Key result
The proposed feature extraction technique and MLP-NN classifier achieved average sensitivities of 95.70%, 78.05%, 49.60%, 89.68%, and 33.89% for N, S, F, V, and Q ECG beats, respectively.
Population
ECG signals from 44 recordings of the MIT-BIH arrhythmia database
Comparison
Feature extraction using S-transform and wavelet… vs Other existing feature extraction techniques
Design
Other
Authors
Loading...
Requires prospective clinical validation before diagnostic use; extends computational ECG classification but leaves real-world applicability open.
A proposed mixture of features and MLPNN classifier achieved high sensitivity for normal and ventricular ectopic beats in the MIT-BIH database.
Samit Ari (2014) studied Arrhythmia. Mixture of ST and WT based features with temporal features and MLPNN classifier vs. Other existing feature extraction techniques was evaluated on Average sensitivity for N, S, F, V, and Q beats. The proposed feature extraction technique and MLP-NN classifier achieved average sensitivities of 95.70%, 78.05%, 49.60%, 89.68%, and 33.89% for N, S, F, V, and Q ECG beats, respectively.
Synapse has enriched 4 closely related papers on similar clinical questions. Consider them for comparative context: