is the set of
integers [9]. The resulting expression is given with

0 0
0
0
1
[ , ] [ ] .
m
m
m
k
k nb a
DWT m n f k
a
a

=
(

= (
(

(2)
The simpler choice is to make a
0
= 2 and b
0
= 1. With
this, wavelet transform is called a dyadic-orthonormal
wavelet transform, and can be easily and quickly
implemented by filter bank techniques normally known as
Multi-Resolution Analysis (MRA) [10].
The Fig. 2 shows a MRA diagram, which is built and
performed by means of two filters: a high-pass filter with
impulse response h[n] and its low-pass mirror version with
impulse response g[n]. These filters are related to the type of
mother wavelet and can be chosen according to the
application. At each stage, the input signal is decomposed
into a coarse approximation signal (which can be considered
as a low-pass version of the input) and an added detail
signal (which can be considered as a high-pass version). The
approximation signal is further decomposed to produce new
coarser representation of the signal. After K levels of
decomposition, reference signal a
K
[n] with resolution
reduced by factor 2
K
with respect to the original signal, as
well as the detail signals d
K
[n], d
K-1
[n], ... d
1
[n] are
obtained. Each detail signal d
i
[n] contains precisely the
information that, together with the reference signal a
i
[n],
enables reconstruction of a
i-1
[n], which is the reference
signal at the next higher resolution.

Fig. 2. Wavelet decomposition over 3 levels.
III. SUPPORT VECTOR MACHINES
Support vector machines are a very popular supervised
machine learning methods used for classification and
regression analysis. The goal of a SVM method is to build a
model using a set of training examples each marked as
belonging into one of the possible classes. Using the model,
a prediction can be made for the class of a new sample.
Given a set of n training examples x
i
which belong in one
of two classes c
i
={-1,1} using SVM we can create a model
which can separate new samples of the classes. The task of
the classification process is to choose a hyperplane which
can best separate the two classes. The hyperplane is
described as

0
: 0 p w x b = , (3)
where w x denotes the dot product and w the normal vector
to the hyperplane. The parameter / b w determines the
offset of the hyperplane from the origin along the normal
vector w. We want to choose the parameters w and b to
maximize the margin, or distance between the parallel
hyperplanes that are as far apart as possible while still
separating the data. These hyperplanes can be described by
the equations:

1
2
: 1,
: 1.
p w x b
p w x b
=

(4)
26
ELEKTRONIKA IR ELEKTROTECHNIKA, ISSN 1392-1215, VOL. 19, NO. 2, 2013
The problem can be solved by minimizing
2 1
2
w , subject
to the constraint that the hyperplane should separate the
samples of the two classes correctly :
minimize
2 1
2
w ,
subject to
( ) 1.
i i
c w x b (5)
This problem can be expressed as

2
,
1
1
arg min arg max [ ( ) 1] ,
2
i
n
i i i
w b
i
w c w x b

=



`

)

(6)
where
i
are non-negative Lagrange multipliers. In this way,
most of the
i
are chosen to be zero. The
i


which

are not
zero correspond to the feature vectors which are hardest to
classify. These feature vectors are called support vectors
[11].

Fig. 3. Choice of support vectors.
In [12] and [13] soft margin SVM was introduced. When
the two classes are not linearly separable soft margin SVM
can still chose hyperplane which best separates the data.
This can be expressed as the following optimization
problem:
minimize
2
1
1
2
n
i
i
w c
=
+

,
subject to
( ( ) ) 1 , 0.
i i i i
c w x b | (7)
The slack variables,
i
, were introduced, which measure
the degree of misclassification of the feature vectors x
i ,
c > 0
is the penalty parameter of the error term, and
( , ) ( ) ( )
T
i j i j
K x x x x | | = is the kernel function. The kernel
function maps the feature vector into a vector space where
the feature vectors are linearly separable. In the proposed
method the kernel is defined by
( , ) ( ) ( )
T T
i j i j i j
K x x x x x x | | = = .
IV. PROPOSED METHOD
For the feature extraction process we use DWT, as used in
[6] and [7]. The DWT has been used intensely in the past
years and in the most cases it is a better choice for the
analysis of the PQ disturbances, compared to the discrete
Fourier transform (DFT), since it provides not only
frequency information, but also information about location
of the components. The wavelet analysis is in fact a measure
of similarity between the basis function (wavelets) and the
signal itself. Therefore, the selection of the most adequate
wavelet mother function to be used in the analysis is one of
the key factors in successful application of wavelets, not
only in power quality applications. As general rule, for
detection of short and fast (transient) disturbances, shorter
filters are proposed as better, while for slow transient
disturbances long filters are presented as particularly good
[9],[14]. This means that selection of the best filter for
detection and classification of PQ disturbances is not an easy
task and in general depends from the application.
In order to reduce the influence of the choice of the
wavelet we propose the use of two DWT with two different
wavelets, one with high support and one with low support.
Introducing the second wavelet transform in the feature
extraction process provides additional information about the
analyzed signal, which makes the classification more
accurate. The increased accuracy comes with the price of
increased computational complexity of the algorithm.
However, the additional wavelet transform allows fewer
levels of decomposition to be used, which reduces the
computational complexity of the algorithm. Additionally, we
design a classification algorithm which also reduces the
number of operations in the test phase.
The signal, which is tested for PQ disturbances, is first
decomposed in l-levels using discrete wavelet transform.
The energy of the detail and approximation coefficients at
each level of decomposition is used as feature vector, and is
calculated according following equations:

2
1
, 1, ,
N
i ij
j
ED d i l
=
= =

, (8)

2
1
N
l lj
j
EA a
=
=

, (9)
where d
ij
1, , i l = is the wavelet detail coefficient in the
wavelet decomposition from level 1 to level l and a
ij
is the
wavelet approximation coefficient in the wavelet
decomposition at level l. N is the total number of wavelet
coefficients at each level of decomposition, ED
i
is the
energy of detail coefficients at the decomposition level i and
EA
l
is the energy of the approximate wavelet coefficients at
decomposition level l. In this way, the size of the analyzed
data is significantly reduced and the original waveform is
represented with only l+1 coefficient. The same feature
vector is also used in [6] and [7].
The overall feature vector is obtained after applying
another wavelet transform and calculation of the energy of
detailed and approximation coefficients in the same manner.
The overall feature vector has length 2l+2. Increasing the
length of the feature vector will increase the computational
cost. With aim to make length of the feature vector and
27
ELEKTRONIKA IR ELEKTROTECHNIKA, ISSN 1392-1215, VOL. 19, NO. 2, 2013
computational cost comparable with other wavelet based
methods for detection and classification of PQ disturbances
we reduce the number of decomposition levels in the process
of feature vector extraction.

Fig. 4. Classification of the power disturbances using SVM decision tree.
Although there are many classification methods we have
chosen SVM as a main of-the-shelf machine learning
method. We have constructed binary decision tree shown on
Fig.4, where for every node a liner-SVM model is created.
The tree is designed analyzing the properties of the seven
signals. At the root node we have grouped the seven types of
signals into two groups in such way that they would be
easiest to separate. In the first group are the signals without
harmonic disturbances and in the other with harmonic
disturbances. The feature vectors extracted from the signal
from the second group will have higher values for the
coefficients corresponding to the energy in the higher
frequencies, thus making the two groups easy to classify.
The rest of tree is constructed in a similar way i.e. grouping
the signals into two groups in a way that will make the
classification easiest. At the leaf nodes the algorithm
separates the signals which are hardest to separate. The
designed decision tree is illustrated at Fig. 5.
The results with the use of the decision tree are similar
with the results using the typical one-against-all or one-
against-one approach. However, in the testing phase only
three decisions are made instead of seven, thus making this
approach faster. We have used the libSVM implementation
for MATLAB [15].
V. EXPERIMENTAL RESULTS
For comparison purposes the power disturbances are
modeled in the same way as in [6][8]. All these works
include the same disturbance types and the same pattern
numbers generated by parametric equations of data
(Table. I) for training and testing of the classification stage.
Seven different classes are considered, including the case
with no power disturbances: normal, swell, sag, harmonic,
outage, sag with harmonic and swell with harmonic,
denoted with C1, C2, C3, C4, C5, C6, C7, respectively. Ten
cycles are included in every signal with a sampling
frequency of 256 samples/cycle i.e. every signal has 2560
samples. The normal frequency is assumed to be 50Hz.
The learning for single binary classifier was done using
training data set with size of 1400 examples. In the training
data set each training class has size of 200 data examples.
The data sets with same size were used in the testing
process.
The choice of the number of decomposition level l has
significant influence on the process of classification.
Choosing higher l will, generally, bring more information in
the system and in that way higher accuracy. On the other
hand, higher number of decompositions means more
calculations i.e. more computational cost. In most of
proposed wavelet based methods for detection and
classification of power quality disturbances the level of
decomposition is set between 10 and 12. Since two DWTs
are used for extraction of feature vectors in the proposed
method we reduce the level of decomposition to l

=7.
Different pair of filters on the same training and test data
set was used in our experiments: Daubachies with length
from 2 to 20 (db2, db4, , db20), Coiflet with length 6, 12,
18, 24, 30 (coif6, , coif30), Beylkin 18, Vaidianathan 24
and two biorthogonal quadrature filter pairs (2
symmetric/symmetric and 2,6 symmetric/symmetric).
Coefficients of all these filters can be found in [16].
Table II shows obtained results when only one wavelet
transform is used in the process of feature vector extraction.
The influence of the used wavelet on the classification
results is evident. When two wavelet transforms with
different wavelets are applied, as explained in Section 1,
significant improvements in the classification processes are
obtained. Some of obtained results are given in Table III.
These results have very high classification accuracy rate.
The results also show that the filter v24, which is mainly
used for harmonic analysis [3], is not appropriate choice for
classification of PQ disturbances.

Fig. 5. Example of separating seven classes of data.

28
ELEKTRONIKA IR ELEKTROTECHNIKA, ISSN 1392-1215, VOL. 19, NO. 2, 2013
TABLE I. PQ DISTURBANCE MODELS.
Disturbance class Model Parameters
normal C1 ( ) sin( ) x t t e = /
swell C2
1 2
( ) (1 ( ( ) ( )))sin( ) x t A u t t u t t t e = + 0.1 0.8 s s ,
2 1
9 T t t T s s ,
sag C3
1 2
( ) (1 ( ( ) ( )))sin( ) x t A u t t u t t t e = 0.1 0.9 s s ,
2 1
9 T t t T s s
harmonic C4
1 3 5 7
( ) ( sin( ) sin(3 ) sin(5 ) sin(7 )) x t A t t t t e e e e = + + +
3 5
2
7
0.05 0.15, 0.05 0.15
0.05 0.15, 1
i


s s s s
s s =

outage C5
1 2
( ) (1 ( ( ) ( )))sin( ) x t A u t t u t t t e = 0.9 1 s s ,
2 1
9 T t t T s s
sag with
harmonic
C6
1 2
( ) (1 ( ( ) ( ))) x t A u t t u t t =
1 3 5
( sin( ) sin(3 ) sin(5 )) t t t e e e + +
0.1 0.9 s s ,
2 1
9 T t t T s s
2
3 5
0.05 0.15, 0.05 0.15, 1
i
s s s s =

swell with
harmonic
C7
1 2
( ) (1 ( ( ) ( ))) x t A u t t u t t = +
1 3 5
( sin( ) sin(3 ) sin(5 )) t t t e e e + +
0.1 0.9 s s ,
2 1
9 T t t T s s
2
3 5
0.05 0.15, 0.05 0.15, 1
i
s s s s =

Additionally, we compared the obtained results with the
results presented in [6], [7] and [8]. In [7] and [8], feature
vectors are extracted after applying wavelet transform with
db4 wavelet in 10 and 12 levels, respectively and have
length of 11 and 13 elements. The results are comparatively
presented in Table IV. As seen from Table IV, the
performance of the proposed wavelet classification methods
exceeds the performance of the classification methods
proposed in [6][8].
In order to analyze the computational complexity of the
proposed method we analyze the number of support vectors
obtained in the training process. The classification function
of the linear SVM is

