Conference PaperPDF Available

Arrhythmia Classification Using Waveform ECG Signals

Authors:
  • Iskenderun Technical University, Hatay, Turkey
  • Iskenderun Technical University
  • KTO Karatay Univeristy

Abstract and Figures

Introduction: An electrocardiogram (ECG) is a non-linear and non-stationary diagnostic signal that has a great importance for cardiac disorders. The computer-assisted analysis of biomedical signals has become an essential tool in recent years. Classifier: This study introduces a deep learning (DL) application on automatic arrhythmia classification. The proposed model consists of a multi-stage classification system on raw ECG using DL algorithms. Deep belief network (DBN) is one of the most effective DL algorithms which have a greedy layer wise training phase. The DBN is composed of both Restricted Boltzmann Machines (RBM) based layer-by-layer unsupervised pre-training procedure and neural network based supervised training. Database: The multistage DBN model classified the MIT-BIH Arrhythmia Database heartbeats into 5 main groups defined by ANSI/AAMI standard: normal beat (N), supraventricular ectopic heartbeat (S), ventricular ectopic heartbeat (V), fusion heartbeat (F), and unknown heartbeat (Q). Preprocessing: All ECGs are filtered with median filters to remove the baseline wander. 6077 of ECGs were segmented from long-term ECGs using a window with a length of 501 data points (R peak of the wave is located at the center of window). All data points are normalized to a [0, 1] range. And the normalized filtered raw ECGs are directly used as features in the DBN. Results: The proposed DBN-based multistage arrhythmia classification has discriminated five types of heartbeats with a high accuracy rate of 95.05%. The achievements prove the success and efficiency of the DBN algorithm on raw ECG signals.
Content may be subject to copyright.
ARRHYTHMIA CLASSIFICATION USING
WAVEFORM ECG SIGNALS
Yakup KUTLU*, Gokhan ALTAN+, Novruz ALLAHVERDI#
*Iskenderun Technical University, Hatay, TURKEY
yakupkutlu@gmail.com
+Mustafa Kemal University, Hatay, TURKEY
gokhan_altan@hotmail.com
#KTO Karatay University, Konya, TURKEY
novruz.allahverdi@karatay.edu.tr
Abstract— An electrocardiogram (ECG) is a non-linear and non-
stationary diagnostic biomedical signal that has a great
importance for cardiac disorders. The computer-assisted analysis
of biomedical signals has become an essential tool in recent years.
This study introduces a deep learning application in automatic
arrhythmia classification. The proposed model consists of a
multi-stage classification system in raw ECG using a Deep belief
network (DBN) which has a greedy layer wise training phase.
The multistage DBN model classified the MIT-BIH Arrhythmia
Database heartbeats into 5 main groups defined by ANSI/AAMI
standards. All ECGs are filtered with median filters to remove
the baseline wander. ECG waveforms were segmented from
long-term ECGs using a window with a length of 501 data points
(R peak of the wave is located at the centre of the window). The
proposed DBN-based multistage arrhythmia classification has
discriminated five types of heartbeats with a high accuracy rate
of 95.05%.
KeywordsArrhythmia, Deep Belief Networks, Deep Learning,
AAMI, Raw ECG Waveform
I. INTRODUCTION
According to the World Health Organization surveys [1],
heart diseases are one of the most important reasons which
cause death. Heart disease symptoms depend on what type of
heart disease you have. An electrocardiogram (ECG) is a non-
linear and non-stationary diagnostic signal that is important
for cardiac disorders [2]. It is hard to assess a cardiac disorder
using ECG because of long processes that need a control in
detail and infrequent arrhythmias. In order to overcome these
challenges, the computer-assisted analysis of biomedical
signals has become an essential method in recent years. The
computer assisted diagnosis and analysis systems achieve
rapid and advanced assessments in long, and hard to identify
processes. Arrhythmia and many cardiac disorders usually
need to use long-term ECG in inspection controls [3].
Therefore, computer-based methods and diagnosis systems
provide major simplicity and reliability in the diagnosis and
treatment of the diseases for cardiologists.
Arrhythmia is a problem concerning the abnormal rhythm
and rate of heartbeats. The heart can beat too fast, too slowly,
or inconsistently in different types of arrhythmias, which may
feel like antagonism affection or fluttering. Arrhythmia may
be classified by rate of heartbeats, mechanism (automaticity,
re-entry, triggered) or duration of the heartbeats [4]. Several
types of arrhythmia are harmless, but some of them refer the
cardiac disorders that may cause death. The ECG is a popular
diagnosis tool which is of the primary importance for
cardiologists [5].
There are many studies that are used for detecting
arrhythmias, classifying them and diagnosing cardiac diseases
that occur as a result of arrhythmias. These studies can be
incorporated into two basic feature extractions: fiducial and
non-fiducial methods. The fiducial methods contain the local
features such as temporal, morphological, amplitude, duration,
interval and segments between two selected waves which are
extracted from ECG waveforms. These methods are based on
the time-domain features on the ECG [6]. The non-fiducial
methods are based on the frequency-domain features such as
wavelet transformations, and the other digital signal
processing techniques that extract new signal forms, sub-
bands and coefficients from ECG waveforms [7].
Deep learning (DL) is an effective and high-performance
machine learning algorithm which is gaining popularity.
Frequently used analyses of the DL are used in image
processing, speech and natural language processing processes.
Actually, DL is a neural network structure which addresses
the deeper feature levels using more hidden layers [8]. In this
study, Deep Belief Networks (DBN), which is an adaptable
DL algorithm, is utilized to classify the heartbeats from
different classes of arrhythmia using ECG waveform as input
of the structure.
The remainder of the paper is structured in the following
manner. The database and the arrhythmia types are defined by
AAMI standards, pre-processing, and feature extraction from
arrhythmia heartbeats are described in detail. The proposed
multistage classification system is explained. The
experimental results that are obtained using the DBN classifier
are presented.
International Conference on Advanced Technology & Sciences (ICAT’16) September 01-03, 2016 Konya-Turkey
240
_____________________________________________________________________________________________________________
____________________________________________________________________________________________________________
II. MATERIALS AND METHODS
The general management of medical treatment and
assessment systems has become effective and convenient
processes because of the recent technological developments in
integrated circuit systems and computer-aided intelligent
monitoring and diagnosis systems. In this section,
information about ECG waveforms and the DBN classifier are
described in detail.
A. Database
There are several arrhythmia databases in the literature. In
this study, the MIT-BIH arrhythmia database (MADB) is
utilized [9]. This database has been used for evaluating
arrhythmia detection and classifying the arrhythmia types.
MADB contains 48 long-term ECGs from 25 men aged 32–89
years, and 22 women aged 23–89 years; each has 11-bit
resolution with 360 Hz sampling frequency. The heartbeats
are labelled as five main arrhythmia types defined by the
Association for the Advancement of Medical Instruments
(AAMI) standard. AAMI standardizations provide an
objective, understanding, and dividual assessments and
monitoring processes of the arrhythmia types for clinical
treatments and an increased capability of testing and training
abilities for supervised learning phases [10]. AAMI classifies
heartbeats into normal beats (N), supraventricular ectopic
heartbeats (S), ventricular ectopic heartbeats (V), fusion
heartbeats (F), and unknown heartbeats (Q). The testing and
training dispersions of the heartbeats from the MADB are
seen in Table I.
TABLE I
DISPERSION OF MADB ACCORDING TO AAMI STANDARDS AND
QUANTITIES OF TEST AND TRAINING SETS
AAMI
classes MIT-BIH heartbeat classes Train
Set
Test
Set
N
Normal beat
Left bundle branch block beat
Right bundle branch block beat
Nodal escape beat
Atrial escape beat
350
350
350
114
8
250
250
250
113
8
S
Aberrated atrial premature beat
Premature or ectopic
supraventricular
Atrial premature contraction beat
Nodal premature beat
74
1
350
42
74
1
250
41
V
Ventricular flutter wave beat
Ventricular escape beat
Premature ventricular contraction
beat
236
53
350
236
53
250
F Fusion of ventricular and normal
beat 350 350
Q
Paced beat
Unclassifiable beat
Fusion of paced and normal beat
350
17
350
250
16
250
Long-term ECG signals can be contaminated by several
types of noise, such as motion during ECG recording,
electromyogram noise, contact noise, clinician artefacts,
coughing, position of patient, baseline wandering, etc. All
ECGs are filtered with two median filters to remove the
baseline wander [11]. 6077 short-term ECGs were segmented
from long-term ECGs using a window with a length of 501
data points (R peak of the wave is located at the center of
window). All data points are normalized to a [0, 1] range.
B. ECG Waveform
The ECG is a method that finds out the regularity or
irregularity of heart beats and heart rates using the electrical
activity of the heart. The recorded electrical activities of the
heart represent for a waveform on the clinical assessments.
These waveforms may have different forms according to the
lead of the ECG [11], [12]. The use of the ECG in medical
assessment processes is very important in detecting the
different waveforms and various cardiovascular heart diseases.
In the entire body only the heart muscle has the ability to
contract spontaneously. Polarity is the event of discharge of
electrical charge of heart tissue. Depolarization is the positive
charging case of electrical activation in heart tissue [13].
The ECG has 0 mV to 5 mV amplitude and a frequency
band between 0.5 Hz and 100 Hz [2], [13]. P, Q, R, S, T and
U waves appear over the baseline in the signal, respectively. If
the amplitude of Q, R and S waves is less than 5 mV, the
wave is referred to using small capitals (q, r, and s). The
remaining portion between the waves is a segment; the
distance between the waves is an interval [12].
Fig. 1 ECG waveform with P, Q, R, S, and T waves
A P wave occurs as the result of the depolarization of the
atrium. First, the right atrium then the left atrium depolarizes.
Therefore, the first part of the P wave occurs when the right
atrium depolarizes; second part of the P wave occurs when the
left atrium depolarizes. Although it depends on the time of the
year, the duration of the P wave is about 0.11 seconds; the
amplitude of the P wave is between 0.18 mV and 0.22 mV on
a normal lead [2].
The QRS complex occurs as the result of the depolarization
of the ventricles. One of the waves (R) forming the QRS
complex is positive; the other two waves (Q and S) are
negative. The Q wave represents the first negative wave after
the P wave; the R wave represents the first positive wave after
the P wave and the S wave represents the next negative wave
after the R wave. The QRS monitored complex varied in
different leads. The QRS samples show significant differences
even among normal individuals. R and S waves refer to the
contraction of the myocardium. The QRS complex indicates
the current causing the left and right ventricle contraction [14].
The QRS complex has the maximum amplitude between the
ECG forms. The duration of the QRS complex does not
International Conference on Advanced Technology & Sciences (ICAT’16) September 01-03, 2016 Konya-Turkey
241
_____________________________________________________________________________________________________________
____________________________________________________________________________________________________________
exceed 0.11 seconds and has an amplitude value up to 2-3 mV
[2].
The T-wave occurs as a result of ventricular re-polarization.
The T-wave may have a pointed or flat view and positive,
negative or biphasic value on various leads. The duration of
the T wave that belongs to a normal subject is between 0.10
and 0.25 seconds. It takes place after about 300ms from the
QRS complex. The positions of these waves vary according to
the heart rhythm. The T wave is closer to the QRS complex
when the heart rhythm accelerates [14].
C. Deep Belief Networks
This study introduces a deep learning (DL) application for
automatic arrhythmia classification. The proposed model
consists of a multi-stage classification system of raw ECG
using DL algorithms. The DBN is one of the most effective
DL algorithms which has a greedy layer wise training phase
[15]. The DBN is composed of both Restricted Boltzmann
Machines (RBM) or an autoencoder based layer-by-layer
unsupervised pre-training procedure and neural network based
supervised training [8], [16]. Considering RBM with input
layer activations (for visible units) and hidden layer
activations (hidden units), bias of the visible unit , bias of
hidden unit :
(,)=     (1)
(,)=(,)
(,) (2)
(,) represents the joint distribution of the RBM and
(,) represents the energy function of the distribution.
RBM is used for calculating the conditional distribution of the
visible and hidden units. Each adjacent two layers create an
RBM. The first visible unit is the input feature vector and the
other RBM parameters = (,,) are denoted by
depending on the first visible unit [17].
In the unsupervised training phase, the sub-network's
hidden layer serves as the visible layer for the next adjacent
layer applying contrastive divergence and the probabilistically
reconstruction of the shared weights is implemented [8]. In the
supervised training phase of the DBN, the calculated shared
weights and the structure of the DBN are unfolded to a neural
network structure for fine-tuning all the parameters of the
deep structure such as the weights and the biases [15]. The
DBN consists of at least two hidden layers (latent variables) in
the neural network. The number of the hidden layers is related
to the deep analysis of the input features in detail [15], [17].
III. EXPERIMENTAL RESULTS
The morphological features are the ones most used in
clinical trials for the diagnosis of the arrhythmia types. The
robust and steady detection of arrhythmia is a common need
for all the cardiac diseases. Each arrhythmia type can be
related to different types of cardiac and pulmoner diseases.
That’s why detection and classification of the arrhythmia
types are so important in the early diagnosis and early
treatment processes. Considering the importance of the
classification of the arrhythmia types, a computer-aided
classification of the 5 arrhythmia types is implemented using a
DBN-based multistage classification. Figure 2 depicts the
structure of the arrhythmia classification model.
Fig. 2 Structure of proposed Arrhythmia Classification Method
Two median filters are applied to remove the noise and the
baseline wanders to raw ECGs. Analysis of the long-term
ECGs is a demanding process for clinicians and also for
computer-aided systems. Considering this situation, ECG
waveforms were extracted from long-term ECGs using the
moving window analysis technique. The R peak centred
window with 501 data points was moved to extract ECG
waveforms. 6077 of ECG waveforms were obtained from
long-term ECGs. ECG waveforms with 501 data points were
directly used as features. Having a great number of the feature
dimensionality causes long and deceiving training processes
for the supervised machine learning algorithms. Feature
dimensionality reduction for the provides for the extraction of
more meaningful classification rules, the elimination of the
pointless feature vector for machine learning algorithms, the
improvement of generalization capabilities using fewer
parameters and reduced complexity and run-time and for the
evaluation and prediction of accuracy for classifiers [18]. The
sequential forward feature selection algorithm is utilized in the
proposed method to reduce feature dimensionality [19]. The
algorithm selects a subset of features which are not yet
selected from 501 data points and the best predict the
arrhythmia types by sequentially selecting features until there
is no improvement in the prediction. The highest accuracy is
achieved using 106 features from the ECG waveforms. The
reduced feature vector is normalized to 0-1. The proposed
DBN-based multistage classifier was trained using 106 data
points. Selected data points on the ECG waveform are seen in
Figure 3 with the red asterisk.
International Conference on Advanced Technology & Sciences (ICAT’16) September 01-03, 2016 Konya-Turkey
242
_____________________________________________________________________________________________________________
____________________________________________________________________________________________________________
Fig. 3 Selected data points from ECG waveforms after feature
dimensionality reduction (Red asterisk)
The proposed multistage DBN model separates N, S, V, F,
and Q types of arrhythmias, respectively. 4 of the DBN
models are used in the proposed system. The RBM based
greedy layer-wise pre-training is used in this model at the
unsupervised learning stages of all DBNs with 5 epochs. The
parameters of the RBM were denoted by iterations. The
models were tested with a limited number of the parameters
and the highest classification performances are given. The
learning rate of the model is 3 and the softmax output function
was utilized constantly. The proposed multistage arrhythmia
classification model consists of 4 DBN structures with various
numbers of hidden units. The DBN1 has 2 hidden layers with
100-260 hidden units; the DBN2 has 3 hidden layers with
230-520-210 hidden units; the DBN3 has 2 hidden layers with
120-240 hidden units; and the DBN4 has 2 hidden layers with
70-190 hidden units. The four DBN structures are connected
sequentially and have the ability to separate five classes of
arrhythmia types defined by ANSI/AAMI.
The training set of the DBN-based automatic arrhythmia
classification model includes 4,077 of ECG waveforms from
various types of heartbeat classes distributed homogeneously.
The DBN-based multistage model is tested using 2,000 of
ECG waveforms. The confusion matrix of the classifier is
seen in Table II.
TABLE II
CONFUSION MATRIX OF MULTISTAGE CLASSIFIER
Labels Predicted heartbeats
N S V F Q
True heartbeats
N 489 2 8 9 3
S 0 290 7 3 8
V 2 0 472 2 5
F 4 5 9 179 13
Q 5 3 4 7 471
Zhang et al. used inter-beat features, amplitude morphology
and morphological distance features for separating 4 types of
arrhythmia by the Support Vector Machines (SVM)
classification algorithm with 86.66%, 93.81%, and 98.98% for
accuracy, sensitivity, and selectivity, respectively [20]. Melin
et al. utilized cycle features and fiducial features with an
Artificial Neural Network (ANN) and Learning Vector
Quantization based multistage classification algorithm and
classified 15 types of arrhythmia with an accuracy rate of
99.16% [21]. Thomas et al. extracted wavelet based
coefficients from 4th and 5th scale of Wavelet transform, high
order statistics and fiducial features using the QRS complex
from the ECG with ANN and presented an accuracy rate of
94.64% and a sensitivity rate of 94.60% for 5 classes of
arrhythmia types [22]. Batra et al. utilized invariant features
and Principle Component Analysis features using the SVM
classifier with the cross validation technique and achieved an
accuracy rate of 84.82% for 11 classes of arrhythmia types
[23]. Leutheuser et al. compared the Naive Bayes and k-NN
classifier algorithms using statistical and high order statistical
features, heartbeat features and template based features from
segmented ECGs for the real-time classification of 2 types of
arrhythmias on android-based mobile devices with reported
accuracies of 93.30% and 56.10% for k-NN and Naive Bayes
classifiers, respectively [24]. Alajlan et al. extracted
morphological features, high order statistical features and non-
fiducial features applying the Discrete wavelet transform, S
transform and classified arrhythmia types into 2 classes using
the SVM machine learning algorithm with high performances
of 93.49%, and 93.14% for accuracy, and sensitivity,
respectively [25].
DL algorithms, especially the DBN, are being effectively
used in ECG analysis. The DBN is utilized at both feature
extraction [26], [27] and classification stages [16], [28].
Huanhuan et al. used the DBN-based learning features from
complete waveforms and R-R timing interval features with a
multi-stage (5 stages) SVM classifier model. They achieved
an accuracy rate of 98.82% for 6 classes of arrhythmia types
[27]. Rahhal et al. extracted temporal features, morphological
features and DBN-based features using stacked denoising
autoencoders. They fed the all features to the SVM for
training and classification. They classified 2 classes of
arrhythmia types defined by ANSI/AAMI with an overall
accuracy rate of 98.49% [26]. Yan et al. utilized R-R interval
features, beat features and raw ECG signals from multi-lead to
feed the DBN classifier and achieved a high accuracy rate of
98.82% for 12 classes of arrhythmia types [16]. There are lots
of studies based on different types of arrhythmia classification.
We focused on the arrhythmia types defined by ANSI/AAMI
and the considerable studies are compared in Table 3.
TABLE III
COMPARISON OF THE RELATED WORKS FOCUSED ON
ARHYTHMIA DETECTION DEFINED BY AAMI
Related
Works
Features Classifier Accuracy
Owis et al.
[29]
Correlation dimension,
Lyapunov exponents
k-NN 86.67%
Martis et al.
[30]
DWT, LDA, PCA PNN 99.28%
Kim et al.
[31]
CWT, Morphological
feature, DWT, PCA, LDA
ELM 97.94%
Tadejko et
al. [32]
Morphological features,
Wavelet Transform
SVM 97.82%
Llamedo et
al. [33]
Wavelet Transform,
Morphological features
LD 78.00%
Alvarado et
al. [34]
Pulse based features LD 93.60%
Ye et al. [35] Interval Features, Wavelet
Transform, ICA, PCA
SVM 86.40%
International Conference on Advanced Technology & Sciences (ICAT’16) September 01-03, 2016 Konya-Turkey
243
_____________________________________________________________________________________________________________
____________________________________________________________________________________________________________
Proposed ECG Waveform DBN 95.05%
CWT: Continuous Wavelet Transform, LD: Linear Discriminant, ELM: Extreme Le arning
Machines, PNN: Probabilistic Neural Network, DWT: Discrete Wavelet Transform
It is hard to compare the studies in a stable way, because of
reasons such as the different number of subjects, different
number of the arrhythmia types, different subjects, different
databases and different classification types. High
classification performances are reported in the literature. In
this study, the efficiency of the DL algorithms has been
proven with high classification performances of 95.05%,
93.87%, and 94.51% for accuracy, sensitivity, and selectivity,
respectively.
IV. CONCLUSIONS
PQRS complexes and T waves plots a regular form in
normal sinus rhythm. Any obvious changes occurring in the
PQRST lines indicate the irregularity or arrhythmia in
heartbeats. Since the determination of the features such as
intervals, segment measurements, heart rate, and the
frequency of R waves have great benefits for clinicians to
identify the cardiac diseases and arrhythmias, the physiology
and the morphology of the ECG waveforms have frequently
been used in clinical trials [12], [14]. The meaningful data
points for arrhythmia classification are thickened between S-T
waves and P-Q waves for the proposed DBN-based multistage
classification model.
The proposed DBN-based multistage arrhythmia
classification has discriminated five types of heartbeats with a
high accuracy rate of 95.05%. The achievements prove the
success and efficiency of the DBN algorithm in raw ECG
signals.
REFERENCES
[1] WHO, “The top 10 causes of death.” [Online]. Available:
http://www.who.int/mediacentre/factsheets/fs310/en/. [Accessed: 07-
Aug-2016].
[2] J. G. Webster, Medical Instrumentation, Application and Design, 4th ed.
Boston: Houghtoon Mifflin Company, 1978.
[3] Y. C. Yeh, C. W. Chiou, and H. J. Lin, “Analyzing ECG for cardiac
arrhythmia using cluster analysis,” Expert Syst. Appl., vol. 39, no. 1, pp.
1000–1010, 2012.
[4] P. Hamilton, “Open source ECG analysis,” Comput. Cardiol., vol. 29,
pp. 101–104, 2002.
[5] D. Ge, N. Srinivasan, and S. M. Krishnan, “Cardiac arrhythmia
classification using autoregressive modeling.,” Biomed. Eng. Online, vol.
1, p. 5, 2002.
[6] S. A. Israel, J. M. Irvine, A. Cheng, M. D. Wiederhold, and B. K.
Wiederhold, “ECG to identify individuals,” Pattern Recognit., vol. 38,
no. 1, pp. 133–142, 2005.
[7] K. N. Plataniotis, D. Hatzinakos, and J. K. M. Lee, “ECG Biometric
Recognition Without Fiducial Detection,” in 2006 Biometrics
Symposium: Special Session on Research at the Biometric Consortium
Conference, 2006, pp. 1–6.
[8] Y. Bengio and O. Delalleau, “Justifying and generalizing contrastive
divergence,” Neural Comput., vol. 21, no. 6, pp. 1601–1621, 2009.
[9] G. B. Moody and R. G. Mark, “The impact of the MIT-BIH arrhythmia
database.,” IEEE Eng. Med. Biol. Mag., vol. 20, no. 3, pp. 45–50.
[10] Y. Kutlu and D. Kuntalp, “A multi-stage automatic arrhythmia
recognition and classification system,” Comput. Biol. Med., vol. 41, no.
1, pp. 37–45, 2011.
[11] U. Rajendra Acharya, J. S. Suri, J. A. E. Spaan, and S. M. Krishnan,
Advances in cardiac signal processing. 2007.
[12] M. Gabriel Khan, Rapid ECG Interpretation(Contemporary Cardiology),
3rd editio. Humana Press, 2007.
[13] Dr Patrick Davey, “ECG (electrocardiogram),” NetDoctor, pp. 1–4,
2011.
[14] S. Kara, “Sensing of ECG signals and Imaging at the Computer in Real
Time,” Erciyes University, 1991.
[15] Y. Bengio, P. Lamblin, D. Popovici, and H. Larochelle, “Greedy Layer-
Wise Training of Deep Networks,” Adv. Neural Inf. Process. Syst., vol.
19, no. 1, p. 153, 2007.
[16] Y. Yan, X. Qin, Y. Wu, N. Zhang, J. Fan, and L. Wang, “A restricted
Boltzmann machine based two-lead electrocardiography classification,”
2015 IEEE 12th International Conference on Wearable and Implantable
Body Sensor Networks (BSN). pp. 1–9, 2015.
[17] G. E. Hinton, S. Osindero, and Y.-W. Teh, “A fast learning algorithm
for deep belief nets.,” Neural Comput., vol. 18, no. 7, pp. 1527–54, 2006.
[18] H. S. Lee, Q. lan Cheng, and N. V. Thakor, “ECG waveform analysis by
significant point extraction. I. Data reduction,” Comput. Biomed. Res.,
vol. 20, no. 5, pp. 410–427, 1987.
[19] D. Ververidis and C. Kotropoulos, “Sequential forward feature selection
with low computational cost,” in Signal Processing Conference 2005
13th European, 2005, vol. 13, pp. 1–4.
[20] Z. Zhang, J. Dong, X. Luo, K. S. Choi, and X. Wu, “Heartbeat
classification using disease-specific feature selection,” Comput. Biol.
Med., vol. 46, no. 1, pp. 79–89, 2014.
[21] P. Melin, J. Amezcua, F. Valdez, and O. Castillo, “A new neural
network model based on the LVQ algorithm for multi-class
classification of arrhythmias,” Inf. Sci. (Ny)., vol. 279, pp. 483–497, Sep.
2014.
[22] 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.
[23] A. Batra and V. Jawa, “Classification of Arrhythmia Using Conjunction
of Machine Learning Algorithms and ECG Diagnostic Criteria,” Int. J.
Biol. Biomed., vol. 1, pp. 1–7, 2016.
[24] H. Leutheuser, S. Gradl, P. Kugler, L. Anneken, M. Arnold, S.
Achenbach, and B. M. Eskofier, “Comparison of real-time classification
systems for arrhythmia detection on Android-based mobile devices,”
IEEE Eng. Med. Biol. Soc. Annu. Conf., vol. 2014, pp. 2690–2693, 2014.
[25] N. Alajlan, Y. Bazi, F. Melgani, S. Malek, and M. A. Bencherif,
“Detection of premature ventricular contraction arrhythmias in
electrocardiogram signals with kernel methods,” Signal, Image Video
Process., vol. 8, no. 5, pp. 931–942, Jul. 2014.
[26] M. M. Al Rahhal, Y. Bazi, H. AlHichri, N. Alajlan, F. Melgani, and R.
R. Yager, “Deep Learning Approach for Active Classification of
Electrocardiogram Signals,” Inf. Sci. (Ny)., vol. 345, pp. 340–354, Feb.
2016.
[27] M. Huanhuan and Z. Yue, “Classification of Electrocardiogram Signals
with Deep Belief Networks,” Computational Science and Engineering
(CSE), 2014 IEEE 17th International Conference on. pp. 7–12, 2014.
[28] N. Allahverdi, G. Altan, and Y. Kutlu, “Diagnosis of Coronary Artery
Disease Using Deep Belief Networks,” 2. Int. Conf. Eng. Nat. Sci., The
Book of Abstracts p.9, 2016.
[29] M. I. Owis, A. H. Abou-Zied, a. B. M. Youssef, and Y. M. Kadah,
“Study of features based on nonlinear dynamical modeling in ECG
arrhythmia detection and classification,” IEEE Trans. Biomed. Eng., vol.
49, no. 7, pp. 733–736, 2002.
[30] R. J. Martis, U. R. Acharya, C. M. Lim, and J. S. Suri, “Characterization
of ECG beats from cardiac arrhythmia using discrete cosine transform in
PCA framework,” Knowledge-Based Syst., vol. 45, pp. 76–82, 2013.
[31] J. Kim, S. D. Min, and M. Lee, “An arrhythmia classification algorithm
using a dedicated wavelet adapted to different subjects.,” Biomed. Eng.
Online, vol. 10, no. 1, p. 56, 2011.
[32] P. Tadejko and W. Rakowski, “Hybrid wavelet-mathematical
morphology feature extraction for heartbeat classification,” in
EUROCON 2007 - The International Conference on Computer as a
Tool, 2007, pp. 127–132.
[33] M. Llamedo and J. P. Martinez, “Heartbeat classification using feature
selection driven by database generalization criteria,” IEEE Trans.
Biomed. Eng., vol. 58, no. 3 PART 1, pp. 616–625, 2011.
[34] A. S. Alvarado, C. Lakshminarayan, and J. C. Príncipe, “Time-based
compression and classification of heartbeats,” IEEE Trans. Biomed.
Eng., vol. 59, no. 6, pp. 1641–1648, 2012.
[35] C. Ye, B. V. K. Vijaya Kumar, and M. T. Coimbra, “Heartbeat
International Conference on Advanced Technology & Sciences (ICAT’16) September 01-03, 2016 Konya-Turkey
244
_____________________________________________________________________________________________________________
____________________________________________________________________________________________________________
classification using morphological and dynamic features of ECG
signals,” IEEE Trans. Biomed. Eng., vol. 59, no. 10, pp. 2930–2941,
2012.
International Conference on Advanced Technology & Sciences (ICAT’16) September 01-03, 2016 Konya-Turkey
245
_____________________________________________________________________________________________________________
____________________________________________________________________________________________________________
... Periodic signals exist in daily lives. In biomedical domain, electrocardiogram (ECG) [18] and body temperature [16,25] are critical periodic signals in examining patients health status. ECG, in particular, is an important measure to diagnose patient heart diseases [14] such as Myocardial Infarction, AV Block, and Ventricular Tachycardia. ...
Preprint
Full-text available
Periodic signals play an important role in daily lives. Although conventional sequential models have shown remarkable success in various fields, they still come short in modeling periodicity; they either collapse, diverge or ignore details. In this paper, we introduce a novel framework inspired by Fourier series to generate periodic signals. We first decompose the given signals into multiple sines and cosines and then conditionally generate periodic signals with the output components. We have shown our model efficacy on three tasks: reconstruction, imputation and conditional generation. Our model outperforms baselines in all tasks and shows more stable and refined results.
... Cardiac disease is detected through the analyses of variation in the morphology of the ECG signal. The characteristic feature of a normal ECG signal during one cardiac cycle is the P-wave followed by the QRS complex continued by a T-wave [10,11]. The sample of the normal ECG signal is shown in Fig. 1 [12]. ...
Article
Full-text available
Electrocardiogram (ECG) signal is one of the most reliable methods to analyse the cardiovascular system. In the literature, there are different deep learning architectures proposed to detect various types of tachycardia diseases, such as atrial fibrillation, ventricular fibrillation, and sinus tachycardia. Even though all types of tachycardia diseases have fast beat rhythm as the common characteristic feature, existing deep learning architectures are trained with the corresponding disease-specific features. Most of the proposed works lack the interpretation and understanding of the results obtained. Hence, the objective of this letter is to explore the features learned by the deep learning models. For the detection of the different types of tachycardia diseases, the authors used a transfer learning approach. In this method, the model is trained with one of the tachycardia diseases called atrial fibrillation and tested with other tachycardia diseases, such as ventricular fibrillation and sinus tachycardia. The analysis was done using different deep learning models, such as RNN, LSTM, GRU, CNN, and RSCNN. RNN achieved an accuracy of 96.47% for atrial fibrillation data set, 90.88% accuracy for CU-ventricular tachycardia data set, and also achieved an accuracy of 94.71, and 94.18% for MIT-BIH malignant ventricular ectopy database for ECG lead I and lead II, respectively. The RNN model could only achieve an accuracy of 23.73% for the sinus tachycardia data set. A similar trend is shown by other models. From the analysis, it was evident that even though tachycardia diseases have fast beat rhythm as their common feature, the model was not able to detect different types of tachycardia diseases. The deep learning model could only detect atrial fibrillation and ventricular fibrillation and failed in the case of sinus tachycardia. From the analysis, they were able to interpret that, along with the fast beat rhythm, the model has learned the absence of P-wave which is a common feature for ventricular fibrillation and atrial fibrillation but sinus tachycardia disease has an upright positive P-wave. The time-based analysis is conducted to find the time complexity of the models. The analysis conveyed that RNN and RSCNN models could achieve better performance with lesser time complexity.
... The researches on early diagnosis of COPD by distinguishing healthy lung sounds and pathological lung sounds, and detecting different severities of the COPD are the pioneer approaches in signal analysis. The literature usually focuses on cardiac diseases using ECG [8], [24], [25], neurological disorders using EEG [26], disabled activities using EMG. It is a recent area analyzing musical characteristic auscultation signals including lung, tracheal, vesicular, and bronchial sounds for detecting abnormalities on respiratory and cardiopulmonary diseases. ...
Article
Full-text available
Deep Learning (DL) is an effective way that reveals on computation capability and advantage of the hidden layer in the network models. It has pre-training phases which define the output parameters in unsupervised ways and supervised training for optimization of the pre-defined classification parameters. This study aims to perform high generalized fast training for DL algorithms with the simplicity advantage of Extreme Learning machines (ELM). The applications of the proposed classifier model were experimented on RespiratoryDatabase@TR. Hilbert-Huang Transform was applied to the 12-channel lung sounds for analyzing amplitude-time-frequency domain. The statistical features were extracted from the intrinsic mode function modulations of lung sounds. The feature set was fed into the proposed Deep ELM with the HessELM-AE. The proposed model was structured with 2 hidden layers (340,580 neurons) to classify the lung sounds for separating Chronic Obstructive Pulmonary Disease and healthy subjects. The classification performance was tested using 6-fold cross-validation with proposed Deep. HessELM-AE has achieved an influential accuracy rate of 92.22% whereas the conventional ELM-AE has reached an accuracy rate of 80.82%.
... Kutlu [48] performed a multi-stage classification system for two lead ECG using considerable number of features(106 ECG waveform features) and a Deep Belief Network (DBN) as classifier to overcome the disadvantage of having a cumbersome network with no physiology interpretation. Though use of features does make the physiological interpretation easier incase of false positives, the training time was extremely large due to large number of feature extracted and use of DBN network. ...
