Key result
An artificial neural network composite method successfully compressed ECG data, improved retrieved signal quality by eliminating high-frequency interference, and accurately extracted signal features.
Why the study?
Does an error-back-propagation artificial neural network improve data compression and feature extraction of ECG signals?
Population
ECG signals from a Military Hospital (MH) database and CSE database
Comparison
Error-back-propagation artificial neural network… vs Original uncompressed ECG signals
Design
Other
Authors
Loading...
May aid ECG signal processing in technical settings; leaves open prospective clinical validation before any practice change.
Does an error-back-propagation artificial neural network improve data compression and feature extraction of ECG signals?
An artificial neural network with a 335-4-4-335 topology provides efficient data compression, noise reduction, and accurate feature extraction for ECG signals.
Saxena et al. (1997) studied ECG signals. Error-back-propagation artificial neural network (ANN) vs. Original signal was evaluated on Data compression, signal retrieval and feature extraction. An artificial neural network composite method successfully compressed ECG data, improved retrieved signal quality by eliminating high-frequency interference, and accurately extracted signal features.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: