Key result
A linear discriminant analysis (LDA) based ECG classifier achieved comparable accuracy to support vector machines with significantly reduced computational complexity, consuming 182.94 nW at 1.08 V.
Population
ECG data samples from Physionet and Southampton General Hospital Cardiology Department
Comparison
Linear discriminant analysis classifier and… vs Support vector machine classifiers and other…
Authors
Loading...
May enable low-power wearable ECG monitoring; leaves open clinical validation of real-world performance.
An ultra low-power LDA-based ECG classifier achieves comparable accuracy to SVM with significantly reduced computational complexity, demonstrating potential for on-body remote monitoring.
Chen et al. (2013) studied Normal and abnormal electrocardiograms (ECGs). Linear discriminant analysis (LDA) based ECG classifier vs. Support vector machine classifiers was evaluated on Classification accuracy and computational complexity. A linear discriminant analysis (LDA) based ECG classifier achieved comparable accuracy to support vector machines with significantly reduced computational complexity, consuming 182.94 nW at 1.08 V.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: