Reconstruction of the ECG signal using the multichannel wavelet-based filtering system.
Open access peer-reviewed article
This Article is part of Bioinformatics; Healthcare information management Section
Article metrics overview
383 Article Downloads
View Full Metrics
Article Type: Research Paper
Date of acceptance: January 2023
Date of publication: February 2023
DoI: 10.5772/dmht.13
copyright: ©2023 The Author(s), Licensee IntechOpen, License: CC BY 4.0
Electrocardiography (ECG) has been a subject of research interest in human identification because it is a promising biometric trait that is believed to have discriminatory characteristics. However, features of ECGs that are recorded at different times are often likely to vary significantly. To address the variability of ECG features over multiple records, we propose a new methodology for human identification using ECGs recorded on different days. To demonstrate the applicability of our method, we use the publicly available ECG ID dataset. The main goal of this work is to extract the most significant and discriminative wavelet components of the ECG signal, followed by utilizing the ECG spectral change for human identification using multi-level filtering technique. Our proposed multi-channel identification system is based on using the Maximal Overlap Discrete Wavelet Transform (MODWT) and its inverse (the IMODWT) to create multiple filtered ECG signals. The discriminative feature that we utilize for human identification is based on modeling the dynamic change of the frequency components in these multiple filtered signals. To reach the best possible identification performance, we use the Weighted Majority Voting Method (WMVM) for ECG classification. We evaluated the robustness of our proposed method over several random experiments and obtained 92.29% average identification accuracy, 0.9495 precision, 0.9229 recall, 0.0771 FRR and 0.0013 FAR. These results indicate that filtering some of the ECG wavelet components along with performing data fusion technique can be utilized for human identification.
random signals
ECG biometric
Fréchet distance
ECG features
ECG classification
wavelet transform
data fusion
weighted majority vote
Author information
In recent years, physiological signals have showed great potential in human recognition [1–3]. In addition, it has been demonstrated that physiological signal-based identification systems are more robust against counterfeit than the existing conventional and traditional biometric systems [4, 5]. Therefore, researchers have presented various methods to investigate the possibility of human recognition via biomedical signals [6–8]. Specifically, among different biomedical signals, the electrocardiogram (ECG) has been widely studied as a new approach in human identification. It has been shown that ECG based biometric systems achieve satisfactory identification accuracy in a wide range of applications [3]. In fact, the ECG has some key advantages, including mainly its hidden nature and its liveness assurance, which make it preferable to other biometric modalities such as face, fingerprint and iris [3, 5] since they can be damaged or stolen. Additionally, the ECG has several characteristics that are required for any biometric modality. In general, a biometric trait should satisfy the following requirements to be used for human recognition [9, 10]:
Universality: the trait should be present in living population.
Uniqueness: major differences in trait characteristics should be derived among different people.
Collectability: the trait should be quantitatively measurable and easily accessible.
Acceptability: the trait should be user friendly and widely acceptable.
Resistance to circumvention: the trait should be resistant to the various spoofing attacks.
Permanence: the extent to which the trait features should remain stable over time.
The ECG satisfies most of the abovementioned requirements because it is essentially a vital sign and is present in all living people [11–13]. In addition, it has been proven that the ECG has unique patterns among individuals [3] and it can be easily recorded using a single lead [14, 15]. Moreover, the ECG can be hardly forged due to its biological nature and liveness indicator [16]. However, the stability of ECG features is one of the most controversial characteristics because it has been demonstrated that cardiac signals are highly affected by many geometrical, individual, and technical factors [5, 17].
To illustrate, geometrical attributes such as heart size, cardiac muscle thickness, heart shape and the number of cardiac cells involved in the electrical activity directly dictate the routes of the electrical current inside the heart [5, 18, 19]. On the other hand, personal characteristics including mainly the health status, age and weight could cause changes in the heart position and orientation [20]. Hence, these factors shift the electrical current orientation, and also change the conductivity of the heart [5, 20]. Additionally, the electrode features such as the type, quantity, degree of dryness and position may cause some changes in the electrical properties of the electrodes [5, 18, 20]. Consequently, all these previously mentioned factors create morphological variations in the ECG signals which are highly remarkable in ECGs that are recorded on different times [18]. This changeability of the ECG features is usually categorized as intra-subject variability and inter-subject variability [21]. Where the former one refers to the variations within or between ECGs of a single subject, the latter refers to the variations of ECGs of different subjects [3, 5].
In fact, the inter-subject variability is highly desired for human identification because the uniqueness of the ECG signal can be explained through finding the core differences between cardiac signals of different individuals [5, 20]. On the other hand, the intra-subject variability could be beneficial because the dynamic change between ECG features of a single subject can be modeled to create individual based biometric signatures [3, 18]. Hence, a perfect biometric trait should have a very high inter-subject variability. In contrast, it should have very low intra-subject variability [3, 5, 16]. However, the stability of these parameters over time, i.e. their permanence, remain the main challenge in using multiple ECGs for human identification.
The variability of ECG features can be clearly noticed when analyzing the fiducial and non-fiducial characteristics of such a biomedical signal. For example, in figure 1 we show the heart beats of two subjects from the ECG-ID database. Obviously, the inter-subject variability can be observed by the various morphologies that form the personal heartbeats of these two individuals. On the other hand, the intra-subject variability can be noticed as the significant fluctuations in the amplitude of the QRS complexes. In addition, figure 2 shows the intra-subject variability which can be seen as the rapid changes in the ECG frequency components when the data are recorded on different days. Moreover, figure 3 shows the various morphological bundles of the ECG heartbeat such as the right bundle branch block beat, the left bundle branch block beat and normal beat [22].
All the previously presented factors reflect that utilizing the cardiac signal for human recognition does not only depend on choosing the appropriate features, but also relies on categorizing the variability of ECG features over time [23]. In this work, we focus on investigating the feasibility of human identification using ECGs that are recorded on two different days. Specifically, we selected the ECG-ID data because it was originally recorded for biometric purposes. For each subject, two 20-second ECG recordings were chosen. These ECG signals were recorded over a six-month period [24, 25]. The original ECG-ID data have ECG recordings of 90 subjects; however, we only choose signals of 62 subjects who have normal ECG waveforms, where the QRS complex has the highest amplitude. The remaining subjects were excluded because their T wave is tall and higher than the QRS complex. In addition, we designed our method to decompose the ECG using SYM4 which generally detects the QRS features. Therefore, including all the database and treating it equally without changing the mother wavelet or classifying the reference data according to the heartbeat morphology, would have affected the performance of our methodology because there is a significant difference between features of normal heartbeats and other types of heart beats with larger T waves.
The use of ECG in various clinical diagnostic applications has significantly demonstrated different characteristics of this human cardiac signal. Therefore, the potential use of ECG for human identification was driven by utilization of these features to create a new biometric modality. To the best of our knowledge, the first attempt to utilize the ECG for human recognition was presented by Biel
Dar
On the other hand, Morteza
Abdeldayem
Further, Kim
Furthermore, the research investigations in [35] reported that the QRS complex exhibits significant features among different individuals and such features can be utilized for human authentication. The authors in [36] and [23] have shown that the ECG signal reveal varied and unique patterns. The research findings in [37] showed that ECG based biometric identification highly relies on the type of methods that are utilized for feature selection (fiducial vs non fiducial methods). The work in [7] also showed that deep learning networks such as CNN can be employed to extract discriminatory features among multiple ECGs. Generally, utilizing the ECG for human identification depends on many factors including mainly, noise filtering, features selection, features extraction, ECG classification and addressing the variability of the ECG data [2, 3, 23].
In this paper, we focus on identifying individuals using multiple ECGs. These multiple ECGs are recorded on different days, and they are more likely to have some variability in features. Based on our previous work in [38], modeling the dynamic change in ECG spectral features and using Fréchet based distance measurement for ECG classification have shown excellent results on individual recognition. However, when we select the ECG data from different days, the identification performance decreases significantly. This is expected because of the above-mentioned reasons on the variability of ECG features. To solve this problem, the main contributions of this paper include:
Addressing the variability of ECG features at the preprocessing stage by decomposing the signal and performing data filtering methods. Unlike the previous works where the processing stage involved noise removal and signal correction [26, 30–32], in this paper we focus on partitioning the signal variability according to its wavelet components. The variability of the ECG features can be analyzed by decomposition of the signal into its wavelet components [39]. To accomplish our objective, we show that filtering some of the high frequency wavelet components in a set of parallel processes can be modeled for human identification. The main advantage of this process is to reduce the variability of the ECG features at the fundamental wavelet components while keeping majority of the signal information [40].
Proposing a new technique for data fusion at the classification stage to reach true identification. To achieve our goal, we show that utilizing the minimum Fréchet distances between filtered versions of multiple ECGs can be modeled to create a weighted scoring technique based on majority voting for reaching correct identification. The main advantage of our proposed weighted majority voting includes using the minimum distance between multiple ECGs - a unique feature that has an effective role in decision making [41].
In this work, we propose a method for individual identification using multiple ECGs that are recorded on two different days. The general flowchart of our proposed methodology is shown in figure 4.
As mentioned above, we used the public ECG ID database of 62 subjects because it was originally recorded for biometric purposes [25]. For each subject, we selected two ECG recordings. The public ECG ID data do not have information about the exact time and date in which the ECGs were recorded. However, all the ECG recordings were taken over a six-month period. We grouped the ECG ID data into two categories, namely the referencing data and testing data. To achieve our goal of identifying individuals using multiple ECGs, we use the ECGs from the former group for referencing purposes and we use the ECGs from the latter group for testing purposes.
The Maximal Overlap Discrete Wavelet Transform (MODWT) like the Discrete Wavelet Transform (DWT) is a linear filtering process which is used to decompose a signal into a set of time dependent wavelet and scaling coefficients [39]. However, MODWT is non-orthogonal transform compared to DWT [39]. The MODWT basic idea relies on using the values that are removed from DWT by down sampling. Therefore, MODWT is a highly redundant transform compared to DWT since it is defined for all samples sizes. Like the DWT, the MODWT is utilized to perform multiresolution analyses (MRAs) and the redundancy of the MODWT enables instantaneous comparison between the original time series and its decomposition at each level. Most importantly, the MODWT coefficients of various scales are usually not correlated. Thus, it is a useful transform to partition the variability of the signal [39].
The ECG is a nonstationary signal, and its features are often localized in time and frequency [22]. Therefore, it is better to analyze such a signal using wavelets because they are utilized to decompose the signal and provide sparser representation [3]. However, choosing the most appropriate wavelet function depends on the ECG features of interest [2]. Specifically, the QRS complex is the prominent wave of the ECG; therefore, we selected the sym4 as an analyzing wavelet to decompose the ECG into time-varying frequency (scale) components. In addition, the QRS complex can be easily segmented compared to the P and T waves since they require expert labeling to achieve proper segmentation [42, 43]. The sym4 wavelet resembles the QRS complex and is an appropriate choice to detect most of the ECG information [14].
In figure 5, we show a comparison between the sym4 wavelet and the QRS complex. The figure shows that the sym4 resembles the QRS complex. Although sym4 is generally utilized to detect QRS features, it also can detect non QRS features by changing the scale and translation parameters [44]. In this paper, the wavelet coefficients are computationally returned based on utilizing different versions of the analyzing wavelet. The small scales, compressed versions of sym4, are utilized to detect the high frequency components of the signal. In contrast, the large scales, stretched versions of SYM4, are utilized to detect the low frequency components of the signal [44, 45].
In signal processing, real world biological signals such as the ECG are sampled over finite intervals of discrete times [46]. Therefore, the ECG data can be written as a discrete function
According to equations (1) and (2), the MODWT returns
In this work, we set
The ECG is an aperiodic random signal whose value at any instant is unknown and it is generally unpredictable [22]. In addition, the ECG features exhibit some changes over time, specifically, the mean and variance of the ECG are a function of time, and they can vary significantly from heartbeat to heartbeat [46]. The variability of ECG features is caused by physiological and non-physiological factors which we have explained in the introduction [3, 5]. Consequently, it has been demonstrated that utilizing the ECG for human recognition highly requires building identification systems that are adaptable to the variability of ECG features [23]. To achieve our objective, we developed a multi-channel wavelet-based filtering system because we expect that by filtering some of the wavelet components, the variability of ECG features will reduce, and the performance of the identification process will increase.
In fact, all the ECG wavelet-based features including the high frequency and the low frequency components can be useful for the identification process [38, 45]. Therefore, we designed our filtering systems to remove different wavelet components at different levels of the filtering process [46]. The proposed system is designed to filter the high frequency components in a set of parallel processes. The main goal here is to remove some of the components which may have high variability between ECGs that are recorded at different times. To illustrate, we applied a windowing technique based on short time Fourier transform (STFT) to see how the variance of detail coefficients at each scale changes over time. In addition, each window contains an ECG time segment that approximately has a full heartbeat. According to figure 7, the variance of detail coefficients at scales 1–4 (the high frequency wavelet components of the ECG signal) shows significant change across multiple heartbeats compared to the variance of details coefficients at scales 5–10 (the low frequency wavelet components of the ECG signal). However, the change in the variance over time of the detail coefficients at scales 1–4 is subject based. Therefore, filtering different high frequency wavelet components of the ECG signal in a set of parallel processes helps to reduce the variability of ECG features.
However, our filtering system is not designed to filter the low frequency components, which are calculated by utilizing larger scales of the analyzing wavelet, because we expect that such components have most of the permanent information of the ECG (see figure 7). Technically, because we eliminated some of the wavelet information, the reconstructed signals are named as filtered ECGs [39]. Since we apply different levels of filtration, we create different types of filtered ECGs [40]. The main goal here is to find the most significant wavelet components of the ECG signal which are utilized to create our multi-channel identification system.
In figure 8, we show our Parallel High Frequency Filtering System (PHFFS) which consists of five channels. In addition, table 1 shows the wavelet coefficients that are removed at each level of the filtering system. The PHFFS removes the detail coefficients from levels
Filtering channel | Removed coefficients using PHFFS system | Filtered signal notation |
---|---|---|
1 | ||
2 | ||
3 | ||
4 | ||
5 | |
Then, the ECG is reconstructed using the Inverse Maximal Overlap Discrete Wavelet Transform (IMODWT) at each level of these filtering processes [39]. Therefore, the output of the PHFFS consists of several filtered ECGs. According to table 1, the PHFFS constructs five types of filtered ECGs which are defined as
The feature extraction stage involves utilizing significant characteristics from the ECG for human identification. Since ECG is a random time varying signal, it generally has intra feature variability between multiple heartbeats [4, 22]. Therefore, the most appropriate way to utilize the ECG for human identification does not only depend on filtering some of the wavelet components but also involves tracking the dynamic change of features among multiple heartbeats [2]. In our previous work [38], we introduced a new feature that is based on modeling the dynamic change of ECG spectral components. This feature, extracted from the main signal, has shown excellent results for individual recognition. Differently, in this work we extract the dynamic change of the spectral components in each of the filtered ECG signals.
The complete process of extracting the dynamic change of the ECG frequency components can be found in [38]. In short, let
ECG classification for human identification purposes is the process of correctly assigning a class for the transformed feature matrices [9, 16, 30, 44, 47]. Technically, the procedure for choosing the right classifier highly depends on the geometrical characteristics of the feature matrix [38]. Here, we also refer to our previous findings on the robustness of utilizing the Fréchet distance for correctly classifying the covariance matrices of the ECG dynamic features [38]. In short, let
In this work, the scaling coefficients (
In addition, equation (8) returns the minimum Fréchet distance:
Since our PHFFS consists of
Data fusion is a process of combining information collected from a multisensory system to form a final decision [41]. The use of multisensory data has been widely applied in many fields including medical applications [48]. In general, the data collected from a multisensory system are incomplete or overlapping which may cause improper decision making. Therefore, data fusion is an essential step that improves the overall performance of a multisensory system [49–51].
In this work, we utilize the reconstructed ECG signals as information collected from multiple detectors. To reach a common final decision, we aim to combine the multiple decisions that are obtained from the wavelet-based filtering channels [41]. As explained in the previous stage,
Here we propose a scoring technique to reach a final decision using the weighted majority voting method (WMVM) [40, 41]. Our technique is based on computing a weighted score for each person picked by the classification process. For each person in
Consequently, we obtain
However, if more than one filtering channel picked a similar identity as seen in figure 11, a higher weighted score is calculated for that person according to equations (9) and (10) respectively. In data fusion, adding a measurement-based higher score for decisions which have been made using a multisensory system depends on the statistical parameters of the corresponding measurement [41]. To illustrate, figure 12 shows an example of the range of minimum Fréchet distance which are obtained after randomly choosing multiple testing data and applying equations (4)–(6) and (8) respectively. For any of the filtering channels if the range of the minimum distance is very low, it will result in higher weighted scores which make the WMVM method very biased to one filter. In contrast, if the range of the minimum distance is very high, it will result in lower weighted scores which make the outcome of the corresponding filtering channel less effective to reach a final decision. According to figure 12, the range of the minimum distances obtained from each filter is very close, which makes our scoring method sufficient to reach a true final decision.
In this stage, the identification step is a process of picking one identity from the multiple identities obtained by the classification process. As explained above, the WMVM assigns a weighted score for each person selected by the classification process. To reach a final decision, the identity which has the higher weight is chosen, such that:
In short, features of multiple ECGs which belong to a same class might be different whenever it is recorded [19]. Utilizing the complete information of multiple ECGs (e.g., the wavelet components) might not adequately obtain the required minimum distance to reach the right class. The variability in the ECG features might be due to the variability in the individual bases of the ECG wavelet components [18]. Therefore, we developed our multichannel Fréchet based scoring method to achieve the maximum possible similarity between multiple ECGs by parallelly filtering some of the wavelet components [39]. Finally, we combine the outcome of this multi-level filtering technique to reach a final class using equations (9), (10), and (11) respectively.
We have applied our proposed method using multiple ECGs of 62 subjects from the ECG ID database. The experiments set up are designed according to the following steps:
For each subject (
A random test data
Next, the five filtered test ECGs are created using equations (1)–(3) and they are labeled as
Then, the five spectral feature matrices are computed from each of the filtered test ECGs and labeled as
After that, for each subject (
A random reference data
Next, step 1.2 is repeated to create the five filtered reference ECGs and labeled as
Then, step 1.3 is repeated to extract the five spectral feature matrices and labeled as
After that, the Fréchet distance between each test feature in step 1.3 and its corresponding many reference features in step 1.4.3 is calculated using equation (4). In addition, the results are stored in the following distance vectors
Then using equation (7), the classification process is performed based on the minimum Fréchet distance in each of the five distance vectors that are obtained from step 1.5 and the results are stored in the
Also, the values of the corresponding five minimum distances are stored in the
Next, equations (9), (10) are used to find a weighted score for each identity that is picked by step 1.6.
After that, the final level classification is performed using equation (11).
Next, steps 1–3 are repeated 50 times (
Finally, we obtained the
In addition, for each subject (row), the elements of the
We examined the performance of our method in terms of the personal identification accuracy using equation (15) such that:
In addition, we evaluated the average identification accuracy of each filter using equation (16):
The personal identification accuracy using our filtering system has shown good results. Consequently, figure 14 shows full details of the personal identification accuracy at each filter. In addition, table 2 shows that most of the subjects are identified with an identification accuracy ranging from 91% to 100%, with best findings of 42 subjects. Furthermore, figure 15 shows the average identification accuracy using each filter individually with the best findings of 85.55% for filter
Personal identification accuracy | 91–100 (%) | 81–90 (%) | 71–80 (%) | Less than 70% | MODWT filter |
---|---|---|---|---|---|
Total subjects identified | 42 | 4 | 5 | 11 | |
40 | 4 | 7 | 11 | ||
40 | 5 | 4 | 13 | ||
34 | 6 | 6 | 16 | ||
24 | 8 | 5 | 25 |
We evaluated the performance of our proposed method after we performed data fusion using the WMVM. The personal identification accuracy is calculated using equation (17):
In addition, we evaluated the average identification accuracy of our proposed method using equation (18):
Consequently, the personal identification accuracy significantly increased as shown in table 3. After we combined the information using the WMVM, 53 subjects were identified with an identification accuracy ranging from 91% to 100%. In addition, figure 16 shows the full details of the personal identification accuracy for each subject. Moreover, table 4 shows the average identification accuracy of the proposed method.
Personal identification accuracy | 91–100 (%) | 81–90 (%) | 71–80 (%) | Less than 70% |
---|---|---|---|---|
Total subjects identified | 53 | 3 | 2 | 4 |
According to table 4, we excluded six subjects who have less than 80% identification accuracy (subjects with red and yellow bars in figure 16). These subjects were excluded because none of the filtering channels were able to identify them indicating that their ECG features from multiple days had significant variability. As a result, our proposed method for ECG based human identification which is based on filtering some of the wavelet components and applying the WMVM for data fusion has achieved 98.07% identification accuracy. These findings indicate that applying the WMVM is significantly useful since it accurately combines information obtained from multiple filtering channels to correctly reach the final class.
Average identification accuracy | 92.29% | 97.24% | 98.07% |
Number of subjects | 62 | 58 | 56 |
We evaluated the general performance of our proposed method using the following parameters:
Precision: the rate of truly identifying subjects to the total number of identifications:
Accordingly, table 5 shows the precision, recall, FAR and FRR parameters computed by performing classification at each filter. As a result, the best findings are achieved via applying the
Moreover, we evaluated the performance of the proposed method using the receiver operating characteristic curve (ROC), which shows the tradeoff between the true positive rate and false positive rate. Consequently, figure 18 shows the ROC of the proposed method with the closest curve to the top left corner achieved via performing data fusion. In addition, we obtained our highest area under the curve (ROC AUC) that is equal to 0.9608 via applying the WMVM.
Filter/data fusion | Precision | Recall | FRR | FAR |
---|---|---|---|---|
0.8624 | 0.8519 | 0.1481 | 0.0024 | |
0.8631 | 0.8555 | 0.1445 | 0.0024 | |
0.8680 | 0.8423 | 0.1577 | 0.0026 | |
0.8069 | 0.7919 | 0.2080 | 0.0034 | |
0.6787 | 0.6878 | 0.3213 | 0.0053 | |
WMVM | 0.9495 | 0.9229 | 0.0771 | 0.0013 |
Furthermore, we analyzed the performance using the precision recall curve (PR) as shown in figure 19. Consequently, the best results were also obtained after performing data fusion. According to figure 19, the closest curve to the top right corner with PR AUC equal to 0.9362 is achieved via using the WMVM. As previously mentioned, we repeated the process of randomly selecting the test data 50 times for each subject. Consequently, figure 20 shows the cross-validation results in terms of the average identification accuracy of each experiment. These results further show that filtering some of the wavelet components and performing data fusion using the proposed voting method can be utilized to identify subjects from multiple ECGs.
In general, the use of ECG for human identification is a challenging task that depends mainly on choosing the appropriate features and classifiers [1, 2, 5, 22]. Different studies have presented different ECG features which can be utilized for biometric purposes [3]. In our previous work, we had proposed a study on the most appropriate features and classifiers [38]. However, the variability of ECG features remains a major challenge for utilizing the cardiac signal as a biometric modality for real applications [23]. Previous studies have achieved excellent identification results; however, topics regarding the variability of ECG features were not discussed [4, 22, 38, 52]. Therefore, we proposed a methodology to investigate the feasibility of human identification using multiple ECGs that are recorded at different days.
Table 5 shows performance comparison with state-of-the-art methods and summarizes the main algorithms that are used in these previous approaches. The performance of our method has shown excellent results compared to some of the approaches in the literature [26, 29, 32, 33] as shown in table 6. In addition, our performance slightly exceeded some of the recent methods in ECG biometrics which are based on time frequency analysis of the cardiac signal [28, 30, 34]. Although method [27] reported 100% accuracy, the authors used ECG data of 21 subjects which makes the use of this method very limited due to the small data size. The method of Ciocoiu
Authors | Methodology | Accuracy (%) |
---|---|---|
Dar | Proposed a multiresolution analysis of the DWT features using the Har wavelet coefficients of the heartbeats | 82.3 |
Lee | Proposed a time frequency representation of the ECG data using the robust RPCANet and DWT | 97.5 |
Arwa | Developed a wavelet-based method to extract the ECG power and energy features and utilizing Euclidean and linear discriminant analysis (LDA) classifiers for identification | 83.3 |
Abdeldayem | Proposed a methodology based on the spectro-temporal dynamic characteristics of the ECG signal using short time Fourier STFT, Morse wavelets and CNN | 97.86 |
Choi | Introduced a method to convert the ECG data into 2D resized spectrograms that are utilized for identification | 93 |
Kim | Proposed a method based on likelihood ratio test (GLRT) and composite hypothesis testing | 93 |
Tan | Presented a methodology that is based on the time frequency distribution of the ECG and the statistical n-best adaptive Fourier decomposition (SAFD) | 98 |
Proposed method | Proposed a filtering system that is based on MODWT to test the ECG feasibility of human identification using multiple signals and performing weighted majority voting method (WMVM) for decision fusion | 98.07 |
In addition, to make our proposed method clinically applicable, the ECG can be utilized in multibiometric identification systems. The combination of the intrinsic characteristic of the ECG with the extrinsic characteristics of some of the existing biometrics such as voice and iris recognition can increase patient security in clinics. Furthermore, clinics can benefit from deploying the ECG biometrics in telemedicine to update the personal records periodically for identification purposes. Generally, ECG records should be updated according to the personal health status and age to be utilized for human identification [20].
However, there are some limitations to our methodology. Specifically, topics on optimizing the number of filters, ECG data clustering and personal ECG selection for enrolment purposes need to be addressed in future work. According to figure 13, the number of MODWT filters that are required to correctly identify individuals is subject relevant, which may limit the applicability of our method due to the long computational time. However, optimizing techniques might address this problem to reduce the number of required filters. Also, implementing our method requires to cluster the ECG into different groups to further reduce the screening time since our method depends on finding the minimum Fréchet distance of one random testing data and all the referencing data. In our future work, we will address this problem by utilizing the MODWT scaling coefficients to cluster the ECG referencing data. Moreover, our method was evaluated based only on two ECG records per subject. Therefore, the applicability of our method should be investigated on larger ECG records. Accordingly, future work should focus on selecting the most appropriate personal ECG records which may require to perform similarity measurements algorithm at the enrolment stage of the biometric system.
One of the main challenges to utilize ECG for human identification is to address the variability of ECG features across multiple records [5, 22]. To solve this problem, we proposed a methodology for human identification using multiple ECGs via applying data filtering and data fusion techniques. To model the changeability of ECG features over multiple records, we utilized the MODWT to create a multi-channel filtering system that is used for partitioning the variability of ECG features according to its wavelet components followed by removing different wavelet components at different levels of the filtering system [39]. The proposed filtering system is utilized to identify subjects with reduced amounts of the signal information through filtering the wavelet components that may have significant change across multiple ECG records [40]. In addition, we proposed the WMVM technique which is utilized to combine information obtained from multiple filtering channels [41]. The WMVM is a scoring technique based on the minimum Fréchet distances and is utilized to obtain a common final decision for reaching correct identification. The experimental results have shown that our proposed method has achieved an identification accuracy ranging from 92.29% to 98.07%. In addition, we achieved 0.9495 precision, 0.9229 recall, 0.0771 FRR and 0.0013 FAR. In conclusion, ECG based human identification using multiple ECGs is feasible. However, it requires implementing methods that are adaptable with variability ECG features because it may adversely influence the performance of biometric applications.
The authors declare no conflict of interest.
Written by
Article Type: Research Paper
Date of acceptance: January 2023
Date of publication: February 2023
DOI: 10.5772/dmht.13
Copyright: The Author(s), Licensee IntechOpen, License: CC BY 4.0
© The Author(s) 2023. Licensee IntechOpen. This is an Open Access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted reuse, distribution, and reproduction in any medium, provided the original work is properly cited.
Impact of this article
383
Downloads
707
Views
1
Crossref Citations
1
Dimensions Citations
3
Altmetric Score
Join us today!
Submit your Article