0120321011460708 9



$%&'()*++,-..///01234564578%45602&,05908:.84:';0,*,.<=>?@.84:';A(.B@C%2+(+*'(<%23456()*++,-..///01234564578%45602&,05908:.84:';0,*,.<=>?@.5C%2+A
.BD:8+%3856(?'5&()*++,-..///01234564578%45602&,05908:.84:';0,*,.<=>?@.5C%2+.':8+%3856?'5&A

9EFG!H9!I

9
 JK
$84:5L5+8(M27+5N:5*O(?'P48P(>4Q%3&5+8P5(R(=48S'378+57(M2*5&&5:8L5*(T23/%P'3+%O(>4:%4'785

9
 U 

?5+8P(M5Q+2P*5*O(T2768+(V>T>(W%&,6'P7(T27,8,+'P(?54X'354X(Y'65+54(R(Z54+'4O(>4:%4'785
Y38(W272&5:'/8O(=48S'378+57(>765&(>4:%4'785O(>4:%4'785
['38(\8C%/%O(=48S'378+57(M2*5&&:8L5*(T23/%P'3+%O(>4:%4'785
@3:*8(\815L54+%O(>4Q%3&5+8P5O(=48S'378+57(Y'C'657(M53'+O(>4:%4'785
D389P(@6Q%47(V8754X54O(?'P48P(>4Q%3&5+8P5O(=48S'378+57(@+&5(<5L5(M5P57753O(>4:%4'785

] 9
 
Y65&'+(\8:%:%O(=48S'378+57(M2*5&&5:8L5*(T23/%P'3+%O(>4:%4'785
M2*5&&5:(^5'48(V5+*8QO(=48S'378+57(M2*5&&5:8L5*(T23/%P'3+%O(>4:%4'785
_8&535(W272&5($5P8&O(=48S'378+57(M2*5&&5:8L5*(T23/%P'3+%O(>4:%4'785
D3&5:8(Y5+38L5(\815L5O(=48S'378+57(M2*5&&5:8L5*(T23/%P'3+%O(>4:%4'785

>YY`-(abcdRedfg

h'Q'3'49'(M545X'&'4+(?%%6()*++,7-..///0&'4:'6'L09%&.:%/46%5:R:'7P+%,.A
()*++,7-..///0&'4:'6'L09%&.:%/46%5:R:'7P+%,.A

T''3Rh'S8'/'37().84:';0,*,.<=>?@.5C%2+.:87,65LM'&C'37*8,.ciA
T2C6895+8%4(D+*897().84:';0,*,.<=>?@.,5X'7.S8'/.,2C6895+8%4'+*897A
h'X87+'3().84:';0,*,.<=>?@.27'3.3'X87+'3A
@2+*%3(j28:'684'7().84:';0,*,.<=>?@.5C%2+.72C&8778%47k52+*%3j28:'684'7A

 
2
2!2" 2
  62#
 0120321011460708 9
 

$%&''()*++,-./012332401536+3(078.,9:;:

<=>)?@ABCD0.2<E&FG?B/HI.J

K3'.L5M'.37)
N.0@$%&''(*++@@@1OC-7M47M).37M41C6(1M51.,+.7,0=1(&(+GPQRS+73'.L5M'.37J$TCU)5-.U0$%&''(*++@@@1OC-7M47M).37M41C6(1M51.,+.7,0=1(&(+GPQRS+73'.L5M'.37+)CU)5-.U0DM.

S-'.540$R06(4M'0$%&''()*++,35)12332401536+,35C607'+,+:G3PVW>X>T),RFH)YFX'ZZY(Z.[R6G\]:+0,.'8C)(9)&M-.72^3C.,9::H_E>`aH:>HYE:abHH:E^-'(3;9'-C0^),9'
$%&''()*++,35)12332401536+,35C607'+,+:G3PVW>X>T),RFH)YFX'ZZY(Z.[R6G\]:+0,.'8C)(9)&M-.72^3C.,9::H_E>`aH:>HYE:abHH:E^-'(3;9'-C0^),9'-C0J
c$%&''()*++,-./012332401536+L40+,+:T3,OXA=(7E64@dN@?YZeR]Q'WR@4f-V<+/.0@8C)(9)&M-.72J

P)0-

G3C-7M4$e37'07'

S44

B-3@)0
Bf$Q))C0$%&''(*++@@@1OC-7M47M).37M41C6(1M51.,+.7,0=1(&(+GPQRS+.))C0+M-5&./0J
Bf$SC'&3-$%&''(*++@@@1OC-7M47M).37M41C6(1M51.,+.7,0=1(&(+GPQRS+)0M-5&+MC'&3-)J
Bf$R.'40$%&''(*++@@@1OC-7M47M).37M41C6(1M51.,+.7,0=1(&(+GPQRS+)0M-5&+'.'40)J
?'&0-$G3C-7M4)$%&''(*++@@@1OC-7M47M).37M41C6(1M51.,+.7,0=1(&(+.7,0=J

$%&''()*++@@@1)'M'53C7'0-1536+J

 
2
2!2" 2
  12#
 0120321011460708 9
 

)EF33B*HHG3.3I1+-37,JI12HBAA;C?UCAHG+22.,WHMK+7G3NAP6

d1-3)94c7
b.57)01-3)G4c7)G2.//7,b.57)01-3)G4c7)L70.+/3b.57)01-3)G4c7)/.,K7,
&-01,2.341-
d1,)e7.L7,G)EF33B*HHSSSJQ+,-./-.G41-./J+2BJ.IJ4LH4-L7fJBFBH$%&'(H4-01,2.341-H,7.L7,GP
d1,)(+3F1,G)EF33B*HHSSSJQ+,-./-.G41-./J+2BJ.IJ4LH4-L7fJBFBH$%&'(H4-01,2.341-H.+3F1,GP

g7WS1,LG
(-L,14L)EF33B*HHSSSJQ+,-./-.G41-./J+2BJ.IJ4LH4-L7fJBFBH$%&'(HG7.,IFMG+RQ7I3N(-L,14LP)(B/45.G4)EF33B*HHSSSJQ+,-./-.G41-./J+2BJ.IJ4LH4-L7fJBFBH$%&'(HG7.,IFM
G+RQ7I3N(B/45.G4P)(+K27-37L)e7./43W)EF33B*HHSSSJQ+,-./-.G41-./J+2BJ.IJ4LH4-L7fJBFBH$%&'(HG7.,IFMG+RQ7I3N(+K27-37Lh;@e7./43WP)i/.GG4jI.341-
EF33B*HHSSSJQ+,-./-.G41-./J+2BJ.IJ4LH4-L7fJBFBH$%&'(HG7.,IFMG+RQ7I3Ni/.GG4jI.341-P)k7I4G41-)9+BB1,3)9WG372)EF33B*HHSSSJQ+,-./-.G41-./J+2BJ.IJ4LH4-L7fJBFBH$%&'(HG
G+RQ7I3Nk7I4G41-h;@9+BB1,3h;@9WG372P)lfB7,3)9WG372)EF33B*HHSSSJQ+,-./-.G41-./J+2BJ.IJ4LH4-L7fJBFBH$%&'(HG7.,IFMG+RQ7I3NlfB7,3h;@9WG372P)d1,S.,L)iF.4-4-K
EF33B*HHSSSJQ+,-./-.G41-./J+2BJ.IJ4LH4-L7fJBFBH$%&'(HG7.,IFMG+RQ7I3Nd1,S.,Lh;@iF.4-4-KP)d+ccW)m+.-34jI.341-)'F71,W)&
EF33B*HHSSSJQ+,-./-.G41-./J+2BJ.IJ4LH4-L7fJBFBH$%&'(HG7.,IFMG+RQ7I3Nd+ccWh;@m+.-34jI.341-h;@'F71,Wh;@&P)b.2L.-4
EF33B*HHSSSJQ+,-./-.G41-./J+2BJ.IJ4LH4-L7fJBFBH$%&'(HG7.,IFMG+RQ7I3Nb.2L.-4P)bW9mn)EF33B*HHSSSJQ+,-./-.G41-./J+2BJ.IJ4LH4-L7fJBFBH$%&'(HG7.,IFMG+RQ7I3NbW9m
o7,.-K5.3)n+-.5)EF33B*HHSSSJQ+,-./-.G41-./J+2BJ.IJ4LH4-L7fJBFBH$%&'(HG7.,IFMG+RQ7I3Ne75.W.G.h;@o7,.-K5.3h;@n+-.5P)9b9)p.37S.W
EF33B*HHSSSJQ+,-./-.G41-./J+2BJ.IJ4LH4-L7fJBFBH$%&'(HG7.,IFMG+RQ7I3N9b9h;@p.37S.WP)'G+5.2131)EF33B*HHSSSJQ+,-./-.G41-./J+2BJ.IJ4LH4-L7fJBFBH$%&'(HG7.,IFM
G+RQ7I3N'G+5.2131P)R.I5B,1B.K.341-)EF33B*HHSSSJQ+,-./-.G41-./J+2BJ.IJ4LH4-L7fJBFBH$%&'(HG7.,IFMG+RQ7I3NR.I5B,1B.K.341-P)R.I5S.,L)IF.4-4-K
EF33B*HHSSSJQ+,-./-.G41-./J+2BJ.IJ4LH4-L7fJBFBH$%&'(HG7.,IFMG+RQ7I3NR.I5S.,Lh;@IF.4-4-KP)L7I4G41-)G+BB1,3)GWG372
EF33B*HHSSSJQ+,-./-.G41-./J+2BJ.IJ4LH4-L7fJBFBH$%&'(HG7.,IFMG+RQ7I3NL7I4G41-h;@G+BB1,3h;@GWG372P)7fB7,3) GWG372
EF33B*HHSSSJQ+,-./-.G41-./J+2BJ.IJ4LH4-L7fJBFBH$%&'(HG7.,IFMG+RQ7I3N7fB7,3h;@GWG372P)4-37,7G3)4-)/7.,-4-K)EF33B*HHSSSJQ+,-./-.G41-./J+2BJ.IJ4LH4-L7fJBFBH$%&'(HG
G+RQ7I3N4-37,7G3h;@4-h;@/7.,-4-KP)/7.,-4-K).IF47T727-3)EF33B*HHSSSJQ+,-./-.G41-./J+2BJ.IJ4LH4-L7fJBFBH$%&'(HG7.,IFMG+RQ7I3N/7.,-4-Kh;@.IF47T727-3P)/7.,-4-K
EF33B*HHSSSJQ+,-./-.G41-./J+2BJ.IJ4LH4-L7fJBFBH$%&'(HG7.,IFMG+RQ7I3N/7.,-4-Kh;@2134T.341-P)2134T.G4)R7/.Q.,)EF33B*HHSSSJQ+,-./-.G41-./J+2BJ.IJ4LH4-L7fJBFBH$%&'(
G+RQ7I3N2134T.G4h;@R7/.Q.,P

$%&'()*)$+,-./)&-01,2.345.)6)78&99:*);<=>8?>@A)6B8&99:*);@?C8>D>?
6) )EF33BG*HHGIF1/.,JK11K/7JI1J4LHI43.341-GM+G7,N/;+0(,%(((($OF/N7-P66 )EF33BG*HHL1.QJ1,KH31IH;<=>8?>@AP66

EF33B*HH4LJB1,3./K.,+L.J1,KHM,70NR,1SG7O21LNT47SQ1+,-./OQ1+,-./NC;UP66 )EF33B*HHG4-3.;J,4G375L4534JK1J4LHQ1+,-./GHL73.4/M4LNAA<DP

)EF33BG*HHG7.,IFJI,1GG,70J1,KHMVN;<=>8?>@AP
)EF33BG*HHSSSJG3.3I1+-37,JI12HP

)EF33B*HHG3.3I1+-37,JI12HBAA;C?UCAHG+22.,WHMK+7G3NAP6

X722Y   Z22"[2\02]

!7^ _

`Y`  !" \0 aX722Y   Z2

 
2
2!2" 2
  #2#
 JUITA
Jurnal Informatika
Vol. 9 No. 1, May 2021

PREFACE

Assalaamu’alaikum Wr. Wb.

With thanks to Allah, JUITA Volume 9 Number 1, which is the first issue in 2021, has been able
to be presented to the readers of academics, practitioners, and students. In this edition, we present
articles as a result of research covering applications and developments in image and signal
processing, data mining, games, software engineering, information retrieval, android programming,
and machine learning. Our gratitude goes to all those who have helped, especially to the authors,
the editorial board and reviewers, and the technical editor team, for your willingness to take the
time to prepare the manuscript for this journal.

As in the previous issue, we need to say that JUITA is published twice a year (2 numbers),
namely in May and November. Starting from Volume 9, JUITA uses the language of instruction for
the manuscript in English. To maintain consistency and editorial quality, JUITA adopts the IEEE format
with modifications to the font size and layout. Likewise, writing citations and references using the
IEEE style. We sincerely hope that the criticism and suggestions from readers will be for improvement
for the sake of improving the quality of this journal.

Wassalaamu’alaikum Wr. Wb.

Editor.

ii
 JUITA
Jurnal Informatika
Vol. 9 No. 1, May 2021

TABLE OF CONTENTS

i. Front Cover
ii. Editor Preface
iii. Table of Content

Japanese Hiragana Handwriting Pattern Recognition Using Template Matching

Correlation Method
Imam Riadi, Abdul Fadlil, Putri Annisa.................................................................................. 1

Comparison of Steganography Using the Discrete Cosine Transform Method on Image

Based Bilinear, Nearest Neighbor, and Spline Interpolation
Garno Garno, Adhi Rizal, Arip Solehudin, Reza Ekstanza, Dadang Yusup............................. 9

An Approach of Brain-Computer Interface Electroencephalography for Measuring Visual

Height Intolerance
Moch Yusuf Asyhari, Dhomas Hatta Fudholi, Fery Luvita Sari……......................................... 17

Data Mining for Potential Customer Segmentation in the Marketing Bank Dataset A'la
Maulida Ayu Fitriani, Dany Candra Febrianto....................................................................... 25

A Survey of Data Mining Techniques for Smart Museum Applications

Shinta Puspasari, Ermatita Ermatita..................................................................................... 33

Compression Analysis Using Coiflets, Haar Wavelet, and SVD Methods

Muhamad Aznar Abdillah, Anton Yudhana, Abdul Fadlil...................................................... 43

Use of Wavelets in Electrocardiogram Research: a Literature Review

Darwan Darwan, Hindayati Mustafidah............................................................................... 49

Development of an Android-Based Sign Language Education Game Using a Scrum-Game

Approach
Imam Fauzy Muldani Rachmat, Gazali Gazali....................................................................... 57

Indonesian Plate Number Identification Using YOLACT and Mobilenetv2 in the Parking
Management System
I Kadek Gunawan, I Putu Agung Bayupati, Kadek Suar Wibawa, I Made Sukarsa,
Laurensius Adi Kurniawan..................................................................................................... 69

Maturity Level of ITSM Analysis Using ITIL V3 Framework in State Electricity Enterprise
Purwokerto
Resad Setyadi, Enggar Priyatiningsih.................................................................................... 77

iii
 JUITA
Jurnal Informatika
Vol. 9 No. 1, May 2021

Decision Support System for Service Quality Using SMART and Fuzzy ServQual Methods
Sri Lestari, Muhammad Reza Romahdoni............................................................................. 83

A New Approach in Query Expansion Methods for Improving Information Retrieval

Lasmedi Afuan, Ahmad Ashari, Yohanes Suyanto................................................................. 93

Goal-Oriented Requirements Engineering: State of the Art and Research Tren

Rosa Delima, Retantyo Wardoyo, Khabib Mustofa............................................................... 105

A Deep Learning Using DenseNet201 to Detect Masked or Non-masked Face

Faisal Dharma Adhinata, Diovianto Putra Rakhmadani, Merlinda Wibowo, Akhmad
Jayadi..................................................................................................................................... 115

Improving Neural Network Performance with Feature Selection Using Pearson

Correlation Method for Diabetes Disease Detection
April Firman Daru, Mohammad Burhan Hanif, Edi Widodo................................................. 123

The Empirical Comparison of Machine Learning Algorithm for the Class Imbalanced
Problem in Conformational Epitope Prediction
Binti Solihah, Azhari Azhari, Aina Musdholifah..................................................................... 131

iv
 JUITA: Jurnal Informatika e-ISSN: 2579-8901; Vol. 9, No. 1, May 2021

Use of Wavelets in Electrocardiogram Research:

a Literature Review
Darwan1, Hindayati Mustafidah2*
1
Mathematics Education, FITK, IAIN Syekh Nurjati Cirebon, Indonesia
2
Informatics Engineering, Universitas Muhammadiyah Purwokerto, Indonesia
1darwan@syekhnurjati.ac.id
2*corr-author: h.mustafidah@ump.ac.id

Abstract - Currently the introduction and detection of
heart abnormalities using electrocardiogram (ECG) is
very much. ECG conducted many research approaches in
various methods, one of which is wavelet. This article aims
to explain the trends of ECG research using wavelet
approach in the last ten years. We reviewed journals with
the keyword title "ecg wavelet" and published from 2011
to 2020. Articles classified by the most frequently discussed
topics include: datasets, case studies, pre-processing,
feature extraction and classification/identification
methods. The increase in the number of ECG-related
articles in recent years is still growing in new ways and
methods. This study is very interesting because only a few
researchers focus on researching about it. Several
approaches from many researchers are used to obtain the
best results, both by using machine learning and deep
learning. This article will provide further explanation of
the most widely used algorithms against ECG research
with wavelet approaches. At the end of this article, the
critical aspects of ECG research can be done in the future,
namely the use of data in the form of signals and images,
as well as the use of deep learning to be a very large
opportunity for researchers.
and Indonesia [2]. Therefore, we are expected to
maintain the condition of the body, especially the heart
in order to stay healthy.
World Health Organization (WHO) data in 2015
shows 17.7 million people worldwide die from
cardiovascular disease (heart) or 45% of the 39.5 million
deaths worldwide [3]. According to the AHA (America
Heart Association) nearly one in three people die from
heart disease. According to the Ministry of Health (2020)
heart disease (especially coronary) is the highest cause of
death, followed by cancer, diabetes mellitus with
complications, tuberculosis, then chronic obstructive
pulmonary disease (COPD).
To maintain the heart condition we are expected to
always do a heart check. Heart condition checks are
performed using aids such as: electrocardiogram (ECG),
blood test, nuclear heart scanning, cardiac
catheterization, cardiac training test, echocardiography
and coronary angiography [4]. A frequent and common
tool used to check for heart abnormalities is with an
electrocardiogram (ECG) (Fig. 1).

