Biometric systems based on ECG using ensemble empirical mode decomposition and Variational Mode decomposition

Abstract

Electrocardiogram (ECG) based biometric is challenging to be developed with the aim of high-security access. This biometric system is more diffi cult to falsify, compared to the conventional biometric systems. From previous proposed studies, there is still a gap to improve the accuracy of the system. Therefore in this study, a new protocol is proposed to improve the performance of the ECG biometric system compared to previously reported studies. This study decomposes the ECG signals using a method based on empirical mode decomposition (EMD) based, which are Variational Mode Decomposition (VMD) and Ensemble Empirical Mode Decomposition (EEMD). These two methods are the development of the EMD method to overcome one main problem of EMD. That is, the EMD method generates oscillations with the same time scales, which stored in different decomposition levels. A private ECG dataset, recorded using one lead ECG signal from 11 subjects, is used in this study. ECG signals from each person are then segmented into ten windows to become training data and test data. VMD and EEMD methods are used to decompose ECG signals into fi ve sub-signals. Feature extraction based on statistical calculations is applied at each level of decomposition to obtain the characteristics of the ECG signal. Mean, variance, skewness, kurtosis, and entropy are evaluated as predictors. Support vector machines and 10-fold cross-validation are used to validate the performance of the proposed method. Our simulations demonstrate that the proposed method outperforms several previous studies and achieves an accuracy of up to 98.2%.

The hidden waves in the ECG uncovered revealing a sound automated interpretation method

“…Moreover, the new parameters can be used in experimental assays to test medical and preventive strategies, to study the evolution of the heart's functioning and could even allow inferring personal identity, as well as www.nature.com/scientificreports/ circumstances as the emotional state at the time of data collection. The important question of biometric identification using ECG features has received attention recently in the literature (see 17,25,26,32,37,38 among others). The reduced error rate when the 105 QT patients are discriminated is a piece of evidence of the potential of FMM ecg parameters in biometric identification.…”

“…Also, the papers by 4 , 21 – 23 and 24 extended the list of procedures and their pros and cons for the automatic analysis of ECGs. In general, machine learning approaches success is very dependent on the training set, the selection of diagnostic groups, the preprocessing and the database, see 25 , 26 or 27 among others. Furthermore, they are rigid and black-box procedures that are susceptible to adversial attacks 28 .…”

Efficient Implementation of Double Random Phase Encoding and Empirical Mode Decomposition for Cancelable Biometrics

“…A non-stationary signal can be mathematically broken down using EMD into a collection of functions known as Intrinsic Mode Functions (IMFs) and remainder r n . EMD can be applied in the time domain [20]. The EMD preserves the original signal properties while breaking down.…”

Implementation of first order statistical processor on FPGA for feature extraction

“…Extraction of statistical features on cases of sleep apnea detection based on ECG signals reported in [10]. Statistical parameters are also used in ECG biometrics as reported in [11]. Other studies on the characterization of EEG signals also use statistical computations [12]- [15].…”