

ORIGINAL ARTICLE 

Year : 2015  Volume
: 5
 Issue : 1  Page : 3039 

Electrocardiogram based identification using a new effective intelligent selection of fused features
Hamidreza Abbaspour, Seyyed Mohammad Razavi, Nasser Mehrshad
Department of Electronics, Faculty of Electrical and Computer Engineering, University of Birjand, Birjand, Iran
Date of Submission  25Oct2014 
Date of Acceptance  30Dec2014 
Date of Web Publication  18Sep2019 
Correspondence Address: Hamidreza Abbaspour Department of Electronics, Faculty of Electrical and Computer Engineering, University of Birjand, Birjand Iran
Source of Support: None, Conflict of Interest: None  2 
DOI: 10.4103/22287477.150389
Over the years, the feasibility of using Electrocardiogram (ECG) signal for human identification issue has been investigated, and some methods have been suggested. In this research, a new effective intelligent feature selection method from ECG signals has been proposed. This method is developed in such a way that it is able to select important features that are necessary for identification using analysis of the ECG signals. For this purpose, after ECG signal preprocessing, its characterizing features were extracted and then compressed using the cosine transform. The more effective features in the identification, among the characterizing features, are selected using a combination of the genetic algorithm and artificial neural networks. The proposed method was tested on three public ECG databases, namely, MITBIH Arrhythmias Database, MITBIH Normal Sinus Rhythm Database and The European STT Database, in order to evaluate the proposed subject identification method on normal ECG signals as well as ECG signals with arrhythmias. Identification rates of 99.89% and 99.84% and 99.99% are obtained for these databases respectively. The proposed algorithm exhibits remarkable identification accuracies not only with normal ECG signals, but also in the presence of various arrhythmias. Simulation results showed that the proposed method despite the low number of selected features has a high performance in identification task. Keywords: Biometrics, identification, electrocardiogram, genetic algorithm, neural networks
How to cite this article: Abbaspour H, Razavi SM, Mehrshad N. Electrocardiogram based identification using a new effective intelligent selection of fused features. J Med Signals Sens 2015;5:309 
How to cite this URL: Abbaspour H, Razavi SM, Mehrshad N. Electrocardiogram based identification using a new effective intelligent selection of fused features. J Med Signals Sens [serial online] 2015 [cited 2020 Oct 30];5:309. Available from: https://www.jmssjournal.net/text.asp?2015/5/1/30/150389 
Introduction   
Biometric systems are able to do identification with enhanced security based on biological and behavioral data, which are always available. Fingerprint, iris, face and electrocardiogram (ECG) are examples of biological data that are used in biometric systems. On the other hand, gait, speech, and signature are some of the behavioral characteristics used in these systems. Biometric systems designed based on each of these biometrics are different in terms of performance, permanence, collectability, circumvention, uniqueness, and acceptability. ^{[1],[2]}
Studies have shown that ECG signal is one of the most accurate biometrics. ^{[3],[4]} Identification based on ECG was first performed by Biel et al. ^{[5]} The authors of this study and other related studies showed that details of the electrical activity of the heart observed in the ECG signal can be used in identity recognition systems. ^{[6],[7]} The ECG signal formation is a function of structural and functional anatomy of the heart and its surrounding tissues. Therefore, it is expected that the ECG biometric is unique. ECG signal confirm the viability and cannot be easily forged. Moreover, this signal provides a considerable amount of information about mental, physiological, and clinical status of subjects. ^{[8]}
Electrocardiogram based biometric systems can be categorized according to its characteristics such as the number of data channels, operating environment, feature extraction, and classification techniques. Among these characteristics, feature extraction method can have great influence on the system performance. In many studies, nonfiducial features extracted from the frequency content of the ECG signal (wavelet and Fourier coefficients) have been used. ^{[9]}
Frequency content based ECG features compared to its spatial features can be more easily extracted. Obtaining the ECG signal spatial features, its different fiducial points should be localized while the extraction of frequencybased features needs one or more ECG segments, so it is only necessary to locate the position of the R peaks. ^{[9]}
However, the numbers of nonfiducial features extracted from discrete wavelet transform (DWT) and discrete Fourier transform (DFT) coefficients are too much. It is expected that these features are not of equal Importance in various issues such as arrhythmia detection, identification, and authentication. Review of the studies done on each of these areas shows that the optimal set of features for a specific application (different from other uses) is not so far selected.
For example, 256 biorthogonal DWT coefficients of each RR segment of ECG have extracted by Wan and Yao. ^{[10]} Belgacem et al. ^{[11]} have used five levels of db3 DWT coefficients of the mean RR cycles. Chiu et al. ^{[12]} connected Samples around the Rpeak of ECG signal (43 before and 48 after) for 4 beats and formed the input signal of 512 samples for each individual. Ninelevel Haar DWT coefficients are then extracted as features. Nonzero coefficients in the discrete cosine transform (DCT) of autocorrelated (AC) ECG signal are used as a feature by Wang et al. ^{[13]} Fang and Chan ^{[14]} are also used a composition of the reflection and DCT coefficients. Plataniotis et al. ^{[15]} extracted features by applying DCT on AC sequences of ECG segments. AC and DCT or linear discriminant analysis were merged by Agrafioti and Hatzinakos. ^{[16]} Ye et al. ^{[17]} were applied DWT and independent component analysis (ICA) onto the two most routinely leads used for the continuous monitoring of cardiac signals to extract features. They extracted 118 coefficients of db8 wavelet components and 18 ICA components from each heartbeat segment. Gurkan et al. ^{[18]} were used a combination of 20 AC/DCT features and 13 Melfrequency cepstral coefficient features. In addition, information of the QRS complex have been considered as the third feature set using 120 samples of ECG signal around the Rpeak (60 samples each side of Rpeak). Saechia et al. ^{[19]} were used significant components of the Fourier transform of the ECG signals as features.
In previous researches, all wavelet and/or Fourier coefficients are used as the features. Obviously, only distinguishing unique features should be used in the identification. It is evident that all samples of the ECG signal in selected segments as well as all wavelet and/or Fourier transform coefficients do not have such a property. In this study, a new intelligent method for selecting the most distinguishing fused features that have unique values for each individual is proposed. The proposed feature selection method has been developed based on a combination structure of artificial neural networks (ANNs) and genetic algorithms (GAs).
The organization and structure of the study are such that the required primary concepts underlying the proposed method are firstly presented and then the proposed method is explained. Finally, simulation results, discussion, and conclusions are presented.
METHODS
The overall block diagram of the proposed method for selection of effective features in the identification using ECG signal is shown in [Figure 1]. Before describing the different stages of the proposed method, we first need to explain some basic concepts used. These concepts consist of discrete wavelet, Fourier and cosine transforms, reflection coefficients, GA and neural networks. Finally, the different steps of the procedure, including preprocessing, feature fusion, intelligent selection of fused features and classification will be described in detail.
Discrete Cosine Transform
The DCT, and in particular the DCTII, is often used in signal processing, especially for lossy data compression, because it has a strong "energy compaction" property. ^{[20],[21]} Most of the signal information tends to be concentrated in a few lowfrequency components of the DCT, approaching the KarhunenLoθve transform (which is optimal in the decorrelation sense) for signals based on certain limits of Markov processes. The DCTII is probably the most applications such as feature selection to as "the DCT". ^{[20],[21]} The N real numbers are transformed into the N real numbers as it can be seen in Eq. 1.
(1)
Discrete Fourier Transform
Analyzing the frequency content of the signal simply is possible using the DFT. The DFT coefficients (the absolute value of in Eq 2) may be used in many practical applications such as feature selection.
(2)
It should be noted that DFT does not provide any information about the local properties such as the location of frequency components appearance in the signal.
Discrete Wavelet Transform
The combined TimeFrequency analysis of nonstationary signals (such as the ECG) is an important issue. In addition to the features related to the frequency content of the ECG signal obtained using DFT, TimeFrequency features obtained from DWT is also used, so that will be described.
Reflection Coefficients
On the basis of autoregressive (AR) or allpole model, an ECG beat can be characterized as an output of a casual, stable, linear time invariant stationary system of Eq. 3 given by AR parameters.
(3)
AR parameters of this system, commonly known as the linear prediction coefficients and is assumed to be white Gaussian excitation with zero mean and variance. To calculate the AR parameters, often the YuleWalker equations are used as in. ^{[22]} AR coefficients are very sensitive to noises. Therefore, instead of using them, reflection coefficients, are utilized.
As a reflection coefficients estimation method, suppose that E is the amount of energy of the prediction error that is determined as follows.
(4)
The minimum prediction error of a Ppole model is given by
. (5)
Where, is energy of the signal. Based on the values of the correlation and the theory of minimum prediction error, by applying a recursive procedure of LevinsonDurbin, reflection coefficients are extracted directly. In this direct method, the following equations set are solved recursively for to obtain reflection coefficients.
(6)
Where.
Genetic Algorithm
Genetic algorithm is an optimization algorithm based on Darwin's theory of evolution that mimics the process of natural selection. The purpose of applying GA to the problems is to evaluate the ability of the algorithm to find optimal solutions in terms of convergence and its performance for different settings. ^{[23]} An overall framework of GA can be in the form of the following pseudo code. ^{[24]}
Step 0:
Initialize parameters (e.g. population size, crossover rate, mutation rate and the maximum number of population generation)
Step 1: Create an initial population randomly
Step 2:
Evaluate current population (compute the fitness of all chromosomes)
Step 3:
While (termination condition not satisfied) do (steps 48)
Step 4: Select from (perform selection)
Step 5: Recombine P (t) (perform mutation and crossover)
Step 6:
Evaluate current population (compute the fitness of all chromosomes)
Step7:
Step8: Go to Step 3
Neural Networks
In this study, the selected features by GA are applied to a multilayer perceptron neural network (MLP). MLP has a feedforward layer structure with errorbased learning algorithm. The MLP design is determined completely by an input layer where the number of neurons is equal to the number of selected features, one or more hidden layer (s) and an output layer where the number of neurons is equal to the number of the target classes . The input vector is applied to the input layer and on the track ahead passes through all layers. Each neuron in the hidden layer is related to all neurons in its previous and next layers. The process of classification begins by the input nodes allocation to the corresponding input data vector components; then data will be released in a way ahead and through perceptron until reach the output nodes . MLP as a classifier estimates the necessary separator functions and assigns input vectors to the corresponding target class. A learning algorithm corrects the weights for minimizing the error between the desired output and the MLP output.
Data Preparation
Three wellknown databases available on the Physionet website have been used for the implementation of this research.
The MITBIH Arrhythmia database includes 48 ECG records of 47 subjects consists of 25 men at the ages of 3289 years, and 22 women at the ages 2389 years. Each record lasts almost >30 min, and includes records of the top and bottom lids. Each record is digitized with a depth of 11bit and sampled with a frequency 360 Hz and has been saved in the range of 10 mV.
The MITBIH Normal Sinus Rhythm database includes ECG records of 18 persons consists of 5 men at the ages of 3645 years and 13 women at the ages of 2050 years. Normal heart function of these people was a factor of choosing them. All records were sampled with a rate of 250 Hz.
The European STT database includes ECG records of 78 individuals contains 70 men at the ages of 3084 years and 8 women at the ages of 5571 years. Recording of each ECG signal lasts 2 h and sampled with a rate of 250 Hz and resolution of 12 bits and has been saved in the range of 20 mV.
Preprocessing of the Electrocardiogram Signal
In the preprocessing stage, after noise removal, individuals ECG records are segmented and then normalized. Noise components in the recorded ECG signals created by various noise sources include base line wander, the AC noise and high frequency noises. Removal of additive noise (Eq. 7) is performed using wavelet and Butterworth filtering.
(7)
Where is the noisy signal; ECG is the cleared signal and is additive white noise. The ECG signal can be shown by coefficients obtained by DWT. The Key for eliminating noise is to remove all wavelet coefficients that are produced by noise. So the coefficients exceed to a certain extent must be eliminated and removed by thresholding. Generally four types of the thresholding methods exist that are universal, minimax, Stain's unbiased risk, and hybrid. Furthermore, two types of standard threshold function in applications of noise removal called the hard and soft thresholding are given in Eqs. 8 and 9. ^{[25]}
(8)
(9)
The threshold value of in DWT was introduced by Donoho where N is the length of the noisy signal and s is the standard deviation of noise. ^{[25]} In this study, "db6" was used as a mother wavelet. ECG signals were decomposed to five levels, and the universal soft thresholding is applied on each level.
In addition, there is the possibility of baseline shift of the ECG signal because of the presence of artifacts. This problem should be resolved after clearing the signal by wavelet transform and before signal segmentation stage. To remove base line shifts, a simple secondorder Butterworth lowpass filter with a cutoff frequency of 40 Hz has been used.
For effective segmentation of the ECG records, Pan and Tampkin's algorithm have been used in order to detect Rwave. ^{[26],[27]} Then the RR cycles are resampled to have similar lengths.
Afterward, each RR cycle of the filtered ECG signal is normalized by the following equation.
(10)
In this formula respectively shows the normalized ECG signal with zero mean and unit variance, filtered ECG signal, the mean, and standard deviation. [Figure 2] shows two RR segments of ECG signal before and after preprocessing stage.  Figure 2: Two electrocardiogram segments before (left) and after (right) preprocessing
Click here to view 
Finally, to reduce the data acquisition time, which is an important issue in biometric systems, only ten RR cycles were selected randomly from each person's ECG record and will be sent to the feature extraction stage.
Feature Extraction and Fusion
In this research work, wavelet, Fourier, and reflection coefficients were extracted from individual's ECG segments. Then these features were combined and fused to form the basic features set.
To access to more effective frequency domain features, ECG segments are divided into five sub segments. DFT is then taken on these sub segments, and subsequently in order to compress the energy, only important coefficients of these five sub segments are selected using DCT.
TimeFrequency features suitable for identification are extracted using five level coefficients (A _{5} and D _{1} to D _{5} ) of db6 wavelet. Obviously other wavelets used in previous researches on the ECG signal ^{[28],[29],[30],[31],[32],[33]} were evaluated for this application and among them, db6 wavelet have been selected by trial and error.
Consuming DWT coefficients as the features increases the dimensions of the features set. So the DCT, were applied to the DWT coefficients at different levels. Then the main coefficients of DCT were considered as the features.
Reflection coefficients, which are obtained from AR modeling of the ECG signal, when used in conjunction with DCT coefficients, provide excellent results for human identification. ^{[34]} In this study, ten reflection coefficients extracted from each segment of individuals ECG record and added to the features set.
Intelligent Genetic Algorithm and Artificial Neural Network Based Selection of Fused Features
Most of the classifiers in the lower dimensions of the features provide acceptable results; however, in large dimensions of the features, they are confused and faced with the famous problem of the curse of dimensionality. ^{[35]} In general, it is not clear, which features subset makes the highest distinction for the desired pattern classes; on the other hand, the possibility of evaluating all existing subsets is not affordable. So to find the best and most appropriate features subset among a large collection of features is a problem, which in many cases we are faced with it.
It is expected that all of the features that can be extracted from the ECG signal, don't have equal importance in various applications such as arrhythmia detection or identification. A good selection of features increases the recognition rate and speed and has a positive effect on the storage, retrieval and processing of data. This method is developed in such a way that it is able to select important features that are necessary for identification using analysis of ECG signal.
The aim of different feature selection methods is to find the best subset among 2 ^{N} candidate subsets. As it was mentioned before, in all these methods, based on the application, a subset is selected as an answer that is able to optimize an evaluation function. It is evident that the final goal of a pattern recognition problem is to minimize the classification error in all classes. Despite the fact that each method will try to select the best features, but due to the extent of the possible responses and the set of answers that can be increased by N powers, it is difficult to find the optimal answer and in the medium and large Ns is very costly and sometimes impossible. Hence in the problems with the high number of candidate features, Metaheuristic optimization algorithms such as GA have been proposed to perform feature selection. ^{[36],[37]}
In this study, ANN has been used as a classifier for evaluation of the features subset produced by GA. The number of input layer neurons depends on the number of desired features. Each subset has an estimated error that its inverse is considered as a criterion of eligibility of the features subset.
The overall proposed feature selection process by GAANN is shown in [Figure 3]. Moreover, parameters for GA and ANN are reported in [Table 1] and [Table 2] respectively.  Figure 3: Feature selection process by genetic algorithmartificial neural network
Click here to view 
In this feature selection issue, cost function or estimation error should be minimized. In addition, additional and irrelevant features also should be removed from the features set. So, the cost function is normalized by a penalty term as follows.
(11)
In the above formula, D is the total number of the features, d is the number of selected features and MSE is mean squared error. So, NN orients the GA to find the most optimal solution by giving value to each chromosome string.
In the feature selection problem, the chromosomes (possible answers) are considered as binary strings, and their dimensions are proportional to the features vector. Each bit of the binary string represents a feature value. Ones and zeros for each bit string, indicating the participation or nonparticipation of its corresponding feature value respectively. For example, chromosome 00101000 means that the third and the fifth features are selected. [Figure 4] illustrates a chromosome used in this method.
Each chromosome represents a subset of features. Using ANN, cost (MSE) of features subset (after training) is obtained for the test set. Then the bests are selected as parents of the next generation.
Experimental results   
In this section, performance of the proposed algorithm is evaluated by testing it on ECG records available in three popular databases of Physionet website. Ten segments of the ECG records of each individual are considered. After features extraction and fusion of each individual sample, the best and most appropriate subset of features for identification is selected by the proposed method and applied to an MLP classifier. The average of ten implementation identification rate over 20% of each individual samples have been reported. To ensure the over training does not occur, 20% of the each individual samples were used for validation. The remaining 60% of each individual samples were used for the training process.
In this research, more comprehensive database is selected compared with similar studies. In order to demonstrate the generalization ability of the algorithm, implementation results have been reported on three common databases. In addition, the training and testing samples for each class (individual) have been considered more comparing similar studies. For each person, the algorithm runs ten times. In each run, ten randomly selected ECG segment are used. This means that for each individual, 100 ECG segment are selected.
The remaining wavelet, Fourier and reflection coefficients after feature selection stage, for four different samples of a person, as well as samples from four different people, which are selected randomly from the MITBIH database are shown in [Figure 5] [Figure 6] [Figure 7] [Figure 8].  Figure 5: Wavelet approximation coefficients for different samples of an individual (left) and samples of different individuals (right)
Click here to view 
 Figure 6: Wavelet fifth level detail coefficients for different samples of an individual (left) and samples of different individuals (right)
Click here to view 
 Figure 7: Discrete Fourier transform coefficients for different samples of an individual (left) and samples of different individuals (right)
Click here to view 
 Figure 8: Reflection coefficients for different samples of an individual (left) and samples of different individuals (right)
Click here to view 
Some studies in the field of ECG biometrics and their results are reported in [Table 3]. The rates of decrease in the dimensions of the features set, before and after compression and intelligent selection process, as well as the correct identification rates, have been reported in [Table 4]. Correct identification rate is defined as the rate at which the system rightly states a match between the person's biometrics and those biometric records previously collected. ^{[38]} {transformed into the N real numbers 3}  Table 4: Results of applying the proposed algorithm on different databases
Click here to view 
Furthermore, the proposed identification system performance was evaluated based on four other conventional statistical criteria called TPR (Recall) and TNR (Specificity) and FPR (Fall Out) and FNR (Miss Rate). The TPR and TNR statistical criteria are presented in Eqs. 12 and 13. The FPR and FNR statistical criteria are easily calculated from the TPR and TNR respectively (FPR = 1 − TNR and FNR = 1 − TPR).
(12)
(13)
TP, TN, FP and FN parameters used in the Eqs. 12 and 13 are presented in [Table 5]. TP is the number of samples of the target class, which is assigned correctly to the target class. TN is the number of samples of other classes that are correctly assigned to other classes. FP is the number of samples of other classes, which mistakenly assigned to the target class. FN is the number of samples of the target class, the mistakenly assigned to other classes. The performance of the proposed algorithm using these parameters is reported in [Table 6]^{[39]}.  Table 5: TP, FN, TN and FP definition according to the classification accuracy of the cardiac cycle
Click here to view 
Discussions and conclusions   
In this study, a new intelligent method for selecting the most distinguishing fused features, which have unique values for each individual, is proposed. It is obvious that all samples of the ECG signal in selected segments as well as all wavelet and/or Fourier transform coefficients do not have such a property to distinguish each individual uniquely. Whereas, only distinguishing unique features should be used in the identification. For this purpose, features extracted from the DFT and DWT analysis of the ECG signal segments, were firstly compressed by the cosine transform to reduce redundancy of features. Some reflection coefficients also extracted from ECG signal segments and added to the fused features set and then an intelligent GAANN based method is utilized for selecting more effective subset of features for identification task.
Reflection coefficients when used in conjunction with DCT components provide excellent results for human identification. It is clearly observed from [Figure 5] [Figure 6] [Figure 7] [Figure 8] that selected features offers a great intraclass compactness and interclass separability.
Comparison of classification accuracies of [Table 3] and [Table 4], and also the results reported in [Table 6] shows that our new proposed method, which is validated by the greater number of one channel long/short term ECG records obtained from healthy and patient individuals available in three popular databases of physionet website despite the lower number of selected features gives better identification results than the other researches. Moreover, the proposed method requires less time to train and test the classifier and has a lower computational complexity. The results of the experiments shows, our new proposed algorithm has demonstrated remarkable performance compared to other ECG based identification techniques.
References   
1.  Bolle RM, Connell JH, Pankanti S, Ratha NK, Andrew W. Senior, Guide to Biometrics. New York: SpringerVerlag; 2003. 
2.  Chirillo J, Blaul S. Implementing Biometric Security. Inianapolis: Wiley; 2003. 
3.  Israel SA, Irvine JM, Wiederhold BK, Wiederhold MD. The Heartbeat: The Living Biometric. New York, USA: WileyIEEE Press; 2009. 
4.  Israel SA, Irvine JM, Cheng A, Wiederhold MD, Wiederhold BK. ECG to identify individuals. Pattern Recognit 2005;38:13342. 
5.  Biel L, Pettersson O, Philipson L, Wide P. ECG analysis: A new approach in human identification. IEEE Trans Instrum. Meas 2001;50:80812. 
6.  Irvine J, Wiederhold B, Gavshon L, Israel S, McGehee S, Meyer R, et al. Heart rate variability: A new biometric for human identification. Paper presented at: International Conference on Artificial Intelligence; 2001; Washington, USA. 
7.  Kyoso M, Uchiyama A. Development of an ECG identification system. Paper presented at: 23 ^{rd} Annual International Conference of the IEEE; 2001; Istanbul, Turkey. 
8.  Odinaka I, Lai PH, Kaplan AD, O`Sullivan JA, Sirevaag EJ, Kristjansson SD, et al. Ecg biometrics: A robust shorttime frequency analysis. Paper presented at: IEEE International Workshop on Information Forensics and Security. Seattle, USA. 2010. 
9.  Agrafioti F, Gao J, Hatzinakos D. Heart biometrics: Theory, methods and applications. Biometrics B 2011;3:199216. 
10.  Wan Y, Yao J. A neural network to identify human subjects with electrocardiogram signals. Paper presented at: World Congress on Engineering and Computer Science; 2008; San Francisco, USA. 
11.  Belgacem N, Ali A, Fournier R, BereksiReguig F. ECG based human authentication using wavelets and random forests. Int J Cryptography Inf Secur 2012;2:111. 
12.  Chiu CC, Chuang CM, Hsu CY. A Novel personal identity verification approach using a discrete wavelet transform of the ECG signal. Paper presented at: International Conference on Multimedia Ubiquitous Engineering; 2008; Busan, Korea. 
13.  Wang Y, Agrafioti F, Hatzinakos D, Plataniotis KN. Analysis of human electrocardiogram for biometric recognition. EURASIP J Adv Signal Process 2008;19:148658. 
14.  Fang SC, Chan HL. Human identification by quantifying similarity and dissimilarity in electrocardiogram phase space. Pattern Recognit. 2009;42:182431. 
15.  Plataniotis KN, Hatzinakos D, Lee JK. ECG biometric recognition without fiducial detection. Paper presented at: Biometrics Symposium Special Session Research Biometric Consortium Conference; 2006; Baltimore, USA. 
16.  Agrafioti F, Hatzinakos D. ECG based recognition using second order statistics. Paper presented at: 6 ^{th} Annual Communication Networks and Services Research Conference; 2008. Halifax, Canada. 
17.  Ye C, Coimbra MT, Kumar BV. Investigation of human identification using twolead electrocardiogram (ECG) signals. Paper presented at: Fourth IEEE International Conference on Biometrics: Theory Applications and Systems; 2010; Washington, USA. 
18.  Gurkan H, Guz U, Yarman BS. A novel biometric authentication approach using electrocardiogram signals. Conf Proc IEEE Eng Med Biol Soc 2013;2013:425962. 
19.  Saechia S, Koseeyaporn J, Wardkein P. Human identification system based ECG signal. In: TENCON 2005 2005 IEEE Region 10. IEEE; 2005. p. 14. 
20.  Ahmed N, Natarajan T, Rao KR, Discrete cosine transform. IEEE Transactions on Computers 1974;23:9093. 
21.  Rao K, Yip P, Discrete Cosine Transform: Algorithms, Advantages, Applications. Boston: Academic Press; 1990. 
22.  Kay SM. Modern Spectral Estimation: Theory and Application. Englewood Cliffs, NJ: PrenticeHall, 1988. 
23.  Singhi SK, Liu H. Feature subset selection bias for classification learning. Paper presented at: 23 ^{rd} International Conference on Machine Learning; 2006; Pensilvania, USA. 
24.  Nasiri JA, Naghibzadeh M, Yazdi HS, Naghibzadeh B. ECG arrhythmia classification with support vector machines and genetic algorithm. In: Computer Modeling and Simulation, 2009. Third UKSim European Symposium on. IEEE; 2009. p. 18792. 
25.  Donoho DL. Denoising by softthresholding. IEEE Trans Inf Theory 1995;41:61327. 
26.  Khan MG. Rapid ECG Interpretation. Totowa, New Jercy: Humana Press; 2003. 
27.  Pan J, Tompkins WJ. A realtime QRS detection algorithm. IEEE Trans Biomed Eng 1985;32:2306. [ PUBMED] 
28.  Fatemian SZ, Hatzinakos D. A new ECG feature extractor for biometric recognition. Paper presented at: 16 ^{th} International Conference on Digital Signal Processing; 2009; Santorini, Greece. 
29.  Li C, Zheng C, Tai C. Detection of ECG characteristic points using wavelet transforms. IEEE Trans Biomed. Eng 1995;42:218. 
30.  Belgacem N. ECG based human authentication using wavelets and random forests. Int J Cryptography Inf Secur 2012;2:111. 
31.  Chan AD, Member S, Hamdy MM, Member S, Badre A, Badee V. Wavelet distance measure for person identification using electrocardiograms. IEEE Trans Instrum Meas 2008;57:24853. 
32.  Rooijakkers MJ, Rabotti C, Bennebroek M, Van Meerbergen J, Mischi M. Lowcomplexity Rpeak detection in ECG signals: A preliminary step towards ambulatory fetal monitoring. Paper presented at: 23 ^{rd} Annual International Conference of the IEEE Engineering in Medicine and Biology Society; 2011; Boston, USA. 
33.  Tan HGR, Tan AC, Khong PY, Mok VH. Best wavelet function identification system for ecg signal denoise applications. Paper presented at: International Conference on Intelligent and Advanced Systems; 2007; Kuala lumpur, Malaysia. 
34.  Fattah SA, Mahdee Jameel AS, Goswami R, Saha SK, Syed N, Akter S, et al. An approach for human identification based on time and frequency domain features extracted from ECG signals. In: TENCON 20112011 IEEE Region 10 Conference. IEEE; 2011. p. 25963. 
35.  Bellman R. Dynamic programming and Lagrange multipliers. Proc Natl Acad. Sci U S A 1956;42:767. 
36.  Fodor IK. A Survey of Dimension Reduction Techniques. Technical Report. UCRLDR 148494. Lawrence Livermore National Lab 2002. p. 118. 
37.  Kira K, Rendell LA. The feature selection problem: Traditional methods and a new algorithm. In: AAAI; 1992. p. 12934. 
38.  Management Association Information Resources. Cyber Crime: Concepts, Methodologies, Tools and Applications. USA: IGI Global; 2011. p. 485. 
39.  Irvine JM, Israel SA, Scruggs WT, Worek WJ. eigenPulse: Robust human identification from cardiovascular function. Pattern Recognit 2008;41:342735. 
Authors   
Hamidreza Abbaspour was born in Mashhad, IRAN, in 1988. He received his M.Sc. degree in Electrical Engineering from the University of Birjand, Birjand, Iran, in 2014 and he is presently pursuing the Ph.D. degree at the University of Birjand, Birjand, Iran. His research interests include Biometrics, Pattern Recognition, Digital Signal and Image Processing, Neural Networks, and Artificial Intelligence Algorithms.
Seyyed Mohammad Razavi received the B.S. degree in Electrical Engineering from Amirkabir University of Technology, Tehran, Iran, in 1994 and the M.Sc. degree in Electrical Engineering from the Tarbiat Modares University, Tehran, Iran, in 1996, and the Ph.D. degree in Electrical Engineering from the Tarbiat Modares University, Tehran, Iran, in 2006. Now, he is an Associate Professor in the Department of Electrical and Computer Engineering, the University of Birjand, Birjand, Iran. His research interests include Computer Vision, Pattern Recognition and Artificial Intelligence Algorithms.
Nasser Mehrshad received the B.S. degree from Ferdowsi University of Mashhad, Mashhad, Iran, in 1995 and the M.Sc. and Ph.D. degrees from Tarbiat Modares University, Tehran, Iran, in 1998 and 2005, respectively, both in Biomedical Engineering. He is currently an Associate Professor in the Department of Electrical and Computer Engineering, the University of Birjand, Birjand, Iran. His research interests include Computer Vision, Digital Signal and Image Processing, Biometrics, and Biomedical Data Mining.
[Figure 1], [Figure 2], [Figure 3], [Figure 4], [Figure 5], [Figure 6], [Figure 7], [Figure 8]
[Table 1], [Table 2], [Table 3], [Table 4], [Table 5], [Table 6]
