Key result
Neural network and wavelet algorithms outperform other methods for QRS detection across all noise types.
Why the study?
The noise sensitivities of different ECG detection algorithms under various synthesized noise types and levels were not fully characterized.
Neural network and wavelet transform-based ECG detection algorithms demonstrate superior robustness to various noise types compared to derivative and digital filter-based methods.
No QRS detector performs without error at highest noise levels; leaves open need for robust NN- or WT-based algorithms in clinical ECG monitoring.
This paper presents an analysis of noise sensitivities of different detection algorithms for electrocardiogram (ECG) taken from MIT-BIH arrhythmia database. Seven methods used in this paper are based on derivatives, digital filters (DF), neural network (NN) and wavelet transform (WT). The raw ECG is corrupted with 5 different types of synthesized noise, namely, power line interference, base line drift due to respiration, abrupt baseline shift, electromyogram (EMG) interference and a composite noise made from other types. A total of 315 data sets are constructed from 15 raw data sets for each type of noise adding 0%, 25%, 50%, 75% and 100% noise levels. The application of the methods to detect QRS complexes of a total of 33,774 beats of ECG shows that none of the algorithms are able to detect all QRS complexes without any false positives for all of the noise types at the highest noise level. Algorithms based on NN and WT show better performance considering all noise types and the two algorithms perform similarly. The result of this study will help to develop a more robust ECG detector and this will make ECG interpretation system more effective. DOI: http://dx.doi.org/10.11591/ijece.v3i3.2516
No takes yet. Share an insight, caveat, or question.
Hossain et al. (2013) studied Arrhythmia. ECG detection algorithms (derivatives, digital filters, neural network, wavelet transform) vs. Other algorithms was evaluated on Detection of QRS complexes without false positives. Algorithms based on neural networks and wavelet transforms showed better performance in detecting QRS complexes across all noise types, though none achieved perfect detection at the highest noise level.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: