Key result
A proposed method combining multirate processing and machine learning for ECG arrhythmia classification achieved up to 97.06% accuracy and a 13-fold compression gain compared to fixed-rate solutions.
Why the study?
Wearable gadgets are growing in cloud-based health monitoring systems, where signal compression, computational efficiency, and power efficiency are imperative for diagnosing cardiovascular diseases from ECG signals.
The proposed multirate processing and machine learning method provides high classification accuracy for cardiac arrhythmias while significantly reducing computational complexity and enhancing compression gain.
No takes yet. Share an insight, caveat, or question.
May enable efficient wearable ECG monitoring; leaves open prospective clinical validation.
Qaisar et al. (2021) studied Cardiac arrhythmias. Multirate processing with selective subbands and machine learning vs. Equivalent fixed-rate solutions was evaluated on Classification accuracy. A proposed method combining multirate processing and machine learning for ECG arrhythmia classification achieved up to 97.06% accuracy and a 13-fold compression gain compared to fixed-rate solutions.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: