ASSESSMENT AND COMPARISON OF TIME REALIGNMENT

METHODS FOR SUPERVISED HEART BEAT CLASSIFICATION

G. de Lannoy

1

, M. Verleysen

1

and J. Delbeke

2

1

Machine Learning Group, Universit´e catholique de Louvain, pl. du Levant 3, 1348 Louvain-la-Neuve, Belgium

2

Departement of physiology and pharmacology, Universit´e catholique de Louvain

av. Hippocrate 54, 1200 Bruxelles, Belgium

Keywords:

Heart beat classiﬁcation, Time realignment, Dynamic time warping, Trace segmentation, Wavelet transform,

Nearest neighbor classiﬁer.

Abstract:

A reliable diagnosis of cardiac diseases can sometimes only be obtained by observing the heart of a patient

for a long time period where every single heart beat is of importance. Computer-aided classiﬁcation of heart

beats is therefore of great help. The classiﬁcation of the complete heart beat has many advantages compared

to a classiﬁcation of the QRS complex only or feature extraction methods. Nevertheless, the task is challeng-

ing because of the time-varying property of the heart beats. In this work, four time-alignment methods are

evaluated and compared in the context of supervised heart beat classiﬁcation. Among the four methods are

three time series resampling methods by linear interpolation, cubic splines interpolation and trace segmen-

tation. The fourth method is a realignment algorithm by dynamic time warping. The multiple sources of

artifacts are ﬁltered by discrete wavelet transform. As it only relies on a dissimilarity measure, the k−nearest

neighbor classiﬁer is a suitable choice for supervised classiﬁcation of time series like ECG signals in multiple

classes. Two different experiments corresponding to inter-patient and intra-patient classiﬁcation are conducted

on representative dataset built from the standard public MIT-BIH arrhythmia database.

1 INTRODUCTION

The importance of the electrocardiogram (ECG) sig-

nal for the diagnosis of cardiac diseases is widely

known (Clifford et al., 2006). However, a reliable di-

agnosis can sometimes only be obtained by observing

the ECG of a patient for a long-term period, compris-

ing hundreds to thousands of heart beats (Chudacek

et al., 2007; Cuesta-Frau et al., 2003; Jekova et al.,

2008). Just a very few number of these beats may ac-

tually reveal a pathology and the complete set of beats

must therefore be taken into account for the diagno-

sis.

Such long-term ECG signals are often recorded

using the very popular Holter recorders. These sys-

tems are ambulatory heart activity recordings, with a

signal storing time ranging from 24 to 48 hours. They

are used in the clinical diagnosis of some disease con-

ditions and by pharmaceutical groups for the evalua-

tion of new drugs during phase-one studies.

Due to the high number of beats to evaluate, anal-

ysis is performed off-line by cardiologists, keeping in

mind that the diagnosis may rely on just a few tran-

sient patterns. The duration of the process makes this

task very expensive. Reliable visual inspection is dif-

ﬁcult and computer-aided detection of the pathologi-

cal beats is of major importance. However, this is a

difﬁcult task in real situations.

First, several sources of noise typically pollute the

ECG signal. Among these, power line interferences,

muscular artifacts, poor electrode contacts and base-

line wandering due to respiration can sometimes be

identiﬁed. These artifacts can largely degrade the

quality of the signal and therefore complicate the beat

identiﬁcation. Second, another hurdle is that the heart

rhythm can be quite unstable and variable in normal

conditions.

The classiﬁcation of the complete heart beat is a

different problem than the classiﬁcation of the QRS

complex only. In the latter case, beats are deﬁned

by cutting a ﬁxed-size window around the R spikes.

The size of the window is of similar length for all

beats, but the duration of QRS complexes varies with

time and pathologies. For this reason, a ﬁxed win-

dow size may lead to incorrect extraction of the QRS

complex. Furthermore, some pathologies can only be

239

Lannoy G., Verleysen M. and Delbeke J. (2009).

