Self-Powered ECG Device for Health Monitoring
Author Information
Author(s): Rajendran Jegan, Wilson Sukumari Nimi, Jose P. Subha Hency, Rajendran Manikandan, Saikia Manob Jyoti, Vozzi Giovanni
Primary Institution: University of Memphis
Hypothesis
Can a self-powered electronic module improve ECG signal processing and personalized health monitoring?
Conclusion
The developed device achieved 99.72% accuracy in ECG classification using a random forest with deep decision tree architecture.
Supporting Evidence
- The device integrates an energy-harvesting facility for continuous operation.
- Experimental results showed a significant reduction in overlapping samples from ECG data.
- The random forest classifier achieved the highest accuracy of 99.72% for ECG classification.
- The device can operate under various light conditions, enhancing its usability.
- Wavelet packet decomposition was used to improve feature extraction from ECG signals.
Takeaway
This study created a device that can monitor heart health without needing a battery, using light to power itself.
Methodology
The study involved developing a self-powered ECG device with energy harvesting, signal processing, and machine learning for classification.
Limitations
The study may be limited by the dataset size and the specific conditions under which the device was tested.
Statistical Information
P-Value
0.0003
Statistical Significance
p<0.05
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website