A Long-Term, Portable ECG Patch Monitor Based on Flexible Dry Electrode

PurposeLong-term electrocardiogram (ECG) monitoring is an essential approach for the early diagnosis of cardiovascular diseases. Flexible dry electrodes that contains electrolyte without water could be a potential substitution of wet electrodes for long-term ECG monitoring. Therefore, this paper developes a long-term, portable ECG patch based on flexible dry electrodes, namely SEUECG-100.MethodA device consists of analog-front-end acquisition, data acquisition, and storage modules is developed and tested. An impedance test was conducted to compare the skin-electrode impedance of the flexible dry electrode and the Ag/AgCl wet electrode. The ECG signals were simutanously collected from the same subject using the SEUECG-100 and Shimmer device , which were then compared and analyzed from the perspective of ECG morphology, RR interval, and signal quality indices (SQI).ResultsThe experimental results reveal that the flexible dry electrode has the characteristics of low skin-electrode impedance. SEUECG-100 could collect high-quality ECG signals. The ECG signals collected by the two devices have a high RR interval correlation (r=0.999). SQI results show that SEUECG-100 is better than the Shimmer device in overcoming baseline drift. Long-term ECG acquisition and storage experiments show that SEUECG-100 could collect ECG signals with good stability and high reliability.ConclusionThe implementation of the proposed system design with dry electrodes could can effectively record long-term ECG monitoring with high quality in comparison to systems with wet electrodes from both impedance characteristics and signal morphology aspects.

Contribution of Different Subbands of ECG in Sleep Apnea Detection Evaluated Using Filter Bank Decomposition and a Convolutional Neural Network

A variety of feature extraction and classification approaches have been proposed using electrocardiogram (ECG) and ECG-derived signals for improving the performance of detecting apnea events and diagnosing patients with obstructive sleep apnea (OSA). The purpose of this study is to further evaluate whether the reduction of lower frequency P and T waves can increase the accuracy of the detection of apnea events. This study proposed filter bank decomposition to decompose the ECG signal into 15 subband signals, and a one-dimensional (1D) convolutional neural network (CNN) model independently cooperating with each subband to extract and classify the features of the given subband signal. One-minute ECG signals obtained from the MIT PhysioNet Apnea-ECG database were used to train the CNN models and test the accuracy of detecting apnea events for different subbands. The results show that the use of the newly selected subject-independent datasets can avoid the overestimation of the accuracy of the apnea event detection and can test the difference in the accuracy of different subbands. The frequency band of 31.25–37.5 Hz can achieve 100% per-recording accuracy with 85.8% per-minute accuracy using the newly selected subject-independent datasets and is recommended as a promising subband of ECG signals that can cooperate with the proposed 1D CNN model for the diagnosis of OSA.

Driver Monitoring of Automated Vehicles by Classification of Driver Drowsiness Using a Deep Convolutional Neural Network Trained by Scalograms of ECG Signals

Driver drowsiness is one of the leading causes of traffic accidents. This paper proposes a new method for classifying driver drowsiness using deep convolution neural networks trained by wavelet scalogram images of electrocardiogram (ECG) signals. Three different classes were defined for drowsiness based on video observation of driving tests performed in a simulator for manual and automated modes. The Bayesian optimization method is employed to optimize the hyperparameters of the designed neural networks, such as the learning rate and the number of neurons in every layer. To assess the results of the deep network method, heart rate variability (HRV) data is derived from the ECG signals, some features are extracted from this data, and finally, random forest and k-nearest neighbors (KNN) classifiers are used as two traditional methods to classify the drowsiness levels. Results show that the trained deep network achieves balanced accuracies of about 77% and 79% in the manual and automated modes, respectively. However, the best obtained balanced accuracies using traditional methods are about 62% and 64%. We conclude that designed deep networks working with wavelet scalogram images of ECG signals significantly outperform KNN and random forest classifiers which are trained on HRV-based features.

Signal Folding for Efficient Classification of Near-Cyclostationary Biological Signals

The classification of biological signals is important in detecting abnormal conditions in observed biological subjects. The classifiers are trained on feature vectors, which often constitute the parameters of the observed time series data models. Since the feature extraction is usually the most time-consuming step in training a classifier, in this paper, signal folding and the associated folding operator are introduced to reduce the variability in near-cyclostationary biological signals so that these signals can be represented by models that have a lower order. This leads to a substantial reduction in computational complexity, so the classifier can be learned an order of magnitude faster and still maintain its decision accuracy. The performance of different classifiers involving signal folding as a pre-processing step is studied for sleep apnea detection in one-lead ECG signals assuming ARIMA modeling of the time series data. It is shown that the R-peak-based folding of ECG segments has superior performance to other more general, similarity based signal folding methods. The folding order can be optimized for the best classification accuracy. However, signal folding requires precise scaling and alignment of the created signal fragments.