ASSESSMENT AND COMPARISON OF TIME REALIGNMENT METHODS FOR SUPERVISED HEART BEAT CLASSIFICATION.

In Proceedings of the International Conference on Bio-inspired Systems and Signal Processing, pages 239-244

DOI: 10.5220/0001434602390244

Copyright

c

SciTePress

identiﬁed by using more information than this QRS

complex only. A complete heart beat is deﬁned as the

activity between the start of a P wave and the start

of the next one. The time-varying property of such

data challenges the automatic computer-aided classi-

ﬁcation methods.

Indeed, standard classiﬁcation algorithmswork on

data arrays of identical dimension. A pre-processing

step is therefore required to deal with time series of

different lengths. This pre-processing step can be the

extraction of the same number of typical ECG fea-

tures from each beat. However, the complete mor-

phology of the beat can hardly be summarized in a set

of features, and the discriminativeinformationmay be

missing in the chosen features. A more sophisticated

pre-processing step is to resample and/or to realign

the signal in order to have the same number of sam-

ples in each beat. The advantage is that the complete

heart beat can then be used as input to any classiﬁer

without loss of information. Moreover, advanced re-

sampling methods can correct for time shifts and re-

align observations.

In this paper, four temporal realignment methods

are evaluated in the context of complete heart beat

classiﬁcation. These methods have proven successful

in variousdisciplines such as speech processing, spec-

tral data analysis and signal ﬁltering. The remaining

of this paper is structured as follows. After this intro-

duction, Section 2 gives a short review of the litera-

ture about the state of the art in ECG beat classiﬁca-

tion. Section 3 sets the theoretical background for the

methods used in this work. Section 4 introduces the

methodology followed in this work. Finally, Section

5 shows the experiments on a real database and the

corresponding results.

2 STATE OF THE ART

A large body of literature about the ECG beat classiﬁ-

cation has arisen in recent years. Computer-aided al-

gorithms for the automatic classiﬁcation of the heart

beats can be separated in two groups: supervised or

unsupervised (Clifford et al., 2006). In the ﬁrst case,

it is necessary to have a set of manually labeled heart

beats. In the second case, because manually labeled

reference beats are not available, automatic diagnosis

is impossible.

Clustering techniques are among the most used

unsupervised processing techniques (Clifford et al.,

2006). A comparison between clustering algorithms,

realignment algorithms and feature extraction meth-

ods for unsupervised beat classiﬁcation has been con-

ducted in (Cuesta-Frau et al., 2003). More recently,

the results of the previous work have been improved

by introducing the J-means heuristic for heart beat

clustering (Rodriguez-Sotela et al., 2007). Self-

organizing maps (SOM) have also been investigated

with very promising results (Clifford et al., 2006).

The disadvantage of unsupervised methods, beside

the fact that an automatic diagnosis cannot be ob-

tained, is the empirical choice of the number of clus-

ters (or of SOM prototypes). In the case of heart beats,

this choice is hard to make a priori and it can signiﬁ-

cantly affect the results.

The vast majority of supervised beat classiﬁcation

algorithmsreportedin the literature work either on the

QRS complex only, either on features extracted from

the signal, or a combination of both (Clifford et al.,

2006). In the ﬁrst case, only the QRS complex is ex-

tracted from the ECG signal by deﬁning a ﬁxed-size

window around the R spike. The beat time-varying

duration property is therefore avoided. In the second

case, common time-domain features include the time

interval between characteristic ECG patterns such as

R-R and Q-T intervals, the Hermite basis function ex-

pansion of the QRS complex and order statistics of

the QRS sequence. Frequency domain descriptors

such as Fourier or wavelet transform coefﬁcients are

alternative interesting features. Classiﬁcation meth-

ods such as artiﬁcial neural networks (ANNs), sup-

port vector machines (SVMs) and combined methods

have been applied with success for QRS classiﬁcation

(Clifford et al., 2006). A recent comprehensive re-

view of supervised classiﬁcation methods of the QRS

complex can be found in (Jekova et al., 2008).

