Leveraging Multiple Distinct EEG Training Sessions for Improvement of Spectral-Based Biometric Verification Results.

Most studies on EEG-based biometry recognition report results based on signal databases, with a limited number of recorded EEG sessions using the same single EEG recording for both training and testing a proposed model. However, the EEG signal is highly vulnerable to interferences, electrode placement, and temporary conditions, which can lead to overestimated assessments of the considered methods. Our study examined how different numbers of distinct recording sessions used as training sessions would affect EEG-based verification. We analyzed the original data from 29 participants with 20 distinct recorded sessions each, as well as 23 additional impostors with only one session each. We applied raw coefficients of power spectral density estimate, and the coefficients of power spectral density estimate converted to the decibel scale, as the input to a shallow neural network. Our study showed that the variance introduced by multiple recording sessions affects sensitivity. We also showed that increasing the number of sessions above eight did not improve the results under our conditions. For 15 training sessions, the achieved accuracy was 96.7 ± 4.2%, and for eight training sessions and 12 test sessions, it was 94.9 ± 4.6%. For 15 training sessions, the rate of successful impostor attacks over all attack attempts was 3.1 ± 2.2%, but this number was not significantly different from using six recording sessions for training. Our findings indicate the need to include data from multiple recording sessions in EEG-based recognition for training, and that increasing the number of test sessions did not significantly affect the obtained results. Although the presented results are for the resting-state, they may serve as a baseline for other paradigms.

A New Approach to Detecting Atrial Fibrillation Using Count Statistics of Relative Changes between Consecutive RR Intervals.

BACKGROUND: The ratio of the difference between neighboring RR intervals to the length of the preceding RR interval (x%) represents the relative change in the duration between two cardiac cycles. We investigated the diagnostic properties of the percentage of relative RR interval differences equal to or greater than x% (pRRx%) with x% in a range between 0.25% and 25% for the distinction of atrial fibrillation (AF) from sinus rhythm (SR). METHODS: We used 1-min ECG segments with RR intervals with either AF (32,141 segments) or SR (32,769 segments) from the publicly available Physionet Long-Term Atrial Fibrillation Database (LTAFDB). The properties of pRRx% for different x% were analyzed using the statistical procedures and metrics commonly used to characterize diagnostic methods. RESULTS: The distributions of pRRx% for AF and SR differ significantly over the whole studied range of x% from 0.25% to 25%, with particularly outstanding diagnostic properties for the x% range of 1.5% to 6%. However, pRR3.25% outperformed other pRRx%. Firstly, it had one of the highest and closest to perfect areas under the curve (0.971). For pRR3.25%, the optimal threshold for distinction AF from SR was set at 75.32%. Then, the accuracy was 95.44%, sensitivity was 97.16%, specificity was 93.76%, the positive predictive value was 93.85%, the negative predictive value was 97.11%, and the diagnostic odds ratio was 514. The excellent diagnostic properties of pRR3.25% were confirmed in the publicly available MIT-BIH Atrial Fibrillation Database. In a direct comparison, pRR3.25% outperformed the diagnostic properties of pRR31 (the percentage of successive RR intervals differing by at least 31 ms), i.e., so far, the best single parameter differentiating AF from SR. CONCLUSIONS: A family of pRRx% parameters has excellent diagnostic properties for AF detection in a range of x% between 1.5% and 6%. However, pRR3.25% outperforms other pRRx% parameters and pRR31 (until now, probably the most robust single heart rate variability parameter for AF diagnosis). The exquisite pRRx% diagnostic properties for AF and its simple computation make it well-suited for AF detection in modern ECG technologies (mobile/wearable devices, biopatches) in long-term monitoring. The diagnostic properties of pRRx% deserve further exploration in other databases with AF.

Statistical and Diagnostic Properties of pRRx Parameters in Atrial Fibrillation Detection.

BACKGROUND: We studied the diagnostic properties of the percentage of successive RR intervals differing by at least x ms (pRRx) as functions of the threshold value x in a range of 7 to 195 ms for the differentiation of atrial fibrillation (AF) from sinus rhythm (SR). METHODS: RR intervals were measured in 60-s electrocardiogram (ECG) segments with either AF (32,141 segments) or SR (32,769 segments) from the publicly available Physionet Long-Term Atrial Fibrillation Database (LTAFDB). For validation, we have used ECGs from the Massachusetts Institute of Technology-Beth Israel Hospital (MIT-BIH) Atrial Fibrillation Database. The pRRx distributions in AF and SR in relation to x were studied by histograms, along with the mutual association by the nonparametric Spearman correlations for all pairs of pRRx, and separately for AF or SR. The optimal cutoff values for all pRRx were determined using the receiver operator curve characteristic. A nonparametric bootstrap with 5000 samples was used to calculate a 95% confidence interval for several classification metrics. RESULTS: The distributions of pRRx for x in the 7-195 ms range are significantly different in AF than in SR. The sensitivity, specificity, accuracy, and diagnostic odds ratios differ for pRRx, with the highest values for x = 31 ms (pRR31) rather than x = 50 (pRR50), which is most commonly applied in studies on heart rate variability. For the optimal cutoff of pRR31 (68.79%), the sensitivity is 90.42%, specificity 95.37%, and the diagnostic odds ratio is 194.11. Validation with the ECGs from the MIT-BIH Atrial Fibrillation Database confirmed our findings. CONCLUSIONS: We demonstrate that the diagnostic properties of pRRx depend on x, and pRR31 outperforms pRR50, at least for ECGs of 60-s duration.

