Waltenegus Dargie

Yalemzerf Getnet, Waltenegus Dargie

Cost-effective wireless electrocardiograms (ECGs) enable long-term and scalable monitoring of cardiac patients in their home and work environments. Because they offer greater freedom of movement, they are also suitable for investigating the relationship between cardiac workload and underlying physical exertion. However, this requires that the quality of the generated data meets the standards of clinical devices. The aim of this study is to examine this closely. We therefore analyze data from 54 healthy subjects who performed five physical activities using wireless ECGs outside of clinical settings and without medical supervision. The results are compared with clinically collected data from standard 12-lead ECGs (2493 subjects) and Holter ECGs (29 subjects), with particular attention to the RR interval time series (tachogram) and heart rate variability (HRV). Our study shows significant statistical agreement between the different datasets. We calculated the 95% confidence intervals for the mean RR interval and HRV assuming that (1) the statistics of the 12-lead ECGs could serve as reliable reference, and (2) the statistics of the 12-lead ECGs cannot be taken as reliable reference. The p-values for both conditions (for the RR interval: 0.23 and 0.26 respectively; for HRV: 0.10 and 0.11 respectively) suggest that there is insufficient evidence to reject the hypothesis that significant statistical agreement exists between the different datasets.

Sajad Farrokhiørcidicon, Lerick Sequeira, Shanna L. Burke et al.

This study investigates heart rate (HR) and heart rate variability (HRV) responses to physical activity in breast cancer survivors using wearable electrocardiogram (ECG) data collected in real-world settings. Reliable HRV analysis in such environments is challenging due to motion artifacts and activity-related signal degradation. To address this, we use an approach that combines accelerometer and gyroscope data for activity intensity segmentation (light, moderate, vigorous) with a robust ECG processing pipeline incorporating R-peak detection and annotation-free signal quality assessment. Because vigorous activity produced unreliable HRV estimates, analyses focused on light and moderate activity levels. Using 30~s, 1~min, and 2~min windows, HR and HRV metrics were computed and compared between breast cancer survivors and healthy controls. Cancer survivors consistently exhibited elevated HR and reduced HRV across activity levels. During light activity, HR increased from 95.7~bpm in controls to 103.4~bpm in cancer survivors. Differences became more pronounced during moderate activity, where RMSSD decreased from 39.7~ms to 22.1~ms and SDNN from 42.6~ms to 25.1~ms. Statistical analyses showed significant group differences with strong and consistent effects across observations. In addition, the proposed ECG quality assessment framework reliably identified high-quality signal segments, achieving near-perfect valid RR ratios (0.99) without manual annotations. Overall, these findings demonstrate impaired and activity-dependent autonomic regulation in cancer survivors and highlight the importance of motion-aware activity segmentation and robust ECG quality control for accurate physiological monitoring in real-world wearable settings.

Sina Montazeri, Waltenegus Dargie, Yunhe Feng et al.

Human activity recognition is critical for applications such as early intervention and health analytics. Traditional activity recognition relies on inertial measurement units (IMUs), which are resource intensive and require calibration. Although electrocardiogram (ECG)-based methods have been explored, these have typically served as supplements to IMUs or have been limited to broad categorical classification such as fall detection or active vs. inactive in daily activities. In this paper, we advance the field by demonstrating, for the first time, robust recognition of activity only with ECG in six distinct activities, which is beyond the scope of previous work. We design and evaluate three new deep learning models, including a CNN classifier with Squeeze-and-Excitation blocks for channel-wise feature recalibration, a ResNet classifier with dilated convolutions for multiscale temporal dependency capture, and a novel CNNTransformer hybrid combining convolutional feature extraction with attention mechanisms for long-range temporal relationship modeling. Tested on data from 54 subjects for six activities, all three models achieve over 94% accuracy for seen subjects, while CNNTransformer hybrid reaching the best accuracy of 72% for unseen subjects, a result that can be further improved by increasing the training population. This study demonstrates the first successful ECG-only activity classification in multiple physical activities, offering significant potential for developing next-generation wearables capable of simultaneous cardiac monitoring and activity recognition without additional motion sensors.

Siddhant Deshpande, Yalemzerf Getnet, Waltenegus Dargie

With the proliferation of wireless electrocardiogram (ECG) systems for health monitoring and authentication, protecting signal integrity against tampering is becoming increasingly important. This paper analyzes the performance of CNN, ResNet, and hybrid Transformer-CNN models for tamper detection. It also evaluates the performance of a Siamese network for ECG based identity verification. Six tampering strategies, including structured segment substitutions and random insertions, are emulated to mimic real world attacks. The one-dimensional ECG signals are transformed into a two dimensional representation in the time frequency domain using the continuous wavelet transform (CWT). The models are trained and evaluated using ECG data from 54 subjects recorded in four sessions 2019 to 2025 outside of clinical settings while the subjects performed seven different daily activities. Experimental results show that in highly fragmented manipulation scenarios, CNN, FeatCNN-TranCNN, FeatCNN-Tran and ResNet models achieved an accuracy exceeding 99.5 percent . Similarly, for subtle manipulations (for example, 50 percent from A and 50 percent from B and, 75 percent from A and 25 percent from B substitutions) our FeatCNN-TranCNN model demonstrated consistently reliable performance, achieving an average accuracy of 98 percent . For identity verification, the pure Transformer-Siamese network achieved an average accuracy of 98.30 percent . In contrast, the hybrid CNN-Transformer Siamese model delivered perfect verification performance with 100 percent accuracy.