Verification and comparison of MIT-BIH arrhythmia database based on number of beats

International Journal of Electrical and Computer Engineering (IJECE)
Vol. 11, No. 6, December 2021, pp. 4950~4961
ISSN: 2088-8708, DOI: 10.11591/ijece.v11i6.pp4950-4961  4950
Journal homepage: http://ijece.iaescore.com
Verification and comparison of MIT-BIH arrhythmia database
based on number of beats
Akram Jaddoa Khalaf, Samir Jasim Mohammed
Department of Electrical Engineering, Faculty of Engineering, University of Babylon, Iraq
Article Info ABSTRACT
Article history:
Received Nov 24, 2020
Revised Mar 30, 2021
Accepted Apr 9, 2021
The ECG signal processing methods are tested and evaluated based on many
databases. The most ECG database used for many researchers is the MIT-
BIH arrhythmia database. The QRS-detection algorithms are essential for
ECG analyses to detect the beats for the ECG signal. There is no standard
number of beats for this database that are used from numerous researches.
Different beat numbers are calculated for the researchers depending on the
difference in understanding the annotation file. In this paper, the beat
numbers for existing methods are studied and compared to find the correct
beat number that should be used. We propose a simple function to
standardize the beats number for any ECG PhysioNet database to improve
the waveform database toolbox (WFDB) for the MATLAB program. This
function is based on the annotation's description from the databases and can
be added to the Toolbox. The function is removed the non-beats annotation
without any errors. The results show a high percentage of 71% from the
reviewed methods used an incorrect number of beats for this database.
Keywords:
ECG
Heartbeat
MATLAB
MIT-BIH arrhythmia database
QRS-detection
WFDB
This is an open access article under the CC BY-SA license.
Corresponding Author:
Akram Jaddoa Khalaf
Department of Electrical Engineering
University of Babylon
Hilla, Babylon, Iraq
Email: eng.akram@uobabylon.edu.iq
1. INTRODUCTION
The electrocardiogram (ECG) was generally used for the observation of cardiac physiology as a
cost-effective and non-invasive process. For the cardiologist to diagnose cardiac diseases, the ECG signal
shows heart functionality. The ECG field is developed significantly, considering the most common death is
generally from cardiovascular diseases [1]. Many applications are based on the ECG signal, such as
measuring the heart-rate, biometric-identification, movement-recognize, and diagnosing-abnormality [2].
Generally, the first ECG standard material available for testing and performance evaluation is the
MIT-BIH arrhythmia database [3]. It played together with the American Heart Association (AHA) database
an interesting role in stimulating manufacturers of arrhythmia analyzers to compete on the basis of
objectively measurable performance. The value of common databases for basic research and medical device
development and evaluation is attributed to the MIT-BIH arrhythmia database. The MIT-BIH has comprised
variable ECG signals with a variable: noise, artifacts, beat types, and wave shapes. A 48-records with two
channels for each ECG-signal and an annotation file are included. These signals are recording from 25 men
and 22 women for a half-hour period at 360 samples per second. The database has been annotated with
112,647 annotations, and these annotations have been verified [3]. It has been classified into two main
annotation categories: the beats and the non-beats. The beat annotations for the MIT-BIH arrhythmia
database consist of 15 subtypes, and the non-beats annotations consist of 24 subtypes, as shown in Table 1.

Int J Elec & Comp Eng ISSN: 2088-8708 
Verification and comparison of MIT-BIH arrhythmia database … (Akram Jaddoa Khalaf)
4951
The beat type consists of 14 classified beats types and one unclassified beats type. The beats annotations are
occurring for any type of QRS waves in ECG-signal. Therefore, this database is widely used for testing,
performance evaluating, and learning for QRS-detection methods. In general, the databases are used to
evaluate any new algorithm's performance before implementing it in devices for many applications. So, any
errors for this evaluation will cause an error in the device decision. In biomedical applications like QRS-
detection, which is substantial for many ECG monitoring devices, the detecting errors for these devices may
affect doctor's diagnosis and treatment depending on these devices. So, verifying the database for these
applications will improve the doctor's decision.
Table 1. The description of beat and non-beat annotations for MIT-BIH arrhythmia database
Beat annotations Non-beat annotations
Code Description Code Description
N Normal beat [ Start of ventricular flutter/fibrillation
L Left bundle branch block beat ! Ventricular flutter wave
R Right bundle branch block beat ] End of ventricular flutter/fibrillation
A Atrial premature beat x Non-conducted P-wave (blocked APC)
a Aberrated atrial premature beat (N Normal sinus rhythm
J Nodal (junctional) premature beat (P Paced rhythm
S Supraventricular premature or ectopic beat (atrial or nodal) (B Ventricular bigeminy
V Premature ventricular contraction (VT Ventricular tachycardia
F A fusion of ventricular and normal beat (T Ventricular trigeminy
e Atrial escape beat (SVTA Supraventricular tachyarrhythmia
j Nodal (junctional) escape beat (IVR Idioventricular rhythm
E Ventricular escape beat (NOD Nodal (A-V junctional) rhythm
/ Paced beat (AFIB Atrial fibrillation
f A fusion of paced and normal beat (AFL Atrial flutter
Q Unclassifiable beat (VFL Ventricular flutter
(AB Atrial bigeminy
(PREX Pre-excitation (WPW)
(BII 2° heart block
(SBR Sinus bradycardia
| Isolated QRS-like artifact
~ Change in signal quality
":TS Tape slippage
":PSE Pause
":MISSB Missed beat
Until now, more than two thousand works cited the MIT-BIH arrhythmia database. It is unique in
terms of arrhythmia classification since it offers five arrhythmia standards groups [2]. The QRS detection
methods are essential for most of the cited works, including arrhythmia detection, classification, and
diagnosing applications. Depending on this database, many QRS detection algorithms have been developed,
tested, and evaluated. The QRS detection algorithms are based on the beats annotations in the database
signals for testing and evaluation. These beats are used as learning data for the methods depending on the
learning technique.
Many researchers used MATLAB for algorithm implementation based on the waveform database
(WFDB) Toolbox [4]. This Toolbox consists of the functions that are used for reading, writing, and signals
processing the files of PhysioNet databases. The MIT-BIH arrhythmia is one of the PhysioNet databases
which contains data and annotations files. The WFDB is used to extract the ECG-signals and these
annotations from the MIT-BIH arrhythmia database for all records. It can extract one type of beats or non-
beats annotations or extract all annotations without any filter. So, it is not easy to extract all beat annotations
only, which is leads to errors from reading the non-beat annotations. When reviewing the existing methods
that used the MIT-BIH arrhythmia database, we noted that not all these methods are considered the same
number of beats for the same database records. Also, this difference affects even slightly the evaluation
results used to compare the performance of the methods.
This work will study the reasons for reading different numbers of beats and methods comparison
with correction and verification. Furthermore, a new function is designed to extract the correct beats and
remove the non-beats annotations from the original database files based on WFDB Toolbox for MATLAB.
In section 2, the MIT-BIH arrhythmia database and its annotation types in detail are described.
Section 3 present the proposed function that extracts the correct beat from the annotation files. Then, section
4 demonstrates the results and discussion for revising the existing methods with a comparison based on each
method's beat number. Finally, in section 5, the conclusion is summarized.

 ISSN: 2088-8708
Int J Elec & Comp Eng, Vol. 11, No. 6, December 2021 : 4950 - 4961
4952
2. MIT-BIH ARRHYTHMIA DATABASE
The MIT-BIH arrhythmia database is one of the most substantial ECG databases. Contrasting
database signals, noise, and artifacts make it suitable for testing and evaluation. Moreover, the verified
annotations files that contain the beats and non-beats types, as shown in Table 2 and Table 3. These tables
show the MIT-BIH arrhythmia database annotations for each record based on the PhysioNet annotations
descriptions for beats and non-beats annotations. There are more than these annotation types, which are
shown in other databases.
Table 2. MIT-BIH arrhythmia database beat annotations
Record
No.
Total
Anno-tations
N L R A a J S V F e j E / f Q
Total
Beats
100 2274 2239 33 1 2273
101 1874 1860 3 2 1865
102 2192 99 4 2028 56 2187
103 2091 2082 2 2084
104 2311 163 2 1380 666 18 2229
105 2691 2526 41 5 2572
106 2098 1507 520 2027
107 2140 59 2078 2137
108 1824 1739 4 17 2 1 1763
109 2535 2492 38 2 2532
111 2133 2123 1 2124
112 2550 2537 2 2539
113 1796 1789 6 1795
114 1890 1820 10 2 43 4 1879
115 1962 1953 1953
116 2421 2302 1 109 2412
117 1539 1534 1 1535
118 2301 2166 96 16 2278
119 2094 1543 444 1987
121 1876 1861 1 1 1863
122 2479 2476 2476
123 1519 1515 3 1518
124 1634 1531 2 29 47 5 5 1619
200 2792 1743 30 826 2 2601
201 2039 1625 30 97 1 198 2 10 1963
202 2146 2061 36 19 19 1 2136
203 3108 2529 2 444 1 4 2980
205 2672 2571 3 71 11 2656
207 2385 1457 86 107 105 105 1860
208 3040 1586 2 992 373 2 2955
209 3052 2621 383 1 3005
210 2685 2423 22 194 10 1 2650
212 2763 923 1825 2748
213 3294 2641 25 3 220 362 3251
214 2297 2003 256 1 2 2262
215 3400 3195 3 164 1 3363
217 2280 244 162 1542 260 2208
219 2312 2082 7 64 1 2154
220 2069 1954 94 2048
221 2462 2031 396 2427
222 2634 2062 208 1 212 2483
223 2643 2029 72 1 473 14 16 2605
228 2141 1688 3 362 2053
230 2466 2255 1 2256
231 2011 314 1254 1 2 1571
232 1816 397 1382 1 1780
233 3152 2230 7 831 11 3079
234 2764 2700 50 3 2753
Total 112647 75052 8075 7259 2546 150 83 2 7130 803 16 229 106 7028 982 33 109,494
Each beat's annotation is a QRS-complex with different types as normal-beat or other beats. On the
other hand, The Non-beat annotations are ventricular flutter wave, start/end of ventricular flutter, and starting
for many types of rhythm like (sinus, paced, ventricular, supraventricular, atrial fibrillation, atrial flutter, and
heart block). These are annotated ECG signal to show at this point one of the rhythms are starting. So, it is
not a beats (QRS) annotation. The ventricular flutter (record 207) is excepted for many QRS-detection
methods because it is defined on the ECG by a sinusoidal wave without a clear showing of the QRS-complex

4953
wave and T wave. The QRS detection methods based on the MIT-BIH arrhythmia database use the beat
annotation only because the non-beats annotations are not shown QRS waves for testing, evaluation, and
learning.
The number of beats annotations are shown in Table 2 with (109,494 Beats) for all 48 records. This
number should be a standard number of beats depending on the original database annotation details and the
PhysioNet annotations descriptions for beats and non-beats types. Also, the QRS detection methods are
excluded from the 472 ventricular flutter waves from record no. 207, because these waves are considered as
non-beat annotations based on the annotation's description of PhysioNet as shown in Table 3.
Table 3. MIT-BIH arrhythmia database non-beat annotations
Record
No.
Total
Anno-
tations
[
!
]
x
(N
(P
(B
(VT
(T
(SVTA
(IVR
(NOD
(AFIB
(AFL
(VFL
(AB
(PREX
(BII
(SBR
|
~
":TS
":PSE
":MISSB
Total Non-Beats
100 2274 1 1
101 1874 1 4 4 9
102 2192 2 3 5
103 2091 1 6 7
104 2311 22 23 37 82
105 2691 1 30 88 119
106 2098 21 18 1 1 30 71
107 2140 1 2 3
108 1824 11 1 8 41 61
109 2535 1 2 3
111 2133 1 8 9
112 2550 1 10 11
113 1796 1 1
114 1890 2 1 1 7 11
115 1962 1 6 2 9
116 2421 1 8 9
117 1539 1 3 4
118 2301 10 1 12 23
119 2094 49 37 17 4 107
121 1876 1 12 13
122 2479 1 2 3
123 1519 1 1
124 1634 6 2 3 2 2 15
200 2792 70 71 7 43 191
201 2039 37 16 12 1 3 3 4 76
202 2146 3 4 1 2 10
203 3108 21 1 21 2 26 57 128
205 2672 7 6 1 2 16
207 2385 6 472 6 10 4 2 1 1 6 2 15 525
208 3040 27 26 8 24 85
209 3052 11 10 7 19 47
210 2685 5 2 1 9 1 17 35
212 2763 1 1 13 15
213 3294 22 19 2 43
214 2297 13 2 10 5 4 1 35
215 3400 3 2 30 2 37
217 2280 33 9 1 24 1 4 72
219 2312 133 8 2 1 10 3 1 158
220 2069 9 8 4 21
221 2462 1 2 8 12 12 35
222 2634 32 4 31 24 42 3 15 151
223 2643 11 7 7 3 10 38
228 2141 21 20 24 20 3 88
230 2466 104 103 1 2 210
231 2011 2 6 5 427 440
232 1816 1 35 36
233 3152 36 28 6 1 2 73
234 2764 2 1 8 11
Total 112647 6 472 6 193 530 60 221 61 83 26 4 36 107 45 6 3 103 5 1 132 616 6 3 428 3153
3. HEARTBEATS FILTER FUNCTION
In this paper, a MATLAB function is designed to filter the annotations file for any PhysioNet
databases included the MIT-BIH arrhythmia. The function removes the non-beat annotation shown in Table 3
so, the annotations file will contain the beat annotation only shown in Table 2. On the other hand, the existing

 ISSN: 2088-8708
4954
MATLAB-WFDB function (rdann) reading the annotations file can read all annotations or one annotation.
So, rdann cannot filter the annotation by beats or non-beats type; for this reason, the function with new
features was proposed with new features to filter the data correctly without any errors.
This function is simple, but it is important to standardize the beats number for any researcher that
are used PhysioNet databases. This function can be added to the MATLAB-WFDB toolbox to simply filtered
the annotations files by removing the non-beat annotations precisely with the standard values. The function
read and search all annotations data files for each record, as shown in Figure 1. If the annotation is one of the
non-beat types, this annotation will be removed from the annotation data. Also, it has to be used for any
PhysioNet database to extract the beat annotation by removing the non-beat annotations used to prepare the
data for many applications, including QRS-detection methods.
Start
Read the
annotation (Ann)
If
Ann is non-beat
Table 2
Delete The Ann
yes
No
Figure 1. The function flowchart
4. THE COMPARISON AND VERIFICATION RESULTS WITH DISCUSSION
The work focuses on the verification and comparison of the MIT-BIH arrhythmia database used for
the QRS-detection algorithm. The proposed heartbeats filter function can apply to all MIT-BIH databases
from the PhysioNet site. The reviewed QRS-detection methods are not using the same number of heartbeats
for the MIT-BIH arrhythmia database. This number should be standard for this database because it depends
on the original database's beats number. Simultaneously, not all the QRS-detection methods are considering
the same number of beats for the same database records. The revision for the existing QRS-detection
methods using the MIT-BIH arrhythmia database has summarized the errors for these methods based on the
beats for records shown in Table 4 (see in Appendix). The incorrect records are indicated by bold, the Total
(T), and Errors (E) in this table. The methods should use the same number of beats without any difference,
but the errors are occurring by researchers. All the reviewed methods are revised, compared, and verified
based on beats number for each database record. Table 5 summarizes the total beats number, total error per
record, and total error per database for different methods to evaluate these methods' incorrectness.
The total number of beats for the MIT-BIH arrhythmia database used from the reviewed methods is
calculated; this number should be 109,494 heartbeats for all database records, as shown in section 2. The beat
errors for these methods compared to the correct number of beats for this database are determined to find the
number of methods that used the correct beat's value. Also, the other methods contained errors start from 1
beat to 1400 beats for the overall database. Table 5 shows the percentage of references number for each error
per the total references that were reviewed. Moreover, it shows the total number of errors for each reference
per each record (sum of the absolute values of errors) and the total number of errors for each reference per
overall database, which takes a positive or negative value.
The beats errors per all data record up to 1400 beats and 29% of the total reviewed methods use the
correct beats number. On the other hand, 71% are using incorrect beats number. Also, the number of
incorrect methods is higher than the number of correct methods based on our comparison. So, we propose
this study. Each record in the database for the reviewed methods has been studied for beats errors calculation.

4955
Figure 2 describes the number of references that contain errors for each record. For each record, the
percentage of the reference number that occurs error per all references is calculated to evaluate the record
error reasons. The records error percentage is started from 53% for record no. 207 to 9% for records (102,
103, 112, 117, 119, 122, 123, and 230).
Table 5 and Figure 2 show the difference between these methods for the same records used from the
same database. After the results are studied, the following obvious points are established:
a. The correct number of the beats is 109,494 beats without adding or removing any data.
b. The designed function extracts the correct heartbeats number of all records for the MIT-BIH arrhythmia
database.
c. If the beats number exceed the correct number:
− Some non-beat annotations have been added and should be mentioned in the methods.
− The data has been repeated for record and should be mentioned in the methods.
d. If the beats number less than the correct number:
− Some beat annotations have been removed and should be mentioned in the methods.
e. This database contains some errors before digitalization and verification [1].
f. The WFDB toolbox does not include the beats or non-beats filter for the (rdann) function that reads the
annotations files.
g. The copy and paste records beat numbers between the researchers without verification.
h. A high number of annotation types (39 annotations) confuse the researchers.
i. According to Figure 2, the most error occurs in record no. 207 because many researchers are counting
the 472 ventricular flutter waves, but these waves are considered as non-beat annotations based on the
annotation's description of PhysioNet.
j. From Figure 2, records no. 209 is the second, and records no. 214 is the third most errors beats for the
reviewed methods, but the number of errors is low and not exceeds eight beats and nine beats,
respectively.
k. According to Figure 2, the lowest error records (102, 103, 112, 117, 119, 122, 123, and 230) because
these records contain the lowest non-beat annotations.
Table 5. Total beat annotations and errors for the reviewed methods
References Count of ref
Percentage
ref
Total beats Total errors per record
Total Errors per
database
[5-24] 20 29% 109494 0 0
[25] 1 1% 109493 1 -1
[26-31] 6 9% 109496 2 2
[32] 1 1% 109495 3 1
[33] 1 1% 109488 6 -6
[34] 1 1% 109488 6 -6
[35] 1 1% 109486 8 -8
[36] 1 1% 109481 13 -13
[37-39] 3 4% 109508 16 14
[40-42] 3 4% 109510 18 16
[43] 1 1% 109483 23 -11
[44] 1 1% 109488 36 -6
[45] 1 1% 109478 44 -16
[46] 1 1% 109443 51 -51
[47] 1 1% 109428 66 -66
[48] 1 1% 109328 166 -166
[49] 1 1% 109357 203 -137
[50] 1 1% 109255 239 -239
[51-56] 6 9% 109809 329 315
[57] 1 1% 109788 348 294
[58] 1 1% 109267 357 -227
[59] 1 1% 109134 360 -360
[60] 1 1% 109097 423 -397
[61-63] 3 4% 109966 472 472
[64] 1 1% 109965 473 471
[65] 1 1% 109966 474 472
[66] 1 1% 109996 502 502
[67] 1 1% 109369 567 -125
[68] 1 1% 109985 579 491
[69] 1 1% 109663 603 169
[70] 1 1% 110159 665 665
[71] 1 1% 110008 738 514
[72] 1 1% 109036 1400 -458
Total 68 100%

 ISSN: 2088-8708
4956
Figure 2. Records errors per overall references
5. CONCLUSION
This paper presented a method for finding the correct beats number for the MIT-BIH arrhythmia
database with a comparison study and design a function for MATLAB to extract the correct values for any
PhysioNet databases. In this way, the number of beats that are using by the researchers will be standards. The
non-beat annotations affected the results of the QRS-detection methods in two ways. First, the proposed
methods' evaluation accuracy is not calculated correctly because the number of database beats is incorrect.
Second, the methods based on machine learning are trained depending on incorrect information. So, the
learning operation was not proper, and the results of the methods are not correct. Most reviewed methods
used an incorrect number of beats, 29% of researchers used the correct number, and 71% are used incorrect
beats. The proposed function should be added to the MATLAB-WFDB Toolbox to filter the annotations files
to remove the non-beat annotations correctly and extract the standard beat values. It can be used for any other
programing language to read the annotations files from the PhysioNet databases like python.
APPENDIX
Table 4. The beat annotation for the reviewed methods
Rec [5-24] [25] [26-30] [31] [32] [33] [34] [35] [36] [37-39] [40-42] [43] [44] [45] [46] [47] [48]
100 2273 2273 2273 2273 2273 2273 2272 2272 2272 2273 2273 2273 2273 2273 2271 2273 2272
101 1865 1865 1865 1865 1865 1865 1865 1865 1865 1865 1865 1865 1865 1865 1864 1865 1864
102 2187 2187 2187 2187 2187 2187 2187 2187 2187 2187 2187 2187 2187 2187 2186 2187 2187
103 2084 2084 2084 2084 2084 2084 2084 2084 2084 2084 2084 2084 2084 2084 2083 2084 2084
104 2229 2229 2229 2229 2229 2229 2228 2228 2228 2229 2229 2229 2229 2230 2228 2229 2227
105 2572 2572 2572 2572 2572 2572 2572 2572 2572 2572 2572 2572 2572 2572 2571 2572 2555
106 2027 2027 2027 2027 2027 2027 2027 2027 2027 2027 2027 2027 2027 2027 2026 2027 2027
107 2137 2136 2137 2137 2137 2137 2136 2137 2137 2137 2137 2137 2137 2137 2136 2137 2135
108 1763 1763 1763 1763 1763 1763 1763 1763 1763 1774 1774 1760 1774 1763 1762 1763 1761
109 2532 2532 2532 2532 2532 2532 2532 2532 2532 2532 2532 2532 2532 2532 2531 2532 2532
111 2124 2124 2124 2124 2124 2124 2124 2124 2124 2124 2124 2124 2124 2124 2123 2124 2124
112 2539 2539 2539 2539 2539 2539 2539 2539 2539 2539 2539 2539 2539 2539 2538 2539 2539
113 1795 1795 1795 1795 1795 1795 1794 1794 1794 1795 1795 1795 1795 1795 1793 1795 1794
114 1879 1879 1879 1879 1879 1879 1879 1878 1879 1879 1879 1872 1879 1879 1878 1879 1879
115 1953 1953 1953 1953 1953 1953 1953 1953 1953 1953 1953 1952 1953 1953 1952 1953 1952
116 2412 2412 2412 2412 2412 2412 2412 2412 2412 2412 2412 2412 2412 2412 2411 2412 2410
117 1535 1535 1535 1535 1535 1535 1535 1535 1535 1535 1535 1535 1535 1535 1534 1535 1535
118 2278 2278 2278 2278 2278 2278 2278 2278 2277 2278 2278 2278 2278 2288 2277 2278 2278
119 1987 1987 1987 1987 1987 1987 1987 1987 1987 1987 1987 1987 1987 1987 1986 1987 1987
121 1863 1863 1863 1863 1863 1863 1863 1862 1862 1863 1863 1863 1863 1863 1862 1863 1863
122 2476 2476 2476 2476 2476 2476 2476 2476 2476 2476 2476 2476 2476 2476 2475 2476 2476
123 1518 1518 1518 1518 1518 1518 1518 1518 1518 1518 1518 1518 1518 1518 1517 1518 1518
124 1619 1619 1619 1619 1619 1619 1619 1619 1619 1619 1619 1619 1619 1619 1618 1619 1619
200 2601 2601 2601 2601 2601 2601 2601 2601 2601 2601 2601 2601 2601 2601 2600 2601 2581
201 1963 1963 1963 1963 1963 1963 1963 1963 1962 1963 1963 1963 1963 1963 1962 1963 1950
202 2136 2136 2136 2136 2136 2135 2136 2136 2136 2136 2136 2136 2136 2136 2135 2136 2133
203 2980 2980 2980 2980 2980 2980 2980 2980 2980 2980 2980 2980 2980 2980 2979 2980 2949
205 2656 2656 2656 2656 2656 2656 2656 2656 2655 2656 2656 2656 2656 2656 2655 2656 2647
207 1860 1860 1862 1860 1862 1860 1860 1860 1860 1860 1862 1862 1860 1862 1859 1794 1859
53%
43%
34%
31%
26%
25%
25%
25%
25%
24%
22%
22%
18%
16%
15%
15%
15%
15%
15%
15%
15%
13%
13%
13%
13%
13%
12%
12%
12%
12%
12%
12%
12%
10%
10%
10%
10%
10%
10%
10%
9%
9%
9%
9%
9%
9%
9%
9%
0
5
10
15
20
25
30
35
40
207
209
214
104
210
108
118
208
222
203
217
231
213
113
100
107
201
215
220
221
233
114
200
202
205
223
101
105
115
116
121
228
232
106
109
111
124
212
219
234
102
103
112
117
119
122
123
230
No.
of
Errors
for
all
Ref.s
Record No.

4957
Table 4. The beat annotation for the reviewed methods (continue)
Rec [5-24] [25] [26-30] [31] [32] [33] [34] [35] [36] [37-39] [40-42] [43] [44] [45] [46] [47] [48]
208 2955 2955 2955 2955 2955 2955 2955 2955 2955 2955 2955 2955 2955 2946 2954 2955 2921
209 3005 3005 3005 3004 3005 3004 3005 3004 3004 3004 3004 3004 3004 3005 3004 3005 3002
210 2650 2650 2650 2650 2650 2650 2650 2650 2650 2650 2650 2650 2650 2647 2649 2650 2644
212 2748 2748 2748 2748 2748 2748 2748 2748 2748 2748 2748 2748 2748 2748 2747 2748 2747
213 3251 3251 3251 3251 3251 3251 3250 3250 3250 3251 3251 3251 3251 3251 3249 3251 3249
214 2262 2262 2262 2261 2261 2261 2262 2261 2261 2265 2265 2265 2265 2254 2261 2262 2261
215 3363 3363 3363 3363 3363 3361 3363 3363 3363 3363 3363 3363 3363 3353 3362 3363 3362
217 2208 2208 2208 2208 2208 2208 2208 2208 2208 2209 2209 2209 2209 2208 2207 2208 2208
219 2154 2154 2154 2154 2154 2154 2154 2154 2154 2154 2154 2154 2154 2154 2153 2154 2154
220 2048 2048 2048 2048 2048 2048 2047 2048 2047 2048 2048 2048 2048 2048 2047 2048 2047
221 2427 2427 2427 2427 2427 2427 2427 2427 2426 2427 2427 2427 2407 2427 2426 2427 2427
222 2483 2483 2483 2483 2483 2483 2483 2483 2483 2483 2483 2483 2483 2484 2482 2483 2482
223 2605 2605 2605 2605 2605 2605 2605 2605 2605 2605 2605 2605 2605 2605 2604 2605 2603
228 2053 2053 2053 2053 2053 2053 2053 2053 2053 2053 2053 2048 2053 2053 2052 2053 2053
230 2256 2256 2256 2256 2256 2256 2256 2256 2256 2256 2256 2256 2256 2256 2255 2256 2256
231 1571 1571 1571 1571 1571 1571 1571 1571 1571 1571 1571 1571 1571 1571 1570 1571 1571
232 1780 1780 1780 1780 1780 1779 1780 1780 1780 1780 1780 1780 1780 1780 1779 1780 1780
233 3079 3079 3079 3079 3079 3079 3079 3079 3078 3079 3079 3079 3079 3079 3078 3079 3071
234 2753 2753 2753 2753 2753 2753 2753 2753 2753 2753 2753 2753 2753 2753 2752 2753 2753
T 109494 109493 109496 109492 109495 109488 109488 109486 109481 109508 109510 109483 109488 109478 109443 109428 109328
E 0 1 2 2 3 6 6 8 13 16 18 23 36 44 51 66 166
Rec [49] [50] [51-56] [57] [58] [59] [60] [61-63] [64] [65] [66] [67] [68] [69] [70] [71] [72]
100 2269 2273 2273 2273 2267 2265 2273 2273 2273 2273 2273 2273 2274 2270 2273 2273 2272
101 1862 1864 1865 1865 1859 1860 1865 1865 1865 1865 1865 1865 1866 1862 1865 1873 1864
102 2183 2187 2187 2187 2181 2180 2187 2187 2187 2187 2187 2187 2187 2186 2187 2186 2186
103 2081 2084 2084 2084 2081 2078 2084 2084 2084 2084 2084 2084 2084 2083 2084 2084 2083
104 2225 2226 2230 2230 2224 2222 2230 2229 2229 2230 2229 2229 2229 2219 2229 2235 2228
105 2582 2566 2572 2572 2564 2565 2572 2572 2572 2572 2572 2572 2602 2559 2572 2578 2571
106 2024 2023 2027 2027 2024 2021 2027 2027 2027 2027 2027 2027 2026 2025 2027 2096 2026
107 2133 2135 2137 2137 2131 2131 2137 2137 2137 2137 2137 2137 2136 2135 2137 2138 2136
108 1761 1759 1763 1763 1757 1757 1763 1763 1763 1763 1763 1763 1763 1747 1774 1763 1762
109 2528 2527 2532 2532 2526 2524 2532 2532 2532 2532 2532 2532 2533 2531 2532 2519 1649
111 2121 2123 2124 2124 2120 2118 2124 2124 2124 2124 2124 2124 2123 2120 2124 2124 2123
112 2535 2539 2539 2539 2536 2531 2539 2539 2539 2539 2539 2539 2539 2537 2539 2549 2538
113 1791 1795 1795 1797 1791 1789 1795 1795 1795 1795 1795 1795 1794 1792 1795 1795 1794
114 1875 1832 1879 1879 1872 1872 1879 1879 1879 1879 1879 1879 1890 1878 1879 1885 1878
115 1949 1953 1953 1953 1945 1946 1953 1953 1953 1953 1953 1953 1953 1950 1953 1960 1952
116 2408 2392 2412 2412 2409 2404 2412 2412 2412 2412 2412 2412 2395 2407 2412 2401 2411
117 1532 1535 1535 1535 1532 1530 1535 1535 1535 1535 1535 1535 1535 1534 1535 1538 1534
118 2275 2278 2275 2275 2273 2271 2275 2278 2278 2278 2278 2278 2278 2275 2288 2298 2277
119 1984 1987 1987 1987 1985 1981 1987 1987 1987 1987 1987 1987 1988 1985 1987 2010 1986
121 1859 1863 1863 1863 1858 1856 1863 1863 1863 1863 1863 1863 1863 1860 1863 1871 1862
122 2472 2476 2476 2476 2471 2468 2476 2476 2476 2476 2476 2476 2476 2475 2476 2477 2475
123 1515 1518 1518 1518 1514 1513 1518 1518 1518 1518 1518 1518 1519 1517 1518 1518 1517
124 1616 1619 1619 1619 1613 1613 1619 1619 1619 1618 1619 1619 1619 1618 1619 1602 1618
200 2597 2600 2601 2601 2595 2593 2607 2601 2601 2601 2601 2601 2601 2560 2601 2599 2600
201 1961 1934 1963 1963 1946 1959 1963 1963 1963 1963 1963 1963 1949 1954 2000 1963 1962
202 2132 2132 2136 2136 2134 2128 2136 2136 2136 2136 2136 2136 2138 2134 2136 2135 2135
203 3003 2926 2982 2978 2976 2973 2982 2980 2980 2980 2980 2980 2988 2962 2980 2982 2979
205 2652 2653 2656 2656 2650 2648 2656 2656 2656 2656 2656 2656 2656 2654 2656 2657 2655
207 1855 1857 1862 1862 1856 1850 1862 2332 2332 2332 2332 1543 2324 2246 2332 1862 2331
208 2951 2940 2956 2954 2953 2946 2956 2955 2955 2955 2955 2955 2953 2937 2955 2952 2954
209 3001 3005 3004 3004 2999 2997 3004 3005 3004 3005 3005 3006 3006 3002 3005 3051 3004
210 2646 2628 2647 2647 2645 2642 2647 2650 2650 2650 2650 2640 2652 2640 2650 2645 2649
212 2744 2748 2748 2748 2746 2740 2748 2748 2748 2748 2748 2748 2748 2746 2748 2761 2747
213 3246 3250 3251 3251 3245 3241 3251 3251 3251 3251 3251 3471 3250 3247 3251 3245 3250
214 2258 2258 2262 2262 2255 2254 2262 2262 2262 2262 2262 2259 2262 2259 2262 2273 2261
215 3358 3363 3363 3362 3357 3353 3363 3363 3363 3363 3363 3363 3362 3360 3363 3398 3362
217 2205 2207 2208 2208 2202 2202 2208 2208 2208 2208 2208 2208 2208 2207 2208 2270 2207
219 2151 2154 2154 2154 2150 2147 2154 2154 2154 2154 2154 2154 2154 2152 2287 2154 2153
220 2044 2047 2048 2048 2041 2041 2048 2048 2048 2048 2048 2048 2048 2047 2048 2068 2047
221 2423 2426 2427 2427 2422 2420 2427 2427 2427 2427 2457 2427 2427 2426 2427 2447 2426
222 2478 2481 2484 2484 2492 2474 2484 2483 2483 2483 2483 2483 2485 2481 2483 2624 2482
223 2601 2604 2605 2605 2603 2581 2605 2605 2605 2605 2605 2589 2604 2604 2605 2636 2604
228 2050 2050 2053 2053 2048 2047 2053 2053 2053 2053 2053 2053 2060 2051 2053 2116 2052
230 2252 2256 2256 2256 2252 2248 2256 2256 2256 2256 2256 2256 2256 2253 2256 2257 2255
231 1568 1571 1886 1886 1566 1565 1186 1571 1571 1571 1571 1571 1571 1570 1573 1569 1570
232 1778 1780 1780 1767 1719 1776 1780 1780 1780 1780 1780 1780 1783 1779 1780 1734 1779
233 3074 3078 3079 3076 3135 3069 3079 3079 3079 3079 3079 3079 3077 3076 3079 3074 3078
234 2749 2753 2753 2753 2747 2745 2735 2753 2753 2753 2753 2753 2751 2751 2753 2763 2752
T 109357 109255 109809 109788 109267 109134 109097 109966 109965 109966 109996 109369 109985 109663 110159 110008 109036
E 203 239 329 348 357 360 423 472 473 474 502 567 579 603 665 738 1400

 ISSN: 2088-8708
4958
REFERENCES
[1] S. Mendis et al., "Global atlas on cardiovascular disease prevention and control," Geneva: World Health
Organization in Collaboration with The World Heart Federation and the World Stroke Organization, 2011.
[2] S. K. Berkaya, A. K. Uysal, E. S. Gunal, S. Ergin, S. Gunal, and M. B. Gulmezoglu, "A survey on ECG analysis,"
Biomedical Signal Processing and Control, vol. 43, pp. 216-235, May 2018, doi: 10.1016/j.bspc.2018.03.003.
[3] G. B. Moody and R. G. Mark, "The impact of the MIT-BIH Arrhythmia Database," in IEEE Engineering in
Medicine and Biology Magazine, vol. 20, no. 3, pp. 45-50, May-June 2001, doi: 10.1109/51.932724.
[4] I. Silva and G. B. Moody, "An Open-source Toolbox for Analysing and Processing PhysioNet Databases in
MATLAB and Octave," Journal of Open Research Software, vol. 2, no.1, pp. 1-27, Sep. 2014, doi: 10.5334/jors.bi.
[5] A. J. Khalaf and S. J. Mohammed, "A QRS-Detection Algorithm for Real-Time Applications," International
Journal of Intelligent Engineering and Systems, vol. 14, no. 1, pp. 356-367, 2020, doi: 10.22266/ijies2021.0228.33.
[6] C. Nayak, S. K. Saha, R. Kar and D. Mandal, "An Efficient and Robust Digital Fractional Order Differentiator
Based ECG Pre-Processor Design for QRS Detection," in IEEE Transactions on Biomedical Circuits and Systems,
vol. 13, no. 4, pp. 682-696, Aug. 2019, doi: 10.1109/TBCAS.2019.2916676.
[7] A. Sharma, S. Patidar, A. Upadhyay, and U. R. Acharya, "Accurate tunable-Q wavelet transform based method for
QRS complex detection," Computers & Electrical Engineering, vol. 75, pp. 101-111, May 2019, doi:
10.1016/j.compeleceng.2019.01.025.
[8] A. Bajaj and S. Kumar, "QRS complex detection using fractional Stockwell transform and fractional Stockwell
Shannon energy," Biomedical Signal Processing and Control, vol. 54, Sep. 2019, Art. no. 101628, doi:
10.1016/j.bspc.2019.101628.
[9] T. Nguyen, X. Qin, A. Dinh, and F. Bui, "Low Resource Complexity R-peak Detection Based on Triangle
Template Matching and Moving Average Filter," Sensors, vol. 19, no. 18, Sep. 2019, Art. no. 3997, doi:
10.3390/s19183997.
[10] C. Nayak, S. K. Saha, R. Kar, and D. Mandal, "Optimal SSA‐based wideband digital differentiator design for
cardiac QRS complex detection application," International Journal of Numerical Modelling: Electronic Networks,
Devices and Fields, vol. 32, no. 2, Nov. 2018, Art. no. e2524, doi: 10.1002/jnm.2524.
[11] Ö. Yakut and E. D. Bolat, "An improved QRS complex detection method having low computational load,"
Biomedical Signal Processing and Control, vol. 42, pp. 230-241, Apr. 2018, doi: 10.1016/j.bspc.2018.02.004.
[12] D. Yang and Y. Zhang, "A Real-time QRS Detector Based on Low-pass Differentiator and Hilbert Transform," in
MATEC Web of Conferences, Guangzhou, China, vol. 175, pp. 1-6, 2018, doi: 10.1051/matecconf/201817502008.
[13] T. Sharma and K. K. Sharma, "QRS complex detection in ECG signals using locally adaptive weighted total
variation denoising," Computers in Biology and Medicine, vol. 87, pp. 187-199, Aug. 2017, doi:
10.1016/j.compbiomed.2017.05.027.
[14] S. Jain, A. Kumar, and V. Bajaj, "Technique for QRS complex detection using particle swarm optimisation," IET
Science, Measurement & Technology, vol. 10, no. 6, pp. 626-636, Sep. 2016, doi: 10.1049/iet-smt.2016.0023.
[15] T. Sharma and K. K. Sharma, "QRS Complex Detection in ECG Signals Using the Synchrosqueezed Wavelet
Transform," IETE Journal of Research, vol. 62, no. 6, pp. 885-892, Sep. 2016, doi:
10.1080/03772063.2016.1221744.
[16] S. Yazdani and J. Vesin, "Extraction of QRS fiducial points from the ECG using adaptive mathematical
morphology," Digital Signal Processing, vol. 56, pp. 100-109, Sep. 2016, doi: 10.1016/j.dsp.2016.06.010.
[17] D. Castells-Rufas and J. Carrabina, "Simple real-time QRS detector with the MaMeMi filter," Biomedical Signal
Processing and Control, vol. 21, pp. 137-145, Aug. 2015, doi: 10.1016/j.bspc.2015.06.001.
[18] F. Bouaziz, D. Boutana, and M. Benidir, "Multiresolution wavelet-based QRS complex detection algorithm suited
to several abnormal morphologies," IET Signal Processing, vol. 8, no. 7, pp. 774-782, Sep. 2014, doi: 10.1049/iet-
spr.2013.0391.
[19] G. Nallathambi and J. C. Príncipe, "Integrate and Fire Pulse Train Automaton for QRS detection," in IEEE
Transactions on Biomedical Engineering, vol. 61, no. 2, pp. 317-326, Feb. 2014, doi:
10.1109/TBME.2013.2282954.
[20] Y. Li, F. Hong, and J. Song, "A new approach of QRS complex detection based on matched filtering and triangle
character analysis," Australasian Physical & Engineering Sciences in Medicine, vol. 35, no. 3, pp. 341-356, Jul.
2012, doi: 10.1007/s13246-012-0149-x.
[21] Z. Zidelmal, A. Amirou, M. Adnane, and A. Belouchrani., "QRS detection based on wavelet coefficients,"
Computer Methods and Programs in Biomedicine, vol. 107, no. 3, pp. 490–496, Sep. 2012, doi:
10.1016/j.cmpb.2011.12.004.
[22] M. Adnane, Z. Jiang, and S. Choi., "Development of QRS detection algorithm designed for wearable
cardiorespiratory system," Computer Methods and Programs in Biomedicine, vol. 93, no. 1, pp. 20-31, Jan. 2009,
doi: 10.1016/j.cmpb.2008.07.010.
[23] F. Chiarugi, V. Sakkalis, D. Emmanouilidou, T. Krontiris, M. Varanini and I. Tollis, "Adaptive threshold QRS
detector with best channel selection based on a noise rating system," 2007 Computers in Cardiology, 2007,
pp. 157-160, doi: 10.1109/CIC.2007.4745445.
[24] M. Cvikl, F. Jager, and Z. Andrej, "Hardware Implementation of a Modified Delay-Coordinate Mapping-Based
QRS Complex Detection Algorithm," EURASIP Journal on Advances in Signal Processing, vol. 2007, no. 1,
Apr. 2007, doi: 10.1155/2007/57286.