Article
Detecting and classifying cardiac arrhythmias is critical to the diagnosis of patients with cardiac abnormalities. In this paper, a novel approach based on deep learning methodology is proposed for the classification of single-lead electrocardiogram (ECG) signals. We demonstrate the application of the Restricted Boltzmann Machine (RBM) and deep belief networks (DBN) for ECG classification following detection of ventricular and supraventricular heartbeats using single-lead ECG. The effectiveness of this proposed algorithm is illustrated using real ECG signals from the widely-used MIT-BIH database. Simulation results demonstrate that with a suitable choice of parameters, RBM and DBN can achieve high average recognition accuracies of ventricular ectopic beats (93.63%) and of supraventricular ectopic beats (95.57%) at a low sampling rate of 114 Hz. Experimental results indicate that classifiers built into this deep learning-based framework achieved state-of-the art performance models at lower sampling rates and simple features when compared to traditional methods. Further, employing features extracted at a sampling rate of 114 Hz when combined with deep learning provided enough discriminatory power for the classification task. This performance is comparable to that of traditional methods and uses a much lower sampling rate and simpler features. Thus, our proposed deep neural network algorithm demonstrates that deep learning-based methods offer accurate ECG classification and could potentially be extended to other physiological signal classifications, such as those in arterial blood pressure (ABP), nerve conduction (EMG), and heart rate variability (HRV) studies.
Chapter
Electrocardiogram (ECG) having an important place in medical industries and medical science. But there is many machine-based learning to identify diseases using ECG data. The main problem present in machine learning report is analyzed by doctors it may be possibility prediction or analysis about disease not sure. We develop proposed solution using deep learning which give high accuracy in ECG-based report. Generally, deep learning architecture layer-type convolution ID-1, Max pooling, dropout, convolution ID-2, dense and dropout layers. In ECG, classification layer presents some result as shown in simulation result. Using ECG, we can diagnose many cardiac diseases by using previously trained patient ECG into cardiac condition. In our proposed research work having three different condition of ECG-waveform using MIT-BIH database of arrhythmia to evaluate proposed work. In the proposed work main focus is on simplicity, reliability and applicable deep learning techniques. Simulation result has confusion matrix graph (N, A, O, E it representing four diseases), confusion matrix table to identify accuracy about disease. The proposed algorithm achieved a classification accuracy, sensitivity, and specificity of 93.79%, 84.36%, 94.34% respectively. In layered architecture classify different layers used in application of deep neural network convolution.KeywordsECGCNNDeep learningMIT-BIH database
Chapter
Object detection has made immense improvements in natural images during the last decade but not so much in aerial images. Detection of miniature objects in aerial images remains challenging as they contain only a few pixels and extremely large input sizes. Moreover, tiny objects are easily fooled by the backstory and increase the difficulty of accurate detection. Many algorithms are used for object detection purposes, and YOLOR is one of them. YOLOR “You Only Learn One Representation” is a one-stage detector. It is specially made for object detection, whereas other algorithms include object classification or analysis. In CNN, only, one task is carried out at a time, whereas YOLOR is a unified model useful for multitasking purposes. In this paper, we discussed tiny object detection in aerial images using YOLOR. Based on our research, we found that the AI-TOD dataset contains object instances in eight categories, with 86% of the objects being smaller than 16 pixels in size. The AI-TOD can be used to assess the performance of a variety of small objects. The mean size of objects is approximately 12.8 pixels, which is considerably smaller than the other datasets.KeywordsDeep learningExplicit knowledgeImplicit knowledgeTiny object detectionNeural network
Preprint
Full-text available
Electroencephalography (EEG) signals signals are often used to learn about brain structure and to learn what thinking. EEG signals can be easily affected by external factors. For this reason, they should be applied various pre-process during their analysis. In this study, it is used the EEG signals received from 109 subjects when opening and closing their right or left fists and performing hand and foot movements and imagining the same movements. The relationship between motor activities and imaginary of that motor activities were investigated. Algorithms with high performance rates have been used for feature extraction , selection and classification using the nearest neighbour algorithm.
Conference Paper
As a typical disease, heart disease seriously threatens human health, and its suddenness has hindered the diagnosis and treatment for the patients. Therefore, a fast and accurate real-time analysis method is useful to assist doctors in disease diagnosis. In this paper, we mainly design three different automatic classification algorithms to classify the heart beats of electroencephalography. The algorithm is mainly based on one-dimensional convolutional neural network (CNN), and the appropriate network structure is found by comparing the classification performance of different structural models. We also use the support vector machine (SVM) and stacking methods to improve the CNN network. The data used in this paper are all from the MIT-BIH Arrhythmia Database. We use the ten-core cross-validation method to classify the four types of heart beats. The results show that among the three types of algorithms, the stacking algorithm works best and the classification accuracy is as high as 99.1%.
Article
Full-text available
In this study, a decision-support system is presented to aid cardiologists during the diagnosis and to create a base for a new diagnosis system which separates two classes (CAD and no-CAD patients) using an electrocardiogram (ECG). 24 hour filtered ECG signals from PhysioNet were used. 15 second short-term ECG segments were extracted from 24 hour ECG signals to increase the number of samples and to provide a convenient transformation in a short period of time. The Hilbert-Huang Transform, which is effective on non-linear and non-stationary signals, was used to extract the features from short-term ECG signals. Instinct Mode Function (IMF) was extracted by applying Empirical Mode Decomposition to short-term ECG signals. The Hilbert Transform (HT) was applied to each IMF to obtain instantaneous frequency characteristics of the signal. Dataset was created by extracting statistical features from HT applied to IMF. Deep Belief Networks (DBN) which have a common use in Deep Learning algorithms were used as the classifier. DBN classification accuracy in the diagnosis of the CAD is discussed. The extracted dataset was tested using the 10-fold cross validation method. The test characteristics (sensitivity, accuracy and specificity) that are the basic parameters of independent testing in the medical diagnostic systems were calculated using this validation method. Short-term ECG signals of CAD patients and no-CAD groups were classified by the DBN with the rates of 98.05%, 98.88% and 96.02%, for accuracy, specificity and sensitivity, respectively. The DBN model achieved higher accuracy rates than the Neural Net
Conference Paper
Full-text available
In this study, a decision-support system is presented to aid cardiologists during the diagnosis and to create a base for a new diagnosis system which separates two classes (CAD and no-CAD patients) using an electrocardiogram (ECG). 24 hour filtered ECG signals from PhysioNet were used. 15 second short-term ECG segments were extracted from 24 hour ECG signals to increase the number of samples and to provide a convenient transformation in a short period of time. The Hilbert-Huang Transform, which is effective on non-linear and non-stationary signals, was used to extract the features from short-term ECG signals. Instinct Mode Function(IMF) was extracted by applying Empirical Mode Decomposition to short-term ECG signals. The Hilbert Transform (HT) was applied to each IMF to obtain instantaneous frequency characteristics of the signal. Dataset was created by extracting statistical features from HT applied to IMF. Deep Belief Networks (DBN) which have a common use in Deep Learning algorithms were used as the classifier. DBN classification accuracy in the diagnosis of the CAD is discussed. The extracted dataset was tested using the 10-fold cross validation method.The test characteristics (sensitivity, accuracy and specificity) that are the basic parameters of independent testing in the medical diagnostic systems were calculated using this validation method. Short-term ECG signals of CAD patients and no-CAD groups were classified by the DBN with the rates of 98.05%, 98.88% and 96.02%, for accuracy, specificity and sensitivity, respectively. The DBN model achieved higher accuracy rates than the Neural Network classifier.
