Key result
A mixture of experts network structure classified five types of ECG beats with an accuracy of 96.89%, achieving higher accuracy rates than stand-alone neural network models.
Why the study?
Does a mixture of experts network improve classification accuracy of ECG beats compared to stand-alone neural network models?
Population
ECG beats obtained from the Physiobank database
Comparison
Mixture of experts network structure using… vs Stand-alone neural network models
Design
Other
Authors
Loading...
May improve automated ECG classification accuracy; leaves open prospective clinical validation before practice adoption.
Does a mixture of experts network improve classification accuracy of ECG beats compared to stand-alone neural network models?
A mixture of experts network using wavelet transform features achieves high accuracy (96.89%) in classifying various types of ECG beats, outperforming stand-alone neural networks.
Elif Derya Übeylı (2008) studied ECG beats classification. Mixture of experts (ME) network structure vs. Stand-alone neural network models was evaluated on Classification accuracy. A mixture of experts network structure classified five types of ECG beats with an accuracy of 96.89%, achieving higher accuracy rates than stand-alone neural network models.
Synapse has enriched 4 closely related papers on similar clinical questions. Consider them for comparative context: