Human identification using a new matching Pursuit-based feature set of ECG

Utilization of a hierarchical electrocardiogram classification model for enhanced biometric identification

Emerging research on artificial intelligence (AI) has leveraged the unique properties of electrocardiogram (ECG) signals for user identification. ECG signals, known for their resistance to forgery and tampering, offer security advantages. However, these signals fluctuate in response to physical and cognitive stress. Despite their security benefits, these dynamic characteristics present challenges for consistent user identification owing to their variable amplitudes and shapes. To address these problems, we propose a 2-stage user identification system that integrates ECG signals and status information. This system classifies the user's ECG status and uses the feature values in a second model to improve dynamic feature learning ability. This allows identification with high accuracy even in various stress states of the user. This increases the real-life usability of the ECG user identification system. The effectiveness of the proposed method was confirmed through a performance evaluation using CSU-BIODB(Chosun University-BIO Database) and the public MIT-BIH(Massachusetts Institute of Technology - Beth Israel Hospital Arrhythmia Laboratory) ST Change database, with identification accuracies of 92.08% and 95.83%, and f1-scores of 0.9207 and 0.9369, respectively. Compared with existing single user identification models, our approach demonstrated accuracy improvements of 9.3% and 36.76% for each database. These findings underscore the potential of the new 2-stage model for enhancing the practicality of ECG-based user identification systems and provide a promising foundation for future research on deep learning signal processing.

Single heartbeat ECG authentication: a 1D-CNN framework for robust and efficient human identification

This study proposes a small one-dimensional convolutional neural network (1D-CNN) framework for individual authentication, considering the hypothesis that a single heartbeat as input is sufficient to create a robust system. A short segment between R to R of electrocardiogram (ECG) signals was chosen to generate single heartbeat samples by enforcing a rigid length thresholding procedure combined with an interpolation technique. Additionally, we explored the benefits of the synthetic minority oversampling technique (SMOTE) to tackle the imbalance in sample distribution among individuals. The proposed framework was evaluated individually and in a mixture of four public databases: MIT-BIH Normal Sinus Rhythm (NSRDB), MIT-BIH Arrhythmia (MIT-ARR), ECG-ID, and MIMIC-III which are available in the Physionet repository. The proposed framework demonstrated excellent performance, achieving a perfect score (100%) across all metrics (i.e., accuracy, precision, sensitivity, and F1-score) on individual NSRDB and MIT-ARR databases. Meanwhile, the performance remained high, reaching more than 99.6% on mixed datasets that contain larger populations and more diverse conditions. The impressive performance demonstrated in both small and large subject groups emphasizes the model's scalability and potential for widespread implementation, particularly in security contexts where timely authentication is crucial. For future research, we need to examine the incorporation of multimodal biometric systems and extend the applicability of the framework to real-time environments and larger populations.

Using beat-to-beat heart signals for age-independent biometric verification

Use of non-stationary physiological signals for biometric verification, reduces the ability to forge. Such signals should be simple to acquire with inexpensive equipment. The beat-to-beat information embedded within the time intervals between consecutive heart beats is a non-stationary physiological signal; its potential for biometric verification has not been studied. This work introduces a biometric verification method termed "CompaRR". Heartbeat was extracted from longitudinal recordings from 30 mice ranging from 6 to 24 months of age (equivalent to ~ 20-75 human years). Fifty heartbeats, which is close to resting human heartbeats in a minute, were sufficient for the verification task, achieving a minimal equal error rate of 0.21. When trained on 6-month-old mice and tested on unseen mice up to 18-months of age (equivalent to ~ 50 human years), no significant change in the verification performance was noted. Finally, when the model was trained on data from drug-treated mice, verification was still possible.

The Identification of ECG Signals Using Wavelet Transform and WOA-PNN

Electrocardiogram (ECG) signal identification technology is rapidly replacing traditional fingerprint, face, iris and other recognition technologies, avoiding the vulnerability of traditional recognition technologies. This paper proposes an ECG signal identification method based on the wavelet transform algorithm and the probabilistic neural network by whale optimization algorithm (WOA-PNN). Firstly, Q, R and S waves are detected by wavelet transform, and the P and T waves are detected by local windowed wavelet transform. The characteristic values are constructed by the detected time points, and the ECG data dimension is smaller than that of the non-reference detection. Secondly, combined with the probabilistic neural network, the mean impact value algorithm is used to screen the characteristic values, the characteristic values with low influence are eliminated, and the input and complexity of the model are simplified. Finally, a WOA-PNN combined classification method is proposed to intelligently optimize the hyper parameters in the probabilistic neural network algorithm to improve the model accuracy. According to the simulation verification on three databases, ECG-ID, MIT-BIH Normal Sinus Rhythm and MIT-BIH Arrhythmia, the identification accuracy of a single ECG cycle is 96.97%, and the identification accuracy of three ECG cycles is 99.43%.

A New 12-Lead ECG Signals Fusion Method Using Evolutionary CNN Trees for Arrhythmia Detection

The 12 leads of electrocardiogram (ECG) signals show the heart activities from different angles of coronal and axial planes; hence, the signals of these 12 leads have functional dependence on each other. This paper proposes a novel method for fusing the data of 12-lead ECG signals to diagnose heart problems. In the first phase of the proposed method, the time-frequency transform is employed to fuse the functional data of leads and extract the frequency data of ECG signals in 12 leads. After that, their dependence is evaluated through the correlation analysis. In the second phase, a structural learning method is adopted to extract the structural data from these 12 leads. Moreover, deep convolutional neural network (CNN) models are coded in this phase through genetic programming. These trees are responsible for learning deep structural features from functional data extracted from 12 leads. These trees are upgraded through the execution of the genetic programming (GP) algorithm to extract the optimal features. These two phases are used together to fuse the leads of ECG signals to diagnose various heart problems. According to the test results on ChapmanECG, including the signals of 10,646 patients, the proposed method enjoys the mean accuracy of 97.60% in the diagnosis of various types of arrhythmias in the Chapman dataset. It also outperformed the state-of-the-art methods.

Verhulst map measures: new biomarkers for heart rate classification

Recording, monitoring, and analyzing biological signals has received significant attention in medicine. A fundamental phase for understanding a bio-system under various conditions is to process the corresponding bio-signal appropriately. To this effect, different conventional and nonlinear approaches have been proposed. However, since the non-stationary properties of the bio-signals are not revealed by traditional linear methods, nonlinear dynamical techniques play a crucial role in examining the behavior of a bio-system. This work proposes new bio-markers based on the chaotic nature of the biomedical signals. These measures were introduced using the Verhulst map, a simple tool for characterizing the morphology of the reconstructed phase space. For this purpose, we extracted the features from the heart rate (HR) signals of six groups of meditators and non-meditators. For a typical classification problem, the performance of some conventional classifiers, including the k-nearest neighbor, support vector machine, and Naïve Bayes, was appraised separately. In addition, the competence of a hybrid classification strategy was inspected using majority voting. The results indicated a maximum accuracy, F1-score, and sensitivity of 100%. These findings reveal that the proposed framework is eminently capable of analyzing and classifying the HR signals of the groups. In conclusion, the Verhulst diagram-based measures are simple and based on the dynamics of the bio-signals, which can be served for quantifying different signals in medical systems.

A multiview feature fusion model for heartbeat classification

Objective.An electrocardiogram (ECG) is one of the most common means to diagnose arrhythmia according to different waveforms clinically. Although there are advanced classification methods such as deep learning, the single view feature cannot meet the demand of classification accuracy for new individuals. To this end, a classification model based on multiview fusion was proposed.Approach.First, handcrafted view features were extracted from heartbeats and then deep view features were obtained from the deep learning model. The features of two different perspectives were fused in the fully connected layer, and the random forest classifier was used instead of the Softmax classifier for classification. Notably, Bayesian optimization was utilized in the hyper-parameter tuning of the classifier. The proposed method employed the MIT-BIH database to classify five classes: normal heartbeat (N), left bundle branch block heartbeat (LB), right bundle branch block heartbeat (RB), atrial premature contraction (APC) and premature ventricular contraction (PVC).Main results.The experimental results achieved a higher average accuracy of 98.93%, average precision of 96.92%, average sensitivity of 96.46%, and average specificity of 99.33% in five types of heartbeat classification for inter-patient.Significance.The proposed framework improves the performance of ECG detection for new individuals. And it provides an feasible algorithmic model for single-lead wearable devices with multiview fusion.