Conference Paper
Full-text available
An restricted Boltzmann machine learning algorithm were proposed in the two-lead heart beat classification problem. ECG classification is a complex pattern recognition problem. The unsupervised learning algorithm of restricted Boltzmann machine is ideal in mining the massive unlabelled ECG wave beats collected in the heart healthcare monitoring applications. A restricted Boltzmann machine (RBM) is a generative stochastic artificial neural network that can learn a probability distribution over its set of inputs. In this paper a deep belief network was constructed and the RBM based algorithm was used in the classification problem. Under the recommended twelve classes by the ANSI/AAMI EC57: 1998/(R)2008 standard as the waveform labels, the algorithm was evaluated on the two-lead ECG dataset of MIT-BIH and gets the performance with accuracy of 98.829%. The proposed algorithm performed well in the two-lead ECG classification problem, which could be generalized to multi-lead unsupervised ECG classification or detection problems.
Article
Full-text available
The electrocardiogram (ECG) is a key diagnostic tool in heart disease and may serve to detect ischemia, arrhythmias, and other conditions. Automatic, low cost monitoring of the ECG signal could be used to provide instantaneous analysis in case of symptoms and may trigger the presentation to the emergency department. Currently, since mobile devices (smartphones, tablets) are an integral part of daily life, they could form an ideal basis for automatic and low cost monitoring solution of the ECG signal. In this work, we aim for a realtime classification system for arrhythmia detection that is able to run on Android-based mobile devices. Our analysis is based on 70% of the MIT-BIH Arrhythmia and on 70% of the MIT-BIH Supraventricular Arrhythmia databases. The remaining 30% are reserved for the final evaluation. We detected the R-peaks with a QRS detection algorithm and based on the detected R-peaks, we calculated 16 features (statistical, heartbeat, and template-based). With these features and four different feature subsets we trained 8 classifiers using the Embedded Classification Software Toolbox (ECST) and compared the computational costs for each classification decision and the memory demand for each classifier. We conclude that the C4.5 classifier is best for our two-class classification problem (distinction of normal and abnormal heartbeats) with an accuracy of 91.6%. This classifier still needs a detailed feature selection evaluation. Our next steps are implementing the C4.5 classifier for Android-based mobile devices and evaluating the final system using the remaining 30% of the two used databases.
Article
Early detection of cardiac diseases using computer aided diagnosis system reduces the high mortality rate among heart patients. The detection of cardiac arrhythmias is a challenging task since the small variations in electrocardiogram (ECG) signals cannot be distinguished precisely by human eye. In this paper, dual tree complex wavelet transform (DTCWT) based feature extraction technique for automatic classification of cardiac arrhythmias is proposed. The feature set comprises of complex wavelet coefficients extracted from the fourth and fifth scale DTCWT decomposition of a QRS complex signal in conjunction with four other features (AC power, kurtosis, skewness and timing information) extracted from the QRS complex signal. This feature set is classified using multi-layer back propagation neural network. The performance of the proposed feature set is compared with statistical features extracted from the sub-bands obtained after decomposition of the QRS complex signal using discrete wavelet transform (DWT) and with four other features (AC power, kurtosis, skewness and timing information) extracted from the QRS complex signal. The experimental results indicate that the DWT and DTCWT based feature extraction technique classifies ECG beats with an overall sensitivity of 91.23% and 94.64%, respectively when tested over five types of ECG beats of MIT-BIH Arrhythmia database.
Book
The Electrocardiogram.- Analysis of Electrocardiograms.- Prediction of Cardiac Signals Using Linear and Nonlinear Techniques.- Visualization of Cardiac Health Using Electrocardiograms.- Heart Rate Variability.- Data Fusion of Multimodal Cardiovascular Signals.- Classification of Cardiac Patient States Using Artificial Neural Networks.- The Application of Autoregressive Modeling in Cardiac Arrhythmia Classification.- Classification of Cardiac Abnormalities Using Heart Rate Signals: A Comparative Study.- Storage and Transmission of Cardiac Data with Medical Images.- Assessment of Cardiac Function in Filling amp Systolic Ejection Phases: A Mathematical and Clinical Evaluation.- Arterial Wave Propagation and Reflection at a Bifurcation Site.- ECG Signal Conditioning by Morphological Filters.- Multivariate Analysis for Cardiovascular and Respiratory Signals.- Phase Space Analysis for Cardiovascular Signals.- Linear, Non-Linear and Wavelet Analysis of Cardiac Health Using Heart Rate Signals.- Soft Tissue Biomechanics of the Left Ventricular Myocardium.- Wavelets and its Application in Cardiology.- 1/f Fluctuation of Heart Rate in Postoperative and Brain-Dead Patients.- Stress During Speech Therapy.