0 views

Original Title: BSPC 2017

Uploaded by rekha

- Face Recognition by Generalized Two-dimensional FLD Method and Multi-class SVM
- Application of multivariate principal component analysis on dimensional reduction of milk composition variables
- Xlstat Getting Started Manual(1)
- Multivariate Analyses Using SAS
- Face Image Retrieval in Image Processing a Survey
- Rom Proposal
- Advanced Machine Learning
- Alterasi
- Factor Analysis
- 856-876
- 3-36805_InsideBIGDATAGuidetoMarchineLearning2014
- Talk13-SOMS-PCA-ICA-MDS2014.pdf
- Sneha. G.Gondane
- Content production and perception of copyright - Aliprandi & Mangiatordi (2013)
- Ch3-Mathematical and Physical Backgrounds
- Smart Grid Comm
- Velocidad Promedio Con Redes Neuronales
- PAN-Sharpening Using Content-Specific Orthogonal Linear Transform
- Principal Components Analysis (PCA)Final
- Data Compression Issues With Pattern Matching in Historical Data

You are on page 1of 8

journal homepage: www.elsevier.com/locate/bspc

Technical Note

techniques on automated arrhythmia classiﬁcation

Rekha Rajagopal ∗ , Vidhyapriya Ranganathan

Department of Information Technology, PSG College of Technology, Coimbatore 641 004, India

a r t i c l e i n f o a b s t r a c t

Article history: Automation in cardiac arrhythmia classiﬁcation helps medical professionals to make accurate decisions

Received 9 December 2015 upon the patient’s health. The aim of this work is to evaluate the performance of ﬁve different linear and

Received in revised form nonlinear unsupervised dimensionality reduction (DR) techniques namely principal component analysis

16 September 2016

(PCA), fast independent component analysis (fastICA) with tangential, kurtosis and Gaussian contrast

Accepted 20 December 2016

functions, kernel PCA (KPCA) with polynomial kernel, hierarchical nonlinear PCA (hNLPCA) and principal

polynomial analysis (PPA) on classiﬁcation of cardiac arrhythmias using probabilistic neural network

Keywords:

classiﬁer (PNN). The design phase of the classiﬁcation model comprises of the following stages: pre-

Biomedical signal processing

Decision support systems

processing of the cardiac signal by eliminating detail coefﬁcients that contain noise, feature extraction

Feature extraction through Daubechies wavelet transform, dimensionality reduction through unsupervised DR techniques,

Supervised learning and arrhythmia classiﬁcation using PNN. PCA is a widely used DR technique for mapping high dimen-

sional data to its low dimensional representation. But real world data like electrocardiogram (ECG) signals

are complex and nonlinear in nature. This work concentrates on performance analysis of four nonlinear

DR techniques and conventional linear PCA technique on classiﬁcation of cardiac arrhythmias. Entire

MIT-BIH arrhythmia database is used for experimentation. The experimental results demonstrate that

the combination of PNN classiﬁer (at spread parameter, = 0.4) and fastICA DR technique with tangential

contrast function exhibit highest F score of 99.83% with a minimum of 10 dimensions. hNLPCA and KPCA

requires more computation time for low dimensional mapping. PPA performs about 10% better than PCA

and serves intermediate between linear and nonlinear techniques.

© 2016 Elsevier Ltd. All rights reserved.

dimensional space to meaningful representation in lower dimen-

Cardiovascular disease is a leading cause of global mortality. sional space such that the dimensionality of data is reduced to

Hence, there is a need to develop automation strategies for the manageable size. Dimensionality reduction is very important in a

management of sudden cardiac death [1]. Abnormality in the nor- classiﬁcation system in order to mitigate the curse of dimension-

mal rhythm of heartbeat causes arrhythmia. ANSI/AAMI EC57: 1998 ality, computational complexity and memory requirement. Curse

classiﬁcation standard categorize arrhythmias into ﬁve classes, of dimensionality means that for a given sample size, there is a

namely: non ectopic beat (N), supra ventricular ectopic beat (S), maximum number of features above which the performance of

ventricular ectopic beat (V), fusion beat (F) and unknown beat (Q). a classiﬁer gets degraded. The objective of this work is to evalu-

The diagnosis of a speciﬁc class of arrhythmia is done by careful ate the performance of ﬁve different unsupervised dimensionality

monitoring of long term electrocardiograph (ECG) signal. Automa- reduction techniques in the classiﬁcation of ECG arrhythmias.

tion in ECG arrhythmia classiﬁcation is very essential in order to

make fast and accurate decision on arrhythmia class. The important

2. Related works

requirements of an automated system are reduced complexity, fast

decision making and less memory. This can be accomplished with

Several research works are carried out for automation in

the use of dimensionality reduction techniques.

arrhythmia classiﬁcation. In general, the algorithm used for

automated classiﬁcation includes (i) preprocessing, (ii) feature

extraction, (iii) dimensionality reduction and (iv) classiﬁcation. The

∗ Corresponding author. preprocessing of recorded ECG signals is done in order to elimi-

E-mail addresses: rekha.psgtech@gmail.com, jp.psgtech@gmail.com nate the important noises that degrade the classiﬁer performance,

(R. Rajagopal), rvidhyapriya@gmail.com (V. Ranganathan). such as baseline wandering, motion artifact, power line interfer-

http://dx.doi.org/10.1016/j.bspc.2016.12.017

1746-8094/© 2016 Elsevier Ltd. All rights reserved.

2 R. Rajagopal, V. Ranganathan / Biomedical Signal Processing and Control 34 (2017) 1–8

Table 1

Number of heartbeats in each class. Connuous ECG recordings from MIT_BIH

Heartbeat type N S V F Q arrhythmia database

Full database 87643 2646 6792 794 15

ence and high frequency noise. Currently, researchers use many

ﬁltering techniques like morphological ﬁltering [2], integral coef-

ﬁcient band stop ﬁltering [3], ﬁnite impulse response ﬁltering [4],

Wavelet based feature extracon

5–20 Hz band pass ﬁltering [5,6], median ﬁltering [7] and wavelet

based denoising [7–9] for preprocessing.

Commonly extracted ECG features include (i) Temporal features

of heartbeat like P–Q interval, QRS interval, S–T interval, Q–R inter-

val, R–S interval and R–R interval between adjacent heartbeats. (ii) Dimensionality reducon

Amplitude based features like P peak amplitude, Q peak ampli- (Linear – PCA)

tude, R peak amplitude, S peak amplitude and T peak amplitude. (Non-linear - fast ICA, Kernel PCA, hNLPCA,

(iii) Wavelet transform based features that include Haar wavelet, PPA)

Daubechies wavelet and discrete Meyer wavelet at various decom-

position levels of 4, 6 and 8. (iv) Stockwell transform based features

that include statistical features taken from a complex matrix of

Stockwell transform, time–frequency contour and time–maximum Divide enre samples into 10 equal sets

amplitude contour.

Dimensionality reduction is applied in order to remove redun-

dancy and extract useful information from captured features. A

training set with class label information is required by supervised

dimensionality reduction techniques to learn the lower dimen- Set Set Set ……... Set

sional representation. Commonly used supervised techniques are

1 2 3 10

linear discriminant analysis (LDA) [10], generalized discriminant

analysis (GDA) [5], neighborhood component analysis and metric

learners. Unsupervised techniques do not require class label infor-

mation and few examples of unsupervised techniques are principal

component analysis, independent component analysis, canonical 90 % Training 10% Tesng

correlation analysis, partial least squares, isomap, kernel PCA, max-

imum variance unfolding, diffusion maps, local linear embedding,

Laplacian eigenmaps, Hessian LLE, Local tangent space analysis,

Sammon mapping and multilayer auto encoders [11]. PNN Classiﬁer

Support vector machine (SVM) [5,12–17], probabilistic neural

network (PNN) [9,15,18,19], multilayer perceptron neural network

(MLPNN) [6,15,20], linear discriminant classiﬁer [7], mixture of

experts [15] and unsupervised clustering [21,22] are commonly Ten fold cross validaon

used by researchers for classiﬁcation of ECG arrhythmia. The

parameters like accuracy, sensitivity and speciﬁcity are used in

literature for evaluating the performance of a classiﬁer.

Most of the research works have compared the performance Fig. 1. Architecture of the proposed work.

of classiﬁers using PCA [2,9], LDA [9,10] and ICA [9,23,24] for

dimensionality reduction. Research works that use nonlinear DR

techniques in arrhythmia classiﬁcation are very minimal. This work

concentrates on evaluating the performance of an automated clas-

siﬁcation system when DR techniques such as fast ICA, Kernel PCA, 4. Methodology

hNLPCA, PPA and PCA are used. The next section discusses the mate-

rials and methods used in this work. Fig. 1 shows the architecture of the proposed work. The entire

experiments are carried out using Matlab R2014a. The details of the

methodology carried out are summarized below.

3. Materials used

The MIT BIH arrhythmia database [25] is used in this work. It 4.1. Data preprocessing

contains 48 half–hour excerpts of two channel ambulatory ECG

recordings, obtained from 47 subjects studied by the BIH arrhyth- The records contain continuous ECG recording for duration

mia laboratory. The recordings were digitized at 360 samples per of 30 min. The raw ECG signals include baseline wander, motion

second per channel with 11 bit resolution over 10 mV range. The artifact and power line interference noise. The discrete wavelet

reference annotations for each beat were included in the database. transform (DWT) is used for denoising the ECG signal and also for

Four records containing paced beats (102, 104, 107 and 217) were extracting the important features from original ECG signal [26,27].

removed from analysis as speciﬁed by AAMI. The total number of DWT captures both temporal and frequency information. The DWT

heart beats in each class is given in Table 1. of the original ECG signal is computed by successive high pass and

R. Rajagopal, V. Ranganathan / Biomedical Signal Processing and Control 34 (2017) 1–8 3

low pass ﬁltering of that signal. This can be mathematically repre- 4.2. Feature extraction

sented in the following Eqs. (1) and (2),

The entire database (97,890 heartbeats) is divided into ten sets

∞ each containing 9789 heartbeats. Nine sets are used for train-

yhigh [k] = x [n] g [2k − n] (1) ing (88,101 heartbeats) and one set for testing (9789 heartbeats).

n=−∞

From each heartbeat, wavelet based features are extracted by

∞ using Daubechies wavelet (‘db4 ). Daubechies wavelet with level

ylow [k] = x [n] h [2k − n] (2) 4 decomposition is selected in this work after making perfor-

n=−∞

mance comparisons with discrete Meyer wavelet and other levels

of Daubechies wavelet including ‘db2 , ‘db6 . The power spectral

where, x[n] is the original ECG signal samples, g and h are the density of ECG beats showed that most of the ECG signal variations

impulse response of high pass and low pass ﬁlters respectively, occur in the fourth sub band frequency range of (0–11.25 Hz) and

and yhigh [k],ylow [k] are the outputs of high pass and low pass ﬁl- (11.25–22.5 Hz). A total of 107 features are produced by the 4th

ters after sub sampling by 2. This procedure is repeated until the level approximation sub band coefﬁcients and another 107 fea-

required decomposition level is reached. The low frequency com- tures by the 4th level detail sub band coefﬁcients. Fig. 4 shows

ponent is called approximation and high frequency component is the decomposition of heart beat signal (sampled at 360 Hz) into

called detail. approximation and detail sub bands up to level 2. This procedure

In this work, the raw ECG signals are decomposed into approxi- can be repeated for further decomposition.

mation and detail sub bands up to level 9 using Daubechies (‘db8 )

wavelet basis function [28]. The detail coefﬁcients contain most of

the noise information. Hence, soft thresholding is applied to the

detail coefﬁcient at each level. Denoised ECG signal is computed

based on the original approximation coefﬁcient at 9th level and 4.3. Dimensionality reduction

modiﬁed detail coefﬁcient of levels from 1 to 9. After denoising,

the continuous ECG waveform is segmented into individual heart- The coefﬁcients of approximation and detail sub bands at level

beats. This segmentation is done by identifying the R peaks using 4 decomposition of Daubechies wavelet transform are used as

Pan Tompkins algorithm [29] and by considering 99 samples before features to represent each heart beat. Hence each heartbeat is rep-

R peak and 100 samples after R Peak. This choice of 200 samples, resented by 214 features (107 coefﬁcients from approximation sub

including R peak for segmentation is taken because it constitutes band summed with 107 coefﬁcients from detail sub band pro-

one cardiac activity with P, QRS and T waves. Figs. 2 and 3 show a vide 214 features). In order to extract useful information from the

segment of the recorded ECG waveform of patient identiﬁer: 209 features and to remove redundancy the following dimensionality

before and after preprocessing respectively. reduction techniques are applied.

4 R. Rajagopal, V. Ranganathan / Biomedical Signal Processing and Control 34 (2017) 1–8

4.3.2.1. Fast independent component analysis (Fast ICA). ICA makes a

(Sampled at 360 Hz) data representation such that transformed components are statisti-

cally independent from each other. In order to have computational

simplicity and little memory space, ﬁxed point ICA algorithm is

h[n] g[n] used in this work [30]. The steps involved are,

1 Data centering

2 2

This step produces a data set whose mean (x̄) is zero and is

Level 1 detail coefficients shown in (6).

h[n] g[n] (90 to 180 Hz)

XC = X − E{X} (6)

2 Whitening

Level 2 approximation Level 2 detail coefficients

coefficients (45 to 90 Hz)

Eigenvector V and Eigen value E are computed from the covari-

(0 to 45 Hz)

ance matrix of centered data, and whitening is performed as in

Fig. 4. Two level wavelet ﬁlter bank. (7),

Z = E−1/2 V ∗ XC (7)

4.3.1. Linear technique

Linear mapping of high dimensional data to low dimensional 3 Fixed point iteration for one unit

data is done with this technique. The important advantages of linear

technique are its simple geometric interpretations and attractive It estimates one row of the demixing matrix w as a vector wT .

computational properties [11]. Estimation of w proceeds iteratively as in (8) until convergence is

achieved.

4.3.1.1. Principal component analysis (PCA). PCA that maximizes the

amount of variance in the data is used in this work. The steps fol- • Selection of initial random vector w

lowed for dimensionality reduction of data matrix X consisting of

n ECG samples xi (i &1028; {1, 2, .,n}) with D features (The value of wp = E{x g(wT x)} − E{xg (wT x)}w (8)

D is 214 in the proposed work due to 214 features extracted from

each heartbeat using wavelet transform) are given below, where, wp ∗ = wp /wp and wp is the norm of w and g is the contrast

function.

1 Subtraction of the mean

4 Evaluation of next independent components

This step produces a data set whose mean x̄ is zero.

To estimate the other independent components, step 3 is

2 Calculation of covariance matrix C is shown in (3). repeated for getting weight vectors wi , i = 2, 3,.n. To prevent dif-

ferent vectors from converging to the same optimum, the weight

C = (x − x̄)(x − x̄)T (3) vectors are decorrelated using Gram-Schmidt orthogonalization

p T w )w and renormalize

and are given by wp+1 = wp+1 − j=1 (wp+1

j j

3 Calculation of eigenvectors V and eigenvalues E is shown in (4) wp+1 as wp+1 = wp+1 / T w

wp+1 p+1 .

V−1 CV = E (4)

4.3.2.2. Kernel principal component analysis (Kernel PCA). Using

4 Sorting of eigenvectors Kernel PCA [31], the linear operations of PCA are done with non-

linear mapping. Kernel PCA computes the principal eigenvectors

of the kernel matrix instead of computation from the covariance

Eigen vector with highest eigenvalue is the principal compo-

matrix. The steps involved are,

nent of the data. Eigen vectors are ordered by eigenvalue, highest

to lowest.

1 Computation of kernel matrix K

5 Projection of data is shown in (5)

For the data samples {xi }, kernel matrix is computed. The entries

T T

in the kernel matrix are given by ki,j = k(xi , xj ), where k is a kernel

Projected data = V (x − x̄) T (5)

function such as Gaussian or polynomial.

Arrhythmia classiﬁcation is done by varying the selection of

components from 1 to 10 in the projected data and the results are 2 Double centering of K

analyzed.

It means subtracting the mean of the data in the feature space

4.3.2. Nonlinear techniques deﬁned by the kernel function and is shown in (9).

1 1

Nonlinear techniques have the ability to deal with complex

1 1

nonlinear real world data. The following nonlinear techniques are ki,j = − (ki,j − kil − l kjl + 2 klm ) (9)

2 n l n n lm

experimented to analyze its performance in comparison with tra-

ditional PCA. Where, n is the number of data samples.

R. Rajagopal, V. Ranganathan / Biomedical Signal Processing and Control 34 (2017) 1–8 5

Properties of DR techniques.

4 Computation of eigenvectors of covariance matrix ai in the fea-

ture space constructed by k. Technique Mixing model Parameters Computational complexity

5 Projection of data is shown in (10) PCA Linear None O(D3 )

n n

(j) (j) Kernel PCA Non linear k (., .) O(n3 )

yi = a1 k xj , xi , . . ..., ad k x j , x i (10) NLPCA Non linear Net size O(inw)

j=1 j=1

PPA Non linear O(D3 +(D−1)(+1)3 ))

(j)

where, a1 indicates the jth value in the vector a1 and k is the kernel D–Dimensionality of input sample.

function. Arrhythmia classiﬁcation is done by varying the selection g–Contrast function.

of components from 1 to 10 in the projected data and the results ε–Convergence parameter.

n–Number of data points.

are analyzed. i–Number of iterations.

k–Kernel function.

4.3.2.3. Hierarchical nonlinear PCA (hNLPCA). hNLPCA [32] is an w–Number of weights in a neural network.

–Polynomial degree.

extension of PCA in which both the principal component values and

the mapping function is provided by the neural network approach.

Layers involved are input, hidden and output layer. Hidden layer 5 Steps 3 and 4 are repeated for the remaining (D-1) dimensions.

performs nonlinear mapping of high dimensional data to lower Data of reduced dimension will be the input for the next step in

dimensions. Input and output layers have D nodes and hidden layer the sequence.

has d nodes, where, D is the actual dimension and d is the reduced

dimension. hNLPCA means that the same hierarchical order as Properties of above discussed DR techniques are shown in

the linear components of standard PCA is maintained. The steps Table 2.

involved are,

4.4. Probabilistic neural network classiﬁer

1 Feed forward neural network is trained such that the mean

squared error between the input and output is minimized. Probabilistic neural network (PNN) is used for classiﬁcation of

hNLPCA tries to minimize the hierarchical error as well. ECG beats. It is a feed forward network with input, hidden, sum-

mation and output layer. When an input is given, the hidden layer

The hierarchical error function is given in (11), computes the distances from the inputs and training input vectors

to produce a vector whose elements indicates how close the input is

EH = E1 + E 1,2 + E 1,2,3 + . . .. . .. + E 1,2,3...d (11) for a training input. Summation layer sums these contributions for

each class of inputs to produce as its net output a vector of proba-

and E = 12 x̂ − x2 , where x is the data input with Dimension D and bilities. Output layer picks the maximum of these probabilities, and

x̂ is its reconstructed value. produces a 1 for that class and a 0 for the other classes. Radial basis

function (RBF) is used as the transfer function. PNN is trained with

2 Optimal network weights are found using conjugate gradient 88101 ECG beat samples which includes training examples from all

descent approach. ﬁve classes. Training and testing matrix is computed such that each

3 The addition of a weight decay term in order to penalize large row represents an ECG heartbeat and features occupy columns.

network weights w. The performance of the arrhythmia classiﬁer system is eval-

uated using performance metrics such as accuracy, sensitivity,

Etotal = E + v w2 , w is the network weight and v is the weight

i i speciﬁcity, false positive rate and F score. These metrics are com-

decay coefﬁcient. puted by calculating TP (True Positive), TN (True Negative), FP

(False Positive) and FN (False Negative) count and are deﬁned as

3 At each iteration, single error terms such as E1, E1,2 . . . are cal- follows: Sensitivity = TP/(TP + FN), Speciﬁcity = TN/(TN + FP), False

culated separately and d-dimensional space with minimal mean positive rate = FP/(TN + FP), F score = 2TP/(2TP + FP + FN) and Accu-

square error is found. racy = (TP + TN)/(TP + FP + FN + TN). The process is repeated ten

times such that each set is used once for testing. The overall per-

4.3.2.4. Principal polynomial analysis (PPA). PPA models the direc- formance of the classiﬁer is computed by taking the average of all

tions of maximal variance by means of curves instead of straight ten folds.

lines as modeled by PCA [33]. PPA performs simple univariate

regression such that it becomes computationally feasible. The steps 5. Results and discussion

involved are,

The goodness of a classiﬁer in accurately classifying the test

1 Data centering: heartbeat class is measured mainly by the sensitivity and F score.

The reason for not considering accuracy is that even a poor classi-

This step produces a data set whose mean (x̄) is zero and is ﬁer can show good accuracy in favoring class with more training

shown in (12). examples. Fig. 5 shows the results of average accuracy of PNN clas-

siﬁer taken from 10 fold cross validation for different DR techniques

XC = X − E{X} (12) and dimensions. The result shows that kernel PCA with polynomial

nonlinearity is able to get the highest accuracy of 99.88% even at

2 The best vector for data projection is located by ﬁnding the lead- lower dimensions. But the time taken for dimensionality reduction

ing eigenvector of conventional PCA. is higher than PCA, fastICA and PPA because KPCA computes the

3 Conditional mean m̂ of D dimensional data sample x is estimated eigenvectors of the kernel matrix instead of the covariance matrix.

from the projection by a polynomial ﬁtted to minimize the resid- Sensitivity is an important classiﬁcation parameter which indi-

ual |x − m̂|. cates the number of correctly identiﬁed arrhythmias from patients.

4 Conditional mean is subtracted to every data sample Fig. 6 shows the results of average sensitivity taken from 10 fold

6 R. Rajagopal, V. Ranganathan / Biomedical Signal Processing and Control 34 (2017) 1–8

Accuracy in %

98 95 PCA

KPCA-POLY

F score in %

96

85 KPCA-POLY

94 PPA

fastICA-pow3 75 PPA

92

90 fastICA-tanh 65 fastICA-pow3

1 2 3 4 5 6 7 8 9 10 fastICA-tanh

fastICA-gauss 55

Number of dimensions

hNLPCA 1 2 3 4 5 6 7 8 9 10 fastICA-gauss

Number of dimensions hNLPCA

Fig. 5. Results of average accuracy of PNN classiﬁer for different DR techniques and

dimensions. Fig. 9. Results of average F score of PNN classiﬁer for different DR techniques and

dimensions.

100

95 PCA Table 3

Sensivity in %

90

85 KPCA-POLY Variation of average F scores with respect to different spread values during PNN

80 classiﬁcation using fastICA and Kernel PCA DR techniques.

75 PPA

70 Spread parameter Average F Score

65 fastICA-pow3

60 FastICA–tanh KernelPCA–poly

fastICA-tanh

55

fastICA-gauss 0.1 78.11 92.92

1 2 3 4 5 6 7 8 9 10

0.2 99.62 93.05

Number of dimensions hNLPCA 0.3 99.75 93.05

0.4 99.83 92.97

Fig. 6. Results of average sensitivity of PNN classiﬁer for different DR techniques 0.5 99.83 92.97

and dimensions. 0.6 95.87 92.97

0.7 95.87 92.9

0.8 95.87 92.74

100 PCA 0.9 95.87 92.52

Speciﬁcity in %

98 1 95.72 91.66

KPCA-POLY

96 PPA

94 fastICA-pow3 Table 4

Variation of average F scores with respect to different spread values during PNN

92 fastICA-tanh classiﬁcation using PCA, hNLPCA and PPA DR techniques.

1 2 3 4 5 6 7 8 9 10

fastICA-gauss

Number of dimensions Spread parameter Average F Score

hNLPCA

PCA hNLPCA PPA

Fig. 7. Results of average speciﬁcity of PNN classiﬁer for different DR techniques 0.01 61.77 79.13 61.21

and dimensions. 0.02 76.74 92.53 89.19

0.03 78.19 90.51 91.2

0.04 78.6 85.91 91.49

7 0.05 78.74 80.98 91.49

False posive rate in %

5 KPCA-POLY 0.07 78.74 66.63 91.51

4 0.08 78.82 59 91.28

PPA 0.09 78.6 51.34 91.28

3

fastICA-pow3 0.1 78.5 53.22 91.43

2

1 fastICA-tanh

0

fastICA-gauss

1 2 3 4 5 6 7 8 9 10 of various DR techniques and different dimensions are shown in

Number of dimensions hNLPCA Fig. 9. Results show that fastICA with Gaussian nonlinearity gives

highest F-score of 99.67% with 5 dimensions itself.

Fig. 8. Results of average false positive rate of PNN classiﬁer for different DR tech- Table 3 shows the variation of average F scores with respect to

niques and dimensions.

different spread values during PNN classiﬁcation using fastICA and

Kernel PCA DR techniques. PNN with fastICA (tangential contrast

cross validation of a PNN classiﬁer for different DR techniques and function) coefﬁcients yielded highest F-score of 99.83% on spread

dimensions. Experimental results show that fast ICA with Gaus- value 0.4. PNN with Kernel PCA (polynomial kernel) coefﬁcients

sian non linearity is able to achieve 99.54% sensitivity with only yielded highest F-score of 93.05% on spread value 0.2. Table 4 shows

5 dimensions. PCA, which performs a linear mapping, is able to the variation of average F scores with respect to different spread

produce only a maximum sensitivity of 78.74% even when 10 values during PNN classiﬁcation using PCA, hNLPCA and PPA DR

dimensions are used. techniques. PNN with PCA coefﬁcients yielded highest F-score of

Speciﬁcity indicates the true negative rate and is shown in Fig. 7. 78.82% on spread value 0.08. PNN with hNLPCA coefﬁcients yielded

The result shows that kernel PCA with polynomial nonlinearity is highest F-score of 92.53% on spread value 0.02 and PNN with PPA

able to get the highest speciﬁcity of 99.9% even at lower dimensions. coefﬁcients yielded highest F-score of 91.51% on spread value 0.07.

Average false positive rate for different DR techniques and dimen- Time taken by various dimensionality reduction techniques for

sions taken from 10 fold cross validation is shown in Fig. 8. FastICA making a mapping from high dimensional representation of ECG

with Gaussian non linearity produces the least false positive rate of samples (97,890 × 214) with 97,980 heartbeats and 214 features to

0.05% even with two dimensions. F score is an important parameter low dimensional representation (97,890 × 10) reduced to 10 fea-

that combines both precision and recall. The average F score result tures is shown in Table 5.

R. Rajagopal, V. Ranganathan / Biomedical Signal Processing and Control 34 (2017) 1–8 7

Computation time required by various DR techniques for the input ECG data samples.

reduction techniques with different dimensions of data represen-

DR Technique Computation time (Seconds) tations. Experimental results revealed that the conventional linear

PCA 0.6 DR technique like PCA is easy to apply, but is not able to capture

fastICA–gauss 2 important information required for class discrimination from very

KernelPCA–poly 170 lower dimensional data representation. Nonlinear DR techniques

hNLPCA 4576 are able to capture signiﬁcant information from the lower dimen-

PPA 0.8

sional representation itself. At the same time, nonlinear techniques

face the important drawback of tuning the parameters. The time

Table 6 required for computation is also high compared to linear DR tech-

Comparison of arrhythmia classiﬁers classifying classes N, S, V and F. niques. hNLPCA requires comparatively very huge time for low

F Score of each arrhythmia class

dimensional mapping than other techniques because of the tedious

training procedure and slow convergence. PPA is computationally

Class N Class S Class V Class F

feasible, but not able to achieve high sensitivity and F score as

Chazal et al. [10] 92.60 51.09 79.76 0.15 other nonlinear techniques since it is just a nonlinear generaliza-

Llamedo et al. [34] 87.15 53.66 85.38 8.10 tion of PCA. FastICA in combination with PNN classiﬁer provides

Ye et al. [24] 92.80 56.25 70.01 4.43

Llamedo et al. [35] 97.46 58.43 88.58 5.33

the highest sensitivity and F score with reduced computation time.

Zhang et al. [36] 93.69 49.45 88.96 23.95

Herry et al. [37] 95.18 12.19 75.15 0

Proposed 99.91 80.97 91.54 86.76 References

Based on experimental results obtained, it is found that fast Electrocardiol. (2007) 118–122, http://dx.doi.org/10.1016/j.jelectrocard.2007.

06.023.

ICA dimensionality reduction technique with ‘tanh’ non-linearity [2] J. Kim, S. Shin H, K. Shin, M. Lee, Robust algorithm for arrhythmia

produced the best average F-score of 99.83% when tenfold cross classiﬁcation in ECG using extreme learning machine, Biomed. Eng. Online 8

validation was done by dividing the entire dataset into ten equal (1) (2009) 1–12, http://dx.doi.org/10.1186/1475-925x-8-31.

[3] W. Liang, Y. Zhang, J. Tan, Y. Li, A novel approach to ECG classiﬁcation based

sets. The problem with this cross validation approach is that there upon two-layered HMMs in body sensor networks, Sensors (2014)

is a chance for training and testing matrix to get ECG beats from 5994–6011, http://dx.doi.org/10.3390/s140405994.

same patient. Hence experiments were repeated by dividing entire [4] H. Kim, R.F. Yazicioglu, P. Merken, C. Van hoof, H.J. Yoo, ECG signal

compression and classiﬁcation algorithm with quad level vector for ECG

patient records into ten instead of dividing entire ECG beats into holter system, IEEE Trans. Inf. Technol. Biomed. (2010) 93–100, http://dx.doi.

ten partitions, so that 10% of patient records are tested against 90% org/10.1109/TITB.2009.2031638.

of patient records. The results obtained by using fast ICA (tanh [5] B.M. Asl, S.K. Setarehdan, M. Mohebbi, Support vector machine—based

arrhythmia classiﬁcation using reduced features of heart rate variability

non-linearity) DR technique are compared with six arrhythmia

signal, Artif. Intell. Med. 44 (2008) 51–64, http://dx.doi.org/10.1016/j.artmed.

classiﬁers and results are shown in Table 6. Best F Score obtained 2008.04.007.

for each class by arrhythmia classiﬁers are shown bolded. [6] J.J. Oresko, Z. Jin, S. Huang, Y. Sun, Heather Duschland Allen Cheng C. A

wearable smart phone based platform for real time cardiovascular disease

Automatic heartbeat classiﬁcation system was proposed by [10].

detection via electrocardiogram processing, IEEE Trans. Inf. Technol. Biomed.

Morphological and temporal features were used by them and 14 (2010) 734–740, http://dx.doi.org/10.1109/TITB.2010.2047865.

achieved 75.9% sensitivity, 38.5% positive predictivity and 4.7% false [7] Kai Huang, Liqing Zhang, Cardiology knowledge free ECG feature extraction

positive rate for S class. Two ECG leads were used by them for using generalized tensor rank one discriminant analysis, EURASIP J. Appl.

Signal Process. 2014 (1) (2014) 1–15, http://dx.doi.org/10.1186/1687-6180-

feature extraction and ﬁnal decision was obtained by combining 2014-2.

the outputs from two linear discriminant classiﬁers. The proposed [8] B. Zhu, Y. Ding, K. Hao, A novel automatic detection for ECG arrhythmias using

method used ECG signal from only one lead. Random selection maximum margin clustering with immune evolutionary algorithm, Comput.

Math. Methods Med. 2013 (April) (2013) 1–8, http://dx.doi.org/10.1155/2013/

of training samples was done by [24]. Cluster based classiﬁcation 453402.

was done by [35]. Classiﬁer performance was improved by them [9] R.J. Martis, U. Rajendra Acharya, Min Lim Choo, ECG beat classiﬁcation using

with expert assistance. The proposed method does not require any PCA, LDA, ICA and discrete wavelet transform, Biomed. Signal Process. Control

8 (2013) 437–448, http://dx.doi.org/10.1016/j.bspc.2013.01.005.

expert assistance. Feature selection was made by one-versus-one [10] P. Chazal, M.O. Dwyer, Automatic classiﬁcation of heartbeats using ECG

feature ranking stage by [36] and they achieved 88.94%, 79.06%, morphology and heartbeat interval features, IEEE Trans. Biomed. Eng. 51

85.48% and 93.81% sensitivities for classes N, S, V and F respec- (2004), http://dx.doi.org/10.1109/tbme.2004.827359.

[11] Laurens van der Maaten, Eric Postma, Dimensionality Reduction: A

tively using two ECG leads. Synchrosqueezing transform was used

Comparative Review, TiCC, Tilburg University, 2009.

to enhance R peak detection by [37] and achieved 91.02% over- [12] M.H. Song, Jeon Lee, Sungpilcho, Kyoung Joung Lee, Sun Kook Yoo, Support

all accuracy. But classiﬁcation performance of classes other than N vector machine based arrhythmia classiﬁcation using reduced features, Int. J.

Control Automat. Syst. 3 (2005) 571–579.

and V were very poor. The proposed model used only DWT features

[13] Z. Zidelmal, A. Amirou, D. Ould Abdeslamand, J. Merckle, ECG beat

reduced using fast ICA. The results show that F Score of classiﬁer classiﬁcation using a cost sensitive classiﬁer, Comput. Method Prog. Biomed.

in classifying class S is 80.97% and class F is 86.76%. The reason for 111 (2013) 570–577, http://dx.doi.org/10.1016/j.cmpb.2013.05.011.

low F Score is because of heavy overlap of class S with class N and [14] A. Daamouche, L. Hamami, N.A. Farid Melgani, A wavelet optimization

approach for ECG signal classiﬁcation, Biomed. Signal Process. Control 7

few training examples available for certain classes. Future work is (2012) 342–349, http://dx.doi.org/10.1016/j.bspc.2011.07.001.

to overcome class overlap problem and class imbalance problem in [15] E.D. Ubeyli, Usage of Eigen vector methods in implementation of automated

arrhythmia classiﬁcation. Comparison of proposed system is done diagnostic systems for ECG beats, Digit. Signal Process. 18 (2008) 33–48,

http://dx.doi.org/10.1016/j.dsp.2007.05.005.

with existing systems that followed AAMI recommended practice [16] F. Melgani, Y. Bazi, Classiﬁcation of electrocardiogram signals with support

of arrhythmia classiﬁcation in which training and testing data do vector machines and particle swarm optimization, IEEE Trans. Inf. Technol.

not contain ECG beats from same patient. Biomed. 12 (2008) 667–677, http://dx.doi.org/10.1109/TITB.2008.923147.

[17] J. Wiensand, J.V. Guttag, Patient adaptive ectopic beat classiﬁcation using

active learning, Proceedings of the 2010 Computing in Cardiology, IEEE (2010)

6. Conclusion 109–112 http://hdl.handle.net/1721.1/73888.

[18] Manab Kumar Das, Samit Ari, ECG beats classiﬁcation using mixture of

features, Int. Sch. Res. Notices 2014 (2014).

Classiﬁcation of cardiac arrhythmias into ﬁve different classes [19] Manab Kumar Das, Samit Ari, Electrocardiogram beat classiﬁcation using

as per AAMI standard is performed. Classiﬁer performance is S-transform based feature set, J. Mech. Med. Biol. (2014) 14.

8 R. Rajagopal, V. Ranganathan / Biomedical Signal Processing and Control 34 (2017) 1–8

[20] Hari Mohan Rai, Anurag Trivedi, Shailja Shukla, ECG signal processing for [28] B.N. Singh, A.K. Tiwari, Optimal selection of wavelet basis function applied to

abnormalities detection using multi-resolution wavelet transform and ECG signal denoising, Digit. Signal Process. 16 (2006) 275–287, http://dx.doi.

artiﬁcial neural network classiﬁer, Measurement 46 (2013) 3238–3246, org/10.1016/j.dsp.2005.12.003.

http://dx.doi.org/10.1016/j.measurement.2013.05.021. [29] J. Pan, J.W. Tompkins, A real time QRS detection algorithm, IEEE Trans.

[21] Behnaz Ghoraani, Sridhar Krishnan, Discriminant non-stationary signal Biomed. Eng. (1985) 32, http://dx.doi.org/10.1109/tbme.1985.325532.

features clustering using hard and fuzzy cluster labeling, EURASIP J. Adv. [30] Aapo Hyvarinen, Fast and robust ﬁxed point algorithms for independent

Signal Process. 2012 (1) (2012) 1–20, http://dx.doi.org/10.1186/1687-6180- component analysis, IEEE Trans. Neural Netw. (1999) 626–634, http://dx.doi.

2012-250. org/10.1109/72.761722.

[22] Fahim Suﬁ, Ibrahim Khalil, Abdun Naser Mahmood, A clustering based system [31] J. Shawe Taylor, N. Christianini, Kernel Methods for Pattern Analysis,

for instant detection of cardiac abnormalities from compressed ECG, Expert Cambridge University Press, Cambridge, UK, 2004, http://dx.doi.org/10.1017/

Syst. Appl. 38 (2011) 4705–4713, http://dx.doi.org/10.1016/j.eswa.2010.08. CBO9780511809682.

149. [32] M. Scholz, R. Vigario, P.C.A. Nonlinear, A new hierarchical approach, Proc.

[23] Sung Nien Yu, Combining independent component analysis and back ESANN (2002) 439–444.

propagation neural network for ECG beat classiﬁcation, Proc. Conf. IEEE Eng. [33] V. Laparra, S. Jimenez, D. Tuia, G. Camps-Valls, J. Malo, Principal polynomial

Med. Biol. Soc. (2006) 3090–3093. analysis, Int. J. Neural Syst. (2014) 26.

[24] Can Ye, B.V.K. Vijayakumar, M.T. Coimbra, Heartbeat classiﬁcation using [34] M. Llamedo, Martinez Juan Pablo, Heartbeat classiﬁcation using feature

morphological and dynamic features of ECG signals, IEEE Trans. Biomed. Eng. selection driven by database generalization criteria, IEEE Trans. Biomed. Eng.

(2012) 59. 58 (2011) 616–625, http://dx.doi.org/10.1109/TBME.2010.2068048.

[25] G.B. Moody, R.G. Mark, The impact of the MIT BIH arrhythmia database, IEEE [35] M. Llamedo, J.P. Martinez, An automatic patient adapted ECG heartbeat

Eng. Med. Biol. 20 (2001) 45–50, http://dx.doi.org/10.1109/51.932724. classiﬁer allowing expert assistance, IEEE Trans. Biomed. Eng. 59 (2012)

[26] E.B. Mazomenos, D. Biswas, A. Acharyya, Taihai Chen A low-complexity ECG 2312–2320, http://dx.doi.org/10.1109/TBME.2012.2202662.

feature extraction algorithm for mobile healthcare applications, IEEE J. [36] Z. Zhang, J. Dong, X. Luo, K. Choi, X. Wu, Heartbeat classiﬁcation using disease

Biomed. Health Inform. 17 (2013) 459–569, http://dx.doi.org/10.1109/TITB. speciﬁc feature selection, Comput. Biol. Med. 46 (2014) 79–89, http://dx.doi.

2012.2231312. org/10.1016/j.compbiomed.2013.11.019.

[27] Li Deqiang, Pedrycz Witold, J. Nicolino Pizzi, Fuzzy wavelet packet based [37] C.L. Herry, M. Frasch, H. Wu, Characterization of ECG patterns with the

feature extraction method and its application to biomedical signal synchrosqueezing transform. (2015). arXiv:1510.02541.

classiﬁcation, IEEE Trans. Biomed. Eng. 52 (2005) 1132–1139, http://dx.doi.

org/10.1109/TBME.2005.848377.

- Face Recognition by Generalized Two-dimensional FLD Method and Multi-class SVMUploaded byPhungTue
- Application of multivariate principal component analysis on dimensional reduction of milk composition variablesUploaded byresearchinbiology
- Xlstat Getting Started Manual(1)Uploaded byjose
- Multivariate Analyses Using SASUploaded byRaju Vemula
- Face Image Retrieval in Image Processing a SurveyUploaded byEditor IJRITCC
- Rom ProposalUploaded byylee
- Advanced Machine LearningUploaded byanirudhkulukuru
- AlterasiUploaded byArif Hidayat
- Factor AnalysisUploaded byjamazalale
- 856-876Uploaded bymaz_wied74
- 3-36805_InsideBIGDATAGuidetoMarchineLearning2014Uploaded byChris Winne
- Talk13-SOMS-PCA-ICA-MDS2014.pdfUploaded byPeter Parker
- Sneha. G.GondaneUploaded byEEE_Proceedings
- Content production and perception of copyright - Aliprandi & Mangiatordi (2013)Uploaded byProgetto Copyleft-Italia.it
- Ch3-Mathematical and Physical BackgroundsUploaded byjeysam
- Smart Grid CommUploaded byjbsimha3629
- Velocidad Promedio Con Redes NeuronalesUploaded bygiancar
- PAN-Sharpening Using Content-Specific Orthogonal Linear TransformUploaded byBiswabandan Satpathy
- Principal Components Analysis (PCA)FinalUploaded byendale
- Data Compression Issues With Pattern Matching in Historical DataUploaded bystp01
- MVA Section2Uploaded byGeorge Wang
- Learning Rules and Its Computational PropertiesUploaded byDr Mohammed
- Metric LearningUploaded byMarius_2010
- Face RecognitionUploaded bySupriya Subash
- Mandell, Svante, and Mats Wilhelmsson. Willingness to Pay for Sustainable Housing. Journal of Housing Research 20, no. 1 (2011).pdfUploaded byFederico Vallejo Mondragón
- Abdi WiresCS Mfa 2013Uploaded byAriola Devolli
- Anja TextureUploaded bymekalajesi
- 14 Air Quality Monitoring AndUploaded bySanthosh Praveen
- 1-s2.0-S0096300311011416-mainUploaded byValentina Ceaucă
- lec18Uploaded bySourabh Alok Sao

- [IJCST-V5I2P94]:M. Sumithra, S. MalathiUploaded byEighthSenseGroup
- Smola - Introduction to Machine LearningUploaded byEmmanuel Detrinidad
- Reinventing the Retail IndustryUploaded byfoliox
- Survey Paper on Generating Correlation among Different Modalities by Using Parallel Processing for Cross-Media RetrievalUploaded byIJRASETPublications
- chap3_overfittingUploaded byYosua Siregar
- 06 Kunce ChatterjeeUploaded bysouravroy.sr5989
- Neural Networks - Lecture 4.pptUploaded bynaeemkashif
- AI Syllabus CourseUploaded byOnlineDownloads
- 04 Linear ClassifiersUploaded byWai Kit Kong
- High Performance Computing for Big DataUploaded byÍthalo Santana
- Report FinalUploaded bySenthil Kumar
- Machine Learning For Dummies.pdfUploaded byNimish Garg
- [IJCT-V3I4P10] Authors: Ms. Asma Banu R., Mrs. Shoba S. A.,Uploaded byIjctJournals
- 1 Intro to Artificial IntelligenceUploaded byghazi4u
- cs231n_2017_lecture12Uploaded byfatalist3
- Introduction to AI Unit 1Uploaded byAbdun Nafay Qureshi
- ReviewCh7-Markov Chains Part IUploaded byBomezzZ Enterprises
- Adel Lahsasna, Raja Noor Ainon, And Teh Ying Wah - Credit Scoring Models Using SoftUploaded byhenrique_oliv
- A Machine Learning Approach to Musical Style RecognitionUploaded byVlad Apetrei
- CB Insights State of Artificial Intelligence 2018Uploaded byPradyot Rai
- unit1Uploaded byGowthamUcek
- Computation Accuracy of Hierarchical and Expectation Maximization Clustering Algorithms for the Improvement of Data Mining SystemUploaded byIRJET Journal
- Lesson8 ClusteringUploaded byprabhudeen
- Financial time series forecasting using SVMUploaded byKabindra Shrestha
- QUIZ-7-1Uploaded byBob Hwkns
- PRINCIPE_Information Theoretic LearningUploaded byMarcela Lasso
- Prediction of Football Match Score and Decision Making ProcessUploaded byEditor IJRITCC
- Mastering Machine Learning For Penetration Testing.pdfUploaded bycrojas222
- 5 CondensedUploaded byHoussam Menhour
- internship on python and deep learning 2Uploaded byapi-437735794