These methods relying on the classiﬁcation of the

QRS complex or of selected features may miss po-

tentially useful information for discrimination. Some

pathologies can indeed be more accurately identiﬁed

by using more information than the QRS complex

alone, such as Q-T intervals. Furthermore, using a

ﬁxed-size window around the R spike may lead to

wrong QRS extraction because the duration of the

QRS complexes is not stationary. Also, the choice

of the features is of great importance. Summarizing

the complete morphology of the beats into a set of

features is a difﬁcult and application dependent task

(Clifford et al., 2006; Jekova et al., 2008).

In order to circumvent these issues, realignment

methods have recently been applied with success

to unsupervised beat clustering (Cuesta-Frau et al.,

2003). The complete beat can then be considered by

the classiﬁcation procedure. However, contrarily to

clustering, supervised classiﬁcation algorithms rely

more easily on a set of features extracted from the

time series rather than on the raw time series them-

selves. For this reason, despite the advantages of

BIOSIGNALS 2009 - International Conference on Bio-inspired Systems and Signal Processing

240

these methods, very few studies have been reported on

supervised full beat classiﬁcation after realignment.

The k−nearest neighbor (KNN) classiﬁer is an excep-

tion to this. In a similar way to clustering methods, it

only relies on a dissimilarity metric between obser-

vations. Such dissimilarity metrics can naturally be

computed between time series of similar lengths. In

this work, four time series realignment methods are

evaluated in the context of complete heart beat classi-

ﬁcation by k-nearest neighbor classiﬁer.

3 THEORETICAL BACKGROUND

This sections provides a brief account of the theo-

retical background for the signal processing methods

used in this work. The time-frequency ﬁltering by

discrete wavelet transform is brieﬂy described ﬁrst.

Thereafter, the dynamic time warping realignment al-

gorithm is introduced. Finally, a brief summary to

the three resampling algorithms is provided. In the

remainder of this work, these methods are globally

referred to as the realignment methods.

3.1 The Discrete Wavelet Transform

The continuous wavelet transform (CWT) is a time-

frequency decomposition of a signal x(t) by the con-

volution of this signal with a so-called wavelet func-

tion ψ(t) (Mallat, 1999). From a wavelet function,

one can obtain a family of time-scale waveforms by

translation b and scaling a, with a, b ∈ R:

ψ

a,b

(t) =

1

√

a

ψ

t −b

a

. (1)

When a = 1 and b = 0, ψ(t) is called the mother

wavelet. The wavelet transform of a function x(t) ∈

L

2

(R) is a projection of this function on the wavelet

basis {ψ

a,b

} :

T(a, b) =

Z

+∞

−∞

x(t)ψ

a,b

(t)dt . (2)

The discrete wavelet transform (DWT) removes

the redundancy of the CWT by using dyadic scales

and discrete translations. The ﬁrst DWT step pro-

duces two sets of coefﬁcients: approximation coef-

ﬁcients (low frequency components) and detail coef-

ﬁcients (high frequency components), followed by a

dyadic decimation (downsampling). This process is

iterated log

2

(N) times at most, where N is the size of

the signal x(t) (Mallat, 1999).

3.2 Dynamic Time Warping

Dynamic time warping (DTW) is an algorithm that

ﬁnds an optimal alignment function between two

sequences of different lengths (Myers and Rabiner,

1981). It has for example been used with great suc-

cess in speech recognition and process control. The

sequences are warped non-linearly in the time dimen-

sion to determine a measure of their similarity inde-

pendent of certain non-linear variations in the time di-

mension.

Let x and y be two sequences of lengths n

x

and n

y

respectively. The objective is to ﬁnd the best align-

ment between the two sequences, according to a cost

function. The alignment procedure allows us to com-

pare a value x(i) of x with a value y( j) of y. The

whole set of possible comparisons can be represented

as a matrix of size n

x

×n

y

, that can be seen as a multi-

stage graph. The objective is then to ﬁnd a node path

(i

1

, j

1

), (i

2

, j

2

), ...,(i

f

, j

f

) of length f along the graph

such that the ﬁnal cumulative cost D is minimal. The

latter is deﬁned as

D =

f

∑

k=1

[d(i

k

, j

k

)|(i

k−1

, j

k−1

)] , (3)

where d(i, j) is a cost function that allows us to com-

pare a value x(i) of x with a value y( j) of y. A typi-

cal cost function is for example the squared Euclidean

distance:

d(i, j) = (x(i) −y( j))

2

. (4)

The optimization process is performed using dynamic

programming. The cumulative cost of the optimal

alignment path can then be used as a dissimilarity

measure.

3.3 Trace Segmentation

Trace segmentation (TS) is a non-uniform sampling

method used in speech recognition to normalize the

duration of utterances. Standard vector-space norms

can then be used to compare them. The objective is to

retain only the samples of the signal where the main

changes take place (Cuesta-Frau et al., 2003).

Given a sequence x of length n, let us deﬁne the

partial accumulated derivate ∆

j

of x:

∆

j

=

j+1

∑

i=2

|x(i) −x(i−1)| . (5)

The accumulated derivative at the end of the sequence

is

∆ =

n

∑

i=2

|x(i) −x(i−1)| . (6)

ASSESSMENT AND COMPARISON OF TIME REALIGNMENT METHODS FOR SUPERVISED HEART BEAT

CLASSIFICATION

241

If h is the desired number of samples after trace seg-

mentation, the average interval amplitude value of ∆

is given by

L =

∆

h

. (7)

Let us now deﬁne the output sequence x

tr

of length

h obtained by trace segmentation of x. Each sample

x

tr

(l) is taken from the sample x( j) corresponding to

the time when the accumulated derivate exceeds an

integer multiple of L:

x

tr

(l) = x( j)|j = argmin

1<i<n−1

(l ×L < ∆

i

) , (8)

with x

tr

(1) = x(1) and x

tr

(h) = x(n). The sequence

x

tr

thereby includes the values of x where only the

main changes take place.

3.4 Interpolation

Given a sequence x of length n, obtained by sampling

or experiment, regression analysis tries to estimate a

function which closely ﬁts those data points. Inter-

polation is a speciﬁc case of curve ﬁtting, in which

the function must go exactly through the data points.

One of the simplest interpolation methods is linear in-

terpolation. In this case, a linear function is ﬁt at each

interval x

k

, x

k+1

.

Spline interpolation uses low-degree polynomials

in each of the intervals, and chooses the polynomial

pieces such that they ﬁt smoothly together. The re-

sulting function is called a spline (De Boor, 1978).

Spline interpolation incurs a smaller error than linear

interpolation, and the interpolant is smoother. How-

ever, the interpolant is easier to evaluate than the high-

degree polynomials used in polynomial interpolation.

In both cases, the estimated function then allows

us to resample (or stretch) the sequence by generating

new data points within the range of the discrete set of

known data points.

4 METHODOLOGY

In this work, supervised classiﬁcation of complete

heart beats is considered. Let us assume that a refer-

ence database has been obtained and annotated, with

all pathologies of interest being represented. Given

a new ECG signal, for example recorded using an

Holter system, one wants to use the information con-

tained in the reference database in order to predict the

pathologies present in the new signal.

First, all the beats within the signal must be sepa-

rated. Several computer-aided annotation algorithms

have been reported in the literature in order to auto-

matically detect the ECG characteristic points for beat

extraction (Clifford et al., 2006).

Thereafter, a realignment of the beats must be

achieved. Four sequence alignment methods are eval-

uated in this work. The ﬁrst two are interpolation

methods: linear interpolation (LI) and cubic splines

interpolation (CSI). The third method is the trace seg-

mentation method (TS) and the fourth is the dynamic

time warping (DTW) realignment algorithm.

Next, noise and artifacts are ﬁltered by time-

frequency ﬁltering using the the discrete wavelet

transform (DWT) of the heart beats. Moreover,the di-

mensionality of the observations is strongly reduced

by the downsampling of the approximation coefﬁ-

cients at each step of the DWT. This reduces the com-

putational cost of the classiﬁcation algorithm.

Finally, the realigned and ﬁltered heart beats are

reduced to zero mean and unit variance. The beats are

then given as input to a classiﬁer. A natural choice

for supervised classiﬁcation of time series in multi-

ple classes is the k-nearest neighbor (KNN) classiﬁer.

The k-nearest neighbor (KNN) algorithm is a super-

vised classiﬁer where an observation (corresponding

to one heart beat) is assigned to the class most com-

mon amongst its k nearest neighbors in the reference

set. The algorithm is supervised, because the neigh-

bors are taken from a reference set of observations for

which the correct classiﬁcation is known. This can be

thought of as the training set for the algorithm, though

no explicit training step is required.

In order to identify the closest neighbors, a dissim-

ilarity metric must be deﬁned. When using the three

ﬁrst realignment methods the KNN distance measure

is the Euclidean distance between observations, com-

puted on the aligned beats. In the case of the DTW

warping algorithm, the DTW dissimilarity measure

can directly be used in the KNN method, without ef-

fectively computing the realigned time series.

5 EXPERIMENTS AND RESULTS

The performances of the four realignment methods

are evaluated on the public standard MIT-BIH ar-

rhythmia database (Goldberger et al., 2000). It con-

tains 48 half-hour recordings of annotated ECG with

a sampling rate of 360Hz and 11-bit resolution over

a 10-mV range. Except recordings 201 and 202,

each recording comes from a different patient, so the

database contains a total of 47 subjects. The orig-

inal annotations are used. The method deﬁned in

(Rodriguez-Sotela et al., 2007) for extracting com-

plete beats from the R spike annotations is used.

The ﬁve main types of heart beats represented in the

database are used in this study: (1) normal beats (N)

- 74820 cases, (2) left bundle branch block beats (L) -

BIOSIGNALS 2009 - International Conference on Bio-inspired Systems and Signal Processing

242

8050 cases, (3) right bundle branch block beats (R) -

7220 cases, (4) prematureventricularcontractions(V)

- 6970 cases, and (5) paced beats (P) - 7000 cases.

From each of the 47 recordings, three beats of

each type available in the recording are randomly se-

lected. Each patient is thus fairly represented in the

dataset. Nevertheless, only a small subset of record-

ings contains L, R and P types, while almost every

recording contains the N class. Therefore, in order

to obtain the same number of representatives for each

class, other beats are then randomly selected amongst

the recordings and added to the experimental set un-

til equally balanced classes are obtained. The ﬁnal

experimental dataset contains a total number of 600

heart beats, including an equal number of 120 beats

per class where the 47 patients are fairly represented.

The level 3 approximation coefﬁcients of the

DWT with a biorthogonal mother wavelet are used

as features. The classiﬁcation performances are eval-

uated using a KNN classiﬁer with k = 3 neighbors.

Two different experiments are conducted. The ﬁrst

one is an intra-patient classiﬁcation where the com-

plete training set is used for the classiﬁcation of each

heart beat. A typical leave-one-out methodology is

used for the evaluation of the performances. The sec-

ond experiment is an inter-patient classiﬁcation. A

leave-one-out method is also used. However, when

classifying a heart beat of a given patient, all beats

coming from this patient are removed from the train-

ing set. The classiﬁcation is therefore based only

on the annotated beats of other patients, which is a

much harder generalization task. Table 1 shows the

intra-patient classiﬁcation results and Table 2 holds

the inter-patient classiﬁcation results. The values are

average rates computed over ten different random se-

lections during the construction of the experimental

dataset.

When considering the intra-patient experiment,

very similar results are obtained by the two interpo-

lation methods with an average of 90% correct clas-

siﬁcations. Surprisingly, the dynamic time warping

algorithm provides slightly worst results with an av-

erage of 88%. Amongst the four methods, trace seg-

mentation obtains the worst results with an average of

only 70%. The computational time of the two inter-

polation methods and the trace segmentation method

are very similar, allowing real-time analysis. On the

other hand, the running time of the DTW algorithm

makes this method only suitable for off-line analysis.

The results obtained with the inter-patient experi-

ment in Table 2 are unsatisfactory, especially for the

L, R and N types. However, the low results for these

classes are preliminary, since the MIT-BIH database

only contains four patients with left bundle branch

block and ﬁve patients with right bundle branch block,

which is quite insufﬁcient for generalization. These

results regarding generalization between patients of

the MIT database are conﬁrmed in other recent works

(Jekova et al., 2008). Furthermore, the three L, R and

N classes are often considered to be of the same clin-

ical relevance. Indeed, the Association for the Ad-

vancement of Medical Instrumentation (AAMI) rec-

ommends to group these three classes together (Maier

et al., 1999). Table 3 holds the results when the three

L, R and N types are merged together. The results are

comparable to intra-patient performances, and show

that the generalization between patients is possible.

Although numerous studies dealing with heart

beat classiﬁcation have been reported in the literature,

a comparison is difﬁcult to make. Indeed, few stud-

ies address multi-class problems including more than

the N and V heart beat classes. Also, only a subset

including 5 to 10 recordings of the MIT database is

usually used in these studies. Moreover, the training

dataset is constructed in quite different ways, and por-

tions of the recordings including noise are sometimes

rejected during the extraction of beats. For exam-

ple, (Ham and Han, 1996) obtained very different re-

sults with 44 recordings in comparison with (Moraes

et al., 2002) using only 6 recordings to discriminate

between V and N beat types.

In this work, the experimental dataset is created

in such way that the number of heart beats is equally

balanced between each class and that all 47 patients

of the database are fairly represented. The noisy por-

tions of the recordings are also included in the data.

Furthermore, the inter-patient and intra-patient heart

beat classiﬁcations are two very different objectives

and are therefore separated in this study.

Table 1: Intra-patient correct classiﬁcation rate.

N L R V P

LI 91.1 84.5 89.7 92.4 95.8

CSI 91.3 84.4 89.8 92.4 95.8

DTW 90.3 82.1 85.8 91.2 95.0

TS 60.1 64.0 75.0 79.7 73.7

Table 2: Inter-patient correct classiﬁcation rate.

N L R V P

LI 32.0 15.9 38.2 71.1 85.0

CSI 32.1 15.9 38.4 71.1 85.2

DTW 43.3 4.6 46.2 51.2 75.1

TS 27.9 11.7 8.5 53.7 56.8

ASSESSMENT AND COMPARISON OF TIME REALIGNMENT METHODS FOR SUPERVISED HEART BEAT

CLASSIFICATION

243

Table 3: Inter-patient correct classiﬁcation rate, when merg-

ing the L R and N types.

N+L+R V P

LI 81.1 80.7 92.6

CSI 81.3 80.7 92.7

DTW 74.4 79.2 90.0

TS 60.0 72.6 72.6

6 CONCLUSIONS

In this work, four time-alignment methods are evalu-

ated and compared in the context of supervised heart

beat classiﬁcation. Amongst these methods are three

time series resampling algorithms by linear interpo-

lation, cubic splines interpolation and trace segmen-

tation. The fourth method is a realignment algorithm

by dynamic time warping. The multiple sources of

noise and artifacts are ﬁltered by means of a time-

frequency decomposition by discrete wavelet trans-

form. The downsampling induced by DWT approx-

imation coefﬁcients also reduces the dimension of the

observations. Since it only relies on a dissimilarity

measure between observations, the KNN classiﬁer is

a natural choice for supervised classiﬁcation of time

series in multiple classes.