Automatic seizure detection using orthogonal matching pursuit, discrete wavelet transform, and entropy based features of EEG signals

BACKGROUND AND OBJECTIVE

Epilepsy is a prevalent disorder that affects the central nervous system, causing seizures. In the current study, a novel algorithm is developed using electroencephalographic (EEG) signals for automatic seizure detection from the continuous EEG monitoring data.

METHODS

In the proposed methods, the discrete wavelet transform (DWT) and orthogonal matching pursuit (OMP) techniques are used to extract different coefficients from the EEG signals. Then, some non-linear features, such as fuzzy/approximate/sample/alphabet and correct conditional entropy, along with some statistical features are calculated using the DWT and OMP coefficients. Three widely-used EEG datasets were utilized to assess the performance of the proposed techniques.

RESULTS

The proposed OMP-based technique along with the support vector machine classifier yielded an average specificity of 96.58%, an average accuracy of 97%, and an average sensitivity of 97.08% for different types of classification tasks. Moreover, the proposed DWT-based technique provided an average sensitivity of 99.39%, an average accuracy of 99.63%, and an average specificity of 99.72%.

CONCLUSIONS

The experimental findings indicated that the proposed algorithms outperformed other existing techniques. Therefore, these algorithms can be implemented in relevant hardware to help neurologists with seizure detection.

Asymmetry of lagged Poincare plot in heart rate signals during meditation

Background and aim

Heart rate variability (HRV) quantifies the variability in the heart’s beat-to-beat intervals. This signal is a potential marker of cardiac function in normal, pathological, and psychological states. Signal asymmetry refers to an unequal distribution in the signal, which can be found by a two-dimensional Poincare plot. Earlier, heart rate asymmetry (HRA) was assessed using a conventional Poincare plot (lag of 1). In this study, we have investigated the effect of delay on the phase space asymmetry using lagged Poincare’s plot.

Experimental procedure

This study compared the presence/lack of asymmetries in the HRV data of 12 meditators (four Kundalini yoga (Yoga) at an advanced level of meditation, eight Chinese Chi meditators (Chi) ∼1–3 months) to 25 non-meditators (11 spontaneous nocturnal breathing (Normal) and 14 metronomic breathing (Metron)). Poincare’s plots were constructed with six different lags, and HRA was calculated. The analysis was conducted using HRV data provided in the Physionet database.

Results

The results showed that using conventional Poincare’s plot (lag of 1), the lowest HRA was observed in the Metron group. In addition, the HRA index was different between meditators and non-meditator groups. Moreover, as the most significant difference between groups was observed in a delay of 6, the role of the delay selection on the signal asymmetry was revealed.

Conclusion

The difference between lagged HRA responses on Yoga in comparison with other groups can be an emphasis on the importance of choosing the type of meditation technique and its effects on the cardiovascular system.

•

Asymmetries in HRV was assessed in different meditator and non-meditator groups.

•

The role of delay selection was explored on the phase space asymmetry using lagged Poincare plot.

•

A weaker asymmetry was observed in the metronomic breathing group.

•

The most significant difference between groups was perceived in a delay of six.

Schizophrenia diagnosis using innovative EEG feature-level fusion schemes

Electroencephalogram (EEG) has become a practical tool for monitoring and diagnosing pathological/psychological brain states. To date, an increasing number of investigations considered differences between brain dynamic of patients with schizophrenia and healthy controls. However, insufficient studies have been performed to provide an intelligent and accurate system that detects the schizophrenia using EEG signals. This paper concerns this issue by providing new feature-level fusion algorithms. Firstly, we analyze EEG dynamics using three well-known nonlinear measures, including complexity (Cx), Higuchi fractal dimension (HFD), and Lyapunov exponents (Lya). Next, we propose some innovative feature-level fusion strategies to combine the information of these indices. We evaluate the effect of the classifier parameter (σ) adjustment and the cross-validation partitioning criteria on classification accuracy. The performance of EEG classification using combined features was compared with the non-combined attributes. Experimental results showed higher classification accuracy when feature-level features were utilized, compared to when each feature was used individually or all fed to the classifier simultaneously. Using the proposed algorithm, the classification accuracy increased up to 100%. These results establish the suggested framework as a superior scheme compared to the state-of-the-art EEG schizophrenia diagnosis tool.