4959
[25] M. Elgendi, M. Jonkman, and F. De Boer, "Frequency Bands Effects On QRS Detection," in Proceedings of the
Third International Conference on Bio-inspired Systems and Signal Processing, Valencia, Spain, vol. 1,
pp. 428-431, 2010, doi: 10.5220/0002742704280431.
[26] M. S. Manikandan and B. Ramkumar, "Straightforward and robust QRS detection algorithm for wearable cardiac
monitor," Healthcare Technology Letters, vol. 1, no. 1, pp. 40-44, Jan. 2014, doi: 10.1049/htl.2013.0019.
[27] M. S. Manikandan and K. P. Soman, "A novel method for detecting R-peaks in electrocardiogram (ECG) signal,"
Biomedical Signal Processing and Control, vol. 7, no. 2, pp. 118-128, Mar. 2012, doi: 10.1016/j.bspc.2011.03.004.
[28] J. Lewandowski, H. E. Arochena, R. N. G. Naguib and K. Chao, "A simple real-time QRS detection algorithm
utilizing curve-length concept with combined adaptive threshold for electrocardiogram signal classification,"
TENCON 2012 IEEE Region 10 Conference, 2012, pp. 1-6, doi: 10.1109/TENCON.2012.6412176.
[29] N. S. V. K. Chaitanya, A. Radhakrishnan, G. R. Reddy and M. S. Manikandan, "A simple and robust QRS
detection algorithm for wireless medical body area network," 2011 International Conference on Emerging Trends
in Networks and Computer Communications (ETNCC), 2011, pp. 153-158, doi: 10.1109/ETNCC.2011.5958505.
[30] B. Huang and Y. Wang, "Detecting QRS Complexes of Two-Channel ECG Signals by Using Combined Wavelet
Entropy," 2009 3rd International Conference on Bioinformatics and Biomedical Engineering, 2009, pp. 1-4, doi:
10.1109/ICBBE.2009.5162600.
[31] F. Abdelliche, A. Charef, and S. Ladaci, "Complex fractional and complex Morlet wavelets for QRS complex
detection," ICFDA'14 International Conference on Fractional Differentiation and Its Applications 2014, 2014,
pp. 1-5, doi: 10.1109/ICFDA.2014.6967456.
[32] W. Zhu, H. Zhao, and X. Chen, "A new QRS detector based on empirical mode decomposition," IEEE 10th
International Conference on Signal Processing Proceedings, 2010, pp. 1-4, doi: 10.1109/ICOSP.2010.5656499.
[33] S. A. Chouakri, F. B. Reguig, and A. T. Ahmed, "QRS complex detection based on multi wavelet packet
decomposition," Applied Mathematics and Computation, vol. 217, no. 23, pp. 9508-9525, Aug. 2011, doi:
10.1016/j.amc.2011.03.001.
[34] P. Phukpattaranont, "QRS detection algorithm based on the quadratic filter," Expert Systems with Applications,
vol. 42, no. 11, pp. 4867-4877, Jul. 2015, doi: 10.1016/j.eswa.2015.02.012.
[35] J.-W. Lee, K. S. Kim, B. Lee, B. Lee, and M. Ho. Lee, "A Real Time QRS Detection Using Delay-Coordinate
Mapping for the Microcontroller Implementation," Annals of Biomedical Engineering, vol. 30, no. 9,
pp. 1140-1151, Oct. 2002.
[36] J. Lee, K. Jeong, J. Yoon and M. Lee, "A simple real-time QRS detection algorithm," Proceedings of 18th Annual
International Conference of the IEEE Engineering in Medicine and Biology Society, vol. 4, 1996, pp. 1396-1398,
doi: 10.1109/IEMBS.1996.647473.
[37] C. J. Deepu and Y. Lian, "A Joint QRS Detection and Data Compression Scheme for Wearable Sensors," in IEEE
Transactions on Biomedical Engineering, vol. 62, no. 1, pp. 165-175, Jan. 2015, doi:
10.1109/TBME.2014.2342879.
[38] M. R. Arefin and R. Fazel-Rezai, "Computationally efficient QRS detection analysis based on dual-slope method,"
2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 2014,
pp. 2274-2277, doi: 10.1109/EMBC.2014.6944073.
[39] Y. Wang, C. J. Deepu and Y. Lian, "A computationally efficient QRS detection algorithm for wearable ECG
sensors," 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 2011,
pp. 5641-5644, doi: 10.1109/IEMBS.2011.6091365.
[40] C. F. Zhang and T. Bae, "VLSI Friendly ECG QRS Complex Detector for Body Sensor Networks," in IEEE
Journal on Emerging and Selected Topics in Circuits and Systems, vol. 2, no. 1, pp. 52-59, Mar. 2012, doi:
10.1109/JETCAS.2012.2187706.
[41] F. Zhang and Y. Lian, "QRS Detection Based on Morphological Filter and Energy Envelope for Applications in
Body Sensor Networks," Journal of Signal Processing Systems, vol. 64, no. 2, pp. 187-194, Nov. 2009, doi:
10.1007/s11265-009-0430-8.
[42] F. Zhang and Y. Lian, "QRS Detection Based on Multiscale Mathematical Morphology for Wearable ECG Devices
in Body Area Networks," in IEEE Transactions on Biomedical Circuits and Systems, vol. 3, no. 4, pp. 220-228,
Aug. 2009, doi: 10.1109/TBCAS.2009.2020093.
[43] K. Arbateni and A. Bennia, "Sigmoidal radial basis function ANN for QRS complex detection," Neurocomputing,
vol. 145, pp. 438-450, Dec. 2014, doi: 10.1016/j.neucom.2014.05.009.
[44] L. D. Sharma and R. K. Sunkaria, "A robust QRS detection using novel pre-processing techniques and kurtosis
based enhanced efficiency," Measurement, vol. 87, pp. 194-204, Jun. 2016, doi:
10.1016/j.measurement.2016.03.015.
[45] P. Li et al., "A 410-nW Efficient QRS Processor for Mobile ECG Monitoring in 0.18-μm CMOS," in IEEE
Transactions on Biomedical Circuits and Systems, vol. 11, no. 6, pp. 1356-1365, Dec. 2017, doi:
10.1109/TBCAS.2017.2731797.
[46] C.-L. Chen and C.-T. Chuang, "A QRS Detection and R Point Recognition Method for Wearable Single-Lead ECG
Devices," Sensors, vol. 17, no. 9, Aug. 2017, Art. no. 1969, doi: 10.3390/s17091969.
[47] N. Ravanshad, H. Rezaee-Dehsorkh, R. Lotfi and Y. Lian, "A Level-Crossing Based QRS-Detection Algorithm for
Wearable ECG Sensors," in IEEE Journal of Biomedical and Health Informatics, vol. 18, no. 1, pp. 183-192,
Jan. 2014, doi: 10.1109/JBHI.2013.2274809.
[48] S. Torbey, S. G. Akl and D. P. Redfearn, "Multi-lead QRS detection using window pairs," 2012 Annual
International Conference of the IEEE Engineering in Medicine and Biology Society, 2012, pp. 3143-3146, doi:
10.1109/EMBC.2012.6346631.

 ISSN: 2088-8708
4960
[49] W. Chin, C. Chang, C. Tseng, Y. Huang and T. Jiang, "Bayesian Real-Time QRS Complex Detector for Healthcare
System," in IEEE Internet of Things Journal, vol. 6, no. 3, pp. 5540-5549, 2019, doi: 10.1109/JIOT.2019.2903530.
[50] B. S. Shaik, G. V. S. S. K. R. Naganjaneyulu and A. V. Narasimhadhan, "A novel approach for QRS delineation in
ECG signal based on chirplet transform," 2015 IEEE International Conference on Electronics, Computing and
Communication Technologies (CONECCT), 2015, pp. 1-5, doi: 10.1109/CONECCT.2015.7383914.
[51] A. Karimipour and M. R. Homaeinezhad, "Real-time electrocardiogram P-QRS-T detection–delineation algorithm
based on quality-supported analysis of characteristic templates," Computers in Biology and Medicine, vol. 52,
pp. 153-165, Sep. 2014, doi: 10.1016/j.compbiomed.2014.07.002.
[52] S. Salih, S. A. Aljunid, A. Yahya, and K. Y. Ghailan, "A Novel Approach for Detecting QRS Complex of ECG
signal," International Journal of Computer Science, vol. 9, no. 6, pp. 205-2015, Nov. 2012.
[53] S. Taouli and F. Bereksi-Reguig, "Detection of QRS complexes in ECG signals based on empirical mode
decomposition," Global Journal of Computer Science and Technology, vol. 11, no. 20, pp. 11-17, 2011.
[54] Y. Yeh and W. Wang, "QRS complexes detection for ECG signal: The Difference Operation Method," Computer
Methods and Programs in Biomedicine, vol. 91, no. 3, pp. 245-254, Sep. 2008, doi: 10.1016/j.cmpb.2008.04.006.
[55] M. Paoletti and C. Marchesi, "Discovering dangerous patterns in long-term ambulatory ECG recordings using a fast
QRS detection algorithm and explorative data analysis," Computer Methods and Programs in Biomedicine, vol. 82,
no. 1, pp. 20-30, Apr. 2006, doi: 10.1016/j.cmpb.2006.01.005.
[56] J J. Pan and W. J. Tompkins, "A Real-Time QRS Detection Algorithm," in IEEE Transactions on Biomedical
Engineering, vol. BME-32, no. 3, pp. 230-236, Mar. 1985, doi: 10.1109/TBME.1985.325532.
[57] Z.-E. Hadj Slimane and A. Naït-Ali, "QRS complex detection using Empirical Mode Decomposition," Digital
Signal Processing, vol. 20, no. 4, pp. 1221-1228, Jul. 2010, doi: 10.1016/j.dsp.2009.10.017.
[58] P. S. Hamilton and W. J. Tompkins, "Quantitative Investigation of QRS Detection Rules Using the MIT/BIH
Arrhythmia Database," in IEEE Transactions on Biomedical Engineering, vol. BME-33, no. 12, pp. 1157-1165,
Dec. 1986, doi: 10.1109/TBME.1986.325695.
[59] C. Ieong, P. Mak, M. Vai and R. P. Martins, "Sub-µW QRS detection processor using quadratic spline wavelet
transform and maxima modulus pair recognition for power-efficient wireless arrhythmia monitoring," 2016 21st
Asia and South Pacific Design Automation Conference (ASP-DAC), 2016, pp. 21-22, doi:
10.1109/ASPDAC.2016.7427982.
[60] J. P. Sahoo et al., "Autocorrelation and Hilbert transform-based QRS complex detection in ECG signal,"
International Journal of Signal and Imaging Systems Engineering, vol. 7, no. 1, 2014, Art. no. 52, doi:
10.1504/IJSISE.2014.057939.
[61] Z. Zhang et al., "A Kalman filtering based adaptive threshold algorithm for QRS complex detection," Biomedical
Signal Processing and Control, vol. 58, Apr. 2020, Art. no. 101827, doi: 10.1016/j.bspc.2019.101827.
[62] X. Lu et al., "QRS Detection Based on Improved Adaptive Threshold," Journal of Healthcare Engineering,
vol. 2018, pp. 1-8, 2018, doi: 10.1155/2018/5694595.
[63] X. Zhang and Y. Lian, "A 300-mV 220-nW Event-Driven ADC With Real-Time QRS Detection for Wearable ECG
Sensors," in IEEE Transactions on Biomedical Circuits and Systems, vol. 8, no. 6, pp. 834-843, Dec. 2014, doi:
10.1109/TBCAS.2013.2296942.
[64] S. Farashi, "A multiresolution time-dependent entropy method for QRS complex detection," Biomedical Signal
Processing and Control, vol. 24, pp. 63-71, Feb. 2016, doi: 10.1016/j.bspc.2015.09.008.
[65] A. Chen et al., "A Real Time QRS Detection Algorithm Based on ET and PD Controlled Threshold Strategy,"
Sensors, vol. 20, no. 14, Jul. 2020, Art. no. 4003, doi: 10.3390/s20144003.
[66] X. Tang, Q. Hu, and W. Tang, "A Real-Time QRS Detection System With PR/RT Interval and ST Segment
Measurements for Wearable ECG Sensors Using Parallel Delta Modulators," in IEEE Transactions on Biomedical
Circuits and Systems, vol. 12, no. 4, pp. 751-761, Aug. 2018, doi: 10.1109/TBCAS.2018.2823275.
[67] Y. Zhao, Z. Shang, and Y. Lian, "User Adaptive QRS Detection Based on One Target Clustering and Correlation
Coefficient," 2018 IEEE Biomedical Circuits and Systems Conference (BioCAS), 2018, pp. 1-4, doi:
10.1109/BIOCAS.2018.8584803.
[68] M. Elgendi, A. Mohamed, and R. Ward, "Efficient ECG Compression and QRS Detection for E-Health
Applications," Scientific Reports, vol. 7, no. 1, Mar. 2017, doi: 10.1038/s41598-017-00540-x.
[69] J. Darrington, "Towards real time QRS detection: A fast method using minimal pre-processing," Biomedical Signal
Processing and Control, vol. 1, no. 2, pp. 169–176, Apr. 2006, doi: 10.1016/j.bspc.2006.08.002.
[70] A. Ghaffari, H. Goldbayani, and M. Ghasemi, "A new mathematical based QRS detector using continuous wavelet
transform," Computers & Electrical Engineering, vol. 34, no. 2, pp. 81–91, Mar. 2008, doi:
10.1016/j.compeleceng.2007.10.005.
[71] Z. Hou, Y. Dong, J. Xiang, X. Li, and B. Yang, "A Real-Time QRS Detection Method Based on Phase Portraits
and Box-Scoring Calculation," in IEEE Sensors Journal, vol. 18, no. 9, pp. 3694-3702, May 2018, doi:
10.1109/JSEN.2018.2812792.
[72] J. Rahul, M. Sora, and L. D. Sharma, "Exploratory data analysis based efficient QRS-complex detection technique
with minimal computational load," Physical and Engineering Sciences in Medicine, vol. 43, no. 3, pp. 1049–1067,
Jul. 2020, doi: 10.1007/s13246-020-00906-y.

4961
BIOGRAPHIES OF AUTHORS
Akram Jaddoa Khalaf was born in Hilla, Babylon, Iraq, in 1978. He received the B.Sc. degree
in Electrical Engineering in 2001 from the University of Babylon, the HD degree in Computer
Science/Engineering Applications in 2002 from the Iraqi Commission for Computer &
Informatics, and the M.Sc. degree in Electrical Engineering/Electronics and Communications in
2013 from the University of Babylon. He is a staff member at the University of Babylon, Faculty
of Engineering, Biomedical Department, and he is currently a Ph.D. student at the University of
Babylon. His research interests include Wireless Sensor Networks, Biomedical informatics,
Signal Processing, Healthcare systems, Networking, and Machine Learning.
Samir Jasim Mohammed was born in Hilla, Babylon, Iraq, in 9 Oct. 1959. He received the
B.Sc. degree in Electrical Engineering/Electronics and Communications in 1981 from the
University of Sulaymaniyah, the M.Sc. degree in Electrical Engineering/Electronics and
Communications in 1986 from the University of Baghdad, and the Ph.D. degree in
Communication Engineering from the Department of Technical Education-Electrical
Engineering at University of Technology. Currently, he is professor and Head of the Scientific
Composition at the Electrical Engineering Department, University of Babylon. His research
interest is Wireless Communication, Digital Video Broadcasting, Wireless sensor network,
Biomedical informatics, Signal Processing, Healthcare System.

Verification and comparison of MIT-BIH arrhythmia database based on number of beats

More Related Content

What's hot (20)

Similar to Verification and comparison of MIT-BIH arrhythmia database based on number of beats (20)

More from IJECEIAES (20)

Recently uploaded (20)

Verification and comparison of MIT-BIH arrhythmia database based on number of beats