Experiments are conducted on a representative

dataset built from the standard public MIT-BIH ar-

rhythmia database. The ﬁve main types of heart beats

are considered. The experimental dataset is created

so as to include an equal number of beats per class

with all patients being fairly represented. For intra-

patient classiﬁcation, very similar results are obtained

by the two interpolation methods with an average cor-

rect classiﬁcation rate of 90%. Surprisingly, the dy-

namic time warping algorithm provides slightly lower

results with an average of 88%. Amongst the four

methods, the trace segmentation obtains the worst re-

sults with an average of only 70%. On the other hand,

the results obtained for inter-patient classiﬁcation are

unsatisfactory, especially for the L and R types. How-

ever, the low yield obtained for these classes are

preliminary, since the number of patients with these

pathologies in the MIT-BIH database is insufﬁcient

for generalization. When merging these three classes

together as recommended by the AAMI, the results

achieved are then comparable to intra-patient classiﬁ-

cation.

Very few other studies work on a reliable dataset

with multi-class, inter and intra patient classiﬁcation

and comparisons to other works are difﬁcult to ob-

tain. Further works will include a comparison with

the results of other QRS classiﬁcation and feature ex-

traction methods using the same dataset.

ACKNOWLEDGEMENTS

G. de Lannoy is funded by a Belgian F.R.I.A. grant.

This work was partly supported by the Belgian

“R´egion Wallonne” ADVENS 4994 project.

REFERENCES

Chudacek, V., Petrik, M., Georgoulas, G., Cepek, M., Lhot-

ska, L., and Stylios, C. (2007). Comparison of seven

approaches for holter ecg clustering and classiﬁcation.

Engineering in Medicine and Biology Society, 2007.

EMBS 2007. 29th Annual International Conference of

the IEEE, pages 3844–3847.

Clifford, G. D., Azuaje, F., and McSharry, P. (2006). Ad-

vanced Methods And Tools for ECG Data Analysis.

Artech House, Inc., Norwood, MA, USA.

Cuesta-Frau, D., Pres-Corts, J. C., and Andreu-Garcia, G.

(2003). Clustering of electrocardiographic signals in

computer-aided holter analysis. Computer Methods

and Programs in Biomedicine, 72:179–196.

De Boor, C. (1978). A practical guide to splines. Springer-

Verlag, New York.

Goldberger, A., Amaral, L., Glass, L., Hausdorff, J., Ivanov,

P., Mark, R., Mietus, J., Moody, G., Peng, C.-K.,

and Stanley, H. (2000). PhysioBank, PhysioToolkit,

and PhysioNet: Components of a new research re-

source for complex physiologic signals. Circulation,

101(23):e215–e220.

Ham, F. and Han, S. (1996). Classiﬁcation of cardiac ar-

rhythmias using fuzzy artmap. IEEE Transactions on

Biomedical Engineering, 43(4):425–429.

Jekova, I., Botrolan, G., and Christov, I. (2008). As-

sessment and comparison of different methods for

heartbeats classiﬁcation. Medical Engineering and

Physics, 30:248–257.

Maier, C., Dickhaus, H., and Gittinger, J. (1999). Unsuper-

vised morphological classiﬁcation of qrs complexes.

Computers in Cardiology 1999, pages 683–686.

Mallat, S. (1999). A Wavelet Tour of Signal Processing, Sec-

ond Edition (Wavelet Analysis and Its Applications).

IEEE press, San Diego. ISBN 978-0124666061.

Moraes, J., Seixas, M., Vilani, F., and Costa, E. (2002). A

real time qrs complex classiﬁcation method using ma-

halanobis distance. Computers in Cardiology, 2002,

pages 201–204.

Myers, C. S. and Rabiner, L. (1981). A comparative study

of several dynamic time-warping algorithms for con-

nected word recognition. The Bell System Technical

Journal, 60:1389–1409.

Rodriguez-Sotela, J. L., Cuesta-Frau, D., and Castellanos-

Dominguez, G. (2007). An improved method for un-

supervised analysis of ecg beats based on wt features

and j-means clustering. Computers in Cardiology,

34:581–584.

BIOSIGNALS 2009 - International Conference on Bio-inspired Systems and Signal Processing

244