Keywords: ECG, wavelet, dataset, pre-processing, feature

extraction

I. INTRODUCTION
Humans have several very important organs, one of
which is the heart. Maintenance of human heart
conditions is highly recommended, because this organ
has a very vital role. Maintaining the condition and
maintaining the heart early on is something very good.
Because heart malfunction can result in sudden death. In
recent years heart defects have still topped the list of
deaths worldwide. Worldwide deaths are caused by heart
defects [1]. Heart defects in 2019 are the cause of one-
third of all deaths in the world, as well as the ever-
increasing number of deaths. Some of the countries with
the highest number of deaths from heart disease in 2019
were China, followed by India, Russia, the United States, Fig. 1 Electrocardiogram [5]

Use of Wavelets in Electrocardiogram ... | Darwan, Mustafidah, H., 49 – 56 49

JUITA: Jurnal Informatika e-ISSN: 2579-8901; Vol. 9, No. 1, May 2021

Because of the importance of keeping the heart
condition healthy and controlled, there are many studies
whose case studies use the heart. Many approaches are
used to obtain good performance. So with the correct
method of detecting this disease it is possible to apply a
more directed treatment [1]. One approach that is often
used is to use the wavelet method. Wavelet method is
widely utilized in the pre-processing stage as well as
feature extraction. This study tried to study literature
related to ECG using wavelet approach within ten years
(2011-2020). With the conduct of literature review is
expected to obtain a road map related to future researches.
field of basic and clinical sciences. Members of the
Physionet team are actively engaged in innovative work
on physiological signal analysis, both from a basic and
translation perspective. The Physionet platform is
managed by members of the MIT Laboratory for
Computational Physiology. Other core laboratories of
Physionet Resources are Margaret and H.A. Rey Institute
for Nonlinear Dynamics at Beth Israel Deaconess
Medical Center. Some of the databases provided include
MIT-BIH, Europe ST-Database, Fantasia Database, St-
Petersburg, Creighton University database (CUDB),
PTB diagnostic ECG database, and others.

II. METHOD B. SID Medical Technology Co. Ltd.

Research related to electrocardiogram (ECG) has Looking at its website SID Medical was founded in
been widely done by many researchers. From the 2003, which is a medical technology company located in
researcher's research, ECG research has been conducted Shanghai (China) [11]. In December 2015, SID medical
by Pan and Tompkins [6]. Furthermore, many began offering a cloud-based ECG Application Program.
researchers who conducted ECG research also such as With our PC and/or Mobile software installed in the
[7] whose research related to heart abnormalities Cloud. Each patient can upload ECG data and get an
arrhythmia using fuzzy logic method. Various method analysis report. Meanwhile, ECG specialists working
approaches are used to obtain a good end result, such as with SID Medical can download and consult with
fuzzy, wavelet, machine learning or statistical methods patients
[8]. There are even those who use tools (CSA) on Linux In the first stage of the document search results collected
[9]. In this study, researchers tried to conduct research in as many as 97 that researchers obtained. The second
terms of literature studies related to electrocardiograms stage of 97 documents that match the criteria sought
(ECG). (ECG with wavelet method) there are 38 documents. The
Researchers began tracing literature studies related to distribution of the appropriate article search results (38
journals that discussed ECG and used wavelet methods. articles) can be seen in Fig.3. So at this last stage,
ECG research using wavelets is spread in the journals of researchers analyzed the contents of each document
several disciplines such as computer science, electrical based on a predetermined classification scheme.
engineering, applied sciences, and others. Searches were
conducted on several publication database sites
published from 2011 to 2020 with the keyword "ECG
Wavelet", and restricted to the field of Computer
Science.
In this study, we looked at several related journals
("ecg wavelets") whose data was retrieved using data
from Physionet and SID Medical Technology Co. Ltd.
A. Physionet
Physionet is one of the research resources for
Physiological Signals established in 1999 under the
auspices of the National Institutes of Health (NIH) as in
Fig. 2 Physionet website [10]
Fig. 2. Physionet primary and ongoing mission is to
catalyze research and education in the field of
biomedical, by offering free access to physiological and
clinical databases. So Physionet provides free data-
related access for research and educational purposes.
Physionet also held a Computing in Cardiology
conference, as well as an annual series of challenges,
which focused its research on unsolved problems in the

50 Use of Wavelets in Electrocardiogram ... | Darwan, Mustafidah, H., 49 – 56

 JUITA: Jurnal Informatika e-ISSN: 2579-8901; Vol. 9, No. 1, May 2021

for pre-processing that does not use wavelets and uses

Number of Articles by Year other methods (Table I).
7 B. Feature Extraction
6
The extraction phase of this feature is one of the
4 4 4 stages that is often used in research related to Artificial
3 3 3 Intelligence. Related literature review of this study
2 2
almost 67 % paper used all using wavelet at the
extraction stage of its feature. With the use of Discrete
Wavelet Transform-DWT method consists of 50%
journals used using such methods include: [15], [18],
2011 2012 2013 2014 2015
[20], [24-25], [28-32], [35], [38], and [41]. Continuous
2016 2017 2018 2019 2020 Wavelet Transform (CWT) include: [17], [21], [23], and
[39-40]. Wavelet Packet Decomposition (WPD): [33],
Fig. 3 number of articles by year [43], and [48]. Wavelet Packet Transform (WPT): [26],
and Wavelet Reconstruction [41]. Some researchers are
From several case studies that are often examined in using methods other than Wavelet at the extraction stage
research in the case of ECG and wavelets mostly based of the feature as seen in Table II.
on the paper obtained that is related to Arrhythmia. From TABLE I
studies using arrhythmia case studies in general there are USE OF PRE-PROCESSING OTHER THAN WAVELETS
10 studies [12-13], [16-17], [21],[25-26],[28],[38],[43].
Atrial fibrilation mentioned specifically there are four Pre-Processing Years Author
studies [27] [36],[46],[48]. Using normal data there are Baseline Wander Removal 2011 [13]
three studies [16],[39],[42]. Ventricular Tachyarrhytmia QRS Complex Detection 2012 [15]
there are two studies [16],[37]. Other researches include Spectral Analysis, Baseline Wander
Peak Detection R [15], Intracardiac Atrial Fibrillation Removing 2012 [16]
(IAF) and Myaocard Infarct [16], Ischemia [18], Segmentation 2012 [17]
Atherosclerosis [24], Atrial Fibrillation-Ventricular QRS Subtraction 2013 [18]
Fibrillation-Ventricular Contraction [32], Coronary
Hidden Markov Model 2013 [20]
Artery Disease [33], Premature Ventricular Contraction Pattern Identification (Local & Global
and Trial Premature Contraction [42], and ECG signal Pattern) 2013 [21]
denoising [45]. PCA 2013 [24]
Filtering raw signal and extraction of
III. RESULTS AND DISCUSSION beats 2014 [25]
Systematically this study focused on 38 journals P & R peak detection 2015 [27]
starting from 2011 to 2020 related to ECG using Denoising using notch filter 2015 [29]
wavelets from both pre-processing, feature extraction
Noise Repair 2015 [30]
and classification.
Denoising 2016 [31]
A. Pre-Processing Key Features and Frequencies 2016 [32]
ECG related research mostly goes through several Denoising 2018 [38]
stages, namely pre-processing, character extraction and Baseline Drift Removal and Denoising,
classification/identification. While the use of wavelets Noise Removal 2018 [39]
can be used at the pre-processing stage and most are also Data Denoising and Data Segmentation 2018 [40]
used at the stage of feature extraction. Some even do not Noise Identification 2018 [41]
go through the pre-processing stage and go directly to the
Mean 2019 [41]
characteristic extract. Wavelet methods used in the pre-
processing phase based on the journals used are Wavelet
Transform [12],[42],[47], Wavelet Decomposition [14],
Discrete Wavelet Transform-DWT [19],[22],[34-37],
[43-44], [1], Transform-WPT Package Wavelet [46]. As

Use of Wavelets in Electrocardiogram ... | Darwan, Mustafidah, H., 49 – 56 51

JUITA: Jurnal Informatika e-ISSN: 2579-8901; Vol. 9, No. 1, May 2021
TABLE II Accuracy using (1), sensitivity to (2), and specificity
FEATURE EXTRACTION METHODS with (3) [49]:
Feature Extraction Years Author
Beat Normalitation 2013 [19] ்௉ା்ே
Accuracy = x 100% (1)
Peak R & Interval RR 2013 [22] ்௉ା்ேାி௉ାிே
Thresholding and Run-Length
்௉
Encoding 2017 [34] Sensitivity = ்௉ାிே x 100% (2)
Recurrence quantification analysis
(RQA) 2017 [36]
்ே
Segmentation 2018 [37] Specificity = ்ேାி௉ x 100% (3)
Statistic (mean, standard deviation,
kurtosis and skewness) 2018 [42]
where:
P,Q,R,S,T Peak 2019 [43] TP = True Positive,
Histogram 2020 [44] TN = True Negative,
FP = False Positive, and
FN = False Negative.
C. Classification & Performance From the above exposure can be presented overall
At this stage it is mostly related to classification or research related to ECG with wavelet approach, and the
identification. This identification stage is used many methods used and some of them list the results of
methods include: Artificial Neural Network, Support performance can be seen in Table IV.
Vector Machine, Probabilistic Neural Network, and
Convolution Neural Network. The selection of applied IV. CONCLUSION
methods is usually based on the use of data. The use of ECG case studies are very varied to be raised in
the data used will affect the selection of methods at this research. The use of data used by some researchers uses
stage. Classification or identification stage in addition to data available from Physionet with its various data banks.
being able to identify or classify data there are usually In addition, many researchers are taking data directly
some researchers looking for performance. Performance from patients. Data processing in pre-processing is very
that is often used include accuracy, sensitivity and diverse from each researcher, which surely the output of
specificity. In finding the level of accuracy, sensitivity the data presented will be very useful on the extract of
and specificity by using confusion matrix [49]. The use features. From the paper used in this literature review
of Matrix Confusion is one of the methods used to obtain almost 79.5% use wavelets at the extracting stage of its
evaluation results based on matrix tables [50]. characteristics, as well as wavelet methods used are also
TABLE III diverse. Variations in the use of machine learning
MODEL CONFUSION MATRIX [50] algorithms can be used in the classification or
Classified identification stage such as Artificial Neural Network,
Correct Classification Support Vector Machine, Probabilistic Neural Network,
+ -
+ TP FN and Convolution Neural Network. Future Work research
- FP TN is very wide open related to electrocardiogram (ECG),
both the use of data in the form of signals and images.
ECG research using Deep Learning is still very little, so
this is a very big opportunity for researchers in
researching ECG using such methods.

52 Use of Wavelets in Electrocardiogram ... | Darwan, Mustafidah, H., 49 – 56

 JUITA: Jurnal Informatika e-ISSN: 2579-8901; Vol. 9, No. 1, May 2021
TABLE IV
ECG RESEARCH WITH WAVELETS APPROACH
Years Approach The Highest Performance
2011 Wavelet Transform[12], Baseline Wander Removal; Fuzzy Wavelet Sensitivity from MIT-BIH: 99,77
Learning Vector Quantization (FWLVQ) [13], Wavelet %; Sensitivity from Europe: 99,81
Decomposition; Thresholding & Wavelet Reconstruction [14] %; Accuracy: 90,20 %
2012 QRS Complex Detection; DWT [15], Spectral Analysis, Baseline Accuracy: 87,42 %; Sensitivity:
Wander Removing; 6-level Wavelet Transformation Decomposition; 87 %; Specificity: 95 %
ANN Backpropagation [16], Segmentation; Continuous Wavelet
Transform (CWT); ANN Backpropagation [17]
2013 QRS Subtraction; DWT & Morpology Feature Calculation; SVM Accuracy: 93,63 %; Sensitivity:
[18], DWT; Beat Normalization; SVM [19], Hidden Markov Model; 95,20 %; Specificity: 93,29 %;
Discrete Wavelet Transform (DWT) [20], Pattern Identification Accuracy Local Pattern 1: 73,3
(Local & Global Pattern); Continuous Wavelet Transform (CWT) %; Accuracy Local Pattern 2:
[21], Discrete Denoised Wavelet; R Peak & Interval RR [22], 75,0 %;
Coefficient Wavelet Transform (CWT) – Morlet [23], PCA; Discrete Accuracy Global Pattern: 86,6 %;
Wavelet Transform (DWT); SVM [24]
2014 Filtering raw signal and extraction of beats; Discrete Wavelet Accuracy : 97,92 %
Transform (DWT); Multi-Level Perceptron NN [25], Wavelet Packet
Transform (WPT); Probabilistic Neural Network (PNN) [26]
2015 P & R peak detection; Stationary Wavelet Transformation; SVM Sensitivity: 97,00 %; Specificity :
[27], Discrete Wavelet Transform (DWT) & Dual Tree 97,10 %; Sensitivity DWT: 91,23
Complex Wavelet Transform (DTCWT); Multi- %; Sensitivity DTCWT: 91,23 %
layer Backpropagation Neural Network [28], Denoising using notch
filter; Discrete Wavelet Transform (DWT); Statistic (mean, variance,
standard deviation, entropy) [29], Noise Repair; DWT-Daubechies
[30]
2016 Denoising; Discrete Wavelet Transform (DWT) [31], Key Features Accuracy : 96,89 %
and Frequencies; Discrete Wavelet Transformation; SVM [32]
2017 Wavelet Packet Decomposition (WPD) Level 4; K-Nearest Accuracy: 100%; Sensitivity :
Neighbors (KNN) [33], Discrete Wavelet Transformation (DWT); 99,64 %; Specificity : 99,70 %
Thresholding and Run-Length Encoding [34], DWT (Sym8 &
Coeiflet4); Thresholding - Invers DWT [35], Discrete Wavelet
Transform (DWT); Recurrence quantification analysis (RQA);
Probabilistic Neural Network (PNN) [36]
2018 Daubechies wavelet 6 (db6); Segmentation; Eleven Layers Of Accuracy: 99,23 %; Sensitivity:
Convolutional Neural Network (CNN) [37], Denoising; Discrete 99,41 %; Specificity: 98,91 %;
Wavelet Transform; Wavelet Network Classifier [38], Baseline Drift Accuracy Normal: 84 %;
Removal and Denoising, Noise Removal; Continuous Wavelet Accuracy PVC: 98 %; Accuracy
Transform (CWT) and Wavelet Analysis [39], Data Denoising and APC: 86 %
Data Segmentation; CWT; CNN [40], Noise Identification; Inverse
Discrete Wavelet Transform (IDWT) - Sym8 [41], Transformasi
Wavelet – Haar; Statistic (mean, standard deviation, kurtosis and
skewness); Random Forest and information gain analysis [42]
2019 DWT db8 Decomposition Level 8; P,Q,R,S,T Peak; Intelligence Sensitivity : 99,58%
Decision Rule [43], Wavelet Decomposition; Coefficient Processing;
Wavelet Reconstruction [44], Mean; Wavelet Decomposition - Haar
& Symlet [45]
2020 (DWT) Wavelet Based on Atomic Function & Z-Score; Decision Accuracy: 98, 90 %; Sensitivity:
Fine Tree [45], Wavelet Packet Transform (WPT); Histogram; ANN 98,70 %; Specificity: 98,90 %
[46], Wavelet Transform (Comparison 14 Wavelet) [47]; Wavelet
Decomposition – daubechies; Convolution Neural Network [48]

REFERENCES Recognition of ECG signals using wavelet based on

atomic functions,” Integr. Med. Res., pp. 1–12, 2020, doi:
[1] A. Hernandez-matamoros and H. Fujita, “ScienceDirect 10.1016/j.bbe.2020.02.007.

Use of Wavelets in Electrocardiogram ... | Darwan, Mustafidah, H., 49 – 56 53

JUITA: Jurnal Informatika e-ISSN: 2579-8901; Vol. 9, No. 1, May 2021
[2] Gading and Anna, “Penyakit Jantung Penyebab
Kematian Utama di Dunia Artikel ini telah tayang di
Kompas.com dengan judul ‘Penyakit Jantung Penyebab
Kematian Utama di Dunia’, Klik untuk baca:
https://lifestyle.kompas.com/read/2020/12/14/10160752
0/penyakit-jantung-penyebab-ke,” Kompas.com.
https://lifestyle.kompas.com/read/2020/12/14/10160752
0/penyakit-jantung-penyebab-kematian-utama-di-
dunia?page=all (accessed Jan. 26, 2021).
[3] Biro Komunikasi dan Pelayanan Masyarakat, “Penyakit
Tidak Menular Kini Ancam Usia Muda,” Kementeri.
Kesehat. RI, pp. 7–9, 2020, [Online]. Available:
https://www.kemkes.go.id/article/view/20070400003/pe
nyakit-tidak-menular-kini-ancam-usia-muda.html.
[4] J. Y. J. K. U. Kang and Y. Lee, “Coronary heart disease
optimization system on adaptive-network- based fuzzy
inference system and linear discriminant analysis
( ANFIS – LDA ),” 2013, doi: 10.1007/s00779-013-
0737-0.
[5] P. Siwindarto, “Electrocardiograph (ECG / EKG),”
Brawijaya.
http://instrumentasi.lecture.ub.ac.id/electrocardiograph/
(accessed Mar. 10, 2021).
[6] J. Pan and W. J. Tompkins, “A Real-Time QRS
Detection Algorithm,” IEEE Trans. Biomed. Eng., vol.
BME-32, no. 3, pp. 230–236, 1985, doi:
10.1109/TBME.1985.325532.
[7] J. Cabello, D.; Barra, S.; Ruiz, R.; Zapata, E.L.; and Mira,
“FUZZY CLUSTERING: APPLICATION TO THE
DIAGNOSIS OF VENTRICULAR ARRYTHMIAS,”
IEEE Eng. Med. Biol. Soc. 10TH Annu. Int. Conf., no.
Cardiac Arrhythmia Analysis, 1988, doi: CH2566-
8/88/0000--0005.
[8] A. Minchóle, F. Jager, and P. Laguna, “Discrimination
between demand and supply ischemia episodes in holter
recordings,” Annu. Int. Conf. IEEE Eng. Med. Biol. -
Proc., pp. 2579–2582, 2007, doi:
10.1109/IEMBS.2007.4352856.
[9] T. H. Tan, C. S. Chang, Y. F. Chen, and C. Lee,
“Implementation of a portable personal EKG signal
monitoring system,” Lect. Notes Comput. Sci. (including
Subser. Lect. Notes Artif. Intell. Lect. Notes
Bioinformatics), vol. 4901 LNCS, pp. 122–128, 2008,
doi: 10.1007/978-3-540-77413-6_16.
[10] Physionet, “Physionet,” 1970. https://physionet.org/
(accessed Mar. 10, 2021).
[11] S. Medical, “SID Medical,” 2003.
http://www.sidmedical.cn/en/index.asp (accessed Mar.
10, 2021).
[12] L. Y. Di Marco and L. Chiari, “A wavelet-based ECG
delineation algorithm for 32-bit integer online
processing,” Biomed. Eng. Online, vol. 10, pp. 1–19,
2011, doi: 10.1186/1475-925X-10-23.
[13] T. Imah, E. M., and Basaruddin, “KLASIFIKASI BEAT
ARITMIA PADA SINYAL EKG MENGGUNAKAN
54 Use of Wavelets in Electrocardiogram ... | Darwan, Mustafidah, H., 49 – 56
FUZZY WAVELET LEARNING VECTOR
QUANTIZATION,” J. Ilmu Komput. dan Inf., vol. 4, no.
1, 2011.
[14] B. S. Widodo, “Aplikasi Wavelet Untuk Penghilangan
Derau Isyarat Elektrokardiograf,” J. Buana Inform., vol.
2, no. 2, pp. 95–101, 2011, doi: 10.24002/jbi.v2i2.312.
[15] A. Mukherjee and K. K. Ghosh, “An efficient wavelet
analysis for ECG signal processing,” 2012 Int. Conf.
Informatics, Electron. Vision, ICIEV 2012, pp. 411–415,
2012, doi: 10.1109/ICIEV.2012.6317419.
[16] A. Surtono, T. S. Widodo, and M. Tjokronagoro,
“Analisis Klasifikasi Sinyal EKG Berbasis Wavelet dan
Jaringan Syaraf Tiruan,” vol. 1, no. 3, pp. 60–66, 2012.
[17] F. Lutfi and A. Arifin, “Klasifikasi Sinyal
Elektrokardiografi Menggunakan Wavelet Transform
dan Neural Network,” 13th Semin. Intell. Technol. Its
Appl., vol. 62, no. 62 31, pp. 136–140, 2012.
[18] C. H. Fan, Y. Hsu, S. N. Yu, and J. W. Lin, “Detection
of myocardial ischemia episode using morphological
features,” Proc. Annu. Int. Conf. IEEE Eng. Med. Biol.
Soc. EMBS, pp. 7334–7337, 2013, doi:
10.1109/EMBC.2013.6611252.
[19] Q. Zheng et al., “A novel multi-resolution SVM (MR-
SVM) algorithm to detect ECG signal anomaly in WE-
CARE project,” ISSNIP Biosignals Biorobotics Conf.
BRC, 2013, doi: 10.1109/BRC.2013.6487453.
[20] N. P. Hughes, L. Tarassenko, and S. J. Roberts, “Markov
models for automated ECG interval analysis,” Adv.
Neural Inf. Process. Syst., 2004.
[21] K. Balasundaram, S. Masse, K. Nair, and K. Umapathy,
“Automated signal pattern detection in ECG during
human ventricular arrhythmias,” Proc. Annu. Int. Conf.
IEEE Eng. Med. Biol. Soc. EMBS, pp. 1029–1032, 2013,
doi: 10.1109/EMBC.2013.6609679.
[22] J. Utama, “Electrocardiogram ( ECG ) dengan Noise
Reduction Berbasis Wavelet Menggunakan
Pemrograman LabVIEW Electrocardiogram ( ECG )
with Noise Reduction Based on Wavelet Using
LabVIEW Programming,” vol. 1, no. 1, pp. 40–45, 2013.
[23] S. Barmase, S. Das, and S. Mukhopadhyay, “Wavelet
Transform-Based Analysis of QRS complex in ECG
Signals,” 2013, [Online]. Available:
http://arxiv.org/abs/1311.6460.
[24] A. Kaveh and W. Chung, “Automated classification of
coronary atherosclerosis using single lead ECG,” 2013
IEEE Conf. Wirel. Sensor, ICWISE 2013, pp. 108–113,
2013, doi: 10.1109/ICWISE.2013.6728790.
[25] P. Sarma, S. R. Nirmala, and K. K. Sarma, “ECG
classification using wavelet subband energy based
features,” 2014 Int. Conf. Signal Process. Integr.
Networks, SPIN 2014, pp. 785–790, 2014, doi:
10.1109/spin.2014.6777061.
[26] K. Daqrouq, A. Alkhateeb, M. N. Ajour, and A. Morfeq,
“Neural network and wavelet average framing