1
( ) ( ),
m
T
i i i
i
f x sign y x x b
=
= +

(10)
where
i
x are the support vectors and m is the number of the
support vectors. It can be seen that the number of operations
depends of the number of the support vectors. In Table V the
number of support vectors is given for every SVM model of
the designed tree. It can be seen that due to the correct
grouping of the signals in most cases the classification is
very easy and the SVM requires very few support vectors.
The number of support vectors is largest for the SVM that
distinguishes the sags from the outages. This is result of the
fact that the two disturbances are modelled similarly and in
some cases, even for a human, can be difficult to distinguish.
Compared to default multi-class in the libSVM (1 vs 1) the
total number of support vectors is slightly reduced.
However, the proposed classification method does not use
all of the support vectors for a given test sample and in the
case when the signal is not sag or outage the number of
calculations is significantly reduced.
TABLE II. CLASSIFICATION PRECISION FOR DIFFERENT WAVELET FILTERS.
coif6 coif30 db2 db4 db20 v24
C1 100 100 100 100 100 100
C2 100 100 100 100 100 99,5
C3 90 83,5 77 78,5 75,5 78
C4 100 100 100 100 100 100
C5 91,5 91 78,5 81 83 78,5
C6 98 98 100 99,5 97,5 99,5
C7 99,5 99,5 100 99 100 99,5
coif6 coif30 db2 db4 db20 v24
Overall 97,00 96,00 93,6 94,0 93,7 93,6
TABLE III. CLASSIFICATION PRECISION FOR DIFFERENT PAIRS OF WAVELETS.

db4 &
coif30
db6 &
coif12
db6 &
coif30
db4 &
v24
coif6
& v24
C1 100 100 100 100 100
C2 100 100 100 100 100
C3 86,5 90 93 74 88,5
C4 100 100 100 100 100
C5 94,5 96 97,5 87,5 92,5
C6 98 100 98 100 99,5
C7 100 100 100 99,5 100
Overall 97,00 98,00 98,40 94,40 97,20
TABLE IV. PERFORMANCE COMPARISON OF CORRECT CLASSIFICATION
RESULTS.
Class
One
DWT
(db4)
Two
DWT
(db4 &
Coif30)
Ref.
[6]
(db2)
Ref.
[7]
(db4)
Ref.
[8]
(db4)
C1 100 100 100 100 100
C2 100 100 97 100 96,5
C3 78,5 86,5 76,5 87 88
C4 100 100 100 100 100
C5 81 94,5 90 80,5 85,5
C6 99,5 98 71,5 97 100
C7 99 100 98 100 100
Overall 94,00 97,00 90,40 94,93 95,714
TABLE V. NUMBER OF SUPPORT VECTORS PER SVM MODEL, TOTAL
NUMBER OF SUPPORT VECTORS FOR THE SVM-DECISION TREE AND THE
DEFAULT LIBSVM IMPLEMENTATION.

db4 &
coif30
db6 &
coif12
db6 &
coif30
db4 &
v24
coif6
& v24
model1 6 8 7 7 8
model2 2 2 2 2 2
model3 2 2 2 2 2
model4 131 101 96 177 108
model5 4 5 4 4 4
model6 4 5 4 4 4
Total 149 123 115 196 128
1 vs. 1 153 131 118 203 136
VI. CONCLUSIONS
In this paper we have presented a new method for
classification of power quality disturbances based on
29
ELEKTRONIKA IR ELEKTROTECHNIKA, ISSN 1392-1215, VOL. 19, NO. 2, 2013
discrete wavelet transform and support vector machine. High
classification accuracy rate of the proposed method is result
of the use of two wavelets, one with long support and one
with short support. Additionally, analysing the properties of
the power disturbances signals, we have designed a SVM
decision tree that reduces the number of operations made in
the testing phase. The presented results show superior
accuracy compared to similar works.
REFERENCES
[1] S. Taskin, H. Gokozan, Determination of the spectral properties and
harmonic levels for driving an induction motor by an inverter driver
under the different load conditions, Elektronika ir Elektrotechnika
(Electronics and Electrical Engineering), no. 2, pp.7580, 2011.
[2] W. R. A. Ibrahim, M. M. Morcos, Artificial intelligence and
advanced mathematical tools for power quality applications: A
survey, IEEE Trans. Power Delivery, vol. 17, no. 2, pp. 668673,
2002. [Online]. Available: http://dx.doi.org/10.1109/61.997958
[3] M. H. J. Bollen, I. Y. H. Gu, Signal processing of power quality
disturbances. Wiley-IEEE Press, 2006. [Online]. Available:
http://dx.doi.org/10.1002/0471931314
[4] G. Rata, M. Rata, C. Filote, Theoretical and experimental aspects
concerning Fourier and wavelet analysis for deforming consumers in
power network, Elektronika ir Elektrotechnika (Electronics and
Electrical Engineering), no. 1, pp. 6266, 2010.
[5] S. Chen, H. Y. Zhu, Wavelet Transform for Processing Power
Quality Disturbances, EURASIP Journal on Advances in Signal
Processing, 2007. [Online]. Available: http://dx.doi.org/10.1155/
2007/47695
[6] T. K. A. Galil, M. Kamel, A. M. Youssef, E. F. E. Saadany, M. M. A.
Salama, Power quality disturbance classification using the inductive
inference approach, IEEE Trans. Power Delivery, vol. 19, no. 10,
pp. 18121818, 2004. [Online]. Available:
http://dx.doi.org/10.1109/TPWRD.2003.822533
[7] H. He, J. A. Starzyk, A self-organizing learning array system for
power quality classification based on wavelet transform, IEEE
Trans. Power Delivery, vol. 21, no. 1, pp. 286295, 2006. [Online].
Available: http://dx.doi.org/10.1109/TPWRD.2005.852392
[8] M. Uyara, S. Yildirima, M. T. Gencoglub, An effective wavelet-
based feature extraction method for classification of power quality
disturbance signals, Journal Electric Power System Research, vol.
78, pp. 17471755, 2008. [Online]. Available:
http://dx.doi.org/10.1016/j.epsr.2008.03.002
[9] S. Santoso, E. J. Powers, W. M. Grady, P. Hofmann, Power quality
assessment via wavelet transform analysis, IEEE Trans. Power
Delivery, vol. 11, no. 2, pp. 924930, 1996. [Online]. Available:
http://dx.doi.org/10.1109/61.489353
[10] S. Mallat, A theory for multiresolution signal decomposition: the
wavelet representation, IEEE Trans. on Pattern Analysis and
Machine Intelligence, vol. 11, pp. 674693, 1989. [Online].
Available: http://dx.doi.org/10.1109/34.192463
[11] C. M. Bishop, Pattern recognition and machine learning. Springer,
2006.
[12] B. E. Boser, I. Guyon, V. Vapnik, A training algorithm for optimal
margin classifiers, in Proc. of the Fifth Annual Workshop on
Computational Learning Theory, ACM Press, 1992, pp. 144152.
[13] C. Cortes, V. Vapnik, Support-vector network, Machine Learning,
no. 20, pp. 273297, 1995. [Online]. Available:
http://dx.doi.org/10.1007/BF00994018
[14] E. Y. Hamid, Z. I. Kawasaki, H. Yoshida, H. Doi, Wavelet analysis
of voltage disturbances for power quality applications, Trans. Inst.
of Electrictrical Engineering of Japan, vol. 122-B, no. 2, pp. 323
330, 2002.
[15] C. C. Chang, C. J. Lin, LIBSVM - A Library for Support Vector
Machines. [Online]. Available: http://www.csie.ntu.edu.tw/
~cjlin/libsvm/
[16] M. V. Wickerhauser, Adapted wavelet analysis: from theory to
software. IEEE Press, New York, 1994.
30