Using Minimum Redundancy Maximum Relevance Algorithm to Select Minimal Sets of Heart Rate Variability Parameters for Atrial Fibrillation Detection.

Heart rate is quite regular during sinus (normal) rhythm (SR) originating from the sinus node. In contrast, heart rate is usually irregular during atrial fibrillation (AF). Complete atrioventricular block with an escape rhythm, ventricular pacing, or ventricular tachycardia are the most common exceptions when heart rate may be regular in AF. Heart rate variability (HRV) is the variation in the duration of consecutive cardiac cycles (RR intervals). We investigated the utility of HRV parameters for automated detection of AF with machine learning (ML) classifiers. The minimum redundancy maximum relevance (MRMR) algorithm, one of the most effective algorithms for feature selection, helped select the HRV parameters (including five original), best suited for distinguishing AF from SR in a database of over 53,000 60 s separate electrocardiogram (ECG) segments cut from longer (up to 24 h) ECG recordings. HRV parameters entered the ML-based classifiers as features. Seven different, commonly used classifiers were trained with one to six HRV-based features with the highest scores resulting from the MRMR algorithm and tested using the 5-fold cross-validation and blindfold validation. The best ML classifier in the blindfold validation achieved an accuracy of 97.2% and diagnostic odds ratio of 1566. From all studied HRV features, the top three HRV parameters distinguishing AF from SR were: the percentage of successive RR intervals differing by at least 50 ms (pRR50), the ratio of standard deviations of points along and across the identity line of the Poincare plots, respectively (SD2/SD1), and coefficient of variation-standard deviation of RR intervals divided by their mean duration (CV). The proposed methodology and the presented results of the selection of HRV parameters have the potential to develop practical solutions and devices for automatic AF detection with minimal sets of simple HRV parameters. Using straightforward ML classifiers and the extremely small sets of simple HRV features, always with pRR50 included, the differentiation of AF from sinus rhythms in the 60 s ECGs is very effective.

Impact of EEG Frequency Bands and Data Separation on the Performance of Person Verification Employing Neural Networks.

The paper is devoted to the study of EEG-based people verification. Analyzed solutions employed shallow artificial neural networks using spectral EEG features as input representation. We investigated the impact of the features derived from different frequency bands and their combination on verification results. Moreover, we studied the influence of a number of hidden neurons in a neural network. The datasets used in the analysis consisted of signals recorded during resting state from 29 healthy adult participants performed on different days, 20 EEG sessions for each of the participants. We presented two different scenarios of training and testing processes. In the first scenario, we used different parts of each recording session to create the training and testing datasets, and in the second one, training and testing datasets originated from different recording sessions. Among single frequency bands, the best outcomes were obtained for the beta frequency band (mean accuracy of 91 and 89% for the first and second scenarios, respectively). Adding the spectral features from more frequency bands to the beta band features improved results (95.7 and 93.1%). The findings showed that there is not enough evidence that the results are different between networks using different numbers of hidden neurons. Additionally, we included results for the attack of 23 external impostors whose recordings were not used earlier in training or testing the neural network in both scenarios. Another significant finding of our study shows worse sensitivity results in the second scenario. This outcome indicates that most of the studies presenting verification or identification results based on the first scenario (dominating in the current literature) are overestimated when it comes to practical applications.

Experimental Verification of the Concept of Using LOFAR Radio-Telescopes as Receivers in Passive Radiolocation Systems.

The paper presents a new idea of using a low-frequency radio-telescope belonging to the LOFAR network as a receiver in a passive radar system. The structure of a LOFAR radio-telescope station is described in the context of applying this radio-telescope for detection of aerial (airplanes) and space (satellite) targets. The theoretical considerations and description of the proposed signal processing schema for the passive radar based on a LOFAR radio-telescope are outlined in the paper. The results of initial experiments verifying the concept of a LOFAR station use as a receiver and a commercial digital radio broadcasting (DAB) transmitters as illuminators of opportunity for aerial object detection are presented.