 JUITA: Jurnal Informatika e-ISSN: 2579-8901; Vol. 9, No. 1, May 2021
percentage energy for atrial fibrillation classification,”
Comput. Methods Programs Biomed., vol. 113, no. 3, pp.
919–926, 2014, doi: 10.1016/j.cmpb.2013.12.002.
[27] S. Asgari, A. Mehrnia, and M. Moussavi, “Automatic
detection of atrial fibrillation using stationary wavelet
transform and support vector machine,” Comput. Biol.
Med., vol. 60, pp. 132–142, 2015, doi:
10.1016/j.compbiomed.2015.03.005.
[28] M. Thomas, M. K. Das, and S. Ari, “Automatic ECG
arrhythmia classification using dual tree complex
wavelet based features,” AEU - Int. J. Electron. Commun.,
vol. 69, no. 4, pp. 715–721, 2015, doi:
10.1016/j.aeue.2014.12.013.
[29] A. Sharmila, P. Mahalakshmi, V. N. V. L. N. G. Sharma,
G. Dey, and K. Yashwanth, “Detection of artial
fibrillation disorder by ecg using discrete wavelet
transforms,” Asian J. Pharm. Clin. Res., vol. 8, no. 6, pp.
4–6, 2015.
[30] H. AGUIRRE-RAMOS, “Wavelets for correction of ECG
images,” ECORFAN J., vol. 1, no. 1, pp. 36–41.
[31] A. Sampath and T. R. Sumithira, “ECG Morphological
Marking using Discrete Wavelet Transform,” Intell.
Decis. Technol., vol. 10, no. 4, pp. 373–383, 2016, doi:
10.3233/IDT-160264.
[32] H. Ibrahim and I. Owis Mohamed, “Automatic arrhythmia
detection using support vector machine based on discrete
wavelet transform,” J. Med. Imaging Heal. Informatics,
vol. 6, no. 1, pp. 204–209, 2016, doi:
10.1166/jmihi.2016.1611.
[33] S. L. Oh et al., “Automated identification of coronary
artery disease from short-term 12 lead electrocardiogram
signals by using wavelet packet decomposition and
common spatial pattern techniques,” J. Mech. Med. Biol.,
vol. 17, no. 7, 2017, doi: 10.1142/S0219519417400073.
[34] H. Myo Tun, “Analysis on ECG Data Compression Using
Wavelet Transform Technique,” Int. J. Psychol. Brain
Sci., vol. 2, no. 6, p. 127, 2017, doi:
10.11648/j.ijpbs.20170206.12.
[35] A. Aqil, M.; Jbari, A.; Bourouhou, “ECG Signal
Denoising by Discrete Wavelet Transform,” iJOE, vol.
13, no. 9, pp. 51–68, 2017.
[36] S. Saraswat, G. Srivastava, and S. Shukla, “Wavelet
transform based feature extraction and classification of
atrial fibrillation arrhythmia,” Biomed. Pharmacol. J.,
vol. 10, no. 4, pp. 1715–1725, 2017, doi:
10.13005/bpj/1284.
[37] U. R. Acharya et al., “Automated identification of
shockable and non-shockable life-threatening ventricular
arrhythmias using convolutional neural network,” Futur.
Gener. Comput. Syst., vol. 79, no. August, pp. 952–959,
2018, doi: 10.1016/j.future.2017.08.039.
[38] D. D. Patil and R. P. Singh, “ECG Classification Using
Use of Wavelets in Electrocardiogram ... | Darwan, Mustafidah, H., 49 – 56
Wavelet Transform and Wavelet Network Classi fi er,”
pp. 289–303, doi: 10.1007/978-981-10-7868-2.
[39] A. Rodríguez Gómez and Á. Jiménez-Casas, “Analysis
of the ECG Signal Recognizing the QRS Complex and P
and T Waves, Using Wavelet Transform,” Am. J. Eng.
Res. (AJER, no. 7, pp. 51–59, 2018, [Online]. Available:
www.ajer.org.
[40] R. He et al., “Automatic detection of atrial fibrillation
based on continuous wavelet transform and 2D
convolutional neural networks,” Front. Physiol., vol. 9,
no. AUG, pp. 1–11, 2018, doi:
10.3389/fphys.2018.01206.
[41] B. R. de Oliveira, M. A. Q. Duarte, C. C. E. de Abreu, and
J. V. Filho, “A wavelet-based method for power-line
interference removal in ECG signals,” Res. Biomed. Eng.,
vol. 34, no. 1, pp. 73–86, 2018, doi: 10.1590/2446-
4740.01817.
[42] Y. V. Saragih, A. W. Widodo, and M. A. Rahman,
“Pemilihan Fitur Berbasis Wavelet untuk Klasifikasi
Denyut Jantung dari Rekaman Elektrokardiogram,” vol.
3, no. 4, pp. 3140–3147, 2019.
[43] M. Arumugam and A. K. Sangaiah, “Arrhythmia
identification and classification using wavelet centered
methodology in ECG signals,” Concurr. Comput. , vol.
32, no. 17, pp. 1–17, 2020, doi: 10.1002/cpe.5553.
[44] Z. Wang, J. Zhu, T. Yan, and L. Yang, “A new modified
wavelet-based ECG denoising,” Comput. Assist. Surg.,
vol. 24, no. sup1, pp. 174–183, 2019, doi:
10.1080/24699322.2018.1560088.
[45] D. Zhang et al., “An ECG signal de-noising approach
based on wavelet energy and sub-band smoothing filter,”
Appl. Sci., vol. 9, no. 22, 2019, doi:
10.3390/APP9224968.
[46] J. Wang, P. Wang, and S. Wang, “Biomedical Signal
Processing and Control Automated detection of atrial
fibrillation in ECG signals based on wavelet packet
transform and correlation function of random process,”
Biomed. Signal Process. Control, vol. 55, p. 101662,
2020, doi: 10.1016/j.bspc.2019.101662.
[47] C. C. Chen and F. R. Tsui, “Comparing different wavelet
transforms on removing electrocardiogram baseline
wanders and special trends,” BMC Med. Inform. Decis.
Mak., vol. 20, 2020, doi: 10.1186/s12911-020-01349-x.
[48] Y. Zhao, J. Cheng, P. Zhang, and X. Peng, “ECG
classification using deep CNN improved by wavelet
transform,” Comput. Mater. Contin., vol. 64, no. 3, pp.
1615–1628, 2020, doi: 10.32604/cmc.2020.09938.
[49] J. Han, Jiawei; Kamber, Micheline; Pei, Data Mining
Concepts and Techniques, Third. Morgan Kaufmann
Publishers, 2012.
[50] M. Bramer, Principles of Data Mining, Second. Springer,
2013.
55
JUITA: Jurnal Informatika e-ISSN: 2579-8901; Vol. 9, No. 1, May 2021

56 Use of Wavelets in Electrocardiogram ... | Darwan, Mustafidah, H., 49 – 56